Posts

Infographie représentant l'interconnexion entre différents systèmes

Machines surfing the web

/1 Comment/in , /by

There has been constant development in the area of object interconnection via the internet. And this trend is set to continue in years to come. One of the solutions for machines to communicate with each other is the Semantic Web. Here are some explanations of this concept.

 “The Semantic Web gives machines similar web access to that of humans,” indicates Maxime Lefrançois, Artificial Intelligence researcher at Mines Saint-Etienne. This area of the web is currently being used by companies to gather and share information, in particular for users. It makes it possible to adapt product offers to consumer profiles, for example. At present, the Semantic Web occupies an important position in research undertaken around the Internet of Things, i.e. the interconnection between machines and objects connected via the internet.

By making machines work together, the Internet of Things can be a means of developing new applications. This would serve both individuals and professional sectors, such as intelligent buildings or digital agriculture. The last two examples are also the subject of the CoSWoT1 project, funded by the French National Research Agency (ANR). This initiative, in which Maxime Lefrançois is participating, aims to provide new knowledge around the use of the Semantic Web by devices.

To do so, the projects’ researchers installed sensors and actuators in the INSA Lyon buildings on the LyonTech-la Doua campus, the Espace Fauriel building of Mines Saint-Etienne, and the INRAE experimental farm in Montoldre. These sensors record information, like the opening of a window or the temperature and CO2 levels in a room. Thanks to a digital representation of a building or block, scientists can construct applications that use the information provided by sensors, enrich it and make decisions that are transmitted to actuators.

Such applications can measure the CO2 concentration in a room, and according to a pre-set threshold, open the windows automatically for fresh air. This could be useful in the current pandemic context, to reduce the viral load in the air and thereby reduce the risk of infection. Beyond the pandemic, the same sensors and actuators can be used in other cases for other purposes, such as to prevent the build-up of pollutants in indoor air.

A dialog with cards

The main characteristic of the Semantic Web is that it registers information in knowledge graphs: kinds of maps made up of nodes representing objects, machines or concepts, and arcs that connect them to one another, representing their relationships. Each hub and arc is registered with an Internationalized Resource Identifier (IRI): a code that makes it possible for machines to recognize each other and identify and control objects such as a window, or concepts such as temperature.

Depending on the number of knowledge graphs built up and the amount of information contained, a device will be able to identify objects and items of interest with varying degrees of precision. A graph that recognizes a temperature identifier will indicate, depending on its accuracy, the unit used to measure it. “By combining multiple knowledge graphs, you obtain a graph that is more complete, but also more complex,” declares Lefrançois. “The more complex the graph, the longer it will take for the machine to decrypt,” adds the researcher.

Means to optimize communication

The objective of the CoSWoT project is to simplify dialog between autonomous devices. It is a question of ‘integrating’ the complex processing linked with the Semantic Web into objects with low calculating capabilities and limiting the amount of data exchanged in wireless communication to preserve their batteries. This represents a challenge for Semantic Web research.  “It needs to be possible to integrate and send a small knowledge graph in a tiny amount of data,” explains Lefrançois. This optimization makes it possible to improve the speed of data exchanges and related decision-making, as well as to contribute greater energy efficiency.

With this in mind, the researcher is interested in what he calls ‘semantic interoperability’, with the aim of “ensuring that all kinds of machines understand the content of messages that they exchange,” he states. Typically, a connected window produced by one company must be able to be understood by a CO2 sensor developed by another company, which itself must be understood by the connected window. There are two approaches to achieve this objective. “The first is that machines use the same dictionary to understand their messages,” specifies Lefrançois, “The second involves ensuring that machines solve a sort of treasure hunt to find how to understand the messages that they receive,” he continues. In this way, devices are not limited by language.

IRIs in service of language

Furthermore, solving these treasure hunts is allowed by IRIs and the use of the web. “When a machine receives an IRI, it does not need to automatically know how to use it,” declares Lefrancois. “If it receives an IRI that it does not know how to use, it can find information on the Semantic Web to learn how,” he adds. This is analogous to how humans may search for expressions that they do not understand online, or learn how to say a word in a foreign language that they do not know.

However, for now, there are compatibility problems between various devices, due precisely to the fact that they are designed by different manufacturers. “In the medium term, the CoSWoT project could influence the standardization of device communication protocols, in order to ensure compatibility between machines produced by different manufacturers,” the researcher considers. It will be a necessary stage in the widespread roll-out of connected objects in our everyday lives and in companies.

While research firms are fighting to best estimate the position that the Internet of Things will hold in the future, all agree that the world market for this sector will represent hundreds of billions of dollars in five years’ time. As for the number of objects connected to the internet, there could be as many as 20 to 30 billion by 2030, i.e. far more than the number of humans. And with the objects likely to use the internet more than us, optimizing their traffic is clearly a key challenge.

[1] The CoSWoT project is a collaboration between the LIMOS laboratory (UMR CNRS 6158 which includes Mines Saint-Étienne), LIRIS (UMR CNRS 5205), Hubert Curien laboratory (UMR CNRS 5516) INRAE, and the company Mondeca.

Rémy Fauvel

Read on I’MTech

A dictionary for connected devices
économie circulaire, impact environnemental

Economics – dive in, there is so much to discover!

/1 Comment/in , , /by

To effectively roll out circular economy policies within a territory, companies and decision-makers require access to evaluation and simulation tools. The design of these tools, still in the research phase, necessarily requires a more detailed consideration of the impact of human activities, both locally and globally.

“The circular economy enables optimization of the available resources in order to preserve them and reduce pressure on the environment,” explains Valérie Laforest,1 a researcher at Mines Saint-Étienne. Awareness of the need to protect the planet began to develop in earnest in the 1990s and was gradually accompanied by the introduction of various key regulations. For example, the 1996 IPPC (Integrated Pollution Prevention and Control) Directive, which Valérie Laforest helped to implement through her research, aims to prevent and reduce the different types of pollutant emissions. More recently, legislation such as the French Law on Energy Transition for Green Growth (2015) and the Anti-Waste Law for a Circular Economy (2021) have reflected the growing desire to take the environment into account when considering anthropic activities. However, to enable industries to adapt to these regulations, it is essential for them to have access to tools derived from in-depth research on the impacts of their activities.

Decision-support tools for actors

To enable actors to comply with the regulations and reduce their impacts on the environment, they need to be provided with tools adapted to issues that are both global and local. Part of the research on the circular economy therefore concerns the development of such tools. The aim is to design models that are precise enough to be able to characterize and evaluate a system on the scale of an individual territory, while also being general enough to be adapted to territories with other characteristics. Fairly general methodological frameworks can therefore be developed, within which it is possible to determine criteria and indicators specific to certain cases or sectors. These tools should provide decision-makers with the information they need to implement their infrastructures.

At Mines Saint-Étienne and in collaboration with Macéo, a team of researchers is focusing on the development of a tool called ADALIE, which aims to characterize the potential of territories. This tool creates maps of different geographical areas showing different criteria, such as the economic or environmental criteria of these territories, as well as the industries established in them and their impacts. Decision-makers can therefore use this mapping tool as the basis for choosing their priority activity areas. “The underlying issue is about being able to ensure that a territory possesses the dimensions required to implement circular economy strategies, and that they are successful,” Valerie Laforest tells us. In its next phase, the ADALIE program then aims to archive experiences of effective territorial practices in order to create databases.

For each territorial study, the research provides a huge volume of different types of information. This data generates models that can then be tested in other territories, which also enables the robustness of the models to be checked according to the chosen indicators. These types of tools help local stakeholders to make decisions on aspects of industrial and territorial economics. “This facilitates reflection on how to develop strategies that bring together several actors affected by different issues and problems within a given territory,” states Valérie Laforest. To this end, it is essential to have access to methodologies that enable the measurement of the different environmental impacts. Two main methods are available.

Measurements of impact on the circular economy

Life cycle analysis (LCA) aims to estimate environmental impacts spanning a large geographical and temporal scale, taking account of issues such as distance transported. LCA seeks to model all potential consumptions and emissions over the entire life span of a system. The models are developed by compiling data from other systems and can be used to compare different scenarios in order to determine the scenario that is likely to have the least impact.

Read more on I’MTech: What is life cycle analysis?

The other approach is the best available techniques (BAT) method. This practice was implemented under the European Industrial Emissions Directive (IPPC then IED) in 1996. It aims to help European companies achieve performance standards equivalent to benchmark values for their consumption and emission flows. These benchmarks are based on data from samples of European companies. The granting or refusal of an operating license depends on the comparison of their performance with the reference sample. BATs are therefore based on European standards and have a regulatory purpose.

BATs are related to companies’ performance in the use phase, i.e. the performance of techniques is closely scrutinized in relation to incoming and outgoing flows during the use phase. LCA, on the other hand, is based on real or modeled data including information from upstream and downstream of this use phase. The BAT and LCA approaches are therefore complementary and not exclusive. For example, between two BAT analyses of a system to ensure its compliance with the regulations, different models of the systems could be created by conducting LCAs in order to determine the technique that has the least impact throughout its entire life cycle.

Planetary boundaries

In addition to quantifying the flows generated by companies, impact measurements must also include the effects of these flows on the environment on a global scale.

To this end, research and practices also focus on the effects of activities in relation to the different planetary boundaries. These boundary levels reflect the capacity of the planet to absorb impacts, beyond which they are considered to have irreversible effects.

The work of Natacha Gondran1 at Mines Saint-Étienne is contributing to the development of methods for assessing absolute environmental sustainability, based on planetary boundaries. “We work on the basis of global limitations, defined in the literature, which correspond to categories of impacts that are subject to thresholds at the global level. If humanity exceeds these thresholds, the conditions of life on Earth will become less stable than they are today. We are trying to implement this in impact assessment tools on the scale of systems such as companies,” she explains. These impacts, such as greenhouse gas emissions, land use, and the eutrophication of water, are not directly visible. They must therefore be represented in order to identify the actions to be taken to reduce them.

Read more on I’MTech: Circular economy, environmental assessment and environmental budgeting

Planetary boundaries are defined at the global level by a community of scientists. Modeling tools enable these boundaries to be used to define ecological budgets that correspond, in a manner of speaking, to the maximum quantity of pollutants that can be emitted without exceeding these global limits. The next challenge is then to design different methods to allocate these planetary budgets to territories or production systems. This makes it possible to estimate the impact of industries or territories in relation to planetary boundaries. “Today, many industries are already exceeding these boundary levels, such as the agri-food industry associated with meat. The challenge is to find local systems that can act as alternatives to these circuits in order to drop below the boundary levels,” explains the researcher. For example, it would be wise to locate livestock production closer to truck farming sites, as livestock effluents could then be used as fertilizer for truck farming products. This could reduce the overall impact of the different agri-food chains on the nitrogen and phosphorus cycles, as well as the impact of transport-related emissions, while improving waste management at the territorial level.

Together, these different tools provide an increasingly extensive methodological framework for ensuring the compatibility of human activities with the conservation of ecosystems.

1 Valérie Laforest and Natacha Gondran carry out their research in the framework of the Environment, City and Society Laboratory, a joint CNRS research unit composed of 7 members including Mines Saint-Étienne.

Antonin Counillon

This article is part of a 2-part mini-series on the circular economy.
Read more:

Waste management: decentralizing for better management

données de santé, health data

Speaking the language of health data to improve its use

/0 Comments/in , , /by

The world of healthcare has extensive databases that are just waiting to be used. This is one of the issues Benjamin Dalmas, a data science researcher at Mines Saint-Étienne, is exploring in his work. His main objective is to understand the origin of this data to use it more effectively. As such, he is working with players from the public and private sectors for analysis and predictive purposes in order to improve management of health care institutions and our understanding of care pathways.

Research has made great strides in processing methods using machine learning. But what do we really know about the information that such methods use? Benjamin Dalmas is a health data science researcher at Mines Saint-Étienne. The central focus of his work is understanding health data, from its creation to its storage. What does this data include? Information such as the time of a patient’s arrival and discharge, exams carried out, practitioners consulted etc. This data is typically used for administrative and financial purposes.

Benjamin Dalmas’s research involves identifying and finding a straightforward way to present relevant information to respond to the concrete needs of public and private healthcare stakeholders. How can the number of beds in a hospital ward be optimized? Is it possible to predict the flow of arrivals in an emergency room? The responses to these problems rely on the same information: the medical administrative data produced every day by hospitals to monitor their patient pathways.

However, depending on the way in which it is considered, the same data can provide different information. It is the key witness to several investigations. So it must be approached in the right way to get answers.

Understanding data in order to prevent bias

Since it is primarily generated by humans, health data may be incorrect or biased. By focusing on its creation, researchers seek to identify the earliest potential bias. Benjamin Dalmas is working with Saint-Étienne University Hospital Center to study the codes assigned by the hospital upon a patient’s discharge. These codes summarize the reason for which the individual came to the hospital and received care. Doctors who specialize in this coding generate up to 16,000 different codes, a tedious task, for which the hospital wishes to seek assistance from a decision support tool to limit errors. “That means we must understand how humans code. By analyzing large quantities of data, we identify recurring errors and where they come from, and we can solve them,” explains Benjamin Dalmas. Greater accuracy means direct economic benefits for the institution.

However, this mass-produced data is increasingly used for other purposes than reimbursing hospitals. For the researcher, it is important to keep in mind that the data was not created for these new analyses. For example, he has noticed that such a straightforward notion as time may hide a number of different realities. When a consultation time is specified, it may mean one of three things: the actual time of consultation, the time at which the information was integrated in the file, or a time assigned by default. Since the primary objective of this information is administrative, the consultation time does not have a lot of importance. “If we don’t take the time to study this information, we run the risk of making biased recommendations that are not valid. Good tools cannot be created without understanding the data that fuels them,” says the researcher. Without this information, for example, a study focusing on whether or not social inequalities exist and taking into account how long a patient must wait before receiving care, could draw incorrect conclusions.

From reactive to proactive

So researchers must understand the data, but for what purpose? To predict, in order to anticipate, rather than just react. The development of predictive tools is the focus of a collaboration between Mines Saint-Étienne researchers and the company Move in Med. The goal is to anticipate the coordination of care pathways for breast cancer patients. In the case of chronic diseases such as cancer, the patient pathway is not limited to the hospital but also depends on a patient’s family, associations etc. To this end, the researchers are cross-referencing medical data with other social information (age, marital status, socio-economic background, place of residence etc.). Their aim is to identify unexpected factors, in the same way in which the weather, air quality and the even the occurrence of cultural events impact periods of peak arrival in emergency rooms. Predicting the complexity of a care pathway allows the company to allocate the appropriate resources and therefore ensure better care.

At the same time, the Auvergne Rhône-Alpes Regional Health Agency has been working with the researchers since May 2020 to predict hospital capacity strain levels for Covid arrivals. By reporting visual data based on systems of colors and arrows, the researchers provide information about changing dynamics and levels of hospital capacity strain in the region (Covid patient arrivals, positive PCR tests in the region, number of available beds etc.) In this work, researchers are tackling monitoring trends. How are these parameters evolving over time? At what threshold values do they alert the authorities that the situation is getting worse? To answer these questions, the research team provides maps and projections that the health agency can use to anticipate saturation and therefore prevent institutions from becoming overwhelmed, arrange for patients to be transferred etc.

Finding the right balance between volume and representativeness

The study of data raises questions about volume and representativeness, which depend on the user’s request. Proving without equipping oneself requires more data in order to fuel machine learning algorithms. “However, recovering public health data is quite an ordeal. We have to follow protocols that are highly regulated by the CNIL (the French Data Protection Authority) and ethics committees to justify the volume of data requested,” explains Benjamin Dalmas. On the other hand, a request for operational tools must be able to adapt to the on-the-ground realities faced by practitioners. That means working with limited amounts of information. It is a matter of finding the right balance.  

The Mines Saint-Étienne researchers are working with the Saint-Étienne-based company MJ INNOV on these aspects. The company offers an interactive facilitation tool to improve quality of life for individuals with cognitive impairments. Based on videos and sounds recorded during the stages of play, this research seeks to identify the impact of the practice on various subjects (nursing home residents, persons with Alzheimer’s disease etc.). In addition to using the information contained in residents’ files, this involves collecting a limited quantity of new information. “In an ideal world, we would have 360° images and perfect sound coverage. But in practice, to avoid disturbing the game, we have to plan on placing microphones under the table the patients are playing on, or fitting the camera directly within the inside of the table. Working with these constraints makes our analysis even more interesting,” says Benjamin Dalmas.

Measuring the impact of healthcare decision support tools

In the best-case scenario, researchers successfully create a decision support tool that is accessible online. But is the tool always adopted by the interested parties? “There are very few studies on the ergonomics of tools delivered to users and therefore on their impact and actual use,” says Benjamin Dalmas. Yet, this is a crucial question in his opinion, if we seek to improve data science research in such a concrete area of application as healthcare.  

To this end, an appropriate solution often means simplicity. First of all, by being easy-to-read: color schemes, shapes, arrows etc. Visualization and interpretation of data must be intuitive. Second, by promoting explainability of results. One of the drawbacks of machine learning is that the information provided seems to come from a black box. “Research efforts must now focus on the presentation of results, by enhancing communication between researchers and users,” concludes Benjamin Dalmas.

By Anaïs Culot

Read more on I’MTech: When AI helps predict a patient’s care pathway

digital simulation

Digital simulation: applications, from medicine to energy

/0 Comments/in , /by

At Mines Saint-Étienne, Yann Gavet uses image simulation to study the characteristics of an object. This method is more economical in terms of time and cost, and eliminates the need for experimental measurements. This field, at the intersection of mathematics, computer science and algorithms, is used for a variety of applications ranging from the medical sector to the study of materials.

What do a human cornea and a fuel cell electrode have in common? Yann Gavet, a researcher in applied mathematics at Mines Saint-Étienne1 is able to model these two objects as 2D or 3D images in order to study their characteristics. To do this, he uses a method based on random fields. “This approach consists in generating a synthetic image representing a surface or a random volume, i.e. whose properties will vary from one point to another across the plane or space,” explains the researcher. In the case of a cornea, for example, this means visualizing an assembly of cells whose density differs according to whether we look at the center or the edge. The researcher’s objective? To create simulations with properties as close as possible to the reality.

Synthetic models and detecting corneal disorders

The density of cells that make up our cornea –the transparent part at the front of the eye– and its endothelium, provides information about its health. To perform these analyses, automatic cell detection and counting algorithms have been developed using deep neural networks. Training them thus requires access to large databases of corneas. The problem is that these do not exist in sufficient quantity. “However, we have shown that it is possible to perform the training process using synthetic images, i.e. simulated by models,” says Yann Gavet.

How does it work? Using deep learning, the researcher creates graphical simulations based on key criteria: size, shape, cell density or the number of neighboring cells. He is able to simulate cell arrangements, as well as complete and realistic images of corneas. However, he wants to combine the two. Indeed, this step is essential for the creation of image databases that will allow us to train the algorithms. He focuses in particular on the realism of the simulation results in terms of cell geometry, gray levels and the “natural” variability of the observations.

Although he demonstrated that training using synthetic corneal data does not require perfectly realistic representations to perform well, improving accuracy will be useful for other applications. “As a matter of fact, we transpose this method to the simulation of material arrangements that compose fuel cell electrodes, which requires more precision,” explains the researcher.

Simulating the impact of microstructures on the performance of a fuel cell

The microstructure of fuel cell electrodes impacts the performance and durability of solid oxide cells. In order to improve these parameters, researchers want to identify the ideal arrangement of the materials that make up the electrodes, i.e., how they should be distributed and organized. To do this, they play with the “basic” geometry of an electrode: its porosity and its material particle size distribution. This therefore targets the morphological parameters on which the manufacturers intervene when designing the electrodes.

To identify the best performing structures, one method would be to build and test a multitude of configurations. This is an expensive and time-consuming practice. The other approach is based on the simulation and optimization of a large number of configurations. Subsequently, a second group of models simulating the physics of a battery can in turn identify which structures best impact the battery’s performance.

The advantage of the simulations is that they target specific areas within the electrodes to better understand their operation and their overall impact on the battery. For example: exchange zones such as “triple phase” points where ionic, electronic and gaseous phases meet, or exchanges between material surfaces. “Our model allows us to evaluate the best configuration, but also to identify the associated manufacturing process that offers the best energy efficiency for the battery,” says Yann Gavet.

In the medium term, the researcher wishes to continue his work on a model whose dimensions are similar to the observations made in X-ray tomography. An algorithmic challenge that will require more computing time, but will also lead to results that are closer to the reality of the field.

1 Yann Gavet is a researcher at the Georges Friedel laboratory, UMR CNRS/Mines Saint-Étienne

Anaïs Culot

Corenstock Chair: a Trial Cylinder for the Heating Industry

/0 Comments/in /by

As 2021 begins, IMT and elm.leblanc launched the Corenstock Industrial Chair to address issues in energy and digital transition in the domestic heating industry. What is the objective? Within four years, to present a demonstrator for the hot water tank of the future: more resistant, efficient and durable. Behind this prototype lies the development of new economic models for the global transformation of the industry.

The principle of Corenstock Chair (Lifecycle design & systemic approach for energy efficiency of water heating and storage devices), launched in early 2021, is to consider an equipment of the everyday-life to be optimized and used as a model for the transformation of an entire industry. The objective is to present within four years a demonstrator for an innovative hot water tank, more energy efficient, more sustainable and more connected to its users. The project is however not limited to the design of a new domestic hot water tank: it covers the transition problematics of the heating industry as a whole. In line with new business models development, the underlying interest is to redefine the dedicated design methodologies, to generalize sustainable production and end-of-life recovery to implement new economic balances.

The Chair lead by IMT is co-funded in equal parts by the ANR (French Research National Agency) and elm.leblanc, a company specialized in the production of water heaters and boilers. The project relies on the complementary skills of the academic and industrial partners. “We are exploring two key avenues: on the one hand, technological innovation, involving design, materials and smart controls issues” says Mylène Lagardère, a researcher at IMT Lille Douai. She holds the Corenstock Chair, which is jointly coordinated with Xavier Boucher, a researcher at Mines Saint-Etienne. He is responsible for the operational management of the Chair and adds:  “on the other hand, we are working on innovation capabilities, decision-making support for new design methods and the transformation of the production chain together with the company organization”. The two researchers mention that they have “established a trusting and long-term partnership with elm.leblanc, with the goal of pursuing future projects in this area”.

What would be the tank of the future?

“The goal is to improve the energy efficiency of a product that everyone owns at home,” says Mylène Lagardère. Moreover, this equipment is crucial for various thermal systems; whether gas, oil or electricity is used as a source of energy, all of us need to store domestic hot water. To find ways to improve thermal performances, or to select materials to make the cylinder as efficient as possible, involves a significant amount and diversity of research actions. The Chair will thus benefit from the recruiting of 5 PhD students, 4 post-docs and 3 engineers.

Product durability is one of the main areas for improvement. In this sense, predictive maintenance is promising. The use of smart sensors is essential, both to better evaluate the tank performances and to foresee necessary repairs before it breaks down. Mylène Lagardère specifies that the objective is to have “the best compromise between each component, each function of the tank, while taking into account its integration in the environment and the management of the end-of-use”.

Behind the project’s targeted product, general reflection on the entire product life cycle is emerging and address the resources needed for its production, the product durability or the management valorization at the end of use. The project advancements on the improvement of the value chain are expected to be generalized to the entire industry :“The work conducted on the hot water storage tank tank is the entry point for more general work on the economic model itself,” says Xavier Boucher, and these questions are completely integrated in the Corenstock Chair program.

Evolution of the industry

Xavier Boucher emphasizes that “these hot water storage tanks are at the heart of a variable system and a transformation of this sector involves industrial actors at different levels, including the customers as well the maintenance providers”. As a result, the relations to the customers will naturally be modified. The two researchers mention: “this is part of a fairly strong phase of transition in the industries business. It is no longer simply a matter of selling a hot water storage tank, but of including the tank in a multi-actor performance contract.”

From the point of view of companies, they now need to develop customer loyalty and sustainability. “These different levers are necessary to establish a win-win relationship between the customer and the manufacturer,” says Xavier Boucher. Intelligent management offers opportunities to improve energy costs, reduce maintenance costs, and ultimately reduce the final energetic bill. This also reduces for manufacturing and maintenance internal costs.

Mylène Lagardère reports that they aim “to enlighten decision-makers on their economic transformation, particularly through the research for more sustainable indicators”. Her colleague from Saint-Etienne adds “virtualization proves to be a key tool in planning this transition”. The Corenstock Chair assumes the role of simulator of this transformation by observing the behavior of users and various partners. The project combines several routes of innovation, whether aiming towards digital, networking or what is known as digital servicing. This is a strategy converging towards a long-term customer relationship through digital services. “The challenge lies in the evolution of value creation mechanisms,” says Mylène Lagardère.

The Chair is also driven by the dissemination of the results generated and knowledge acquired towards students and future engineers in the field, but also towards the technical and innovation staff of elm.leblanc through professional trainings. Xavier Boucher notes “there are two aspects of training: short modules to increase professional skills, and a specialized master’s degree to integrate more largely the solutions into the industrial framework.” One of the objectives of the specialized master’s degree is to mutualize the skills of each school to encourage interaction between the different expertise domains required.

“Generally speaking, the Chair cannot be simply reduced to technological innovation. On the contrary it covers a global reflection on what the industry of the future is” says Xavier Boucher. This includes facilitating collaboration and opening among different sectors: industrial, technological, and economic. This collaboration is essential to ensure that these transformations are a lasting part of tomorrow’s industry. “The Chair marks what elm.leblanc is building with IMT: a new way of approaching these innovation processes, through a strong collaboration and a relationship of trust to increase the capacity for innovation,” concludes Xavier Boucher.

Tiphaine Claveau.

Circular economy, environmental assessment and environmental budgeting

/0 Comments/in , /by

To implement a robust and durable circular economy strategy, it is important to assess its environmental impacts. Valérie Laforest and Natacha Gondran, both researchers at Mines Saint-Étienne, explain the reasons for incorporating an absolute environmental sustainability assessment method and the underlying concept of “environmental budgeting“.

The lifestyles of our contemporary societies are exerting constant and unsustainable pressure on the balance of our planet. One of the proposed strategies for protecting the Earth’s resources is the circular economy. The concept may seem simple – to encourage recycling and reuse to limit the consumption of raw materials – but environmental impact assessment involves a large number of variables and makes things complicated. This is why researchers are working to design more effective assessment methods for these impacts than the current tools, which are still insufficient. In particular, they are developing a systemic approach that integrates absolute environmental impact assessment.

This issue is at the heart of Valérie Laforest and Natacha Gondran’s work, both researchers at Mines Saint-Étienne1 and members of the Environmental Assessment of Waste, Effluents, Materials, Sediments and Soils (EDEEMS) Scientific Interest Group (SIG). Bringing together seven regional institutions, the EDEEMS SIG carries out, among other things, research on the health and environmental impacts of the circular economy. “The aim is to show that our collaborations can offer the economic world scientific support to overcome the obstacles that still pose a problem”, says Valérie Laforest. The researcher is a specialist in environmental assessment and focusses on the evaluation methods for these impacts. At the heart of the issue, it is important to define the indicators to assess pressure on natural resources and environments caused by humans.

A systemic approach

“This can be very experimental,” says Valérie Laforest. Within the SIG, “we’re starting out on a laboratory scale, then we’ll progressively move up to a pilot level to demonstrate the validity of our work on an industrial scale”. Let us consider the building sector and its impact on ecosystems as an example. Analyses and monitoring are done through ecotoxicology studies or environmental impact assessments from the source of pollutant emissions to their final destination. At the same time, the different transfers constituting all possible interactions between the source and the target, such as groundwater or soils, are also studied.

In the context of the circular economy, evaluating the “source” elements of pollution requires meticulous characterization of the materials produced from recycling. For example, besides the composition of the recycled materials itself, their reactivity must also be studied, with biodegradation tests for sources of organic pollution. These indicators are essential for assessing the different types of pressure on the ecosystems in greater detail.

“There is a growing interest in research into the planet’s limits today. The idea is to compare this work with the impacts generated by production systems using what are known as absolute environmental sustainability assessment methods,” says Valérie Laforest. The Earth not only has a limited amount of resources, but also a limited capacity for absorption. We must therefore take account of all the impacts, both positive and negative, across all sectors. The researcher adds that in order to implement a sustainable circular economy, it is necessary to have “robust and transparent methods that allow us to act with knowledge of the consequences and perfect control of the risks.”

Environmental budgeting

“It is essential to integrate a systemic approach to standardize indicators for the evaluation of environmental impacts,” says Valérie Laforest. And, ultimately, to understand the impact of anthropogenic activities in relation to our planet’s capacity to absorb them. To avoid exceeding this capacity, one idea is to put in place an “environmental budget”. “We are aiming to break down the planet’s absorption capacity by type of activity according to the needs and contribution of each one”, explains Valérie Laforest. “Imagine allocating to each sector of activity a level of emissions that can be absorbed by the planet without too much disruption to the natural balance.”

However, distributing the planet’s total budget across the different activities of society raises various scientific, ethical and political questions. In addition, the total environmental budget for a given sector would have to be able to be broken down between the different brands or companies to see what they consume out of the available budget. “As part of a PhD by Anastasia Wolff, we adapted existing models and tested these methods for the food industry branch of a major retail group. For some indicators, such as climate change, they had already exceeded the allocated budget. Just for eating, this brand and its clients were already exceeding the environmental budget available to them,” explains Natacha Gondran.

Valérie Laforest and Natacha Gondran’s team focuses its work on the choice of relevant indicators, the definition and allocation of this ecological budget to a sector of activity and the evaluation of a given sector’s consumption of and contribution to this budget. It is a mammoth task. This global approach also aims to raise awareness of the scope of the issues in order to target which points to work on to efficiently reduce the environmental impact.

Besides this, there are other essential dimensions for implementing a sustainable circular economy. “The participation and involvement of local actors in the process is essential. It is a key factor of success”, says Valérie Laforest. While the researchers are developing the right tools, it is still vital to work with local actors to understand the situation and implement the process. “At IMT, the circular economy is one of the priority actions on the theme of renewable energy and resources. In addition, IMT is at the heart of numerous projects within its different schools. IMT also supports platforms such as the Plateforme Territoire at Mines Saint-Étienne, which aims in particular to help local actors visualize information through a spatial representation and target priority issues,” says Valérie Laforest.

1 Valérie Laforest and Natacha Gondran carry out their research in the framework of the Environment, City and Society laboratory, a joint CNRS research unit composed of 7 members including Mines Saint-Étienne.

Tiphaine Claveau

Decontaminating and treating waste from the steel industry

/0 Comments/in , /by

The manufacture of steel produces mineral residues called steel slags, which are stored in large quantities in slag dumps. These present a dual challenge. On the one hand, they are potentially harmful for the environment and health, and on the other hand they are a useful resource for certain industries. The HYPASS project at Mines Saint-Étienne aims to address both of these issues. Launched in 2018, it offers new solutions for extracting heavy metals and managing pollution from steel slag dumps.

During the steel manufacturing process, iron ore is heated to high temperatures. A lighter residue phase forms on the surface, like whey. When it has cooled, this artificial rock, the slag, is poured into slag dumps which can spread over several hectares.

In France, there are some 30 million tons of steel slag accumulated in dumps. This residue contains heavy metals that are a danger for health and the environment on a large scale because polluting particles can be transmitted through erosion. It is therefore important to limit the diffusion of these particles. 

However, this slag can be used! There are a wide range of fields of application for steel slag today, including the production of concrete and cement, the glass industry, ceramics and even agriculture. Unfortunately, the presence of heavy metals in the slag can be a stumbling block because they can have a negative impact on the spaces where they are used. These metals, such as chrome, molybdenum or tungsten, each have different industrial uses. By efficiently and optimally extracting the heavy metals from the steel slag, these slag dumps could be decontaminated and new ways of reusing the materials could be developed. 

To address these challenges, the HYPASS (HYdrometallurgy and Phyto Management Approaches for Steel Slag management) project, financed by the French National Research Agency and certified by AXELERA, a competitiveness cluster for the chemical and environmental sectors, was launched in 2018. It includes Mines Saint-Étienne.1 The HYPASS methodology has been implemented at the slag dump in Châteauneuf, in the Loire, which is listed as a member of the SAFIR (French Innovation and Research Sites) network. The project aims to develop an innovative technological approach to allow recovery of strategic metals from slag and, at the same time, a more environmentally-friendly management of steel slag dumps.

Extracting heavy metals                                 

The first part of the project consists in extracting the heavy metals from the slag using hydrometallurgy. This technique extracts minerals using a solution during a process called leaching. “Hydrometallurgy dates from the early 20th century and was originally used on ores with a high metal content, such as gold extraction by cyanidation”, explains Fernando Pereira, a researcher on the HYPASS project at Mines Saint-Étienne. “However, over the last 30 years or so, hydrometallurgy has also been increasingly used for the treatment of waste which could be considered as low metal content ores.”

Although the first stages of the technique can sometimes differ, it generally involves physical pretreatment of the mineral matrix, dissolution of the metals in acid or alkaline reagents, high-temperature roasting and then purification and refining.

As part of the HYPASS project, the researchers from Mines Saint-Étienne, in association with the French Geological Survey (BRGM), have made several important adjustments in the laboratory to the stages in the hydrometallurgical extraction process. These adjustments had to take account of the efficiency of the techniques as well as their financial aspects, because some processes can prove to be particularly expensive when used at an industrial scale.

“The most expensive aspect isn’t the fact of using the different reagents during the leaching stage, but the preliminary grinding and roasting stages [heating to make the metal oxides more soluble] because they require large amounts of energy”, says Fernando Pereira. An important modification to the temperature adjustment during the roasting stage was therefore necessary to optimize the efficiency in relation to cost. Another original adjustment was made in the choice of reagents used to extract the metals. Usual methodologies are based on the use of acids to dissolve the ores, but this implies a non-selective extraction, meaning the different compounds are mixed in the extraction solution. The HYPASS methodology has developed the use of alkaline reagents that allow the specific extraction of strategic metals, thus facilitating their subsequent use as well as that of the mineral matrix. 

Finalization of the phytostabilization method 

The second part of the project consists in stabilizing the slag dump pollution by covering it with plants. However, it is very difficult to grow plants on slag dumps for a number of reasons: the soil of these sites is extremely alkaline, it has no organic matter and few essential elements for growth such as nitrogen and phosphorus. In addition, this soil has poor rainwater retention. It is also highly toxic, due in particular to the presence of a specific form of chromium, known as chromium VI, which is a known carcinogen.

Read more on I’MTech: When plants help us fight pollution

It is therefore a real challenge to grow plants in an environment as hostile as a slag dump. Mathieu Scattolin, in charge of the phytostabilisation part of the HYPASS project, has made important adjustments to the growing conditions of plants in these environments. “Experiments have shown that pH is a key factor for the success of implementing phytostabilization on slag heaps,” says Pereira.

When the soil is too alkaline, certain chemical elements that are important for plant growth (such as manganese, zinc and phosphorus) develop properties that make them less phytodisposable, meaning that less is transferred from the soil to the plant. On the other hand, toxic chemical elements, such as Chrome VI, tend to be assimilated more. 

To resolve these difficulties, a species of fungus called Rhizophagus irregularis was inoculated with the plants. “Wherever we were in the slag dump, the inoculation of Rhizophagus Irregularis led to relatively fast colonization of the root systems”, says the researcher. This symbiosis notably allows the soil to be made less alkaline, thus increasing the phytodisposability of important elements and reducing that of chromium VI. The presence of this fungus in the soil also allowed the supply or organic matter and the increase of the water retention of the soils.

The perfection of the optimal growth conditions was tested in the laboratory and then in experimental sections of Châteauneuf slag dump, which led to a rapid colonization of the root systems. It also led to the launch of a new component in the HYPASS project.

A decision support tool is being developed to compare different scenarios for managing steel slag dumps. Fernando Pereira explains that “this tool will allow us to compare and choose management scenarios for steel slag based on criteria concerning environmental impact, financial costs and support for the ecosystem.” The design work is based on the principles of life cycle analysis (LCA) to allow the tool to provide an estimation of the global environmental impacts for each possible scenario.

In terms of hydrometallurgy, there are still a few phases of development in the laboratory. Kinetic monitoring is envisaged in order to minimize the leaching time of the metals. Metal oxide capture tests and solutions using microwave technology – to see if it is possible to get rid of the roasting stage, which is particularly energy-intensive – are also being developed. The phytostabilization part, on the other hand, seems to be finalized.

A European project is envisaged as a follow-up, including a scale-up and the development of more important laboratory trials. “This would be part of a Horizon Europe-type project” says the researcher, to give a broader perspective of the project.

By Antonin Counillon.

1 Mines Saint-Étienne is part of the HYPASS project through the Environment, City, Society mixed research unit.

Hydrogen: transport and storage difficulties

/0 Comments/in , /by

Does hydrogen hold the key to the great energy transition to come? France and other countries believe this to be the case, and have chosen to invest heavily in the sector. Such spending will be needed to solve the many issues raised by this energy carrier. One such issue is containers, since hydrogen tends to damage metallic materials. At Mines Saint-Étienne, Frédéric Christien and his teams are trying to answer these questions.

In early September, the French government announced a €7 billion plan to support the hydrogen sector through 2030. With this investment, France has joined a growing list of countries that are betting on this strategy: Japan, South Korea and the Netherlands, among others.

Nevertheless, harnessing this component poses major challenges across the supply chain. Researchers have long known that hydrogen can damage certain materials, starting with metals. “Over a century ago, scientists noticed that when metal is plunged into hydrochloric acid [from chlorine and hydrogen], not only is there a corrosive effect, but the material is embrittled,” explains Frédéric Christien, a researcher at Mines Saint-Étienne1. “This gave rise to numerous studies on the impact of hydrogen on materials. Today, there are standards for the use of metallic materials in the presence of hydrogen. However, new issues are constantly arising, since materials evolve on a regular basis.”

Recovering excess electricity produced but not consumed

For the last three years, the Mines Saint-Étienne researcher has been working on “power-to-gas” research. The goal of this new technology: recover excess electricity rather than losing it, by converting it to gaseous hydrogen through the process of water electrolysis.

Read more on I’MTech: What is hydrogen energy?

“Power-to-gas technology involves injecting the resulting hydrogen into the natural gas grid, in a small proportion, so that it can be used as fuel,” explains Frédéric Christien. For individuals, this does not change anything: they may continue to use their gas equipment as usual. But when it comes to transporting gas, such a change has significant repercussions. Hence the question posed to specialists about the durability of materials: what impact may hydrogen have on the steel that makes up the majority of the natural gas transmission network?

Localized deformation

In collaboration with CEA Grenoble (Atomic Energy Commission), the Mines Saint-Étienne researchers have spent three years working on a sample of pipe in order to study the effect of the gas on the material. It is a kind of steel used in the natural gas grid.

The researchers observed a damage mechanism, through the “localization of plastic deformation.” In concrete terms, they stretched the sample so as to replicate the mechanical stress that occurs in the field, due in particular to changes in pressure and temperature. Typically, such an operation results in lengthening the material in a diffuse and homogeneous way, up to a certain point. Here, however, under the effect of hydrogen, all the deformation is concentrated in one place, gradually embrittling the material in the same area, until it cracks. Under normal circumstances, a native oxide layer of the material prevents the hydrogen from penetrating inside the structure. But under the action of mechanical stress, the gas takes advantage of the crack to cause localized damage to the structure.

But it must be kept in mind that these findings correspond to laboratory tests. “We’re a long way from industrial situations, which remain complex,” says Frédéric Christien. “It’s obviously not the same scale. And, depending on where it’s located, the steel is not always the same – some have lining while others don’t and it’s the same thing for heat treatments.” Additional studies will therefore be needed to better understand the effect of hydrogen on the entire natural gas transport system.

The production conundrum

Academic research thus provides insights into the effects of hydrogen on metals under certain conditions. But can it go so far as to create a material that is completely insensitive to these effects? “At this point, finding such a dream material seems unrealistic,” says the Mines Saint-Étienne researcher. “But by tinkering with the microstructures or surface treatments, we can hope to significantly increase the durability of the metals used.”

While the hydrogen sector has big ambitions, it must first resolve a number of issues. Transport and storage safety is one such example, along with ongoing issues with optimizing production processes to make them more competitive. Without a robust and safe network, it will be difficult for hydrogen to emerge as the energy carrier of the future it hopes to be.

By Bastien Contreras.

1 Frédéric Christien is a researcher at the Georges Friedel Laboratory, a joint research unit between CNRS/Mines Saint-Étienne

high temperature fuel cell

Turning exhaust gases into electricity, an innovative prototype

/0 Comments/in , /by

Jean-Paul Viricelle, a researcher in process engineering at Mines Saint-Étienne, has created a small high-temperature fuel cell composed of a single chamber. Placed at the exhaust outlet of the combustion process, this prototype could be used to convert unburned gas into energy.

Following the government’s recent announcements about the hydrogen industry, fuel cells are in the spotlight in the energy sector. Their promise is that they could help decarbonize industry and transportation. While hydrogen fuel cells are the stars of the moment, research on technologies of the future is also playing an important role. At Mines Saint-Étienne[1], Jean-Paul Viricelle has developed a new high-temperature fuel cell – over 600°C – called a mono-chamber. It is unique in that it can be fueled not only by hydrogen, but by a mixture of more complex gases, representative of the real mixtures at the exhaust outlet of a combustion process. “The idea is not to compete with a conventional hydrogen fuel cell, since we’ll never reach the same yield, but to recover energy from the mixtures of unburned gas at the outlet of any combustion process,” explains the researcher, who specializes in developing chemical sensors.

This would help reduce the amount of gaseous waste resulting from combustion. These compounds also contribute to air pollution. For example, unburned hydrocarbons could be recovered, cleaned and oxidized to generate electricity. Why hydrocarbons? Because they are composed of carbon and hydrogen atoms, the fuel of choice for conventional fuel cells. One of the most advanced studies on the concept of mono-chamber cells was published in 2007 by Japanese researchers who recovered a gaseous mixture at the exhaust outlet of a scooter engine. Even though it was not very powerful, the experiment proved the feasibility of such a system. Jean-Paul Viricelle has created a prototype that seeks to improve this concept. It uses a synthetic gaseous mixture, which is closer to the real composition of exhaust gases. It also optimizes the fuel cell’s architecture and materials to enhance its performance.

The inner workings of the cell

A fuel cell consists of three components: two electrodes, which are hermetically separated by an electrolyte. It is fueled by a gas (hydrogen) and air. Once inside the cell, an electrochemical reaction occurs at each electrode. This results in the exchange of electrons, which generates the electricity supplied by the cell. The architecture of conventional cells is often constrained, which prevents them from being reduced in size. To overcome these obstacles, Jean-Paul Viricelle has opted for a mono-chamber cell, composed of a single compartment. In this concept, hydrogen cannot be directly used as a fuel since it is too reactive when it comes into contact with air and could blow up the device! That’s why the researcher fuels it with a gaseous mixture of hydrocarbons and air. What does this new structure change compared to a conventional cell? “The electrolyte no longer acts like a seal, as it does in a conventional cell, and serves only as an ionic conductor. But the cathode, and the anode come into contact with all the reactants. So they must be perfectly selective so that they only react with one of the gases,” explains Jean-Paul Viricelle.

In practice, a synthetic exhaust gas is sent over the cell. The electrochemical reaction that follows is standard: an oxidation at the anode and a reduction at the cathode generate electricity. This cell works at a high temperature (over 600°C), a condition that is essential for the electrolyte to transport the electrons. And, since the gas mixture that fuels the cell gives off heat, a small enough cell could be self-sustaining in terms of heat. This means that once it has been initiated by an eternal heat source, it would become self-sufficient in terms of heat. Moreover, laboratory tests have shown a power density equivalent to that of conventional cells. However, significant gas flows must be sent over this demonstrator that measures 4 cm² with a low energy conversion rate as a result. Stacking mono-chamber cells, rather than a single cell, as is the case for this prototype, could help resolve this problem.

A wide range of applications

For now, markets are more conducive to low-temperature fuel cells in order to prevent the devices from overheating. Nevertheless, the concept developed by Jean-Paul Viricelle presents a number of benefits. It opens the door to new geometries for placing two electrodes on the same surface. Such design flexibility facilitates a move towards miniaturization. Small high-temperature fuel cells could, for example, fuel industrial microreactors. The cells could also be integrated at the exhaust outlet of an engine to convert unburned hydrocarbons into electricity, as in the Japanese experiment. In this case, the energy recovered would power electronic devices and other sensors within the vehicle. More broadly, this energy conversion device could help respond to efficiency issues for any combustion system, including power plants. Despite all this, mono-chamber fuel cells remain concepts that have not made their way out of research laboratories. Why is this? Up to now, there has been a greater focus on hydrogen production than on energy recovery.

By Anaïs Culot.

[1] Jean-Paul Viricelle is the director of the Georges Friedel Laboratory, a joint research unit between Mines Saint-Étienne and CNRS.

AI

AI for interoperable and autonomous industrial systems

/0 Comments/in , /by

At Mines Saint-Étienne, researchers Olivier Boissier, Maxime Lefrançois and Antoine Zimmermann are using AI to tackle the issue of interoperability, which is essential to the industry of the future. The standardization of information in the form of knowledge graphs has allowed them to enable communication between machines that speak different languages. They then operate this system via a network of autonomous distributed agents on each machine to automate a production line.

Taking a train from France to Spain without interoperability means having to get off at the border since the rails are not the same in both countries. A train that hopes to cross over from one rail line to another is sure to derail. The same problem is posed on factory floors – which is why the interoperability of production lines is a key issue for the industry of the future. In an interoperable system, machines can communicate with one another in order to work together automatically, even if they don’t speak the same language. But this is not easy to implement. Factory floors are marked by a kind of cacophony of computer languages. And every machine has its own properties: a multitude of manufacturers, different applications, diverse ways of sending, measuring and collecting information etc. Such heterogeneity reduces the flexibility of production lines. During the Covid-19 crisis, for example, many companies had to reconfigure all of their machines by hand to set up new production operations, such as manufacturing masks. “As of now, on factory floors everything is coded according to an ideal world. Systems are incapable of adapting to change,” says Maxime Lefrançois, a specialist in web semantics. Interoperability also goes hand in hand with competition. Without it, ensuring that a factory runs smoothly would require investing in a single brand of equipment to be certain the various parts are compatible.  

There is no single method for making a system interoperable. Along with his colleagues at Mines Saint-Étienne, the researcher is addressing the issue of interoperability using an approach based on representing data about the machines (manufacturer, connection method, application, physical environment etc.) in a standardized way, meaning independent of the language inherent to a machine. This knowledge is then used by what is known as a multi-agent software system. The goal is to automate a production process based on the description of each machine.

Describing machines to automate decision-making

What does the automation of an industrial system imply? Service delegation, primarily. For example, allowing a machine to place an order for raw materials when it detects a low stock level, instead of going through a human operator. For this, the researchers are developing mechanisms for accessing and exchanging information between machines using the web of things. “On the web, we can set up a communication interface between the various devices via standardized protocols. These methods of interaction therefore reduce the heterogeneity of the language of connected devices,” explains Antoine Zimmermann, an expert in knowledge representation at Mines Saint-Étienne. All of the modeled data from the factory floor is therefore accessible to and understood by all the machines involved.

More importantly, these resources may then be used to allow the machines to cooperate with one another. To this end, the Mines Saint-Étienne team has opted for a flexible approach with local decision-making. In other words, an information system called an autonomous agent is deployed on each device and is able to interact with the agents on other machines. This results in a 4.0 word-of mouth system without loss of information. “An autonomous agent decides what to do based on what the machines upstream and downstream of its position are doing. This reasoning software layer allows the connected device to adjust its behavior according to current status of the system,” says Olivier Boissier, who specializes in autonomous agent systems at Mines Saint-Étienne. For example, a machine can stop a potentially dangerous process when it detects information indicating that a device’s temperature is too high. Likewise, it would no longer be necessary to redesign the entire system to add a component, since it is automatically detected by the other machines.

Read more on I’MTech: A dictionary for connected devices

Depending on the circumstances of the factory floor, a machine may also connect to different production lines to perform other tasks. “We no longer code a machine’s specific action, but the objective it must achieve. The actions are deduced by each agent using the data it collects. It therefore contributes to fulfilling a general mission,” adds the researcher. In this approach, no single agent can achieve this objective alone as each one has a range of action limited to its machine and possesses only part of the knowledge about the overall line. The key to success it therefore cooperation. This makes it possible to transition from producing cups to bottles, simply by changing the objective of the line, without reprogramming it from A to Z.

Towards industrial experiments

Last summer, the IT’m Factory technological platform, a simulated industrial space at Mines Saint-Étienne, hosted a case study for an interoperable and cooperative distributed system. This production line starts out with a first machine responsible for retrieving a cup in a storage area and placing it on a conveyor. A filling system then fills the cup with a liquid. When this second machine has run out of product to pour, it places a remote order with a supplier. At every step, several methods of cooperation are possible. The first is to send a message from one agent to another in order to notify it of the task it has just performed. A second method uses machine perception to detect the action performed by the previous machine. A certain method may be preferable depending on the objectives (production speed etc.).

The researchers have also shown that a robot in the middle of the line may be replaced by another. Interoperability made it possible for the line to adapt to hardware changes without impacting its production. This issue of flexibility is extremely important with a view towards integrating a new generation of nomadic robots. “In September 2020, we start the SIRAM industry of the future project, which should make it possible to deploy interoperable, adaptable information systems to control mobile robotic assistants,” says Maxime Lefrançois. In the future, these devices could be positioned at strategic locations in companies to assist humans or retrieve components at different parts of the production line. But to do so, they must be able to interact with the other machines on the factory floor.  

Anaïs Culot