Published on 28 October 2024
The recycling market is expanding, even to assembly plants! Using a software ecosystem, the European ALICIA project aims to promote the circulation of production resources. Scientists from IMT Atlantique involved in the project are working to develop a platform to optimize production lines, by minimizing machine changeovers and promoting the use of second-hand resources.
In a world where technology is evolving at lightning speed, and where smartphones are an ultimate and essential tool for everyday life, it is tempting to want the latest, most powerful, most spectacular technological features… Meaning that every six months, new models are produced and brought to market.
This breakneck pace of production obviously poses major challenges in terms of sustainability and e-waste management, but also in terms of production lines. Manufacturing a new smartphone model usually means changing the assembly line and equipment. “Many production resources and tools are thrown away before their end-of-life, even though industrial equipment can last up to 20 years,” says Simon Thevenin, operations research scientist at IMT Atlantique and member of the European ALICIA project.
To respond to this problem, this project aims to provide an ecosystem of different software programs to encourage the use of second-hand resources in assembly lines. The ALICIA project began in January 2023 for a three-year period, following a call for projects from the Horizon Europe program around the development of digital tools to support the circular economy. The cases for use are mainly focused on the automotive industry, thanks to the participation of manufacturers from this sector, including Continental and Comau.
The second-hand market for industrial equipment is nothing new, but “there are more and more resources, so it’s a growing market, into which we’re introducing new tools and technologies”, says Simon Thevenin. To meet the needs of factories wishing to create new assembly lines, the ALICIA project offers a circular manufacturing ecosystem (CME) made up of several software components.
The first involves analyzing and identifying the new line’s resource requirements. An e-platform, developed for the project, will catalog second-hand equipment from other plants across Europe. This equipment will be considered against the production assets already available at the client company, and new equipment that can be ordered from manufacturers. An intelligent matching tool developed by IMT Atlantique, the AI-Matchmaking Engine, will then make the link between the plant’s needs and the available resources, new or used.
The future assembly line will then be digitally simulated using a tool called Digital Shadow. “This will enable the customer to visualize the production line, and then decide whether or not to buy second-hand equipment,” says Simon Thevenin. Where appropriate, middleware (third-party software used to enable different IT applications to communicate with each other) called Plug & Produce will facilitate the commissioning of equipment on the assembly line, using digital twins. When decommissioned, the assets can either be recycled, if they have reached the end of their useful life, or placed (back) on the marketplace developed for the project, thus feeding ALICIA’s circular ecosystem.
Diagram showing ALICIA’s circular manufacturing ecosystem (CME) for production resources. IMT Atlantique has developed the AI-Matchmaking Engine, a tool that matches production resources with the requirements of future assembly lines. Credits: ALICIA Project.
An assembly line is a set of stations to which resources are assigned, repeating the same tasks in sequence. The product to be manufactured moves from one station to another until it is ready. Depending on the industry, a line can range from around 20 tasks to 500 or even 1,000 (for car assembly, for example). The design of an assembly line is based on the intersection of the different tasks required to manufacture the product, and the different resources that perform these tasks in a certain amount of time. Traditionally, a line is designed specifically for the product it is to manufacture, and remains fixed for a generation (six months, a year, etc.). Each time the line is redesigned, new tasks and resources are reassigned to each station.
The goal of Simon Thevenin and his team is to develop tools that will determine which equipment to place at each station, whether to buy it new or second-hand, when to replace it, whether to wait for its end-of-life or replace it with new, more efficient technology, and so on. “This involves taking the line’s entire life cycle into account, and imagining how products manufactured in the present will evolve in the future”, says the researcher.
Based on a production line in operation, the scientists imagine several scenarios, in which new tasks requiring new resources are added; as well as the possible evolutions of these scenarios. In the ALICIA project, the scenarios are generated randomly, “but we can ask the client what the most likely changes are,” says Simon Thevenin. By taking these scenarios and possible future modifications into account, the researcher and his team hope to design assembly lines that are more resilient to change: so that with each new product it is easier to modify resources.
The assembly line is thus considered like a combinatorial optimization problem, i.e. aiming to find the best option among a finite number of configurations. This involves a trade-off between different types of cost: linked to the purchase and installation of equipment, to the number of stations, to training technical staff on new machines, and so on. A computer could test all possible combinations and find which is the most optimal, but “the problem is that the number of combinations is generally very large, and in practice, this is not feasible”, says Simon Thevenin.
IMT Atlantique scientists therefore use mathematical models that respect certain rules and constraints. Of course, the more scenarios there are, the longer and more complicated the model is to solve. “We generally set a time limit – for example, one hour – and see how many scenarios the model is capable of solving in that time, whether it’s 100 or 1,000,” says Simon Thevenin. Artificial intelligence techniques, particularly reinforcement learning, are also used to try and solve these “dynamic stochastic” problems. “Stochastic” because of the uncertainty of future scenarios, and “dynamic” because, with each generation, the product changes and so does the assembly line.
The software developed will be able use input data (stations, tasks, resources) to produce proposals for an optimized assembly line, including replacing a damaged piece of equipment with a resource in better condition from the marketplace. Teams at IMT Atlantique are currently completing a first version of the project and will shortly be moving on to the application of the defined use cases. “The next step is to assemble the identified optimal assembly line on a computer, so that the manufacturer can see what it looks like and decide whether or not to take the second-hand approach,” says Simon Thevenin.
The Horizon Europe ALICIA project is coordinated by the Technical University of Munich (TUM), and has been awarded funding of €5.8 million for a three-year period, starting in January 2023. It is the result of a Horizon 2020 project called ASSISTANT, which also involved TUM, but which was coordinated by IMT Atlantique. “The ALICIA project picks up on one of ASSISTANT’s main areas of activity, which is industrial process planning. Sustainability objectives have been added with regards to the purchase of second-hand equipment,” says Simon Thevenin.
This is not the first time the researcher has worked with TUM, as he was also involved in the ASSISTANT project. A number of collaborative projects have already been carried out around the sustainability of industrial production chains – including Reconfigurable and Dreams – as part of the Franco-German Academy for the Industry of the Future. It was therefore only natural that, when setting up the ALICIA project following on from the ASSISTANT project, the teams from the Munich-based institution invited their partners at IMT Atlantique to join them, thus coming full-circle.
Protecting sensitive sites: AI in radar systems