Turning old into new: A second life for vehicle components

AI-supported assistance system for semi-automatic sorting of used components. Credit: Fraunhofer Society

A large number of used parts end up in the scrap yard for recycling every year. However, it is much more resource efficient to remanufacture generators, starter motors and the like as part of a recirculation method. This reduces waste, lowers CO2 footprint and prolongs the life of the products. In the EIBA project, the Fraunhofer Institute for Production Systems and Design Technology IPK is developing an AI-based help system for semi-automatic image-based identification of used parts without QR or barcodes. This will help the worker with the sorting process so that more used components can be sent for remanufacturing.

The circular economy is an important lever for achieving the goals of the Paris Climate Agreement. Remanufacturing – the process of rebuilding used equipment to reflect its original condition – can be a key factor in the circular economy. Given that equipment is reused, the life of the products is extended. Researchers at Fraunhofer IPK are striving for this goal as part of the EIBA project, which is funded by the German Federal Ministry of Education and Research (BMBF). Project partners are Circular Economy Solutions GmbH, Technische Universität Berlin and the National Academy of Science and Engineering acatech. The purpose is to remanufacture used parts instead of recycling them. According to a study from the VDI Center for Resource Efficiency, manufacturing costs can be reduced by up to 80 percent by remanufacturing used parts and material consumption can be reduced by up to about 90 percent.

The four-eye principle reduces the error rate

Clearly identifying and assessing vehicle components is an important challenge in the remanufacturing process. Many products are virtually indistinguishable from each other and are difficult to identify due to dirt and wear. To date, this task has been performed manually by specialists under great time pressure. This is where Fraunhofer IPK’s AI-based assistance system comes in: This system will help employees identify and assess defective wear parts such as starter motors, air conditioning compressors and generators based on the four-eye principle.

Transforming old into new: A second life for vehicle components

Product deviation – two generators with different article numbers are visually identical. Credit: Fraunhofer IPK / Larissa Klassen

People and machines work hand in hand

“In the automotive industry, once the used part has been removed, it is assessed at the sorting center based on certain criteria to determine whether it can be reused,” says Marian Schlüter, researcher at Fraunhofer IPK. “However, this is far from trivial. Article number, which is the only visually reliable property, is no longer legible, scratched, painted or the type plates may have fallen off. This means that the worker stops discarding it by mistake, and it is recycled cleanly. as a material. This is exactly where AI comes into play. It identifies the parts used based on their appearance, regardless of article number, and sends them off for a new life. ” Identification characteristics such as weight, volume, shape, size and color characteristics are used, but customer and delivery data are also included in the evaluation. The employee, on the other hand, discovers any loose components or burned parts, this is where the AI ​​system’s image processing function falls short.

Transforming old into new: A second life for vehicle components

Condition deviation – two starts with identical article numbers differ in appearance due to wear marks. Credit: Fraunhofer IPK / Larissa Klassen

The employee has the last word

But exactly what does the process involve? First of all, the used part undergoes image-based processing. This means that the system scans the packaging to gather information about the product group. By dividing this process into sub-tasks, the search interval for identification is reduced from 1: 120,000 to 1: 5000. The used part is then weighed and recorded by 3D stereo cameras. The results obtained from the image-based processing step are combined with the analysis of sub-specific commercial data, such as origin, date and location, in order to be able to identify the part in a reliable manner. The information is processed by two AI systems simultaneously. The results from the image-based processing step are combined with the analysis of sub-specific commercial data, such as origin, date and location, so that the part used is identified in a reliable and comprehensive manner. “One AI system was trained for image processing, which was our task for the project, and the other was trained for commercial data. We use convolutional neural networks for the AI ​​method of image processing. These are algorithms from the field of machine learning that specialize in extracting. functions from image data “, explains the production engineer. The result of the identification process is shown to the employee, who receives a list of proposals with a preview image and article number and thus retains full control. “The AI ​​is incorporated into the ongoing business and the work process is not disrupted. The worker has no extra tasks to perform, which is extremely important in this time-sensitive process. Our AI system runs on conventional desktops. All the company’s websites can be connected via the cloud , which means that an employee’s practical knowledge can benefit workers elsewhere. ” The versatile technology can be used for all types of dimensionally stable components.

Each year, about five to seven percent of one million used parts processed by Circular Economy Solutions GmbH – that is, up to 70,000 parts – are discarded because they cannot be identified. A study conducted as part of the project showed a recognition accuracy of 98.9 percent. Seen in terms of the 70,000 used parts that are discarded, it is expected that AI-based identification will allow 67,200 more used parts to be fed back to the bike than before.

The project partners continuously review the sustainability of this program. The goal of the project is to keep more used parts in circulation. But is all this worth it given the high amount of energy required to train AI and operate cameras and computers? “The answer to this is a resounding yes. The potential for CO2-equivalent savings are high, while the energy requirements for AI are negligible. According to our forecasts, the AI ​​system will pay for itself in terms of CO2 equivalent to no more than one week “, the researcher concludes.


Use an app to identify components


Provided by Fraunhofer-Gesellschaft

Quote: Turning Old to New: A Second Life for Vehicle Components (2022, April 1) Retrieved April 1, 2022 from https://techxplore.com/news/2022-04-life-vehicle-components.html

This document is subject to copyright. Apart from any fair business for private study or research, no part may be reproduced without written permission. The content is provided for informational purposes only.

Leave a Comment