
Fraunhofer looks to automation for electronics disassembly
Researchers at the Fraunhofer Institute for Factory Operation and Automation IFF are developing technology for automated, nondestructive robotic disassembly of electronics for remanufacturing and material recycling. The project, named iDEAR (Intelligent Disassembly of Electronics for Remanufacturing and Recycling), will help establish an advanced circular economy.
Fraunhofer cites a UN report that e-waste being produced is increasing worldwide and that recycling is not keeping up. As a consequence valuable raw materials are not being recovered or re-used. Further, the rise in e-waste is exacerbated by speed of technology advances, which is cutting the lifespans of electronic devices and driving demand for finite raw materials. Automation of electronics disassembly is key to boosting recycling.
In a press release Fraunhofer states “Worldwide annual e-waste generation could rise to as much as 74 million metric tons by 2030. Only a small fraction of all electronic devices is recycled. Over 80 percent of the e-waste generated ends up in landfills or incinerators, including all the valuable raw materials, precious metals, and rare earths contained in the electronics. Incineration can release hazardous chemicals and substances into the environment.”
E-waste that undergoes treatment typically gets shredded, while only a limited portion is manually disassembled, cleaned of hazardous substances, broken down mechanically and sorted into different fractions. However, manual disassembly entails high costs and is not very effective.
The iDEAR project researchers at Fraunhofer IFF in Magdeburg are combining knowledge management, metrology, robotics and artificial intelligence into an intelligent system for automated and nondestructive disassembly processes to establish a certifiable, closed-loop waste management system.
“We intend to revolutionize the disassembly of e‑waste. Current solutions require substantial engineering and are limited to a particular product group. In the iDEAR project, we are pursuing a data-driven methodology so that as the widest variety of products, from computers to microwaves to home appliances, can be disassembled in real time with little engineering,” says Dr. José Saenz, manager of the Assistive, Service and Industrial Robots Group at Fraunhofer IFF.
Initially iDEAR is concentrating on the automated disassembly of computers. However, the system is intended to be upgradeable for any equipment in the future.
The iDEAR system automates the identification of assemblies using high-precision metrology. Optical sensor systems and 3D cameras with AI-powered algorithms then scan labels with information on the manufacturer, product type and number. They also detect component types and locations, examine geometries and surfaces, assess the condition of fasteners, such as screws and rivets, and detect anomalies.
“Optical metrology helps scan labels and sort different parts, such as screws, for instance. Previously trained machine learning algorithms and AI interpret the image data and enable the identification and classification of materials, plastics and components in real time based on sensor and spectral data,” Saenz explains. For instance, the AI detects whether a screw is concealed or rusted. All the data are stored in a digital disassembly twin, which is a product instance, so to speak, and also provides information on whether a similar product has ever been disassembled.
In the next step, the disassembly sequence is defined so that iDEAR software can determine whether to execute a complete disassembly or only focus on the recovery of specific, valuable components. For example, glued components hinder nondestructive disassembly while rusty or stripped screws or deformed components are also difficult to deal with. The disassembly process starts based on this high-level information. The robot then receives instructions and operations to complete. It is all able to change each tool needed in between the individual steps. The robot is able to perform a wide variety of skills in the disassembly process. The demonstrator even succeeded in tests to remove a motherboard from a computer—a very complex task that requires a high level of precision.
“We used AI for that. An AI agent is initially trained to complete the process on the simulation model and later we transfer the trained robot action to the real-world experimental setup. This isn’t necessary for simple skills, such as localization. We use sensor and camera data for that,” Saenz explains.
Fraunhofer states that “the demonstrators for the subprocesses have been built, including a station for the identification and analysis of computers, a demonstrator of the assessment model connected to the digital twin of the product and the disassembly sequence, a digital twin demonstrator, a demonstrator of the automatic execution of skills-based robot actions for disassembly and a demonstrator of AI generated robot actions to remove motherboards from the housing. In the next step, the demonstrators will be interconnected. The goal is one demonstrator that integrates all of the technological developments and can execute all of the of automated disassembly processes.”
“Recycling and remanufacturing are a key for manufacturing companies to ensure access to raw materials. The recovery of these materials not only reduces the environmental impact of e‑waste but also constitutes a valuable source of raw materials for new products,” Saenz says.
Image: The robot locating and approaching the screws on the computer housing. Copyright Fraunhofer IFF.
