Working on the IFACOM project, supported by the European Commission, the researchers are developing an advanced real-time process control system focused especially on high-precision, high-value and high-performance parts as well as custom-designed components. Combining artificial intelligence and innovative sensors, the system seeks to overcome the long-standing issue of production defects, which cost manufacturers millions of euros a year in waste, production reruns and part redesigns.
“Manufacturing defects are a huge issue for the industry. In some cases, 50% of production can end up as scrap because of defects, while in some complex manufacturing lines the rate of scrap can be as high as 90%,” explains Odd Myklebust, the IFACOM coordinator at the Norwegian University of Science and Technology in Trondheim.
Even slight variances in materials, components or production processes can cause an entire production run to be defective. It does not affect the quality of the parts reaching end users, as strict quality checks are conducted on all batches after production. But therein lies the problem: using current practices, thousands of parts can be produced at considerable expense before a defect is detected.
The solution developed by IFACOM is to check quality continuously during production, not only afterwards. To achieve that, the consortium of 15 academic and industrial partners from 5 EU countries is using advanced sensor and monitoring technology combined with state-of-the-art artificial intelligence to detect and correct defects in real time, as they occur.
The system is designed to automatically monitor the entire factory-floor manufacturing process, from the quality of raw materials entering the production line to variances in tools and processes during each production run. As a closed-loop system, controllers are immediately alerted to any defects, and changes can be made on the fly to eliminate the source of the problem. The approach has the potential to dramatically reduce scrap by detecting production errors instantly, eliminating the propagation of defects along the process stages.
“The system also incorporates knowledge-based loops, providing information and feedback to other levels of the manufacturing chain, such as design and product development, in order to help minimise all failures by continuous optimisation of the production process and the manufacturing system,” Myklebust says.
To test the system, the researchers have developed industrial demonstrators for five end-user partners. For example, with GKN Aerospace, a provider of complex integrated metallic parts for the aerospace industry, the IFACOM system is being used to monitor the robotic assembly of blades on jet engines. And with Italian machine tool manufacturer Alesamonti, the IFACOM technology has been implemented to detect faults in the production of parts for high-precision boring and milling machines.
“Though the demonstrators focus on the aerospace and machine tool sectors, the system can be used in any manufacturing process,” Myklebust notes. “There is therefore a very large market for this and high demand.”
The IFACOM team is focusing its dissemination and commercialisation efforts on small and medium European manufacturers, who stand to gain a competitive edge from implementing zero-defect manufacturing processes. They are planning to work with other, complementary EU-funded projects to further develop the technology in the future, while some of the partners have also informally discussed launching a spin-off company to lead commercialisation of the system.