TRIART Inc. (head office: Iizuka City, Fukuoka Prefecture; CEO: Kentaro Imazu; hereinafter TRIART) and Toyota Motor Kyushu, Inc. (head office: Miyawaka City, Fukuoka Prefecture; President: Osamu Nagata; hereinafter Toyota Kyushu) have started trials of a defect early-warning system on the Lexus production line at Toyota Kyushu Miyata Plant. The system uses collaboration between people and AI to detect in advance extremely subtle defects that experienced workers might notice intuitively.
During the press process, which applies pressure to steel sheets to form panels, the system detects tiny differences in panel shape and steel elongation in mass-produced panels using images from a thermal camera installed inside the press. These differences are important indicators that may cause cracks after forming or lead to future product defects. Until now, detection has relied heavily on the experience and intuition of skilled workers, making it difficult to generalize the skill.
TRIART used its proprietary technology, Composite AI ‘4CAS’*1, which has many achievements in sensibility information processing based on image data, to generate ① a master image representing the standard shape of the panel from thermal camera images, and ② calculate the differences (such as expansion and contraction areas) between the produced panel and the master image. This enabled the evaluation of every panel produced every 5 seconds. This allows for identifying patterns of “what kind of cases lead to the next defect,” enabling more efficient defect prediction detection with the precision of skilled workers. The reliability and processing power of this evaluation were dramatically improved by a unique workflow where the task of generating the image ① does not rely solely on AI learning but involves workers specifying rough shapes midway, then returning to AI computation.
AI-based digital transformation is often associated with “full automation by AI.” However, many challenges can be addressed faster by designing workflows that use people skills when workers already have them or when human judgment is clearly superior, in a complementary relationship with AI. This is especially effective in manufacturing sites where many kinds of parts and production lines make it difficult to apply systems to everything. This approach is based on Composite AI 4CAS, which does not make AI processes a black box but instead consists of multiple linked control AIs. This jointly developed system from Toyota Kyushu and TRIART is a good example of people and AI working as equals in the physical environment of manufacturing.
Toyota Kyushu Miyata Plant is one of the worlds leading Lexus manufacturing sites and has maintained the highest product quality by assigning skilled workers to each process*2. A factory is both a place where products are made and a place where production technologies are created. We hope that new production technologies such as this will give skilled workers more room to refine their skills and intuition and help deliver even more attractive products.
*1 Composite AI = Composite AI. It has a proven track record in sensibility information processing that is difficult to quantify, such as judgments made by human senses, and is also implemented in the difference comparison function of TRIART’s commercially available “Image and Drawing Comparison System MIIDEL.”
*2 The Miyata Plant is widely known as one of the world’s top automotive production sites, having won the highest Platinum Award five times in the factory category of the IQS (Initial Quality Study) conducted by the U.S. market research company J.D. Power, tying the world record.