overcast
At a plant south of Toyota city in Aichi Prefecture, robots began sharing the paintings of quality inspectors, as the coronavirus pandemic accelerated the passage of Toyota’s well-known “go-and-see” formula that helped revolutionize mass production in the 20th century.
Inside the Musashi Seimitsu Industry Co. , Ltd. car portion factory, a robot arm selects and rotates a tapered gear, sweeping its teeth for surface defects. The inspection takes about two seconds, to that of highly professional workers who check about 1,000 sets according to the shift.
“Inspecting 1000 items of the same thing day in and day out requires a lot of skill and experience, but it’s not very creative,” general manager Hiroshi Otsuka said. “We would like to rid workers of these tasks. “
Global brands have long used robots in production, leaving the thorny defect detection paints mainly to humans, but social estrangement measures to prevent the spread of COVID-19 caused a rethinking of the plant.
This has encouraged increased use of robots and other quality technologies, adding remote tracking that was already followed before the pandemic.
In Japan, these approaches are a radical replacement of the genchi genbutsu method (freely translated as “genuine location, genuine thing”) that evolved as a component of Toyota’s production formula and followed Japanese brands for decades with almost zeal.
This procedure requires staff to frequently control all facets of the production chain for irregularities, and has made quality control one of the last human delays in automated plants in a different way.
However, even in Toyota Motor Corp itself, when asked about automating more genchi genbutsu procedures, a spokesperson said, “We are still looking for tactics for our production processes, adding automation processes wherever it makes sense. “
Improvements in synthetic intelligence (AI) have been accompanied by affordable equipment, but also stricter customer quality needs.
“We are seeing a gap between the quality of products manufactured on normal production lines and the quality demanded by our customers,” said Kazutaka Nagaoka, production director of Japan Display, a supplier of Apple Inc. and many automakers. ” The quality of products manufactured in automated lines is incredibly superior and more consistent. “
However, automating inspections is a challenge, given the desire to teach robots to identify tens of thousands of imaginable flaws for an express product and apply that learning instantly.
Musashi Seimitsu’s low default rate of one consistent with 50,000 sets left the company with sufficiently flawed examples to expand an effective AI algorithm.
But one came from Israeli businessman Ran Poliakine, who implemented the artificial intelligence and optical generation he had used in medical diagnostics on the production line.
His concept was to teach the device to detect the good, that the bad, basing the rule set on up to a hundred very better or almost better sets: an amendment to the so-called gold sample.
“If you look at human tissue, you teach a set of rules about what’s smart and what isn’t, and you only have a moment to make the diagnosis,” he said.
Since this advance, the launch of Poliakine, SixAI and Musashi Seimitsu, have created MusashiAI, a joint venture that develops and rents quality robots, a novelty in the field.
Consultations from automakers, spare parts suppliers and other corporations in Japan, India, the United States and Europe have quadrupled since March, when the new global coronavirus, Poliakine said.
“COVID-19 has accelerated movement. Everything is now on steroids, because from house displays remote paintings can paint,” he said.
Earlier this year, auto parts manufacturer Marelli, which has an operational headquarters in Japan and Italy, also launched AI quality inspection robots at a factory in Japan, and told Reuters last month that it sought to make AI play a bigger role in quality inspections in the coming years.
Printer manufacturer Ricoh Co Ltd plans to automate all production processes for drum sets and toner cartridges at one of its Japanese plants until March 2023. Robots already perform the most processes and, since April, technicians have been tracking plant equipment. The house.
“Of course, it must be available to compare and execute responses when disorders arise, but identity and confirmation are responsibilities that we can now perform at home,” said Kazuhiro Kanno, general manager of Ricoh’s printer production unit.
Musashi Seimitsu might not say when he plans to have his plants fully automated, however, Otsuka said that AI complements, not threatening, the go-and-see system.
“AI doesn’t ask, “Why?” But humans do. We hope to free them to ask why and how defects occur,” he said. “This will allow more people to look for tactics for consistent production, which is the purpose of genchi genbutsu. “
The Japan Times LTD. All rights are reserved.