Home PC News Japan explores AI as the pandemic curbs in-person quality control

Japan explores AI as the pandemic curbs in-person quality control

(Reuters) — At a producing unit south of Japan’s Toyota City, robots have started sharing the work of quality-control inspectors as a result of the pandemic accelerates a shift from Toyota’s vaunted “go-and-see” system, which helped revolutionize mass manufacturing inside the 20th century. Inside the auto components plant of Musashi Seimitsu, a robotic arm picks up and spins a bevel gear, scanning its tooth in direction of a light-weight in search of ground flaws. The inspection takes about two seconds — similar to that of extraordinarily educated employees who look at spherical 1,000 fashions per shift.

“Inspecting 1,000 of the exact same thing day in day out requires a lot of skill and expertise, but it’s not very creative,” CEO Hiroshi Otsuka instructed Reuters. “We’d like to release workers from those tasks.”

Global producers have prolonged used robots in manufacturing whereas leaving the knotty work of recognizing flaws primarily to individuals. But social distancing measures to cease the unfold of COVID-19 have prompted a rethink of the manufacturing unit flooring. That has spurred the elevated use of robots and completely different experience for top quality administration, along with distant monitoring, which was already being adopted sooner than the pandemic.

In Japan, such approaches signify an acute departure from the “genchi genbutsu” go-and-see methodology developed as part of the Toyota manufacturing system and embraced by Japanese producers for a few years with nearly non secular zeal. That course of duties employees with persistently monitoring all factors of the manufacturing line to establish irregularities and has made excessive quality administration one in all many last human holdouts in in another case automated factories.

Yet even at Toyota itself, when requested about automating additional genchi genbutsu procedures, a spokesperson acknowledged: “We are always looking at ways to improve our manufacturing processes, including automating processes where it makes sense to do so.”

Quality requires

Improvements in artificial intelligence (AI) have can be found tandem with increasingly cheap instruments however moreover stricter excessive quality requirements from purchasers.

“We’re increasingly seeing a gap between the quality of products made on regular production lines and the quality our customers demand,” acknowledged Kazutaka Nagaoka, chief manufacturing officer at Japan Display, a supplier to Apple, along with fairly just a few automakers.

“The quality of products made on automated lines is overwhelmingly higher and more consistent,” Nagaoka acknowledged.

However, automating inspections is tough, given the necessity to coach robots to ascertain tens of a whole lot of doable defects for a specific product and apply that learning instantly. Musashi Seimitsu’s low defect cost of 1 per 50,000 fashions left the company with out adequate defective examples to develop an surroundings pleasant AI algorithm. But a solution acquired right here from Israeli entrepreneur Ran Poliakine, who utilized AI and optics experience he had utilized in medical diagnostics to the manufacturing line. His idea was to indicate the machine to establish the good, reasonably than the harmful, by basing the algorithm on as a lot as 100 good or near-perfect fashions — a modification of the so-called golden sample.

“If you look at human tissue, you are teaching an algorithm what is good and what is not good, and you only have one second to perform the diagnostic,” he acknowledged.

On steroids

Since the breakthrough, Poliakine’s startup SixAI and Musashi Seimitsu have established MusashiAI, a 3 approach partnership that develops and hires out excessive quality administration robots — a main inside the self-discipline.

Inquiries from automakers, components suppliers, and completely different firms in Japan, India, the United States, and Europe have quadrupled since March, when the novel coronavirus went worldwide, Poliakine acknowledged.

“COVID-19 has accelerated the move. Everything is on steroids now because working from home is showing that remote work can work,” he acknowledged.

Earlier this 12 months, auto components maker Marelli, which has operational headquarters in Japan and Italy, moreover began using AI excessive quality inspection robots at a plant in Japan, and the company instructed Reuters last month that it wanted AI to play an excellent greater place in excessive quality inspections inside the coming years.

Printer maker Ricoh plans to automate all the manufacturing processes for drum fashions and toner cartridges at actually one in all its Japanese vegetation by March 2023. Robots perform numerous the processes already, and since April technicians have been monitoring instruments on the manufacturing unit flooring from residence.

“Of course, you need to be onsite to assess and execute solutions when issues come up, but identifying and confirming are tasks we can now do from home,” acknowledged Kazuhiro Kanno, fundamental supervisor at Ricoh’s printer manufacturing unit.

Musashi Seimitsu will not say when it envisions its manufacturing unit flooring being completely automated, nevertheless Otsuka acknowledged AI stands to complement, not threaten, the go-and-see system.

“AI doesn’t ask ‘Why? Why?’ but humans do. We’re hoping to free them up to ask why and how defects occur,” he acknowledged. “This will enable more people to look for ways to constantly improve production, which is the purpose of ‘genchi genbutsu.’”

(Reporting by Naomi Tajitsu and Makiko Yamazaki, additional reporting by Maki Shiraki and Noriyuki Hirata. Editing by David Dolan and Christopher Cushing.)

Most Popular

Recent Comments