The full version of the article, along with thousands like it, can be found on the following page: Japan looks to AI as coronavirus challenges go-and-see quality control mantra

At a mill south of Japan's Toyota City, Robots have started sharing the work of quality-control inspectors, since the pandemic accelerates a change from Toyota's vaunted "go and see" system that helped revolutionise mass manufacturing in the 20th century.

Within the auto-parts plant of Musashi Seimitsu Industry, a robotic arm picks up and spins a bevel gear, blowing off its teeth against a light seeking surface flaws. The review takes about two seconds - like that of highly trained employees who check around 1,000 units per shift.

Global manufacturers have long used robots in production while departing the knotty work of spotting defects mainly to people. But social distancing measures to prevent the spread of coronavirus have prompted a rethink of the factory floor.

That has spurred the greater usage of robots and other technologies for quality control, including remote monitoring that was already being embraced ahead of the pandemic.

In Japan, such approaches represent an acute departure from the"genchi genbutsu", go-and-see methodology developed within the Toyota Production System and embraced by Japanese producers for decades with almost religious zeal.

That procedure tasks workers with continuously monitoring all parts of the manufacturing line to spot irregularities, also has made quality control one of the past individual hold-outs in differently automated factories.

Yet even at Toyota Motor Corp itself, when asked about automating more genchi genbutsu processes, a spokesman explained, "We are always looking at ways to improve our manufacturing processes, including automating processes where it makes sense to do so."

QUALITY DEMANDS

Improvements in artificial intelligence (AI) have come in tandem with increasingly affordable equipment but also stricter quality requirements from customers.

"We're increasingly seeing a gap between the quality of products made on regular production lines and the quality our customers demand," said Kazutaka Nagaoka, chief manufacturing officer in Japan Display, a provider to Apple Inc in addition to numerous automakers.

However, automating inspections is tough, given the necessity to teach robots to identify tens of thousands of potential flaws for a specific product and apply that learning instantly.

Musashi Seimitsu's low defect rate of a single 50,000 components left the firm with no enough faulty examples to come up with an efficient AI algorithm.

But a remedy came from Israeli entrepreneur Ran Poliakine, who implemented AI and optics technology he had used in medical diagnostics to the manufacturing line.

His thought was to teach the machine to spot the great, rather than the poor, by emphasising the algorithm on up to 100 perfect or near-perfect units - a modification of this so-called gold 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 explained.

'ON STEROIDS'

Since the breakthrough, Poliakine's start-up SixAI and Musashi Seimitsu have created MusashiAI, a joint venture that develops and hires out quality management robots - a first in the field.

Enquiries from automakers, parts providers and other companies in Japan, India, the US and Europe have quadrupled since March when the book coronavirus went global, Poliakine said.

Everything is on steroids now, because working from home is showing that remote work can work," he said.

Earlier this year automobile components maker Marelli, that has operational headquarters in Japan and Italy, also started using AI quality inspection robots at a plant in Japan, also told journalists last month that it desired AI to play a much larger role in quality inspections in the next several years.

Printer maker Ricoh Co Ltd, plans to automate all the production processes for drum units and toner cartridges at one of its Japan plants by March 2023. Robots perform the majority of the processes already, and since April, technicians are tracking equipment on the factory floor from house.

"Of course, you need to be on site to assess and execute solutions when issues come up, but identifying and confirming are tasks we can now do from home," said Kazuhiro Kanno, general manager at Ricoh's printer manufacturing unit.

Musashi Seimitsu will not say when it envisions its own mill floors to be fully automatic, but Otsuka said AI stands to match, 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 said.

"This will enable more people to look for ways to constantly improve production, which is the purpose of 'genchi genbutsu'."

The team at Platform Executive hope you have enjoyed this news article. Initial reporting via our official content partners at Reuters. Reporting by Naomi Tajitsu and Makiko Yamazaki. Additional reporting by Maki Shiraki and Noriyuki Hirata. Editing by David Dolan and Christopher Cushing.

To stay on top of the latest developments across the platform economy and gain access to our problem-solving tools and content sets, you can subscribe for just $19 per month.

This news article was published by Platform Executive, the home of the platform economy.

If you enjoy the content then please post a link on your website, or post on social media to help us get the word out.