Manufacturing in the age of AI – What to expect with data-centric AI inspection


Hanoi, Vietnam–(BUSINESS WIRE)–A recent exchange between leaders of FPT Corporation, FPT softwareLanding AI and Schaeffler explored the potential of applying artificial intelligence (AI) in various methods of inspection and defect detection, within the manufacturing industry.

Identified as the key to further improving competitiveness and strengthening the workforce, AI has the potential to be included in various business processes. One of these areas, AI in visual inspection – with the rise of computer vision and machine learning – has become more popular thanks to the commitment of top players from all sectors.

During the recent online share, experts from FPT Corporation, FPT Software, Landing AI and Schaeffler discussed their visions for the future of AI in real-time quality inspection. All parties emphasized using a data-centric approach to shorten AI training time in machine learning and addressed critical issues facing brownfield factories .

Until recently, factory owners were equipped with rules-based visual inspection, which required IT experts to write pages of rules for the algorithm to detect product defects. These systems are unable to “self-learn” or gain new status outside of the book. Only capable of detecting errors in their rulebooks, rule-based inspection can miss anomalies, requiring manual inspection by on-site personnel.

“Rather than having a vision engineer write pages and pages of rules, you can now show some data to the AI ​​system and create a system that works just as well, but much faster,” said Dr. Andrew Ng – Founder and CEO of Landing IA.

Data-centric AI has consistently proven to be highly effective, dramatically reducing trained AI uptime. In a recent project between Landing AI and a Japanese manufacturer, for example, compared to rules-based inspection that took up to 6 months to build, data-centric AI took just 6 minutes. to learn from skilled data entry and accurately identify product defects. .

Another challenge is the multi-variations between different production lines, not to mention production plants. Each variation required dozens of additional rules for computer vision to conform to. Therefore, factories are constantly looking for new solutions, especially those of AI, integrating with high-resolution cameras and capable of self-learning.

“The large-scale application of AI in our manufacturing processes is a central part of Schaeffler’s digital strategy and will enable the next level of optimization within production”, Roberto Henkel – Senior Vice President Digitalization and Operations IT from Schaeffler.

Earlier this year, Accenture and Frontier Economics estimated that by 2035, AI applications could increase labor productivity by up to 40% across 16 industries. AI would also bring $3.8 trillion (up 45%) in added value to the manufacturing industry, according to the report.

The technology was considered much more reliable at identifying microscopic defects without compromising intense production rates. Thus, product quality, labor productivity were also to increase while saving manpower, thereby reducing production costs.

In Vietnam, FPT Software has worked with Landing AI to offer LandingLens™ – an MLOps visual inspection solution – to hundreds of its customers, including Schaeffler.

Dr. Truong Gia Binh – President of FPT Corporation asserted, “Data-centric AI can also work for sound inspection, electromagnetic inspection or light spectrum inspection.”

This potential direction quickly became an interesting topic. Excitedly, the leaders shared a vision of data-centric AI to inspect quality for hardware and internal errors without physical interaction, as well as receiving sound cues to detect defects.

However, all parties had to overcome the challenges of change management and staff training before successfully applying advanced technologies.

“We need easy-to-use platforms that bring cutting-edge technologies to the shop floor and make them (staff) able to use them,” said Roberto Henkel. This was also the problem Dr. Ng was striving to solve, making AI accessible to everyone. “Data-centric AI technology is the key to enabling people to design data,” Dr Ng explained.

Having supported more than 1,000 global partners to achieve digital transformation, FPT has helped transform both the business structure and the technology of companies in various sectors, providing them with staff training and updates on new technologies. . “We work on the 3 Cs – community, communication and creating shared content,” said Dr Binh.

The FPT President emphasized, “The key point is change management and people management. We are talking about business training, technology transformation and people transformation.” With an intensive background in education, Dr. Andrew Ng has also expressed enthusiasm for training staff on new technologies, ensuring that all key staff acquire the desired skills.

High-quality labor for the high-tech industry is one of Vietnam’s current competitive advantages in the Southeast Asian region, according to a recent remark from the Savills representative. This has attracted a wave of investment from major tech companies from the United States and around the world.

As difficult as the rise of AI can be for those who are still prepared in terms of awareness and capacity, for people who want to grow and take the initiative to acquire the necessary skills, the opportunities will be many.


Comments are closed.