Manufacturing in the Age of AI – What to Expect by Examining Data-Driven AI


Hanoi Vietnam–() –A conversation between leaders from FPT . companyAnd the FPT . programsLanding AI and Schaeffler explored the potential for applying artificial intelligence (AI) in various ways to inspect and detect defects in the manufacturing industry.

Identified as the key to further enhancing competitiveness and strengthening the workforce, AI has the potential to be embedded in various operations. One such area, artificial intelligence in visual inspection – with the rise of computer vision and machine learning – is becoming more and more popular thanks to the participation of major players across industries.

In a recent online post, experts from FPT Corporation, FPT Software, Landing AI, and Schaeffler discussed their visions for the future of Artificial intelligence in real-time quality inspection. All parties emphasized the use of a data-centric approach to shorten the training time of AI in machine learning and addressed critical issues facing structural field factories.

Until recently, factory owners were equipped with rule-based vision checking, which required IT experts to write pages of rules to an algorithm to detect product flaws. These systems are unable to “self-learn” or take a new position outside the book. Only able to detect errors in their rulebooks, rule-based checking may miss anomalies, requiring manual checking by on-site personnel.

Dr. Andrew Ng – Founder and CEO of Landing AI said:

Data-centric AI has consistently proven to be highly efficient, significantly reducing the time required to use trained AI. In a recent project between Landing AI and a Japanese manufacturer, for example, compared to a rule-based scan that took up to 6 months to create, the data-centric AI took only 6 minutes to learn from qualified data entry and precisely identified product flaws.

Another challenge is the multiple differences between different production lines, not to mention production plants. Each variation required dozens of other rules for computer vision to adhere to. Therefore, factories are constantly looking for new solutions, especially artificial intelligence solutions, which are integrated with high-resolution cameras and capable of self-learning.

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

Earlier this year, Accenture and Frontier Economics estimated that by 2035, AI applications could boost labor productivity by up to 40% in 16 industries. According to the report, AI will generate $3.8 trillion (up 45%) in added value to the manufacturing industry.

This technique has been considered more reliable in identifying microscopic defects without compromising the extensive production steps. As such, product quality and labor productivity were also expected to rise with the savings of manpower, thus reducing production costs.

In Vietnam, FPT Software has teamed up with Landing AI to deliver the LandingLens™ system – an MLOps optical inspection solution – to hundreds of its customers, including Schaeffler.

Dr. Truong Jia Binh, president of FPT, emphasized: “Data-driven AI can also work for sound scanning, electromagnetic scanning or spectroscopic scanning.”

This potential trend quickly became an interesting topic. Enthusiastically, the leaders shared a vision of data-centric artificial intelligence to check material quality and internal fault without physical interaction, as well as receive audio cues to detect defects.

However, all parties had to overcome challenges in managing change and training employees before the cutting-edge technologies could be successfully implemented.

“We need easy-to-use platforms that bring high-level technologies to the store floor and make them (employees) able to use it,” said Roberto Henkel. This was also the problem that Dr. Ng was striving to solve, making artificial intelligence accessible to all. “Data-centric AI technology is the key that makes it possible for people to engineer data,” said Dr. Ng.

Having accompanied more than 1,000 global partners to achieve digital transformation, FPT has helped transform the business and technology structure of companies in various industries, providing them with employee training and updates for new technologies. “We are working on 3C – community, communication and building shared content,” said Dr. Benh.

The head of FPT emphasized: “The key point is change management and people management. We are talking about business formations, technological transformations, and people transformations.” With an extensive background in education, Dr. Andrew Ng has also expressed enthusiasm for training staff in new technology, ensuring that all key staff learn the required skill sets.

The high-tech industry’s high-quality workforce has been one of Vietnam’s current competitive advantages within the Southeast Asian region, according to a recent note from a Savills representative. This has attracted a wave of investment from big tech companies from the United States and around the world.

As much as the rise of AI will present a challenge for those who are yet ready in terms of awareness and ability, for individuals willing to grow and take the lead in acquiring the necessary skills, the opportunities will be abundant.


Leave a Reply

Your email address will not be published. Required fields are marked *