AI Controller is Gaining Traction in Industrial Automation

According to Omron’s Tim Foreman, interest in AI is changing. Customers no longer ask whether they can help them with AI. Instead, they ask whether we can help with predictive maintenance, quality control or process optimisation. They come to Omron with a problem that they want them to help solve. The AI controller is becoming an enabler.

Regardless of whether food & drink, pharmaceutical, electronics or automotive, the end goal is the same. That is to produce high quality, defect-free products at a lower cost, using less energy and less labour. And AI can be one of a suite of solutions for achieving those objectives.

Past, present & future

Just as attitudes have evolved, so has the technology. Although AI has existed as a concept since 1957, early applications were both expensive and slow. It took months to obtain the results of a simple calculation due to processing power limitations. Thanks to advancements in mobile technology, computer storage and processing speeds that is no longer true. Calculations take milliseconds and the cost is far lower.

Although tech giants like Amazon and Google have been using AI for some time, AI is still in its infancy in an industrial or factory floor context. I would liken its lifecycle stage to that of robotics 15 years ago, when you needed a maths degree to control a six-axis robot. To implement AI-based systems, you still need experts; you need to understand what you are doing, and it only makes sense in niche applications where the benefits justify the entry costs.

AI for invisible issues

It is also important to remember that AI is not a panacea. As machine builders, data scientists and engineers, we can be guilty of automatically defaulting to tech for the answers, when the more straightforward solution is something far simpler and less sophisticated. (Occam’s razor)

For example, a broken and bent conveyor part. That is an identifiable engineering problem solvable using a traditional mechanical solution. It is the less obvious, intermittent issues – for instance manifesting in micro-stoppages – where AI can add value.

When asked for help by an automotive customer having problems with micro-stoppages, we performed a data scan and a sanity check. This involved connecting probes to the machine to create pictures of the signals generated to establish what was happening. From this we identified several other issues, one of which was the sensor malfunction due to a broken contact. Moreover, we also identified some programming issues, including a logic mistake replicated in other machines on site. The result was a one-day fix that saved the client thousands of euros in scrapped products and reduced downtime by 50%.

AI Controller Powered Problem Solving in Practice

In another application example, we are currently working with a food industry customer to improve seal integrity. By applying an AI controller approach to the sealing operation, we will increase the shelf life by several days and minimise the occurrence of faulty seals, thereby eliminating the rejection risk of a complete batch by retail customers.

Collect, analyse & use.

Most of the projects so far have adopted OMRON’s AI Controller, the world’s first AI controller solution that operates at the edge. This uses the Sysmac NY5 IPC and the NX7 CPU. The controller recognises patterns based on process data collected directly on the production line. By integrating it into the Sysmac factory control platform allows its use in the machine directly, to prevent efficiency losses.

With examples like these and with AI being such a hot topic in the media, it would be easy to assume that every manufacturing business is on board with AI, when this really is not the case. Examples of AI in use on the factory are rare and projects are reliant on the expertise of the technology provider. In another ten years it will be a different story. New AI tools will make AI far more accessible and user-friendly. Thus, enabling manufacturers to take ownership of AI and run with it.

[Image Source: Omron Automation EU]

Subscribe
Notify of
guest
0 Comments
Inline Feedbacks
View all comments