Predictive maintenance & condition monitoring
ARTIFICIAL INTELLIGENCE: HOPE, HYPE AND FOMO
By Tim Foreman, research and development manager, OMRON
wanted to get into AI, the answer, more often than not, was either ‘because my boss asked me to’, ‘because we have a lot of data’ or ‘because it seems like an interesting area’. None of these were particularly solid reasons and certainly did not justify the hefty investment that AI applications would have required at that time. That is changing, and hope, rather than hype or ‘FOMO’, is the driver. Customers do not ask whether Omron can help them with AI anymore. They ask whether Omron can help with predictive maintenance, quality control or process optimisation. They come to the company with a problem that they want help to solve. The adoption of AI is no longer a motive or an aim in itself. Instead, AI has become an ‘enabler’. Whatever the industry - whether food & drink,
T
pharmaceutical, electronics or automotive - the end goal is the same: producing 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 technology. Although AI has existed as a concept since 1957, early applications were unfeasibly expensive and slow: it took a month to obtain the results of a simple calculation due to processing power limitations. Thanks to advancements in mobile technology, computer storage and processing speeds, today, calculations can be carried out in milliseconds and the cost has fallen considerably. Although tech giants like Amazon and Google have been using AI for some time, AI is still in its
26
en years ago when Omron received enquiries about AI-based projects, they were mainly driven by hype or FOMO. When customers were asked why they
infancy in an industrial or factory floor context. Its lifecycle stage can be likened 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 cost of entry can be justified by the benefit.
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. Take for example, a piece of conveyor that is
broken and bent. That is an engineering problem that can be identified and resolved using a traditional mechanical solution. It is the less obvious, intermittent issues - for instance manifesting in micro-stoppages - where AI can add value.
AI-POWERED PROBLEM-SOLVING IN PRACTICE Here is a real-life example: Omron was called in to help an automotive customer who was having problems with micro-stoppages. After performing a data scan, Omron carried out a ‘sanity check’. This involved connecting probes to the machine to create pictures of the signals that were being generated to establish what was happening versus what should have been happening. Omron then developed an experiment to pinpoint the root causes. This enabled the identification and resolution of about ten issues. An issue that stood out involved a sensor malfunction: one of the sensors being monitored seemed not to be working. When Omron asked the customer to
check there was a broken connector. Programming issues were also identified, including a logic mistake that was replicated in many machines on site, which they were then able to fix. All in all, the customer saved tens of thousands of euros in scrapped product and reduced downtime by 50 per cent, which translated to an additional four hours of production time per month. In another application example, Omron is
currently working with a food industry customer to improve seal integrity. Applying an AI approach to the sealing operation will increase the shelf life by several days and minimise the occurrence of faulty seals, thereby eliminating the risk of a complete product batch being rejected by retail customers.
COLLECT, ANALYSE AND UTILISE Most of the projects so far have deployed Omron’s AI Controller – the world’s first AI solution that operates ‘at the edge’ (with the hardware based on the Sysmac NY5 IPC and the NX7 CPU). This controller recognises patterns based on process data collected directly on the production line. It is integrated into Omron’s Sysmac factory control platform, which means it can be used 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 in the factory are few and far between and projects are heavily reliant on the expertise of the technology provider. In another ten years, it will be a different story. Tools will develop that make AI far more accessible and user-friendly, enabling manufacturers to take ownership of AI and run with it.
OMRON
industrial.omron.co.uk October 2022 Instrumentation Monthly
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86
