Ten years ago, I was quite proud of how smart the machines in our factory were. Now, with my current definition of smart, I realise they were quite stupid. Why? Because although they were doing what they were designed to do, the minute they encountered anything unexpected or out of the ordinary, they were stumped. They resorted to asking the operator ‘What is wrong with me?’
Troubleshooting and getting machines back up and running called for smart people − highly skilled operators and experienced software and hardware engineers. The problem is that in the last ten years, these people have become increasingly unavailable.
No more dumb questions
The obvious solution is that machines must get smarter so that they no longer must ask stupid questions. Machine builders engineer systems that can figure out for themselves why they have stopped or why there is a problem. This is already happening to some extent − the use of sensors so that the cartoning machine can tell the operator that it has run out of blanks, for example.
However, you can only get so far with sensors alone. Taking system autonomy to the next level requires artificial intelligence (AI) so that machines can use smart algorithms that can perform sophisticated analytics more akin to human brain circuitry. There is a lot of talk about using AI to emulate human thought processes in industrial applications, but real-time examples of businesses that are successfully unlocking the value of AI are few and far between
Common AI pitfalls
There are two main reasons for this: firstly, companies often fall into the trap of being too generic in their application of AI, and secondly, they do not know how to handle the explosion of data that this broad-brush approach generates. If you are going to look at how AI can be applied in your factory, you should first establish what problem you want to solve, or what improvement you want to make.
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 – will do all of that for you. This controller will record the data at a micro-speed and analyse it using pattern recognition based on process data collected directly on the production line. It is integrated into Omron’s Sysmac factory control platform, which means that it can be used in the machine directly to prevent efficiency losses.
AI in action
As an example, we are currently working with a food industry customer to improve seal integrity. Rather than relying on the operator to recognise when the sealing head is not performing as it should, the packaging machine uses AI to maintain repeatable performance. By applying an AI approach to the sealing operation, we 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.
Machine learning: bridging the experience gap
So far, I’ve only talked about harnessing AI to make machines smarter. The other development trajectory for AI is making people smarter. Data can be returned from physical assets – in this case highly experienced workers – and pattern recognition applied. Put simply, the skilled operator trains the machine, and the machine trains the unskilled operator.
In our laboratory, we are currently experimenting with AI-driven machines that ask operators to assemble products and record how they do it, to discover the smartest way of performing this task so that this technique can be taught to other operators. Another industrial application for machine learning might be the use of AI to establish what actions the operator should be performing on the machine. If the operator’s hands move in the wrong direction, for example, this generates an alert.
Only smarties have the answer
Enterprises that are well advanced on their digital transformation journey will be best placed to harness the value of AI – whether for identifying and training best practices, predicting failures, or monitoring running conditions. However, businesses at the start of their journey shouldn’t be deterred from exploring AI. When ordering a new machine, make sure that it has the functionality to generate data for AI purposes. You don’t have to know what data you require – you just need to know the right questions to ask your machine builder. Also, start small and take a step-by-step approach – human DNA has evolved over millions of years, so it is unrealistic to expect machines to emulate the human brain in a matter of months.
How sustainability unlocks real business impact Rockwell Automation
IT in Manufacturing
Sustainability has moved from a compliance obligation to a strategic driver of resilience and value for manufacturers. Rockwell Automation explains how its Triple A framework and connected-data approach help producers cut energy, water and waste while improving productivity.
Read more...Mining’s AI future will depend on people as well as technology
IT in Manufacturing
South Africa’s mining industry is embracing digitalisation and AI, but AvenirHoldings chief executive officer, Tshidi Mndzebele says the real test is whether the people behind the industry are equipped to move forward with it, and outlines five things mining needs to get right.
Read more...How BIC overcame operational silos to integrate technology and people Rockwell Automation
IT in Manufacturing
Manufacturing giant BIC deployed Plex MES from Rockwell Automation at its Bizerte plant in Tunisia, replacing fragmented, partly in-house software with a single cloud-based execution system that broke operational silos and improved shop-floor visibility.
Read more...AI in industry is an early warning system, not a guarantee Schneider Electric South Africa
IT in Manufacturing
Schneider Electric’s Paul Steyn argues that AI in industrial maintenance is only as good as the infrastructure and people behind it, and explains the three layers a facility needs before predictive maintenance can deliver on its promise.
Read more...SA’s mining industry must put people at the heart of its digital future
IT in Manufacturing
South Africa’s mining industry employs around 470 000 people while its digital transition accelerates. Avenir’s chied executive officer, Tshidi Mndzebele argues that technology should enable and upskill the workforce rather than replace it, setting out five ways mining can make technology work for its people.
Read more...Quality control supports efficient tissue production Valmet South Africa
IT in Manufacturing
Valmet’s advanced quality control technology is helping tissue producers improve product consistency while reducing energy and raw material consumption. Its latest installation at KORO Paper in Vietnam combines real-time measurement, process optimisation and non-contact, nuclear-free quality control.
Read more...Patented algorithm maximises operator efficiency Rockwell Automation
IT in Manufacturing
Rockwell Automation piloted a patented anomaly detection algorithm and FactoryTalk DataMosaix at its Twinsburg electronics plant, giving operators 30 to 60 days’ advance warning of stencil failure, improving fail rates by 22% and achieving a 200% return on investment.
Read more...Cybersecurity must become part of the next era of industrial automation Adroit Technologies
IT in Manufacturing
The EU’s Cyber Resilience Act is setting a global benchmark for connected products, making cybersecurity a core engineering requirement in industrial automation. Adroit Technologies and Mitsubishi Electric explain how building security into controllers, PLCs and drives from the outset helps South African manufacturers protect production and meet international expectations.
Read more...The next generation of engineers is building living labs of innovation Schneider Electric South Africa
IT in Manufacturing
Graduate engineers at Schneider Electric East Africa designed, integrated and commissioned the smart building systems in the company’s new Nairobi head office, demonstrating how practical, real-world project experience accelerates engineering capability and confidence.
Read more...Innodisk launches APEX series edge AI systems for industrial deployment Vepac Electronics
IT in Manufacturing
Innodisk has launched its APEX series edge AI systems, combining hardware, software and system design to simplify industrial AI deployment. The APEX-A100, powered by Qualcomm’s Dragonwing IQ9 processor, delivers up to 100 TOPS with guaranteed availability through 2038.
While every effort has been made to ensure the accuracy of the information contained herein, the publisher and its agents cannot be held responsible for any errors contained, or any loss incurred as a result. Articles published do not necessarily reflect the views of the publishers. The editor reserves the right to alter or cut copy. Articles submitted are deemed to have been cleared for publication. Advertisements and company contact details are published as provided by the advertiser. Technews Publishing (Pty) Ltd cannot be held responsible for the accuracy or veracity of supplied material.
printer friendly version