Researchers at the University of Portsmouth in the UK have created a “virtual engineer” which uses artificial intelligence to predict when machines need maintenance. The technology learns how a machine works and uses this to make accurate predictions about when it needs maintenance, thus avoiding the need for regular maintenance shutdowns or waiting for a machine to fail before calling in an engineer.

Sensors are placed on vulnerable parts of the machine, such as the bearings. Predictive software monitors and analyses the signals, alerting technicians when it detects that a part is not working properly or needs replacing.

“The machines in many processing plants and factories are running day and night and an unscheduled stoppage can cause havoc and can result in huge costs,” explains Dr David Brown (above), head of the University`s Institute of Industrial Research (IIR). “This new diagnostic system prevents potential mechanical failure by identifying the faulty or worn-out part before it causes a problem. 

“It`s the first time this kind of technology has been used on this scale in the processing industry,” he adds. “The traditional approach to machine maintenance is being blown out of the water by real-time diagnostics.”

According to Brown, the really clever part is that the system is adaptive. “During the process of monitoring the machine, the software learns more about how it works, which parts are becoming worn, and anything else that could potentially cause mechanical failure,” he explains.

This is particularly important for custom-built machines. The IIR  system can learn the particular behaviour patterns of an individual machine.

The diagnostic software can direct an engineer to a specific fault which might otherwise take days to identify. “Human beings are highly intelligent and a good engineer might sometimes spot if something is about to break, but this system will help speed up the time it takes to fix,” says Brown.

He predicts significant costs savings to industry, because keeping a specialist engineer on call around-the-clock is expensive. “The entire process becomes very much easier if the company knows when to schedule machine repairs and maintenance in advance,” he points out.

IIR has been working with Stork Food & Dairy Systems (SFDS) the test the new system at some of its processing plants. SFDS develops and supplies processing equipment for the dairy, juice, food and pharmaceutical industries (such as the system shown below). Its customers, which include milk suppliers, run their machines twenty around the clock and they depend on their machines being mechanically reliable. 

“An unplanned stoppage on a production line can be a total disaster,” explains SFDS’ general manager, Luke Axel-Berg. “It can spell chaos for a processing plant, especially a dairy plant where milk is arriving every single day. The cows don’t stop producing milk because a machine has broken. Instead the milk must be sent to an alternative location, putting unexpected pressure on another plant.    

“In the event of a major breakdown lasting several days, we could even risk losing a customer,” he adds. “How do you put a price on that?”

Planned downtime, on the other hand, is less disruptive because users can build supply and delivery around it and arrange in advance for other plants to take over production. “It`s an entirely new way of looking at downtime,” says Axel-Berg.

“Our customers are already calling for a zero fault levels on their machines,” he continues. “Until now, it`s been impossible to guarantee that level of customer service, but this new diagnostic system looks set to change all that by taking away the risk. It will benefit any business which relies on machines to keep its operation turning over – especially if they want to minimise costs and guarantee customer satisfaction.”

The IIR is collaborating with Stork Food & Dairy Systems as part of a Knowledge Transfer Partnership (KTP), a UK government scheme which helps businesses to improve their competitiveness and productivity by partnering with academic institutions.