[Source: Shutterstock]

Modern technologies are often around for a considerable time before gaining acceptance in machine control or a production line. It is also true for the advanced analytics and artificial intelligence that are now creeping into industrial machine control architectures.

These smart technologies are extending traditional machine control to offer enhanced data processing, and learning and decision-making capacities. They can increase availability, efficiency and reliability through predictive maintenance and improve productivity with their ability to make autonomous decisions.

It was not so long ago that the potential of technologies like model-predictive control, PID control, field-oriented control and fuzzy logic were hypothetical. Today, they are so embedded within controller architectures that we take them for granted.

Mitsubishi Electric Europe looks at how embedding smart new technologies in controllers is delivering a new era in machine operation.

Extending machine control architectures

In this context, consider the development possibilities of advanced analytics (AA) and artificial intelligence (AI) technologies for machine control. They can be a driver for increased machine availability for example by delivering more effective predictive maintenance.

This brings us into the realm of Big Data analysis where AA and AI technologies enable the recording and analysis of different machine states in real time. Recognising the current machine status, detecting potential faults on the horizon, and then immediately offering recommendations for remedial actions. The machine operator or maintenance provider can respond before a line stops, or the system even autonomously initiates remedial actions.

By linking that same AI technology into the wider enterprise, like the logistics chain for example, the control system could even mitigate delays in the delivery of replacement components. For instance, it could slow the machine or line down slightly to avoid stopping production altogether.

Going further, AI can begin to make autonomous decisions to optimise productivity. For example, machines work within defined margins for different loads or speeds or safety ranges. AI technology using deep learning algorithms within the controller could enable machines to operate up to and even beyond today’s margins. This would deliver a significant boost to productivity without compromising reliability or safety.

Embedding AI in machines

We are already seeing how applying AI principles to individual machine control processes can be an enabler for operational improvements. For example, Mitsubishi Electric has developed diagnostics based on its AI Technology called Maisart. Embedded into products such as Mitsubishi Electric’s MELIPC edge computing solution, Maisart uses machine learning to analyse collected data to generate a model of the machine’s operational states. This model can detect abnormalities in the machine’s operation in real time, enabling it to provide early warning of impending problems, and enable maintenance personnel to take prompt action.

Another example of using AI is the smart predictive maintenance function of MELFA robots. The Smart Plus function in Mitsubishi Electric’s MELFA robots analyses primary drive components according to actual operating conditions. This warns the operator of failing or deteriorating parts at an early stage. It reduces unplanned downtime and allows the planning of an efficient maintenance schedule.

Secondary benefits

Moreover, during the design phase, the technology offers simulation capabilities to predict the robot’s lifetime and estimate annual maintenance costs. This provides engineers with the opportunity to change the robot’s operation to extend the life cycle. Furthermore, they improve machine availability and reduce maintenance costs, giving a taste of the potential of AA and AI.