Low power artificial intelligence (AI)-on-the-edge real-time machine condition monitoring system for predictive maintenance

Summary A Singapore SME has developed a low power silicon-based AI technology that offers real-time learn-on-the-fly machine condition monitoring system that is able to detect machine anomaly with high accuracy. The SME tech owner would like to seek a licensing partner to collaborate on a co-development project that leverages this technology offer for commercialization. The company would like to conclude license agreements.

Description

The Singapore SME was incorporated in 2018, is a technology provider specialising in developing artificial intelligence (AI) technologies. The SME’s vision is to deliver smart operations for businesses and a wide range of intelligent sensors and products empowered by AI.

This system is an AI based real-time classification and inference system to detect various machine operating conditions based on trained vibration patterns. The goal of this condition-based maintenance is to spot upcoming equipment failure, so that the maintenance can be proactively scheduled when it is needed. This monitoring system also extends the time between maintenance shutdowns, because maintenance is done on an as-needed basis. As a result, it has the potential to decrease maintenance costs and prevent downtime for production.

This solution uses Neuromorphic AI engine based on 3-layers artificial neural network with Radial Basis Function as activation function to model linear and non-linear vibration patterns. This solution operates without the need of a Graphics Processing Unit (GPU) and incorporates a condition monitoring system and a low power edge-based AI.

This solution supports common types of condition-based monitoring include vibration analysis and monitoring and temperature tracking. Real-time data is gathered through sensors, providing an ongoing method of testing and tracking machine health. Besides preventive maintenance, the solution also provides a predictive maintenance technique where the system spots any upcoming equipment failures. Maintenance can hence be proactively scheduled when it is needed, and not before.

The Singapore SME seeks partnerships with MNEs or SMEs of all sizes in the form of a licensing agreement where the partner could license the technology and further develop it to introduce to its customer or market segments.

Advantages & innovations The advantages and innovations include: • Extends the time between maintenance shutdowns. This is because maintenance is done on an as-needed basis. • Does not require a large training dataset. The solution is able to learn-on-the-fly (incremental learning) various vibration patterns while the machine is in continuous operation. • Detects machine anomalies (reports unknown vibration patterns). The solution is able to learn (supervised) on-the-fly, and detects anomaly without the need to bring the system offline. • Scalable system. The solution is able to support multiple wireless accelerometers (or vibration sensors) across a large area using wireless mesh configuration for monitoring of multiple machines. The system will not interfere with the normal operation of the machines that are being monitored.

Stage of development Field tested/evaluated

Source/ contact: Detail (europa.eu)