Rotating machinery are essential components in most of today’s manufacturing and production industries including, but not limited to, gas turbine engines of aircrafts, car engines, truck engines, pumps, and bearings, etc. Considering the importance of rotating machinery maintenance for the CIMPLO users, we are developing a benchmark for fault detection and estimation remaining useful lifetime (RUL) of rotating machineries. Case study in this benchmark is fault detection and diagnosis of induction motor, however, we see a wide application of our models in different systems.
In general, fault detection and diagnosis techniques for electric motors can be supervised measuring quantities such as noise, vibration, and temperature. Whenever mechanical sensors are used to assess the health conditions of a machine, they normally are installed on some expensive or load-critical machines where the high cost of a continuous monitoring system can be justified. Nevertheless, current monitoring can be implemented inexpensively on machines with arbitrary sizes by using current transformers. In this regard, effective and low-cost fault detection techniques can be implemented, hence saving the maintenance and downtime costs of motors. Here, in this benchmark we analyze directly stator current using Fast Fourier Transform (FFT). We then use advanced Machine Learning (ML) techniques to achieve high accuracies with minimal expert knowledge requirements.