Condition Monitoring and Fault Detection in Small Induction Motors Using Machine Learning Algorithms

Abstract

Electric induction motors are one of the most important and widely used classes of machines in modern industry. Large motors, which are commonly process-critical, will usually have built-in condition-monitoring systems to facilitate preventive maintenance and fault detection. Such capabilities are usually not cost-effective for small (under ten horsepower) motors, as they are inexpensive to replace. However, large industrial sites may use hundreds of these small motors, often to drive cooling fans or lubrication pumps for larger machines. Multiple small motors may further be assigned to a single electrical circuit, meaning a failure in one could damage other motors on that circuit. There is thus a need for condition monitoring of aggregations of small motors. We report on an ongoing project to develop a machine-learning-based solution for fault detection in multiple small electric motors. Shallow and deep learning approaches to this problem are investigated and compared, with a hybrid deep/shallow system ultimately being the most effective.

A Comprehensive Methodology for CNN Based Fault Identification in Induction Motors – A Case Study for EV’s

“…Techniques based on machine learning models often use specific signals such as vibration, sound, current, and thermal images [21], [22], [23], [24], [25]. Alternatively, data can be converted to another format and then feature extracted, or neural networks can be used to perform fault diagnosis using temporal and spatial features Deep learning algorithms are also used for fault diagnosis of induction motors.…”

Detection of Inter-Turn Short Circuits in Induction Motors under the Start-Up Transient by Means of an Empirical Wavelet Transform and Self-Organizing Map

“…The IMs are ensembles of important parts like the stator, the rotor, the windings, the rotor shaft, the fan, and the bearings of the shaft and the fan [4,11]. Additionally, several works have found that the previously mentioned components are associated with specific machine faults [12,13]; to this respect, the most common faults correspond to bearing damage in the range of 40% to 51%, followed by stator problems between 16% and 40%; the next are rotor damages with 5% to 10%, and other associated problems appear in a range of 12% to 28% [11,12,14]. Therefore, it is noticed that second major problems found in IMs are an electric type associated with the stator component, particularly, the stator winding faults (SWFs) such as short circuits and damage occurring turn-to-turn, coil-to-coil, phase-to-phase, or phase-to-ground [11].…”