A novel dataset and lightweight detection system for broken bars induction motors using optimizable neural networks

Abstract

Broken rotor bars (BRBs) in induction motors (IMs) are a common kind of failure and one of the most difficult to detect since the induction motor continues to run properly in the absence of any evidence of a malfunction. There have been several approaches presented for identifying BRBs in IMs. However, in order to parameterize the current signal, they need tools with a high computational cost, making an online implementation of the appropriate monitoring system difficult. As a result, this paper proposes a novel AI-based approach to detect and classify BRBs faults in IMs using novel multi-class datasets from two three-phase, 400V induction motors; 2.2kW, two poles, 50 Hz, 24 stator slots and with 20,29 and 32 rotor bars numbers (M24Ns,(20,29,32)Nb), and 2.2kW, four poles, 60 Hz, 36 stator slots with 28 and 44 rotor bars numbers (M36Ns, (28,44)Nb) to help in the analysis of healthy and faulty IMs, as well as classification performance evaluation and benchmarking. The developed lightweight, intelligent, and autodetection system employs a self-configurable neural network model for BRBs in IM models. It provides four classification outputs: healthy, one-BRB, two-BRBs, and three-BRBs. The simulation results characterize the performance of the (M24Ns, (20,29,32) Nb) and (M36Ns, (28,44) Nb) IMs and the combined mode for both motors, demonstrating that the proposed approach is very effective in detecting and classifying BRBs, with a 99.8 % and a prediction time of 1.64 microseconds.