Induction machine stator short-circuit fault detection using support vector machine

Abstract

Purpose This paper provides an effective study to detect and locate the inter-turn short-circuit faults (ITSC) in a three-phase induction motor (IM) using the support vector machine (SVM). The characteristics extracted from the analysis of the phase shifts between the stator currents and their corresponding voltages are used as inputs to train the SVM. The latter automatically decides on the IM state, either a healthy motor or a short-circuit fault on one of its three phases. Design/methodology/approach To evaluate the performance of the SVM, three supervised algorithms of machine learning, namely, multi-layer perceptron neural networks (MLPNNs), radial basis function neural networks (RBFNNs) and extreme learning machine (ELM) are used along with the SVM in this study. Thus, all classifiers (SVM, MLPNN, RBFNN and ELM) are tested and the results are compared with the same data set. Findings The obtained results showed that the SVM outperforms MLPNN, RBFNNs and ELM to diagnose the health status of the IM. Especially, this technique (SVM) provides an excellent performance because it is able to detect a fault of two short-circuited turns (early detection) when the IM is operating under a low load. Originality/value The original of this work is to use the SVM algorithm based on the phase shift between the stator currents and their voltages as inputs to detect and locate the ITSC fault.

An Overview of Diagnosis Methods of Stator Winding Inter-Turn Short Faults in Permanent-Magnet Synchronous Motors for Electric Vehicles

“…Applying machine learning to detect and diagnose faults from data is simple and does not require explicit models. Shallow neural networks mainly include logistic regression [102], support vector machines (SVM) [103], random forest [104], the k-nearest neighbor algorithm [105], and naive Bayes [106], which can adaptively learn features without necessitating the creation of a precise mathematical model, thereby reducing the uncertainty and intricacy associated with human involvement. Nevertheless, conventional shallow neural networks have limitations, including gradient vanishing, overfitting, susceptibility to local minima, and the requirement for substantial prior information, all of which diminish the efficacy of fault diagnosis.…”

Electric Fault Diagnosis in induction Machines using Motor Current Signature Analysis (MCSA)

“…The detection and location of inter-turn short-circuit (ITSC) faults in a three-phase induction motor are carried out in Ref. [4]. This technique employs the phase shifting between the stator currents and their corresponding voltages as input to a support vector machine (SVM), which is in charge of estimating the induction motor operational condition as healthy or with a short-circuit fault in one phase.…”

Hot-Pressing Furnace Current Monitoring and Predictive Maintenance System in Aerospace Applications

“…Part 1 is a temperature monitoring and part 2 current monitoring. The system can use the time to query the electricity consumption statistics of a specific device at a specific time and provide data download [ 23 , 24 , 25 ].…”