Dilated convolutional neural network based model for bearing faults and broken rotor bar detection in squirrel cage induction motors

Fuzzy Reasoning Numerical Spiking Neural P Systems for Induction Motor Fault Diagnosis

“…Specifically, by monitoring and analyzing its relevant operating parameters, the current operating state of an induction motor is evaluated to determine whether a fault exists. If it is in a fault state, the location, severity and development trend of the fault need to be clarified [ 6 , 7 ].…”

“…Deng et al [ 11 ] proposed a new method for bearing fault diagnosis based on empirical wavelet transform, fuzzy entropy and support vector machines. Kumar and Hati [ 6 ] proposed a new detection technique for bearing faults and broken rotor bars of squirrel-cage induction motors based on an extended convolutional neural network model. Although neural networks can be used to find solutions according to the faults that need to be resolved, they also have obvious disadvantages, such as the need to learn from a large number of samples, slow convergence and serious local optimal solutions [ 13 ].…”

Comparative Study between Physics-Informed CNN and PCA in Induction Motor Broken Bars MCSA Detection

“…Different studies propose the use of Machine Learning (ML) and Deep Learning (DL) [ 17 ]. Algorithms such as Support Vector Machines (SVM), K-Nearest Neighbor (K-NN), and Artificial Neural Network (ANN) have proved to be very useful, especially with the huge memory and calculation performance of modern computers [ 18 , 19 ]. Data scientists and Artificial Intelligence (AI) specialists usually fit raw data collected from the IMs into their ML or DL models in order to obtain a diagnosing model for certain faults allowing fault severity supervision; the method in [ 18 , 20 ] shows high performance.…”

“…Algorithms such as Support Vector Machines (SVM), K-Nearest Neighbor (K-NN), and Artificial Neural Network (ANN) have proved to be very useful, especially with the huge memory and calculation performance of modern computers [ 18 , 19 ]. Data scientists and Artificial Intelligence (AI) specialists usually fit raw data collected from the IMs into their ML or DL models in order to obtain a diagnosing model for certain faults allowing fault severity supervision; the method in [ 18 , 20 ] shows high performance. Nevertheless, the aim of the present article is to introduce the physical knowledge we have on IMs in the process of training an Artificial Intelligence (AI) model [ 20 ].…”

“…We can see that Neural Networks (NN) are widely used to solve this problem [ 9 , 18 , 22 ]. In this article, a physical-informed Convolutional Neural Network is used, and a new double input CNN is introduced to obtain a better fault detection efficiency.…”