Convolutional neural network with batch normalisation for fault detection in squirrel cage induction motor

Abstract

Early fault detection in an induction motor is the need of modern industries for minimal downtime and maximum production. A learning technique known as the Convolutional Neural network (CNN) provides automated and reliable feature extraction and selection. Considering these inherent traits of CNN, this study proposes a CNN in combination with batch normalisation (BN)‐based fault detection approach for simultaneous detection of bearing fault and broken rotor bars in squirrel cage induction motors (SCIMs). The SCIM vibration signals have different patterns for different defects, and the architecture of CNN is used in this study for fault diagnosis. For an efficient fault feature extraction, the proposed method uses CNN having multiple stacked layers with BN for faster training. In the proposed method, a CNN model with small kernel size is used along with adaptive gradient optimizer and BN to avoid performance degradation and optimum results. For the validation of the proposed technique, a test set‐up is used along with different fault conditions. The proposed method is also compared with the existing state‐of‐the‐art methods to illustrate its effectiveness.

Classification of Fault Severity in Induction Machine Systems Based on Temporal Convolutions and Recurrent Networks

“…Based on the neurobiology of the visual cortex, convolutional neural network (CNN) [17] is a neural network model that is generally composed of multiple convolutional layers along with fully connected layers. It may also contain subsampling steps.…”

“…Recently, deep learning (DL) is increasingly used to automatically learn complex data representations from raw signals using a network of different abstraction levels [16,17]. However, the capability of these algorithms in TSC is still understudied [18].…”

ANN-Based Pattern Recognition for Induction Motor Broken Rotor Bar Monitoring under Supply Frequency Regulation

“…A three-layered ANN having 10 neurons in each layer is designed in the present work. Two types of ANN are designed and tested in the present work using cascaded forward backdrop and feed-forward backdrop-based designs, as shown in Figure 5a,b, respectively [14,27,29,31,[40][41][42][43][44][45]. ANN training is done using four different algorithms: Bayesian Regulation, Polak-Ribiere Restarts, Gradient Descent with momentum and adaptive learning rate, and finally, Levenberg Marquardt algorithm.…”

“…Furthermore, many researchers have dedicated the artificial neural network (ANN) in the recent past towards the design of an effective fault detection algorithm [26][27][28][29]. The works done in [26,27] deploy convolutional neural networks with an inherent adaptive design for the fusion of feature extraction and classification phases of the fault detection into a single learning body. Furthermore, the authors of [28] concentrate on stator winding fault detection using a fuzzy detection system.…”

A convolutional neural network method based on Adam optimizer with power-exponential learning rate for bearing fault diagnosis

“…Mukherjee et al [25] proposed a light-weight CNN which utilizes vibration sensor measurements for fault event estimation of machines. Kumar et al [26] adopted a CNN model which combined adaptive gradient optimizer and BN to optimize the performance of fault diagnosis. Lomov et al [27] proposed a novel temporal CNN1D2D architecture for various recurrent and convolutional structures for process fault detection.…”