A comprehensive approach to convolutional neural networks‐based condition monitoring of permanent magnet synchronous motor drives

Abstract

The increasing complexity of modern industrial systems calls for automatic and innovative predictive maintenance techniques. As suggested by the Industry 4.0 process, this demand translates in the need of more-intelligent drives. Herein, the use of a special kind of neural networks to interpret the data from motor currents for diagnostic purposes is described. The early detection of possible faults in the electrical motor allows programmed maintenance and reduces the risk of unplanned shutdowns. The innovation is in the overall approach to the neural network training, which does not call anymore for a large set of faulty motors. A large training dataset generated using a combination of tuned motor models and some data augmentation techniques is proposed. The result is a comprehensive and effective motor condition monitoring algorithm, whose hearth is a convolutionary neural network trained by a safe and cheap simulation-based dataset. The details of the design are fully reported here. The method has been implemented in the laboratory and fully tested on both healthy and faulty permanent magnet synchronous motors. The generality of the proposed method also paves the way for the detection of other failures and the application to different electrical motors. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Abnormal Health Monitoring and Assessment of a Three‐Phase Induction Motor Using a Supervised CNN‐RNN‐Based Machine Learning Algorithm

“…A popular RNN model was the LSTM LSTM-RNN, which uses memory cells to retain long-term data to address the issue of vanishing gradients. As a classifcation algorithm, LSTM-RNN additionally includes Softmax layers as well as full levels [22]. Te architecture of the RNN is shown in Figure 4.…”

“…Te characteristics of the inputs are extracted by the CNN, and the retrieved features are further processed by the RNN to lessen the dependence on variables under various variable situations. By eliminating the ambiguity and boundary conditions of the images, it investigates the options one at a time [22]. Te general equations of CRNN are listed in the following equations:…”

“…Tis manuscript utilizes the motor current signature, which is already present in standard drives, and proposes a combination of simulations and upsampling to practice the neural network efectively without any need for numerous broken prototypes, which is the main obstacle to industrial viability [19][20][21][22]. Deep conviction systems for biomedical applications using intuitive procedures with a cross-point approach are analyzed.…”

Artificial Neural Network Based Optimal Feedforward Torque Control of Interior Permanent Magnet Synchronous Machines: A Feasibility Study and Comparison with the State-of-the-Art

“…In contrast to the commonly used motor current signature analysis (MCSA), axial flux monitoring and vibration monitoring, the two proposed ANN-based methods allow to detect broken rotor bar faults online with very high accuracy even under different voltage supplies. In [57], a convolutional neural network (CNN) based condition monitoring system for permanent magnet synchronous motors with interturn and demagnetization faults is proposed. The CNN-based condition monitoring system is able to detect those motor faults in the deteriorated current response with extremely high accuracy (errors less than 0.15%).…”

“…As artificial neural networks are a promising technology, machine learning-based approaches in electrical drives have already been reported in numerous publications (see the recent overview preprint [30] with 259 references). Exemplary applications of ANNs in the field of electrical drive systems are: ANN-based speed, current or speed and current controllers [31][32][33][34][35][36][37][38], ANN-based parameter/system identification [39][40][41], ANN-based temperature or resistance estimation [42,43], ANN-based direct/predictive torque or model predictive control [44][45][46], ANN-based torque observers [47], ANN-based current waveform prediction [48], ANN-based encoderless control [49][50][51][52], ANN-based torque ripple reduction [53,54], ANN-based condition monitoring or fault detection [55][56][57][58], ANN-based optimal pulse patterns [59], and ANN-based multi-objective optimization for machine design [60].…”