A New Method for Diagnosing Motor Bearing Faults Based on Gramian Angular Field Image Coding and Improved CNN-ELM

Abstract

The most common cause of electric motor failure is the bearings, and so methods for fast and accurate diagnosis of motor bearing failure are urgently needed. Traditional fault diagnosis methods have high uncertainty and complexity since they require manual extraction of features. Deep learning has shown good performance in electrical equipment fault detection, and it can directly complete end-to-end diagnosis of motor faults, avoiding human involvement. Here, a new fault diagnosis method is presented which combines Gramian angular field (GAF) image coding, extreme learning machine (ELM) and convolutional neural network (CNN). The method has three main stages: First of all, GAF is utilized to convert the acquired vibration break signals into 2-D pictures. Next, the enhanced CNN model is taken to identify the elements of the converted image quickly and accurately. Finally, the ELM is used as the final classifier to gain further accuracy and diagnostic speed of fault classification. Experiments were designed to validate the proposed method using two different motor bearing fault datasets at Case Western Reserve University and autonomous experiment and performance is compared with several commonly used intelligent diagnosis algorithms. The proposed method's accuracy in the experiment designed in this paper can reach 99.2% at most, and it only takes 0.835s to complete the diagnosis, which outperforms traditional diagnostic methods on both datasets and improving the maximum diagnostic accuracy by 33.6%. The findings indicate that this method can classify various fault types efficaciously, and has the benefits of quick diagnosis, high accuracy, and good generalization ability.INDEX TERMS Gramian angular field image coding, convolutional neural network, extreme learning machine, fault diagnosis.

A new fault diagnosis of rolling bearing on FFT image coding and L-CNN

“…The original 1D bearing vibration signals were coded according to a window length of 2048 and a step size of 1024 smooth overlapping samples, and the four fault type data were coded using Gram's angular sum field (GASF), Gram's angular difference field (GADF), Markov transition field (MTF) [28,29] As can be seen from table 3, when the coding resolution size is 32 × 32 the three image coding methods GASF, GADF, and MTF exhibit the phenomenon of loss for the signal features, and the model diagnosis accuracy was low. In contrast, the FFT-x image coding method has a higher diagnostic accuracy with the same diagnostic speed and a faster diagnostic speed with the same diagnostic accuracy.…”

Application of an Improved Laplacian-of-Gaussian Filter for Bearing Fault Signal Enhancement of Motors

“…Vibration signals can capture crucial dynamic information that reflects the operational states of machines [4,5]. Hence, vibration analysis is a commonly used method in the field of motor bearing fault diagnosis.…”

Rolling bearing fault diagnosis method based on MTF-MFACNN

“…Liang and Feng [15] presented a rolling bearing fault diagnosis method that combined David Hilbert transform (ICEEMDAN-Hilbert) and residual network, and the performance degradation and the potential loss of key feature information of deep learning network were reduced. Zhang et al [16] put forward a new approach to fault diagnosis that combined. Gramm Field image coding, extreme learning machine and CNN to improve the diagnosis accuracy.…”