Anomaly detection in rolling bearings based on the Mel‐frequency cepstrum coefficient and masked autoencoder for distribution estimation

Abstract

It is difficult to establish a classification and recognition model of machinery and equipment based on labeled samples in the actual industrial environment because of the imperfect fault modes and data missing. To solve this problem, a semisupervised anomaly detection method based on masked autoencoders of distribution estimation (MADE) is designed. First, the Mel-frequency cepstrum coefficient (MFCC) is employed to extract fault features from vibration signals of rolling bearings. Then, a group of mask matrices are set on each hidden layer to overcome the perfect reconstruction problem of the autoencoders' input, and the full-connection probability of reconstruction is used to replace the reconstruction error and adopted as the anomaly score. Finally, the diagnostic threshold is determined according to the Youden index. Experimental results show that the MADE method can extract fault-sensitive features from a noisy industrial environment and introduce mask matrices renders to make the network autoregressive, thus solving the problem of perfect reconstruction of autoencoders. It is verified based on three rolling bearing datasets that the accuracy, precision, recall, and F1-score of the proposed method are confirmed to be all 100%. Moreover, the accuracy of the proposed method is 17.19% higher than that of the memory-inhibition method on the rolling bearing dataset provided by the Center for Intelligent Maintenance Systems (IMS) in University of Cincinnati (USA). The accuracy of the proposed method is also improved compared with other state-of-the-art anomaly detection methods.

Fault diagnosis of driving gear in a battery swapping system based on audio features and SRC-Adaboost

“…Previous studies prove that audio features such as MFCC can reduce the noises in the vibration signals, extract more useful low-frequency fault features for subsequent pattern recognition, and demonstrate a better performance in bearing and gearbox fault diagnosis problems [24]. Thus, to track the harmonic frequencies that are related to the fault of the driving gear, both MFCC and GTCC are employed in this study.…”

“…In this study, inspired by the mechanism of the human auditory system, which is more sensitive to low frequency than high frequency [24], audio features, including Mel-frequency cepstral coefficients (MFCCs) and Gammatone cepstral coefficients (GTCCs) are extracted from vibration signals [25]. Meanwhile, the Mel triangle filterbank and Gammatone filterbank used in MFCC and GTCC can also resist high-frequency background noises [26].…”

Masked Autoencoders in Computer Vision: A Comprehensive Survey

“…Here, we only examine the work of MAE in the field of computer vision. It should be noted that MAE also shows remarkable performance in time-series related predictions, such as mechanical anomalies detection [3]- [7], [136]. It can be said that MAE is a new research focus following methods such as the YOLO series and Deeplab series.…”