Bearing Fault Diagnosis Based on Mel Frequency Cepstrum Coefficient and Deformable Space-Frequency Attention Network

Abstract

The main bearing is the core component of gas-fired generator, and its reliability directly affects the stability of the whole system. Therefore, it is of great significance to study the fault diagnosis of the main bearing of gas-fired generator. In the bearing fault diagnosis based on vibration signal, how to extract the signature features of fault effectively is the key to achieving accurate fault diagnosis. Based on extracting the signature features of faults, how to classify the fault features efficiently is another key to achieving accurate fault diagnosis. Based on this, we propose a bearing fault diagnosis method based on Mel frequency cepstrum coefficient (MFCC) and deformable space-frequency attention network (DSFAN). In view of the inconsistent feature distribution of different types of faults, the MFCC algorithm is introduced to preprocess the original fault signals and extract their signature features. Then, the network model DSFAN is constructed based on the space-frequency feature attention mechanism (SFFAM). DSFAN can extract the global constraint features and distributed constraint features of fault signals and realize bearing fault diagnosis. To make full use of classification information, the data processed by MFCC is constructed into a three-dimensional data cube as the input of DSFAN. Finally, the validity of the proposed method MFCC-DSFAN is verified on CWRU, XJTU, and gas-fired generator data sets. The experimental results show the excellent performance of MFCC-DSFAN for fault diagnosis and prove the effectiveness of the attention module in feature extraction.

An Intelligent Ball Bearing Fault Diagnosis System Using Enhanced Rotational Characteristics on Spectrogram

“…However, existing CNNs are limited in their application to fault diagnosis because they require numerous training samples to achieve high diagnostic accuracy. In [21], a bearing fault diagnosis method based on Mel frequency cepstral coefficients (MFCCs) and a CNN was proposed. First, an MFCC was introduced to extract the signature features of the fault signal.…”

“…Our approach involves a fully connected layer and softmax function to determine the probability distribution for classification, incorporating dropout to enhance generalization. For layers requiring an activation function, the clipped rectified linear unit (ReLU) activation function combines the advantages of the ReLU activation function with reduced computational costs and addresses issues relating to exploding activations [21,24,35].…”

A Current Noise Cancellation Method Based on Fractional Linear Prediction for Bearing Fault Detection

“…The majority (45–55%) of motor failures are related to bearings, including generalized roughness and single-point bearing faults [ 4 , 5 ]. When the bearing failure occurs, the damage to the bearing increases over time, which results in the motor being unable to operate properly [ 6 ]. Therefore, early bearing fault diagnosis is crucial for unnecessary downtime, reducing costs, and improving efficiency, and it has gradually become a research hotspot in the industry and academia [ 7 , 8 ].…”