A Combined Short Time Fourier Transform and Image Classification Transformer Model for Rolling Element Bearings Fault Diagnosis in Electric Motors

Abstract

The most frequent faults in rotating electrical machines occur in their rolling element bearings. Thus, an effective health diagnosis mechanism of rolling element bearings is necessary from operational and economical points of view. Recently, convolutional neural networks (CNNs) have been proposed for bearing fault detection and identification. However, two major drawbacks of these models are (a) their lack of ability to capture global information about the input vector and to derive knowledge about the statistical properties of the latter and (b) the high demand for computational resources. In this paper, short time Fourier transform (STFT) is proposed as a pre-processing step to acquire time-frequency representation vibration images from raw data in variable healthy or faulty conditions. To diagnose and classify the vibration images, the image classification transformer (ICT), inspired from the transformers used for natural language processing, has been suitably adapted to work as an image classifier trained in a supervised manner and is also proposed as an alternative method to CNNs. Simulation results on a famous and well-established rolling element bearing fault detection benchmark show the effectiveness of the proposed method, which achieved 98.3% accuracy (on the test dataset) while requiring substantially fewer computational resources to be trained compared to the CNN approach.

Machine learning and deep learning based methods toward industry 4.0 predictive maintenance in induction motors: State of the art survey

“…The result showed that the presented method achieved higher classification accuracy of 92.15% compared to standard DBN and CNN, avoiding the manual feature extraction. An FD/D method for bearing fault identification in IMs was proposed using the image classification transformer (ICT) adapted to work as an image classifier trained in a supervised manner (Alexakos, Karnavas, Drakaki, Tziafettas, 2021). The short time Fourier transform (STFT) was proposed for pre-processing in order to acquire time-frequency representation vibration images from raw data in variable healthy and faulty conditions.…”

“…Therefore, in order to circumvent the disadvantages of CNN architectures when they are applied to limited resources, signal processing and pruning approaches can be applied (Pham et al, 2020). Pre-processing followed by DL methods have been proposed more recently (such as Pham et al, 2020;Aljemely et al, 2021;Alexakos et al, 2021) in order to increase the classification accuracy and improve overall FD/D performance. Differences between laboratory datasets and real industrial ones have been highlighted in research works for future research as well as the need for more available industrial datasets.…”

A remaining useful life prediction method based on PSR-former

“…Ding et al 17 designed a new tokenizer and encoder module to extract features from the time–frequency of vibration data and then used Transformer to diagnose the faults. Alexakos 18 proposed an image classification transformer used to diagnose the vibration images after a short time Fourier transform. Unfortunately, Transformer has not been well mined in the RUL prediction field 17 , so the advantages of Transformer in avoiding recursion, parallel computation, and reducing performance degradation are not well utilized in RUL prediction.…”

A Novel Domain Adaptation-Based Intelligent Fault Diagnosis Model to Handle Sample Class Imbalanced Problem

“…In addition, bearing and gear faults are the most common failure mode which may lead to unexpected fatal failures and elevated maintenance costs. Thus, there is a strong demand for intelligent fault diagnosis techniques of bearings and gears to ensure the security and reliability of mechanical equipment [2][3][4].…”