Abstract
Bearings play a vital role in all rotating machinery, and their failure is one of the significant causes of machine breakdown leading to a profound loss of safety and property. Therefore, the failure of rolling element bearings should be detected early while the machine fault is small. This paper presents the model that detects bearing failures using the continuous wavelet transform and classifies them using a switchable normalization-based convolutional neural network (SN-CNN). State-of-the-art accuracy was achieved with the proposed model using the Case Western Reserve University (CWRU) bearing dataset, which serves as the primary dataset for validating various algorithms for bearing failure detection. Batch normalization techniques were also employed and compared to the proposed model. The spectrogram images were also used as input for further comparison. Using switchable normalization, the proposed model achieved the testing accuracy in between 99.44% and 100% for different batch sizes and datasets.
Highlights
With the rapid advancement in science and technology, the use of electric machines has increased swiftly
Electric machinery is used ubiquitously in manufacturing applications. They are used daily and almost for all applications, which makes them work under unfavorable circumstances, humidity, and excessive loads, leading to motor breakdown resulting in huge maintenance loss, depreciation in production level, severe monetary losses, and possible risk of loss of lives
CONTRIBUTION AND ORGANIZATION Inspired by the widespread use of convolutional neural networks (CNNs), the leading models for deep learning in computer vision, we have used the switchable normalization-based CNN model to detect and classify bearing faults using the scalogram images as input
Summary
With the rapid advancement in science and technology, the use of electric machines has increased swiftly. A deep learning model consists of a multilayer neural network that extracts and learns features from deep layers of input signals These algorithms perform outstandingly with a massive amount of data [10]. B. CONTRIBUTION AND ORGANIZATION Inspired by the widespread use of CNNs, the leading models for deep learning in computer vision, we have used the switchable normalization-based CNN model to detect and classify bearing faults using the scalogram images as input. The proposed model uses data visualization and proper feature generation characteristics of time-frequency analysis, i.e., continuous wavelet transforms (CWT), switchable normalization, which is robust, versatile, and diverse, and the proper feature extraction and classification characteristics of CNN. The following section presents the details regarding the the proposed SN-CNN model, where the data collection, pre-processing, scalogram generation, and feature extraction are described.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have