This study aimed to propose an equal-integral-bandwidth feature extraction method based on fast Fourier transform (FFT) to solve the problem of cumbersome processing and a large amount of calculation in the common feature extraction algorithm for vibration signals of on-load tap changer (OLTC). First, the vibration signals of OLTC were preprocessed in segments, which highlighted the status features and avoided the shortcomings of the FFT spectrum that lacked time axis information. Second, the vibration signal segments were analyzed with FFT, and the generated signal spectrum was divided into several segments according to equal integral. The bandwidth coefficient obtained in each segment was the characteristic value. Third, this study proposed that adding appropriate time domain features and further improving the algorithm could improve the accuracy of fault diagnosis. Finally, the main mechanical faults of OLTC were simulated, and the vibration signals were collected to carry out the fault diagnosis experiment of OLTC. The results showed that the FFT-based equal-integral-bandwidth feature extraction method was simple in processing, small in calculation, easy to implement in an embedded system, and had a high accuracy of fault diagnosis.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.3934/mbe.2021102 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Optimizing Transformer-Based Network via Advanced Decoder Design for Medical Image Segmentation.
Biomed Phys Eng Express
January 2025
Shandong University, No. 72, Binhai Road, Jimo, Qingdao City, Shandong Province, Qingdao, 266200, CHINA.
U-Net is widely used in medical image segmentation due to its simple and flexible architecture design. To address the challenges of scale and complexity in medical tasks, several variants of U-Net have been proposed. In particular, methods based on Vision Transformer (ViT), represented by Swin UNETR, have gained widespread attention in recent years.
View Article and Find Full Text PDFMultimodal Pain Recognition in Postoperative Patients: Machine Learning Approach.
JMIR Form Res
January 2025
Department of Computer Science, University of California, Irvine, Irvine, CA, United States.
Background: Acute pain management is critical in postoperative care, especially in vulnerable patient populations that may be unable to self-report pain levels effectively. Current methods of pain assessment often rely on subjective patient reports or behavioral pain observation tools, which can lead to inconsistencies in pain management. Multimodal pain assessment, integrating physiological and behavioral data, presents an opportunity to create more objective and accurate pain measurement systems.
View Article and Find Full Text PDFIntelligent classification of computer vulnerabilities and network security management system: Combining memristor neural network and improved TCNN model.
PLoS One
January 2025
School of Information and Communication Engineering, Beijing University of Information Science and Technology, Bei Jing City, China.
To enhance the intelligent classification of computer vulnerabilities and improve the efficiency and accuracy of network security management, this study delves into the application of a comprehensive classification system that integrates the Memristor Neural Network (MNN) and an improved Temporal Convolutional Neural Network (TCNN) in network security management. This system not only focuses on the precise classification of vulnerability data but also emphasizes its core role in strengthening the network security management framework. Firstly, the study designs and implements a neural network model based on memristors.
View Article and Find Full Text PDFEnhanced ResNet-50 for garbage classification: Feature fusion and depth-separable convolutions.
PLoS One
January 2025
School of Business Economics, European Union University, Montreux, Switzerland.
As people's material living standards continue to improve, the types and quantities of household garbage they generate rapidly increase. Therefore, it is urgent to develop a reasonable and effective method for garbage classification. This is important for resource recycling and environmental improvement and contributes to the sustainable development of production and the economy.
View Article and Find Full Text PDFIn 2019, the novel coronavirus swept the world, exposing the monitoring and early warning problems of the medical system. Computer-aided diagnosis models based on deep learning have good universality and can well alleviate these problems. However, traditional image processing methods may lead to high false positive rates, which is unacceptable in disease monitoring and early warning.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!