Gear Fault Detection Based on Convolutional Neural Networks and Support Vector Machines
Journal Title: International Journal of Knowledge and Innovation Studies - Year 2024, Vol 2, Issue 4
Abstract
As a critical component of mechanical transmission systems, gears play a vital role in ensuring industrial production runs smoothly. Undetected gear failures can lead to mechanical breakdowns, production interruptions, and even safety hazards. Therefore, an efficient gear fault detection method is essential for maintaining industrial continuity and safety. This paper proposes a hybrid model that integrates convolutional neural networks (CNN) and support vector machines (SVM) for gear fault detection. The model leverages CNNs to automatically extract key features from vibration signals, while SVMs enhance classification accuracy, resulting in a high-precision fault diagnosis system. On a publicly available gear fault dataset, the proposed model achieved an impressive accuracy of 0.9922, significantly outperforming single-classifier models. Moreover, the model exhibits a short training time, demonstrating its computational efficiency. This research provides an effective and automated approach to gear fault detection, offering significant potential for industrial applications.
Authors and Affiliations
Yeqi Fei, Ziyang Meng, Tianxi Chen, Pengfei Zhao
Keywords
Related Articles
- EP ID EP761077
- DOI https://doi.org/10.56578/ijkis020405
- Views 18
- Downloads 1
A Residual Network with Multi-Scale Dilated Convolutions for Enhanced Recognition of Digital Ink Chinese Characters by Non-Native Writers
Digital ink Chinese character recognition (DICCR) systems have predominantly been developed using datasets composed of native language writers. However, the handwriting of foreign students, who possess distinct writing h...
Selection of Enhanced Security Systems Using Complex T-Spherical Fuzzy Models Within a Complex Fuzzy Environment
The theory of Complex T-Spherical Fuzzy Sets (CTSpFSs) is introduced along with their Einstein operational methods under induced variables. This research aims to extend the theoretical framework of complex fuzzy sets (CF...
Racism and Hate Speech Detection on Twitter: A QAHA-Based Hybrid Deep Learning Approach Using LSTM-CNN
Twitter, a predominant platform for instantaneous communication and idea dissemination, is often exploited by cybercriminals for victim harassment through sexism, racism, hate speech, and trolling using pseudony-mous acc...
Understanding Self-Regulated Learning Dynamics Through Computer Simulation: A Model-Based Approach
Self-regulated learning (SRL) is conceptualized as a series of interrelated cognitive and affective processes rather than as isolated events. To elucidate the relationship between students' cognitive engagement and their...
Integration of Fuzzy Inference Systems and Linear Regression for Enhanced Height Prediction of Deodar Cedar Trees in Kumrat Valley
Accurate estimation of tree height is fundamental to sustainable forest management, particularly in regions such as Kumrat Valley, Pakistan, where Deodar Cedar (Cedrus deodara) serves as a vital ecological and economic r...