An Improved Fault Diagnosis Method for Diesel Engines Based on Optimized Variational Mode Decomposition and Transformer-SVM
Open Access
Abstract
Due to the non-stationary and nonlinear characteristics of diesel engine vibration signals, fault features cannot be fully extracted, which limits fault diagnosis performance. To address this issue, an improved fault diagnosis method combining optimized Variational Mode Decomposition with a Transformer and Support Vector Machine is proposed. An improved dung beetle optimization algorithm is employed to obtain optimal parameters for Variational Mode Decomposition. The envelope entropy minimization principle is applied to select the optimal intrinsic mode functions after Variational Mode Decomposition, achieving signal denoising. Analysis of variance is integrated for feature significance testing to screen critical features. The selected features are fed into a Transformer network for training. At the final classification stage, the traditional SoftMax classifier is replaced with a Support Vector Machine classifier.Keywords
This publication has 35 references indexed in Scilit:
- Dynamic tracking MPP control of offshore bifacial floating photovoltaic systems with improved EMPC accounting for chaotic propertiesApplied Energy, 2025
- Marine diesel engine piston ring fault diagnosis based on LSTM and improved beluga whale optimizationAlexandria Engineering Journal, 2024
- A high-performance rolling bearing fault diagnosis method based on adaptive feature mode decomposition and TransformerApplied Acoustics, 2024
- Hybrid physics-infused 1D-CNN based deep learning framework for diesel engine fault diagnosticsNeural Computing and Applications, 2024
- Greedy opposition-based learning for chimp optimization algorithmArtificial Intelligence Review, 2022
- Dung beetle optimizer: a new meta-heuristic algorithm for global optimizationThe Journal of Supercomputing, 2022
- Roller bearing fault diagnosis based on LMD and multi-scale symbolic dynamic information entropyJournal of Mechanical Science and Technology, 2021
- CBSO: a memetic brain storm optimization with chaotic local searchMemetic Computing, 2017
- Diesel Engine Valve Clearance Fault Diagnosis Based on Features Extraction Techniques and FastICA-SVMChinese Journal of Mechanical Engineering, 2017
- Multiplier and gradient methodsJournal of Optimization Theory and Applications, 1969