Research on ferromagnetic resonance type recognition of support vector machine based on chaos theory
Source abstract
Abstract
This study presents an innovative method for identifying ferroresonant overvoltage types in power systems by integrating chaos theory with support vector machine classification. The proposed approach addresses two critical challenges: (1) the limited accuracy of existing identification methods for quasi-periodic and chaotic ferroresonance and (2) the lack of comprehensive feature sets capturing both linear and nonlinear characteristics. Our methodology combines time-domain statistical analysis, frequency-domain energy distribution evaluation, and nonlinear dynamic characterization through Poincaré mapping and Melnikov’s method. Experimental validation using 1203 overvoltage events from 35 to 10 kV substations in shale gas fields demonstrates significant improvements: identification accuracy reaches 98.7% for periodic signals and 89.3% for chaotic cases, with an average processing time of 12.6 ms/event. The system implementation reduces comprehensive operational costs by 19.8% through optimized fault response strategies and preventive maintenance scheduling.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Geoscience and Mining Technology · Advanced Algorithms and Applications · Grey System Theory Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Intelligent Manufacturing, Qingdao Huanghai University 1 , Shandong 266427,
State Grid Jiangsu Electric Power Co. Ltd. 2 , Jiangsu 250000,
Funding
Qingdao West Coast New District University President Fund Project
References (16)
Show source-provided references
1. Recognition technology of internal overvoltage in distribution network based on AD-CNN algorithm
2. Research on overvoltage signal recognition based on adaptive VMD and time-frequency segment energy entropy
3. Partial discharge pattern recognition based on deep convolutional neural network under complex data sources
4. Deep-learning-based Earth fault detection using continuous wavelet transform and convolutional neural network in resonant grounding distribution systems10.1109/jsen.2017.2776238 ↗
5. Detection of ferroresonance in isolated neutral system based on atomic decomposition method10.19595/j.cnki.1000-6753.tces.170078 ↗
6. Identification method of distribution network faults based on singular value of LCD-Hilbert spectrums and multilevel SVM
7. A coarse-to-fine decomposing strategy of VMD for extraction of weak repetitive transients in fault diagnosis of rotating machines10.1016/j.ymssp.2018.07.014 ↗
8. A single-ended protection algorithm based on wavelet multi-resolution analysis and support vector machine for flexible DC systems
9. Feature extraction and classification on partial discharge signals of power transformers based on improved variational mode decomposition and Hilbert transform
10. A novel probabilistic wind speed forecasting based on combination of the adaptive ensemble of on-line sequential ORELM (outlier Robust extreme learning machine) and TVMCF (time-varying mixture copula function)10.1016/j.enconman.2017.02.004 ↗
11. Quantification of the chaotic behavior of ferroresonant voltage transformer circuits10.1109/81.928158 ↗
12. Effect of initial conditions on chaotic ferroresonance in power transformers10.1049/ip-gtd:19971459 ↗
13. Lightning and switching overvoltage identification based on singular value decomposition of time-frequency matrix and multi-level support vector machine
14. A single-ended protection algorithm based on wavelet multi-resolution analysis and support vector machine for flexible DC systems
15. A new algorithm of wide-area backup protection based on PSO-LIBSVM
16. Features extraction and validation from measured overvoltage signal of power system