东北电力技术2026，Vol.47Issue(5)：22-27,6.
基于HGWPSO算法优化SVM的气体泄漏工况诊断技术研究
Research on Gas Leakage Condition Diagnosis Technology of SVM Optimized Based on HGWPSO Algorithm
吴福满 1侯春光1
作者信息
- 1. 沈阳工业大学电气工程学院,辽宁 沈阳 110870
- 折叠
摘要
Abstract
To ensure the safe operation of pressure vessels,it is of vital importance to detect and identify gas leakage conditions in a timely and accurate manner.It proposes a detection technology based on the Hybrid Grey Wolf Particle Swarm Optimization(HGWPSO)algorithm and Support Vector Machine(SVM)in view of the characteristics of gas leakage acoustic signals.The HGWPSO algorithm integrates the global search capability of Grey Wolf Optimization(GWO)with the local search capability of Particle Swarm Optimization(PSO)to achieve a balance between global exploration and local development.Firstly,the experiment collects the leaked sound signal through a microphone array.After denoising by wavelet transform,it extracts the time-domain and frequency-domain features.Secondly,it utilizes the HGWPSO algorithm to search for the hyperparameters of SVM and construct a gas leakage identification model based on HGWPSO-SVM.The results show that the recognition accuracy of this model is as high as 97.67%.Compared with other optimization algorithm models,it has higher reliability and superiority,providing an effective new method for the diagnosis of gas leakage conditions.关键词
气体泄漏检测/声学诊断/混合灰狼粒子群算法/支持向量机Key words
gas leakage detection/acoustic diagnosis/HGWPSO/support vector machine分类
能源科技引用本文复制引用
吴福满,侯春光..基于HGWPSO算法优化SVM的气体泄漏工况诊断技术研究[J].东北电力技术,2026,47(5):22-27,6.
