基于HGWPSO算法优化SVM的气体泄漏工况诊断技术研究OA

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.