基于麻雀算法优化支持向量机的阀门内漏诊断研究  

Research on Valve Internal Leakage Diagnosis Based on Sparrow Search Algorithm Optimized Support Vector Machine

作　　者：龚家乐 曹丽华[1] 李大才 司和勇 GONG Jia-le;CAO Li-hua;LI Da-cai;SI He-yong(School of Energy and Power Engineering,Northeast Electric Power University,Jilin 132012,China)

机构地区：[1]东北电力大学能源与动力工程学院,吉林132012

出　　处：《汽轮机技术》2025年第2期110-112,126,共4页Turbine Technology

基　　金：广东大唐国际雷州发电有限责任公司科技项目“知识图谱在二次再热百万机组健康管理中的应用研究”资助。

摘　　要：由于数据驱动支持向量机模型在阀门泄漏诊断过程中各个参数不具备自适应能力,导致诊断能力较弱,提出了麻雀算法(Sparrow Search Algorithm,SSA)优化支持向量机(support vector machines,SVM)的阀门内漏诊断模型,并在诊断过程和模型诊断性能上与标准SVM模型进行对比分析。结果表明:在诊断过程中,SSA-SVM阀门内漏诊断模型能够适时调整模型参数,并保持较高的诊断性能,多个泄漏诊断指标均优于标准模型。当泄漏诊断准确率优先级高于诊断时间时,SSA-SVM诊断模型拥有更好的阀门泄漏诊断能力。Due to the lack of adaptive capability in the parameters of the data-driven support vector machine(SVM)model during valve leakage diagnosis,which results in weaker diagnostic performance,this paper proposes a valve internal leakage diagnosis model optimized by the Sparrow Search Algorithm(SSA)for SVM.A comparative analysis is conducted between the SSA-SVM model and the standard SVM model in terms of the valve leakage diagnosis process and diagnostic performance.The results show that the SSA-SVM valve internal leakage diagnosis model can adjust model parameters in a timely manner while maintaining high diagnostic performance,outperforming the standard model in several leakage diagnosis metrics.When the priority of leakage diagnosis accuracy is higher than diagnostic time,the SSA-SVM diagnosis model demonstrates superior valve leakage diagnosis capability.

关 键 词：阀门泄漏 支持向量机 麻雀优化算法 故障诊断 

分 类 号：TK264.1[动力工程及工程热物理—动力机械及工程]