基于POA-RVM模型的抽蓄机组故障诊断

Fault diagnosis of pumped storage units based on POA-RVM model

有效的故障诊断方法不仅能快速、准确地辨别抽蓄机组故障类型,还能降低抽水蓄能电站的运行维护成本。针对相关向量机(RVM)有关参数的调整不当导致诊断结果受影响的问题,提出利用鹈鹕优化算法(POA)对相关向量机参数的选取进行优化,构建鹈鹕优化算法和相关向量机组合的分类模型(POA-RVM)。选取仙居抽水蓄能电站4台抽蓄机组在5种状态下的数据进行预处理和特征选取后构成故障样本集,并分别采用标准相关向量机,以及用遗传算法、粒子群算法和灰狼算法优化的相关向量机模型对这些故障样本进行分类。结果表明:与标准相关向量机,以及经遗传算法、粒子群算法和灰狼算法优化的相关向量机模型相比,POA-RVM模型有效提高了抽蓄机组故障诊断的准确率。

Effective fault diagnosis methods can not only quickly and accurately identify the fault types of pumped storage units,but also reduce the operation and maintenance costs of pumped storage power plants.To address the problem of improper parameters adjustment in the relevant vector machine(RVM)leading to the improper diagnosis results,we proposed to optimize selection of the parameters in the RVM by using the pelican optimization algorithm(POA),so a classification model combined with Pelican search algorithm and relevant vector machine(POA-RVM)was constructed.After preprocessing and feature selection of the data of four pumped storage units of the Xianju Pumped Plant under five states,a fault sample set was formed,and these fault samples were classified by using the standard RVM,and the RVM models optimized by genetic algorithm,particle swarm optimization algorithm,and gray wolf optimizer respectively.The results showed that compared with the standard RVM and variety of RVM models optimized by genetic algorithm,particle swarm optimization algorithm and gray wolf optimizer respectively,the POA-RVM model effectively improved the accuracy of fault diagnosis of pumped storage units.