基于IGOA-SVM的变压器故障诊断研究
Research on Transformer Fault Diagnosis Based on IGOA-SVM
李致远 1邵长春 2王致诚2
作者信息
- 1. 柳州铁道职业技术学院,广西 柳州 545616
- 2. 柳州铁道职业技术学院,广西 柳州 545616;柳州市生活用纸专用智能装备工程技术研究中心,广西 柳州 545616
- 折叠
摘要
基本蝗虫优化算法(GOA)容易陷入局部最优.为提高变压器故障诊断精度,本文提出一个采用改进的蝗虫优化算法结合支持向量机技术(IGOA-SVM)的变压器故障诊断模型.首先,利用混沌策略初始化蝗虫种群,以提高初始种群质量和搜索效率.然后,采用非线性递减权重,以平衡算法的局部探索和全局探索能力.最后,利用改进的蝗虫优化算法(IGOA)对SVM 的惩罚系数和核函数参数进行优化,建立了基于溶解气体分析的 IGOA-SVM 变压器故障诊断模型,并通过与GA-SVM、PSO-SVM 和 GOA-SVM 三种故障诊断模型的比较,验证了 IGOA-SVM变压器故障诊断模型的有效性和优越性.
Abstract
The basic grasshopper optimization algorithm(GOA)is prone to get stuck in local optima.To improve the accuracy of transformer fault diagnosis,a transformer fault diagnosis model that combines an improved grasshopper optimization algorithm with support vector machine technology(IGOA-SVM)is proposed in this paper.Firstly,chaos strategy is used to initialize the population in order to improve the quality of the initial population and search efficiency.Then,non-linear decreasing weights are used to balance the algorithm's local exploration and global exploration capabilities.Finally,the IGOA is used to optimize the penalty coefficient and kernel function parameters of SVM and the IGOA-SVM transformer fault diagnosis model based on dissolved gas analysis is established.The effectiveness and superiority of the IGOA-SVM transformer fault diagnosis model is verified by comparing with three fault diagnosis models GA-SVM,PSO-SVM,and GOA-SVM respectively.
关键词
故障诊断模型/溶解气体分析/改进蝗虫优化算法/支持向量机Key words
fault diagnosis model/dissolved gas analysis/improved grasshopper optimization algorithm/support vector machine引用本文复制引用
基金项目
甘肃省科技基金项目(18CX6JA022)
2021年度广西高校中青年教师科研基础能力提升项目(2021KY1392)
2022年度广西高校中青年教师科研基础能力提升项目(2022KY1403)
出版年
2024