基于帝国殖民竞争算法优化支持向量机的电力变压器故障诊断模型

Power transformer fault diagnosis model based on support vector machine optimized by imperialist competitive algorithm

提出了一种基于帝国殖民竞争算法优化支持向量机的变压器故障诊断模型。对支持向量机进行了非线性和多分类变换,构建了k-折平均分类准确率目标函数,建立了帝国殖民竞争算法优化支持向量机的非线性多分类模型,结合交叉验证原理对变压器进行了故障诊断。故障诊断结果表明,所提方法的平均测试准确率优于标准支持向量机和粒子群优化算法优化支持向量机(准确率分别为77.08%、57.97%和61.96%),验证了所提模型的有效性。采用UCI基准数据集对所提模型进行分类测试,结果表明所提模型在解决分类问题上具有较好的泛化性。

A power transformer fault diagnosis model based on SVM-ICA（Support Vector Machine optimized by Imperialist Competitive Algorithm） is proposed. The nonlinear and multi-classification transformation of SVM is carried out and the objective function of k-fold average classification accuracy rate and nonlinear multi-classification model of SVM-ICA are established to diagnose the faults of transformers by combining the cross validation principles. Fault diagnosis results show that the average test accuracy of the proposed method is higher than standard SVM and SVM optimized by particle swarm optimization algorithm,whose accuracy rates are 77.08%,57.97% and 61.96% respectively,which verifies the effectiveness of the proposed model. Classification tests of UCI benchmark data are carried out based on the proposed model,whose results show that the proposed model has a better generalization in solving classification problems.