基于改进量子粒子群优化支持向量机的变压器故障诊断方法

Transformer fault diagnosis method based on support vector machine optimized by improved quantum-behaved particle swarm optimization

为了弥补量子粒子群算法优化支持向量机(QPSO-SVM)在变压器故障诊断中“早熟”收敛的不足,该文提出一种基于改进量子粒子群优化支持向量机算法。通过计算每一代粒子的平均适应值偏离度Δ并引入自扰动算子使“早熟”粒子主动跳出当前局部最优区域,增强算法的全局搜索能力。此外,建立基于所提算法的故障分类模型,对变压器故障样本进行诊断。实例结果表明:相较传统QPSO-SVM算法,改进QPSO-SVM算法可以使粒子主动跳出最优局部范围,且对变压器故障的诊断准确率更高,验证了该文方法在变压器故障诊断方面的有效性与准确性。

In order to make up for the shortcomings of “early maturing” in the transformer fault diagnosis of quantum particle swarm optimization (QPSO) optimization support vector machine (SVM), the improved quantum particle swarm optimization support vector machine (QPSO-SVM) is proposed. It is used to calculate the average fitness deviation of each particle Δ and introduce the self-disturbance operator to lead the early maturing particle hop out of the current local optimal region, so as to enhance the global search ability of the algorithm. Moreover, the fault classification model based on the proposed method is constructed. The results show that, compared with the traditional qpso-svm algorithm, the improved QPSO-SVM algorithm can make particles jump out of the optimal local range actively, and the accuracy of transformer fault diagnosis is higher, which verifies the effectiveness and accuracy of this method in transformer fault diagnosis.