【摘要】 针对电力变压器故障类型只有小样本数据难以准确识别的问题，提出一种基于改进算术优化算法(improved arithmetic optimization algorithm, IAOA)优化支持向量机(support vector machine, SVM)的变压器故障识别方法。该方法通过Piecewise混沌映射对算术优化算法进行改进，可以避免算法陷入局部最优解，利用IAOA对SVM参数进行优化，解决了SVM参数选择困难的问题，进而构造IAOA-SVM分类器对变压器故障进行识别。仿真结果表明，相比较于SVM和AOA-SVM分类器，IAOA-SVM分类器的识别性能最优，对5种、7种变压器故障类型的识别准确率分别为94.32%、99.26%,验证了所提方法的准确性。更多还原

【Abstract】 Aiming at the problem that it is difficult to accurately identify the fault types of power transformers with only small sample data, a transformer fault identification method based on improved arithmetic optimization algorithm( IAOA) optimized support vector machine( SVM) is proposed.This method improves the arithmetic optimization algorithm by Piecewise chaotic mapping to avoid the algorithm falling into the local optimal solution.The IAOA is used to optimize the SVM parameters to solve the problem of SVM parameter selection, and then the IAOA-SVM classifier is constructed to identify the transformer fault.The simulation results show that the IAOA-SVM classifier has the best recognition performance compared with SVM and AOA-SVM classifiers.The recognition accuracy of 5 and 7 transformer fault types is 94.32% and 99.26% respectively, which verifies the accuracy of the proposed method.更多还原