基于免疫抗体记忆分类算法的变压器故障诊断

Transformer Fault Diagnosis Based on Immune Antibody Memory Classification Algorithm

针对传统克隆免疫算法应用于变压器故障诊断时学习速度慢、无分类能力及抗体空间小等缺点,提出一种免疫抗体记忆分类算法。利用免疫抗体识别抗原的原理和抗体记忆功能,将克隆选择与进化算法相结合,通过学习训练抗原及附属类型信息,得到由不同类型检测集组成的故障信息库,从而在保证亲和力的同时,加快学习速度,扩大免疫搜索空间,并利用人工识别球与刺激水平的线性关系对故障类型进行快速诊断。实验结果证明,该算法具有较快的运行速度及较高的诊断准确率。

In order to make up the shortages of traditional cloning immune algorithm that it studies slowly when being applied in transformer fault diagnosis,has no classification ability and antibody space is small,this paper proposes a classification algorithm of antibody memory based on the principle that the antibodies recognize the antigens in the immune space and antibody memory function.By combining the clonal selection and the evolutionary algorithm,and learns the training antigen and subsidiary type information to build the fault information database which is composed of different types of detection aggregate.The learning speed of this algorithm is very fast while the affinity is high enough.At the same time,it has an expanded immunization search space and uses the linear relationship between the Artificial Recognition Ball（ARB） and the stimulation level for rapid diagnosis of the fault types.Experimental results show that the algorithm can improve the speed of diagnosis and the accuracy of fault diagnosis.