优化模糊推理系统在电力变压器故障检测处理中的应用

Application of Optimized Fuzzy Inference System in Power Transformer Fault Detection and Processing

电力变压器故障检测处理工作意义重大,需要借助人工智能算法提升故障检测效率。在分析电力变压器故障检测原理的基础上,提出利用优化模糊推理系统进行电力变压器故障检测处理,通过一维卷积神经网络选取出最优属性,并将其作为自适应神经模糊推理预测模型的输入特征,再利用改进的帝王蝶优化算法(Monarch Butterfly Optimization,MBO)优化模型的分类精准性,从而完成故障的诊断与分类。通过与同其他算法模型的对比,所提模型的精准度高达98.99%,且运行时间仅为1.23 s。这表明该方法在电力变压器故障检测处理中具有高效性和准确性,能够有效提高故障检测效率,为电力系统的稳定运行提供有力保障。

The fault detection and treatment of power transformer is of great significance,and artificial intelligence algorithm is needed to improve the efficiency of fault detection.On the basis of analyzing the principle of power transformer fault detection,this paper proposes to use the optimized fuzzy inference system to detect and process the power transformer fault,and selects the optimal attribute through one-dimensional convolutional neural network,which is used as the input feature of the adaptive neural fuzzy inference prediction model,and then uses the improved Monarch Butterfly Optimization(MBO)to optimize the classification accuracy of the model,thus completing the fault diagnosis and classification.Compared with other algorithm models,it is found that the accuracy of the model proposed in this study is as high as 98.99%,and the running time is only 1.23 s.This shows that this method is efficient and accurate in fault detection and processing of power transformer,which can effectively improve the efficiency of fault detection and provide a strong guarantee for the stable operation of power system.