基于MSMOTE与FA-CNN-LSTM的断路器故障诊断

Fault diagnosis of circuit breakers based on MSMOTE and FA-CNN-LSTM

摘要:

本研究针对断路器数据采集不平衡的问题, 为实现对断路器的高效故障诊断,采用基于马氏距离的改进 合成少数类过采样技术(modified synthetic minority over-sampling technique,MSMOTE)进行数据扩充,并通过萤火虫算法(firefly algorithm,FA)优化卷积长短时记忆网络 (convolutional neural network-long short-term memory,CNN-LSTM)的隐藏层节点数和学习率。将经MSMOTE算法扩充后的数据输入到FA-CNN-LSTM模型中进行训练分类。实验结果表明,所提方法在故障样本较少的情况下同样能实现对断路器的高效故障诊断。通过FA算法的优化,分类准确率达到了99%。因此,本研究提出的断路器故障诊断方法具有较好的性能,为电网设备状态分析提供了一种新的有效途径。

Abstract:

Addressing the issue of imbalanced data acquisition in circuit breakers,this study adopts the Mahalanobis distance-based modified synthetic minority over-sampling technique (MSMOTE) for data augmentation to achieve efficient fault diagnosis for circuit breakers. Additionally,the firefly algorithm (FA) is utilized to optimize the number of nodes in the hidden layers and learning rate of convolutional neural network-long short-term memory (CNN-LSTM).The data expanded by the MSMOTE algorithm is input into the FA-CNN-LSTM model for training and classification.Experimental results indicate that the proposed method can efficiently diagnose circuit breaker faults even in scenarios with limited fault samples.With the optimization by the FA algorithm,the classification accuracy reaches 99%.Therefore,the circuit breaker fault diagnosis method proposed in this study exhibits excellent performance,offering a novel and effective approach for the analysis of power grid equipment status.