基于长短时记忆神经网络在故障故障中参数依靠经验确定，具有不确定性，从而

Based on the fact that the parameters of the long and short-term memory neural network are determined by experience in the faults and are uncertain, which leads to the defects of the model's fault diagnosis accuracy rate being reduced, this paper uses an improved gray wolf algorithm to optimize the long-short-term memory neural network and proposes a LSTM network parameter optimization OLTC fault diagnosis method based on improved gray wolf algorithm. First, use multi-scale weighted permutation entropy and energy entropy based on GOA-VMD tapping as the input of LSM; then use the improved gray wolf algorithm to iteratively optimize the related super arithmetic of LSTM; finally build an IGWO-LSTM combined model for OLTC The different faults in the system are classified. This model overcomes the problem of classification accuracy angle caused by selecting parameters based on experience. The analysis of calculation examples shows that compared with traditional classification algorithms, the proposed method can better classify different faults of OLTC, improve the classification accuracy, and provide a theoretical basis for OLTC online monitoring.

Based on the parameters of long-term memory neural network in fault, which is determined by experience and has uncertainty, which leads to the reduction of the fault accuracy of the model, this paper optimizes the long-term memory neural network by using the improved gray wolf algorithm, and proposes an OLTC fault diagnosis method based on the LSTM network parameter optimization based on the improved gray wolf algorithm. First, multi-scale weighted arrangement entropy and energy entropy based on GOA-VMD joining are used as inputs to LSM, then LSTM's related overriding is iteratively optimized by using the improved gray wolf algorithm, and finally, the IGWO-LSTM combination model is constructed to classify the different faults in OLTC. The model overcomes the problem of selecting parameters according to experience, which leads to the angle of classification accuracy. The study shows that compared with the traditional classification algorithm, the proposed method can classify the different faults of OLTC, improve the classification accuracy, and provide further theoretical basis for OLTC online monitoring.

Based on the fact that the parameters of long-term and short-term memory neural network are determined by experience and uncertain, which leads to the decrease of fault diagnosis accuracy of the model, an improved grey Wolf algorithm is used to optimize the long-term and short-term memory neural network, and an OLTC fault diagnosis method based on Improved Grey Wolf algorithm is proposed. Firstly, the multi-scale weighted permutation entropy and the energy entropy based on goa-vmd demultiplexing are used as the input of LSM; secondly, the improved gray wolf algorithm is used to iteratively optimize the relevant super arithmetic of LSTM; finally, the igwo-lstm combination model is constructed to classify different faults in OLTC. The model overcomes the problem of selecting parameters based on experience, which leads to classification accuracy angle. Example analysis shows that: compared with the traditional classification algorithm, the proposed method can better classify different OLTC faults, improve the classification accuracy, and provide further theoretical basis for OLTC online monitoring.<br>