A fault diagnosis method of high voltage circuit breaker based on depth belief network

Abstract

The invention discloses a fault diagnosis method of a high-voltage circuit breaker based on a depth belief network, which comprises the following steps: step 1, selecting a data sample required by anexperiment, and dividing the unified standardized sample data into a test sample and a training sample according to a specific proportion; Step 2: building and initializing the DBN deep belief networkfault diagnosis model; Step 3, inputting a large number of unlabeled samples or unlabeled samples in the pre-training set from the bottom of the model, and pre-training the RBM in the model by usinglayer-by-layer unsupervised greedy learning; Step 4: the whole model being fine-tuned by genetic algorithm; Step 5, the fault diagnosis model of the high-voltage circuit breaker obtained by training being classified to the fault samples of the test set in step 1, so as to obtain the fault classification result, and the diagnosis accuracy rate of the model being counted. The invention discloses a fault diagnosis method of a high-voltage circuit breaker based on a depth belief network, which can train a large amount of data samples to realize the fault diagnosis function of the high-voltage circuit breaker.

Description

technical field [0001] The invention belongs to the technical field of high-voltage circuit breaker fault diagnosis methods, and specifically proposes a high-voltage circuit breaker fault diagnosis method based on a deep belief network. Background technique [0002] High-voltage circuit breakers play a dual role of control and protection in the distribution network system, so the fault diagnosis of high-voltage circuit breakers is of great significance. At present, many diagnostic methods have been proposed, but there are still some problems and certain limitations. For example, the expert system needs rich expert experience knowledge, which is difficult to obtain at this time; the neural network is easy to fall into local optimum; SVM is a binary classification algorithm, Its multi-classification algorithm, such as one-to-one SVM, has classification overlap and non-classification; while ELM has a faster training speed, but the stability of the trained model diagnosis is poo...

AI Technical Summary

Problems solved by technology

At present, many diagnostic methods have been proposed, but there are still some problems and certain limitations. For example, the expert system needs rich expert experience knowledge, which is difficult to obtain at this time; the neural network is easy to fall into local optimum; SVM is a binary classification algorithm, Its multi-classification algorithm, such as one-to-one SVM, has classification overlap and non-classification; while ELM has a faster training speed, but the stability of the trained model diagnosis is worse

In addition, most of the existing intelligent fault diagnosis methods have low utilization rate of unlabeled samples, and the learning ability is limited, and the scalability is relatively poor.

Images