Transformer fault type diagnosis method based on semi-supervised DBNC

Abstract

The invention discloses a transformer fault type diagnosis method based on a semi-supervised DBNC (deep belief network classifier). The method comprises the following steps: selecting a sample data set; dividing sample data into an unlabelled pre-training set, a labelled set, a test set 1 and a test set 2; performing state coding on a fault type; building a DBNC-based transformer fault diagnosis model; initializing parameters of each layer of the model; training each RBM at the bottom layer by layer by utilizing comparison divergence; optimizing the whole network parameter through back propogation, so as to enable network classification performance to be globally optimal; and storing a trained network, and verifying classification performance of a network by utilizing sample data of the test set 1. The method disclosed by the invention solves the problems that only a small amount of complete data samples can be obtained under normal conditions when deep learning network fault data is adopted for performing analysis and processing in transformer fault diagnosis, a large number of labelled complete data samples are very difficult to acquire and a large amount of manpower and resources are required.

Description

technical field [0001] The invention belongs to transformer fault diagnosis technology, in particular to a transformer fault type diagnosis method based on semi-supervised DBNC. Background technique [0002] As an important equipment for voltage conversion and power distribution in the power system, the power transformer is closely related to the safety and reliability of the power system. However, due to manufacturing defects, human factors, and weather effects, the fault diagnosis and development trend prediction of transformers have always been highly concerned. Most of the power transformers in our country are oil-immersed transformers. At the initial stage of transformer failure, the gas formed is dissolved in the oil, and when the fault energy becomes larger, free gas will be formed. Therefore, Dissolved Gas Analysis (DGA) in oil has become the main means of transformer fault diagnosis. [0003] At present, the fault diagnosis methods of power transformers based on ...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is: to provide a transformer fault type diagnosis method based on semi-supervised DBNC, to solve the existing technology for transformer fault diagnosis using deep learning network to analyze and process a large number of transformer fault data, and then diagnose the transformer fault type ; However, deep learning requires accurate and complete samples in order to obtain satisfactory results. Usually, only a small number of complete data samples can be obtained, and it is very difficult to obtain a large number of complete data samples with labels, which requires a lot of manpower and material resources

Images