ICA-LVQ-based high-voltage circuit breaker fault diagnosis method

Abstract

The invention discloses an ICA-LVQ-based high-voltage circuit breaker fault diagnosis method. The implementation process of the method includes the following steps that: step 1, typical data samples are selected, and are divided into a training set and a test set according to a ratio of 3:1; step 2, the input feature vectors of the training sample obtained in the step 1 are extracted, an LDA algorithm is adopted to perform dimensionality reduction processing, so that a new input feature vector is obtained; step 3, with the input feature vector obtained in the step 2 adopted as input for constructing an ICA-LVQ neural network, and training and learning are carried out, fault classification results are outputted, so that an ICA-LVQ-based high-voltage circuit breaker fault diagnosis model isestablished; and step 4, the high-voltage circuit breaker fault diagnosis model obtained in the step 3 is adopted to classify the samples of the test set in the step 1, and the classification accuracyof the model is put into statistics. The ICA-LVQ-based high-voltage circuit breaker fault diagnosis method of the invention can accurately realize the fault diagnosis of high-voltage circuit breakers.

Description

Technical field [0001] The invention belongs to the technical field of high-voltage circuit breaker fault online monitoring, and specifically relates to an ICA-LVQ-based high-voltage circuit breaker fault diagnosis method. Background technique [0002] Circuit breakers are important equipment in power systems. The reliability of the performance of the circuit breaker is directly related to the reliable operation of the power system, and the reliability of the circuit breaker depends to a large extent on the reliability of its operating mechanism, among which the opening and closing coil is the key component of the operating mechanism. The closing and opening coil current can provide a wealth of information for mechanical fault diagnosis of high-voltage circuit breakers; therefore, fault diagnosis can be performed by extracting the opening and closing coil current signal. [0003] There are many existing fault detection methods for high-voltage circuit breakers, which involve vario...

AI Technical Summary

Problems solved by technology

[0003] There are many existing methods for fault detection of high-voltage circuit breakers, which involve various artificial intelligence algorithms, such as: fuzzy control can use precise mathematical tools to clarify fuzzy concepts or natural language, but its determination of membership functions and fuzzy rules There are certain human factors in the process; the radial basis neural network provides a better structural system for the fault diagnosis problem of circuit breakers, but there are problems that cannot explain the reasoning process and reasoning basis of itself and the neural network cannot work normally when the data is insufficient. Disadvantages of work; LVQ for high voltage circuit breaker diagnosis has the advantages of simple network structure, no need for data preprocessing, and only needs to measure the distance between the input vector and the competition layer to achieve effective classification

However, the LVQ classification is greatly affected by the initial value and does not consider the characteristics of the different importance of the attributes of each dimension of the data. Therefore, in order to solve the above problems, this patent proposes a method based on ICA-LVQ (ICA is the immune cloning algorithm, LVQ is the learning vector Quantitative neural network) high-voltage circuit breaker fault diagnosis method can effectively solve the above problems and classify faults more accurately and quickly

Images