Fault diagnosis method based on BP-Ada Boost nerve network for electric energy meter

Abstract

A fault diagnosis method based on a BP-Ada Boost nerve network for an electric energy meter. The method comprises the following steps: (1) inputting sample data; (2) initializing the network, that is, initializing the distribution weight of the sample data; (3) training a weak classifier of the BP nerve network; (4) calculating the classification error; (5) calculating the weight; (6) adjusting the weight, that is, adjusting the weight of the next training sample according to the calculating result of the step 5; (7) conducting circulating judgment; (8) synthesizing a strong classification function; and (9) achieving classification result statistics and error ratio statistics. The method provided by the invention is used for automatic fault diagnosis of the electric energy meter, and can remarkably improve the fault classification precision through increasing the quantity of classifiers while ensuring the precision of a single BP classifier; for implementation of soft hardware, the training efficiency is greatly improved and the network running time is shortened by the aid of parallel computing principle; and the method provided by the invention has a better utility value and a wide application prospect in the technical fields of automatic fault detection and diagnosis.

Description

(1) Technical field: [0001] The present invention relates to a kind of fault diagnosis method of electronic electric energy meter based on BP-AdaBoost neural network, it is a kind of compound BP neural network improved by AdaBoost algorithm, and is applied to the method in the fault monitoring and diagnosis of electronic electric energy meter, The invention belongs to the technical field of fault automatic detection and diagnosis. (2) Background technology: [0002] In recent years, with the continuous development and progress of power electronics technology and integrated circuit technology, the reliability and maintainability requirements of electronic energy meters are getting higher and higher. However, due to the lack of detailed fault status information and the dependence on the experience of maintenance personnel, the traditional manual fault finding method is difficult to diagnose faults accurately and quickly, resulting in prolonged maintenance cycles and affecting ...

AI Technical Summary

Problems solved by technology

However, due to the lack of detailed fault status information and the dependence on the experience of maintenance personnel, the traditional manual fault finding method is difficult to diagnose faults accurately and quickly, resulting in prolonged maintenance cycles and affecting the production and operation of electronic energy meters. use in life

Images