Improved-gray-Markov-model-based power equipment fault prediction method

Abstract

Provided in the invention is an improved-gray-Markov-model-based power equipment fault prediction method. The method comprises: original data collection is executed on power equipment; apriority step ratio checking on is executed according to fault interval data in the original data; under the circumstances that the apriority step ratio checking is done successfully, a GM (1,1) gray model is established directly; under the circumstances that the apriority step ratio checking is not done successfully, original data transformation is executed and then a GM (1,1) gray model is established; according to the markov chain property, an initial prediction value is determined based on the GM (1,1) gray model, state division is carried out, and then a state transition matrix is established, thereby obtaining a Markov prediction model; and an improved Markov prediction model is obtained based on the obtained Markov prediction model, and a calculation result of the gray model is corrected by using the improved Markov prediction model, thereby obtaining a final prediction value.

Description

technical field [0001] The invention relates to the technical field of power equipment failure prediction, and more specifically, the invention relates to a power equipment failure prediction method based on an improved gray Markov model. Background technique [0002] With the continuous improvement of equipment automation, the dependence of production and operation on equipment maintenance is also increasing. Effective maintenance can improve the reliability and integrity rate of equipment, and can prolong the service life of equipment, which is conducive to promoting enterprise management level, Production efficiency and economic benefits have been comprehensively improved, so maintenance has become an important part of ensuring the production capacity of enterprises. [0003] Maintenance decision-making theory is a high integration of modern maintenance theory and decision-making science. It is a theory and method established based on maintenance ideas and combined with m...

AI Technical Summary

Problems solved by technology

[0009] The technical problem to be solved by the present invention is to solve the above-mentioned defects in the prior art, overcome the problem of low prediction accuracy in the above-mentioned existing research, and establish an improved gray Markov by combining the gray theory with the Markov theory. The model predicts the failure of power equipment. Firstly, the original failure data is grayed out, and the GM (1, 1) prediction model of the power equipment failure interval is established to determine the initial prediction value, and then an improved Markov model is proposed to analyze the initial prediction results. Make corrections and combine the two models to achieve complementary advantages, which can significantly improve the prediction accuracy

Images