Equipment fault diagnosis method and system of electric power system

Abstract

The invention discloses an equipment fault diagnosis method of an electric power system. The method comprises the steps of segmenting an infrared image by utilizing a two-dimensional fuzzy-partition maximal entropy, and performing noise reduction and target segmentation on collected infrared thermogram of a fault point of electric power equipment; classifying and storing all collected image targets of the electric power equipment by utilizing an artificial neural network; finally comparing a separated fault image or a fault prediction point image with the image targets of the electric power equipment and carrying out fusion analyzing according to a stage fusion model, so as to obtain a diagnosis result; and performing the data fusion on conventional fault point empirical data of the electric power equipment and the detected fault point image data, thus obtaining a final fault result or predicted fault position of the electric power equipment. By integrating multiple algorithms, the precise diagnosis steps are formulated, and the modularization and systematic design is adopted, so that a complete and precision way for diagnosing the equipment fault of the electric power system is established, and the running reliability and stability of the electric power system can be improved.

Description

technical field [0001] The invention relates to the field of fault diagnosis of electric power systems, in particular to a method for fault diagnosis of electric power equipment. Background technique [0002] With the increasing scale of the modern power system and the continuous improvement of the voltage level, the damage caused by the failure of the transmission line to the social economy and people's life is more serious. Fast and accurate fault transient identification is the premise of fast restoration of grid power supply, and it is also an important part of fault analysis. Therefore, it is of great significance to study fast and reliable fault transient identification methods to ensure the safety and economy of power systems. [0003] For the research on fault diagnosis methods of power system equipment, predecessors have done a lot of useful exploration. For example, artificial intelligence technologies commonly used in the field of power system equipment fault di...

AI Technical Summary

Problems solved by technology

However, the shortcomings of this method are: 1. The relationship between the observed symptoms and the corresponding diagnosis for the increasingly complex power system network is quite complicated. and poor versatility; 2. This method can only effectively detect the occurrence of faults, and has the function of predicting the occurrence of fault points, which belongs to the diagnosis after the fault

② When missing or wrong alarm information is a key signal, the diagnosis result will be affected

③When the power grid is complex and huge, the scale of the decision table will increase, the reduction will be difficult, and the diagnosis speed and accuracy will decrease

However, this method still has the following disadvantages: ① It is difficult to acquire knowledge

However, there are also some problems in the application of ANN at present: ① How to obtain a complete knowledge base in a large system

② It is difficult to ensure the rapidity of convergence during ANN training and avoid falling into local minimum

③ lack of ability to explain their own behavior and output results

Images