Transformer equipment fault identification method

Abstract

The invention discloses a transformer equipment fault identification method. The transformer equipment fault identification method specifically comprises the following steps of: (1) data preprocessing; (2) judgment of common fault modes; and(3) diagnosis of the fault modes, wherein a state quantity association rule analysis method is utilized, the combinations of a plurality of fault abnormal state quantities of excavated main transformer equipment and different expressions of fault abnormal state quantities of the excavated main transformer equipment are extracted and merged, the mutual influence degree among the fault abnormal state quantities is analyzed, and finally the diagnosis of the fault modes is carried out. A cluster analysis method comprises a hierarchical agglomerative clustering method or a k-Means clustering method, and the state quantity association rule analysis method is an Apriori associating rule algorithm. According to the invention, the plurality of kinds of effective information which may influence the state of the main transformer equipment are fully and reasonably excavated, state evaluation is carried out, and a new idea and method are provided for the state evaluation of the main transformer equipment.

Description

technical field [0001] The invention belongs to the technical field of power transmission and transformation status evaluation and fault diagnosis, and in particular relates to a transformer equipment fault identification method, in particular to a main transformer equipment fault identification method based on k-Means clustering algorithm and correlation analysis. Background technique [0002] The safety of power transmission and transformation equipment is the basis for safe, reliable and stable operation of the power grid, and is of great significance to the power grid. Effective and accurate assessment, diagnosis and prediction of equipment status can significantly improve the reliability of power supply and will improve the level of intelligence in power grid operation. [0003] The research on condition monitoring, evaluation and fault diagnosis technology of high-voltage power equipment in foreign countries was earlier. As early as 1951, the engineers of Westinghouse ...

AI Technical Summary

Problems solved by technology

[0005] At present, the state evaluation methods of power transmission and transformation equipment widely used by my country's power grid companies include equipment state scoring system methods, expert system methods, multi-dimensional equipment state evaluation methods based on traditional machine learning, and sample training methods that introduce remote expert opinions; however, In recent years, with the development of intelligent monitoring equipment, the amount of state parameter data of power transmission and transformation equipment has increased exponentially; and the equipment state data comes from multiple different systems; traditional state evaluation methods cannot handle such multi-source heterogeneous massive data

Images