Iterative closest point-based transformer fault case matching searching method

Abstract

The invention discloses an iterative closest point-based transformer fault case matching searching method. The method comprises the steps of (1) acquiring to-be-tested transformer state data sequences, and finding out all target transformer state data sequences corresponding to the to-be-tested transformer state data sequences in a case library on the basis of the to-be-tested transformer state data sequences; (2) enabling the length of each to-be-tested transformer state data sequence to be consistent with the length of each target transformer state data sequence; (3) extracting characteristic parameters of the to-be-tested transformer state data sequences and characteristic parameters of the target transformer state data sequences, and performing standard normalization processing; (4) performing matching in a rotation and translation mode, and determining distances between the to-be-tested transformer state data sequences and the target transformer state data sequences by performingiterative closest point-based matching searching; (5) sorting the matching degrees based on the distances; and (6) based on a sorting result, assisting in judging faults represented by the to-be-tested transformer state data sequences.

Description

technical field [0001] The invention relates to a search method, in particular to a search method for transformer faults. Background technique [0002] In recent years, the monitoring technology of transformer equipment has been popularized and applied in a large number, so a large amount of condition monitoring data has been collected. A large number of monitoring cases show that the proportion of familial defects in transformer equipment defects is very high, and their monitoring data have certain similarities. An effective attempt for deep mining of state data. [0003] However, at present, it is not very convenient and effective to match the monitoring data of transformers in the existing technology. Usually, it is necessary to search several cases given by a large number of big data sample case libraries, and combine other aspects such as voltage level, manufacturer information or equipment Only by making an auxiliary judgment of the type can a better matching result ...

AI Technical Summary

Problems solved by technology

[0003] However, at present, it is not very convenient and effective to match the monitoring data of transformers in the existing technology. Usually, it is necessary to search several cases given by a large number of big data sample case libraries, and combine other aspects such as voltage level, manufacturer information or equipment Only by making auxiliary judgments based on the type can a better matching result be obtained

Images