Multi-dimensional transformer operation state evaluation method

Abstract

The invention relates to the technical field of transformer state evaluation and particularly relates to a multi-dimensional transformer operation state evaluation method which comprises the followingsteps: acquiring a chromatographic analysis data, an electrical test data and an oilation test data of the transformer oil operation state, and standardizing the acquired datas as sample datas; dividing the standardized datas into training samples and test samples; establishing a transformer operation state multi-dimensional evaluation model by use of the training samples as well as a support vector machine, and acquiring a target function for fault diagnosis; iterating to obtain the best feasible solution of the target function in the transformer operation state multi-dimensional evaluationmodel. According to the method provided by the invention, evaluation is performed in multiple dimensions such as gas dissolved in oil, partial discharge, winding deformation and hot-point temperaturerise and insulating micro water, and the method has the advantages of short fault diagnosis time, fast convergence and the like, and obtains relatively high accuracy; through evidence fusion using multiple factors, the method has the advantages of quite high credibility, clear and accurate evaluation conclusion and strong practicability and operability.

Description

technical field [0001] The invention relates to the technical field of transformer state evaluation, in particular to a multi-dimensional transformer operating state evaluation method. Background technique [0002] As the capacity of the power grid continues to expand, the safe and reliable operation of the power grid is particularly important. As the hub of power transmission in the power system, large power transformers are directly related to the normal, efficient and economical operation of the power grid. Since the power transformer itself is an extremely complex system, it is very difficult to establish a transformer condition-based maintenance model based on real-time status that takes into account both economy and reliability. At present, the main research direction is the evaluation of transformer insulation state at home and abroad. Most of the fault diagnosis methods are realized by the analysis of dissolved gas in oil. There are many researches on fault diagnosi...

AI Technical Summary

Problems solved by technology

The transformer may be affected by many aspects during the actual operation process, such as discharge, micro water and other data, and the analysis of the dissolved gas components in the oil alone may cause errors between the analysis results and the actual situation.

Images