Multifrequency ultrasonic testing regression prediction method for acid value of transformer oil

Abstract

The invention discloses a multifrequency ultrasonic testing regression prediction method acid value of transformer oil. The method comprises the following steps of 1), performing multifrequency ultrasonic characteristic testing and acid value measuring on a transformer oil sample, establishing a transformer oil acid value regression prediction model by means of a support vector regression machine;2), performing optimized combination of a punishment function punishment factor C, a kernel function parameter sigma and an insensitive loss function lost factor epsilon of the transformer coil acidvalue regression prediction model by means of a genetic algorithm; 3), establishing a transformer oil acid value multifrequency ultrasonic wave testing regression prediction model of the support vector regression machine based on the genetic algorithm; and 4), acquiring a multifrequency ultrasonic wave acoustic frequency spectrum of the transformer oil sample, and predicating the acid value in thetransformer oil. The multifrequency ultrasonic testing regression prediction method realizes acquisition of a predicated value of the acid value in the transformer oil through prediction and calculation, high fitting degree between the predicated value of the transformer oil acid value regression model which is established by the support vector machine through genetic algorithm optimization, andlow data error.

Description

technical field [0001] The invention relates to the technical field of transformer oil aging degree detection, in particular to a regression prediction method for transformer oil acid value multi-frequency ultrasonic testing. Background technique [0002] As the hub of the power system, large oil-immersed power transformers are the most expensive and important equipment in the power system. They play a pivotal role in the process of power transmission and transformation. Their safe and reliable operation is of decisive significance to the entire power system. Once the power transformer fails, it will bring huge losses to the national economy. The transformer oil in operation will gradually age under the influence of electricity, heat, force, water and oxygen, and produce a series of oxides that dissolve in the transformer oil, among which the most harmful ones are acidic substances such as formic acid, acetic acid and levulinic acid. The appearance and increase of acidic su...

AI Technical Summary

Problems solved by technology

[0004] The technical problem solved by the present invention is to provide a multi-frequency ultrasonic test regression prediction method for the acid value of transformer oil, which uses the genetic algorithm to optimize the acid value regression model of transformer oil built by the support vector machine to predict the acid value in transformer oil, so as to solve the problem of traditional The prediction results of the standard support vector machine model and the actual transformer oil measurement results are poorly fitted and the data errors are large

Images