Transformer fuzzy prudent reasoning fault diagnosis method based on cost sensitive learning

Abstract

The invention discloses a transformer fuzzy prudent reasoning fault diagnosis method based on cost sensitive learning, and belongs to the field of transformer state evaluation and fault diagnosis. According to the invention, on the basis of acquiring a transformer state evaluation initial sample set and setting a cost sensitive initial matrix, firstly, by combining a Sigmoid multiattribute softening decision, a transformer fault diagnosis multi-class support vector matrix model is constructed; then, a support vector matrix is subjected to normalized ordered weighted averaging, and a fuzzy prudent membership degree weight is calculated; and finally, complementary confidence allocation and information fusion based on a PCR5 method are carried out on a weighed fuzzy prudent membership degree,and based on a confidence allocation fusion final value, transformer fault diagnosis decision determination is carried out. In such process, minimization of an error diagnosis sample number is used as an optimal object, a cost punishment element corresponding the cost sensitive matrix is iteratively corrected on the basis of the fuzzy prudent evidence reasoning process, and an online learning function of the fault diagnosis model is achieved.

Description

technical field [0001] The invention belongs to the field of transformer state evaluation and fault diagnosis, in particular to a transformer fuzzy cautious reasoning fault diagnosis method based on cost-sensitive learning. Background technique [0002] Restricted by factors such as manufacturing processes, materials, and cooling methods, high-voltage, large-capacity power transformers are usually oil-immersed power transformers. As an important part of regional / hub substations, their failure may cause serious power system oscillations or even power outages . Therefore, the evaluation of the working state of the oil-immersed power transformer is particularly important, and it is an important reference for evaluating its operation safety and reliability. It is an important technical means to prevent serious failures of the oil-immersed power transformer. [0003] At present, the commonly used oil-immersed power transformer state assessment method is the dissolved gas analysi...

AI Technical Summary

Problems solved by technology

[0005] However, because the mathematical principles of the above methods have different emphasis on the physical meaning of classification features, different DGA judgment methods based on the same dissolved gas record sample set may draw different diagnosis and evaluation conclusions, and the determination of the final fault diagnosis results requires The accumulation of experience and knowledge to judge

Moreover, in some cases, the measured dissolved gas concentration or ratio information may not be perfect and comprehensive enough to match the existing judgment criteria, so that some faults that may occur inside the power transformer cannot be effectively identified

Therefore, the application of the above-mentioned single method cannot improve the effectiveness and robustness of all types of oil-immersed power transformer fault diagnosis methods. It is necessary to effectively integrate the evaluation and diagnosis information of various DGA methods to improve transformer fault diagnostic accuracy

[0006] In addition, in the process of DGA fault diagnosis of oil-immersed power transformers, only the correct rate of fault diagnosis is targeted, but the influence of misdiagnosis rate and cost of misdiagnosis is not considered effectively, which will also affect the effectiveness and robustness of the final fault diagnosis. influences

Images