On-load tap-changer spring energy storage insufficiency fault identification method based on neural network response surface

Abstract

The invention relates to an on-load tap-changer spring energy storage insufficiency fault identification method based on a neural network response surface. The method is characterized by comprising the following steps: based on a finite element method, establishing an on-load tap-changer fault simulation model by using an entity finite element grid; generating a training sample of a neural networkresponse surface model by adopting a uniform design method, and obtaining output fault characteristics through simulation of a tap switch spring energy storage insufficiency fault; constructing a neural network response surface model through regression analysis of input parameters and output characteristics of a tap switch spring energy storage insufficiency fault; and with the output characteristics of the spring energy storage insufficiency fault adopted as a reference, a willingness function-based multi-target recognition algorithm is adopted to recognize the output fault characteristics of the spring energy storage insufficiency fault. The method is different from a traditional fault identification model based on test data, and has the advantages of high modeling efficiency, high fault identification precision and the like.

Description

technical field [0001] The invention relates to a fault identification method for insufficient spring energy storage of an on-load tap changer based on a neural network response surface. Background technique [0002] On-load tap changer (OLTC) is the only movable part of the converter transformer to realize voltage regulation. It can not only stabilize the load center voltage, but also be indispensable for connecting the power grid, adjusting the load flow, and improving reactive power distribution. It is an important equipment that bears huge mechanical and current shocks during frequent operations. As the number of operations increases, switch brake failure, overheating and burning of contacts, insufficient spring energy storage, loose fasteners and Mechanical and electrical failures such as falling off. According to statistics, the number of on-load tap-changer faults accounts for about 40% of the total faults of transformers, and most of them are caused by mechanical fa...

AI Technical Summary

Problems solved by technology

However, most of the existing tap-changer fault diagnosis methods rely on actual test data. Using these methods to establish a fault diagnosis model requires a large amount of fault data. However, due to the high reliability of the tap-changer at the initial stage of use, equipment defects and Lack of state data, which will lead to less than ideal accuracy of the established model, and the construction speed of some diagnostic models is slow, and it is easy to fall into the local optimal solution, so that the fault cannot be effectively diagnosed. Therefore, a reasonable and effective method is urgently needed Identify and diagnose the typical mechanical faults of the tap changer, and on this basis, guide the operation and maintenance of the tap changer, which has important engineering significance for improving the reliability and safety of the tap changer operation

Images