Monitoring data-based transformer state expert diagnosis method

Abstract

The invention provides a monitoring data-based transformer state expert diagnosis method. The method includes the following steps that: 1, an expert system knowledge base is constructed, wherein the expert system knowledge base is the core of an expert system, and the construction process of the complete expert system knowledge base includes knowledge expression, knowledge acquisition, knowledge storage, knowledge consistency detection and database design; 2, expert scoring rules are established; 3, diagnostic reasoning is carried out, wherein the diagnostic reasoning adopts forward reasoning; and 4, a diagnostic result is obtained. According to the invention, a transformer state comprehensive diagnosis system is built based on expert system theory knowledge, and fast and accurate state diagnosis can be performed on the real-time monitoring data of a transformer based on expert knowledge.

Description

technical field [0001] The invention relates to a diagnosis method, in particular to an expert diagnosis method of a transformer state based on monitoring data. Background technique [0002] With the rapid development of my country's economy, the demand for electricity is increasing day by day. From 2011 to 2020, the electricity consumption of the whole society in my country will maintain a growth rate of more than 3.3-4%, and the electricity consumption of the whole society will reach 6.7-7 trillion kwh. This puts forward higher requirements for the reliability, safety and stability of power equipment, and the fault diagnosis and equipment life prediction of power equipment are becoming more and more important. In September 1990, a major power outage occurred in Guangdong, my country. The short-circuit fault of the 220KV line caused 7 power plants to crack, 13 220KV lines tripped, and 11 220KV substations were blacked out. 2 / 3 of the load in Guangzhou City, 1 / 2 of the load i...

AI Technical Summary

Problems solved by technology

What these methods have in common is to train diagnostic rules based on existing knowledge. The problem includes two aspects: one is that the result of diagnosis depends on the accuracy and richness of existing knowledge; the other is that there may be learning time in training diagnostic rules. Long time, lack of rule knowledge or unstable diagnosis results, etc.

Images