Converter station secondary circuit abnormity identification and early warning method based on deep belief network

Abstract

The invention discloses a converter station secondary circuit abnormity identification and early warning method based on a deep belief network, and the method comprises the steps: building a historical abnormity data set and a normal data set of a mutual inductor coil through a secondary circuit intelligent analysis system, combining a fault equipment part, a fault reason and an operation and maintenance guide rule, and carrying out the summarization to form a typical fault processing knowledge base; forming a fault part sample set with a label according to the historical abnormal data of thetransformer coil in combination with actual operation and maintenance experience; establishing a DBN model, performing unsupervised layer-by-layer training on the DBN model by utilizing the training set with the fault classification label, and finally forming a diagnosis model; inputting samples to be classified into the diagnosis model trained in the step 3 according to classification rules, andoutputting to obtain specific classifications and error values under different classifications n; and sending the error value early warning information to the background of the secondary circuit intelligent analysis system. The problems that the pressing plate state of the protection device is abnormal, and the multi-protection acquisition device is abnormal and cannot give an early warning are solved.

Description

technical field [0001] The invention relates to the technical field of ultra-high voltage direct current transmission, in particular to a method for identifying and early warning of an abnormality in a secondary circuit of a converter station based on a deep trust network. Background technique [0002] UHV DC transmission has the advantages of large transmission capacity, long distance, and low loss. It is an effective way to optimize energy allocation and an important measure to implement my country's "West to East Power Transmission" strategy. As the "brain" of the UHV DC transmission project, the control and protection system not only controls the entire process of AC and DC power conversion and DC power transmission, but also protects all electrical equipment and DC transmission lines in the converter station from damage caused by electrical faults. It is of great significance to ensure the safe and stable operation of UHV DC transmission projects. [0003] The inventio...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the deficiencies of the prior art, the present invention provides a method for identifying and early warning of abnormality in the secondary circuit of a converter station based on a deep trust network, which collects the state of the pressure plate of the DC control protection device and the AC protection device, and uses fault recording to collect multiple protection devices The measurement device solves the problem of abnormal state of the pressure plate of the protection device and the failure of early warning for the abnormality of the multiple protection collection device

Images