Method for diagnosing faults of urban gas pipelines based on deep learning neural network

Abstract

The invention provides a method for diagnosing faults of urban gas pipelines based on a deep learning neural network. According to the method, a deep learning neural network classification model formed by a sparse automatic encoder SAE and SOFTMAX is established and is combined with a pipeline fault type so as to construct a fault diagnosis model, and then the fault classification of the gas pipelines is realized; and by virtue of unsupervised automatic learning characteristic parameters in deep learning and a supervised fine adjustment network, the problems that the characteristic parametersof fault diagnosis of the pipeline are based on experiences and the diagnosis accuracy rate is low are effectively solved, the fault diagnosis of the urban gas pipelines in the working process is relatively rapid, and the stability, precision and reliability of the fault diagnosis are improved.

Description

technical field [0001] The invention relates to the technical field of gas pipeline fault diagnosis, in particular to a method for diagnosing urban gas pipeline faults based on a deep learning neural network. Background technique [0002] Due to the wide laying area and complicated lines of gas pipelines buried underground, when the pipeline fails, if the type of pipeline failure is not accurately judged, correct measures cannot be taken to repair the fault point in time, which not only brings a lot of inconvenience to gas users, but also It also causes a waste of resources, may also bring many safety hazards to surrounding residents, and causes environmental pollution. [0003] In the prior art, generally, domestic fault diagnosis methods commonly used include manual direct detection method, support vector machine (support vector machine, SVM), evidence theory (Dempster-Shafter Evidence Theory, hereinafter referred to as D-S theory) fusion and backpropagation Neural Networ...

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is: in order to overcome the slow speed of manual detection in the prior art, methods such as support vector machine (SVM), evidence theory (D-S) fusion and backpropagation neural network (BPNN) are used in pipeline fault diagnosis. Parameter selection is empirical, and the accuracy of diagnosis results is low.

Images