Two-Level Diagnosis of Heating Pipe Network Leakage Based on Deep Belief Network

Qingwu Fan,Xudong Liu,Shaoen Wu,Yiliang Guo

doi:10.1109/access.2019.2960107

Abstract

This paper takes on the central heating secondary network and establishes a two-level diagnosis model of leakage fault of heating pipe network based on deep belief network (DBN) under the condition of constant and small supply flow quality regulation. Firstly, a leakage condition hydraulic calculation model of the heating pipe network is established with graph theory, which provides the pressure changes of the pressure monitoring points in the pipe network. Then, the first-level diagnostic model for the leakage of the heating pipe network is designed to diagnose the leaky pipe segment by using a deep belief network. Based on the results of the first-level diagnostic model, each leaky pipe segment is treated as a unit and a second-level diagnosis model is then developed to predict the specific leak location. Finally, the model is verified with a branch-pipe network and a loop-pipe network. Experimental results showed that the first-level diagnostic model had a high accuracy rate in the prediction of leaky pipe segments, which was superior to traditional fault diagnosis methods such as BP (Back Propagation Neural Network) and SVM (Support Vector Machines). The second-level diagnostic model can detect the leak location of the leaky pipe with satisfactory results.

Highlights

Urban heating is an essential livelihood issue in northern China’s cities and is closely related to the winter ‘‘smog’’ problem that is of great concern to the whole society in recent years [1]
The results show that the leakage diagnosis model based on deep belief network (DBN) designed in this paper has 86 samples with the prediction errors between −0.5 and 0.5, and the accuracy rate reaches 95.56%
In this paper, we design a two-level diagnostic model for leakage of the heating pipe network based on DBN

Summary

Introduction

Urban heating is an essential livelihood issue in northern China’s cities and is closely related to the winter ‘‘smog’’ problem that is of great concern to the whole society in recent years [1]. In the urban heating system, the leakage fault of the heating pipe network is one of the main failures, which will break the hydraulic balance of the heating network, cause energy waste and affect the operation of the entire heating system. The detection of leakage fault in the heating pipe network can ensure timely maintenance and repair of the pipe network, ensure its safe and stable operation, realize energy saving and emission reduction, and effectively control the operating cost [2]. Q. Fan et al.: Two-Level Diagnosis of Heating Pipe Network Leakage Based on DBN

Methods

Results

Conclusion