To diagnose the blocking fault of the heating network accurately and improve the operation reliability of the heating system, a diagnosis method was proposed based on hydraulic simulation and neural networks. Firstly, to obtain a large number of data samples representing the features of heating-network blockage operation, the blockage simulation expert database was established based on hydraulic simulation. Secondly, the actual hydraulic features of the heating network were obtained by combining representation learning and the heating network's actual data, and the blockage representation expert database was established. Finally, a convolutional neural-network blockage diagnosis model was trained and tested based on the established database. An urban actual heating network was selected as a study case. The results show that the blockage representation data can effectively express the actual hydraulic features of the heating network. The accuracy of diagnosing blockages using simulation data and representation data as samples exceeded 85%.
ZHOUS, LIUC, ZHAOY, et al. Leakage diagnosis of heating pipe-network based on BP neural network[J]. Sustainable Energy, Grids and Networks, 2022, 32: 100869.
CHENZhuo, WANGQing, WANGYifan, et al. Searching and analysis of blocking point in long distance distribution pipeline[J]. Water Technology, 2011, 5(2): 60-61. (in Chinese)
LIShun’an, LITing, WENHuifeng, et al. Analysis of CCTV detection results of drainage pipelines in a city of Southern China[J]. Urban Geotechnical Investigation & Surveying, 2022(5): 169-172. (in Chinese)
[9]
WANGJ, LIUG H, WANGJ, et al. Current status, existent problems, and coping strategy of urban drainage pipeline network in China[J]. Environmental Science and Pollution Research International, 2021, 28(32): 43035-43049.
WANGYan, LUShuwen, LIJie, et al. Research on fault diagnosis of oilfield water injection pipeline network based on SDE-BP method[J]. Chemical Engineering Machinery, 2023, 50(5): 749-757. (in Chinese)
DUANLanlan, TIANQi, DUANPengfei, et al. Fault diagnosis model of heating networks based on BP neural network optimized by genetic algorithm[J]. Journal of North University of China (Natural Science Edition), 2014, 35(3): 303-308. (in Chinese)
[15]
ZHOUS, LIH, GONGP, et al. Hydraulic modeling of double-source and ring-shaped heating networks[J]. Applied Thermal Engineering, 2017, 119: 215-221.
[16]
李沁璘. 人工神经网络综述[J]. 科学与信息化, 2021(7): 181-182.
[17]
LIQinlin. Review of artificial neural networks[J]. Science and informatization, 2021(7): 181-182. (in Chinese)
ZHOULihua, WANGJialong, WANGLizhen, et al. Heterogeneous information network representation learning: a survey[J]. Chinese Journal of Computers, 2022, 45(1): 160-189. (in Chinese)
[20]
LIR, ZHANGH, ZHUANGQ, et al. BP neural network and improved differential evolution for transient electromagnetic inversion[J]. Computers Geosciences, 2020, 137: 104434.
LIUHongtao, WANGHao, WANGJinli, et al. Image denoising in second generation curvelet transform domain based on PCA[J]. Journal of Test and Measurement Technology, 2014, 28(2): 143-148. (in Chinese)
TANJianxin, XIEQian, JINGYanwei, et al. Wind power data standardization technology and wind power big data application method[J]. Microcomputer Applications, 2023, 39(2): 89-92. (in Chinese)
WANGJianrong, DENGLiming, CHENGWei, et al. Study on ECG classification algorithm based on CNN-LSTM-SE[J]. Journal of Test and Measurement Technology, 2024, 38(3): 264-273. (in Chinese)
[29]
APICELLAA, ISGRÒF, POLLASTROA, et al. Adaptive filters in graph convolutional neural networks[J]. Pattern Recognition, 2023, 144: 109867.
JIANGWeiwei, YUJingshan, CHENJipei, et al. Impact of discharge pipe system clogging and flap gate on urban hydrodynamic process[J]. Journal of Water Resources and Water Engineering, 2021, 32(1): 143-150. (in Chinese)
ZHOUYunhao, YANGBaojie, LIUDan, et al. Modeling and simulation of power engineering data prediction and analysis based on Random Forest algorithm[J]. Electronic Design Engineering, 2024, 32(4): 103-106. (in Chinese)
WANGQianqian, SONGPeng, HUAQingfeng, et al. Full waveform inversion based on Adam algorithm with optimized parameters[J]. Chinese Journal of Geophysics, 2023, 66(11): 4654-4663. (in Chinese)
ZHANGWenlong, WEIYan, LIYuanyuan, et al. Intrusion detection algorithm based on CA-ResNet network and nadam optimizer[J]. Journal of Chongqing Normal University (Natural Science), 2021, 38(4): 97-106. (in Chinese)
LIANGShan, LIUXiaobo. Fault identification analysis of DBN rotor system based on cross entropy cost function[J]. Journal of Nanchang Hangkong University (Natural Sciences), 2018, 32(3): 1-7. (in Chinese)