FANPeng-hui,JIANGTao,NIUChao-qun,et al.Fault Diagnosis Method of Drainage Network Based on Liquid Level Monitoring Data and CNN-SVM[J].China Water & Wastewater,2023,39(23):30-39.
基于液位监测及CNN-SVM的排水管网缺陷诊断
- Title:
- Fault Diagnosis Method of Drainage Network Based on Liquid Level Monitoring Data and CNN-SVM
- 摘要:
- 为提高排水管网运维管理能力，使管网结构性、功能性缺陷问题得到有效监测并识别，通过分析排水管网监测任务的具体要求，提出了一种基于液位监测数据及CNN-SVM的排水管网缺陷诊断方法，通过将SVM分类器替换Softmax分类器以改善CNN的分类性能，同时规避SVM对于数据特征提取的劣势。针对排水管道监测环境的复杂性，自行设计并搭建排水管道缺陷试验装置，并结合物联网监测系统进行数据的采集。结果显示，模型能十分有效地进行排水管道缺陷问题的诊断排查，在十分类、十三分类、全分类任务下分别具有94.20%、91.57%、85.34%的准确率。与其他诊断模型相比，在分类精度要求最高的全分类任务中CNN-SVM模型的准确率比次优的CNN-LSTM模型高出了16.94%，并且在精确率、召回率、F1-Measure上也具有明显优势，验证了所提模型的泛化性和有效性。
- Abstract:
- In order to improve the operation and maintenance management ability of drainage pipe network, and the structural and functional defects of pipe network can be effectively monitored and identified，a fault diagnosis method of drainage network based on liquid level monitoring data and CNN-SVM was proposed by analyzing the specific requirements of drainage network monitoring tasks. Softmax classifier was replaced by SVM classifier to improve the classification performance of CNN and avoid the disadvantages of SVM in data feature extraction. In view of the complexity of drainage pipeline monitoring environment, the drainage pipeline defect test device was designed and combined with the Internet of Things monitoring system to collect data.The results showed that the model was very effective in the diagnosis and troubleshooting of drainage pipe defects, with an accuracy of 94.20%, 91.57% and 85.34% under the tasks of ten classification, thirteen classification and full classification, respectively. Compared with other diagnostic models, the CNN-SVM model had a 16.94% higher accuracy than the second?best CNN-LSTM model in all classification tasks requiring the highest classification accuracy, and also had obvious advantages in accuracy rate, recall rate and F1-Measure, which verified the generalization and effectiveness of the proposed model.
相似文献/References:
[1]王浩正,蔡然,骆春会,等.排水管网资产管理技术和工具研究进展[J].中国给水排水,2021,37(2):18.
WANG Hao-zheng,CAI Ran,LUO Chun-hui,et al.Research Progress on Asset Management Technology and Tools of Drainage Network[J].China Water & Wastewater,2021,37(23):18.
[2]李清泉,朱家松,李虹,等.基于漂流式胶囊机器人的管道快速检测系统[J].中国给水排水,2021,37(10):126.
LI Qing-quan,ZHU Jia-song,LI Hong,et al.Rapid Detection System of Pipeline Based on Floating Capsule Robot[J].China Water & Wastewater,2021,37(23):126.
[3]宋瑞宁,戴正晖,王宇,等.管网缺陷对城市排水系统模拟结果的影响[J].中国给水排水,2021,37(11):125.
SONG Rui-ning,DAI Zheng-hui,WANG Yu,et al.Influence of Pipe Network Defects on Simulation Results of Urban Drainage System[J].China Water & Wastewater,2021,37(23):125.
[4]王剑锋,黄微,姚远,等.昆明排水管网在线液位监测网络建设及数据应用[J].中国给水排水,2021,37(11):131.
WANG Jian-feng,HUANG Wei,YAO Yuan,et al.Construction and Data Application of Online Liquid Level Monitoring System in Kunming Drainage Network[J].China Water & Wastewater,2021,37(23):131.
[5]李志丽,姜明洁,潘冉,等.北京市延庆区排水管网监测及运行状态分析[J].中国给水排水,2021,37(20):99.
LI Zhi-li,JIANG Ming-jie,PAN Ran,et al.Monitoring and Operating Condition Analysis of Urban Sewer Network in Yanqing District, Beijing[J].China Water & Wastewater,2021,37(23):99.
[6]郭效琛,李萌,杜鹏飞,等.排水管网在线监测布点数量的确定[J].中国给水排水,2022,38(2):122.
GUO Xiao?chen,LI Meng,DU Peng?fei,et al.Quantification of On?line Monitoring Layout in Urban Drainage Network[J].China Water & Wastewater,2022,38(23):122.
[7]姚越,顾思文,沈旭,等.排水管网排查诊断实践与思考：以北方某缺水城市为例[J].中国给水排水,2022,38(12):113.
YAOYue,GUSi-wen,SHENXu,et al.Practice and Thinking of Investigation and Diagnosis of Urban Sewage Network:Case Study of a Water-deficient City in North China[J].China Water & Wastewater,2022,38(23):113.
[8]王新夏,卢兴,李浩,等.数字化模型在老城区排水管网系统改造中的应用[J].中国给水排水,2022,38(18):58.
WANGXin-xia,LUXing,LIHao,et al.Application of Digital Model in the Reconstruction of Old Urban District Drainage Network System[J].China Water & Wastewater,2022,38(23):58.
[9]梁小光,贺娟,温卫华,等.基于综合水力性能指数的管道排水能力评估及应用研究[J].中国给水排水,2022,38(22):22.
LIANGXiao-guang,HEJuan,WENWei-hua,et al.Drainage Capacity Evaluation of Sewer Networks Based on Comprehensive Hydraulic Performance Index and Its Application[J].China Water & Wastewater,2022,38(23):22.
[10]司艺方,曹佳佳,汪晨倩,等.污水管网行动计划编制策略及宁波江北区实践[J].中国给水排水,2023,39(2):38.
SIYi-fang,CAOJia-jia,WANGChen-qian,et al.Strategy of the Compilation on Sewage Pipe Action Plan and Its Practice in Jiangbei District of Ningbo City[J].China Water & Wastewater,2023,39(23):38.