基于GA优化BP神经网络模型的污水管道系统健康状况评估
摘要：污水管道系统健康评估是城市黑臭水体及城市体检中解决城市水环境污染、内涝灾害等城市病问题的核心和依据。以污水管道系统为研究对象，根据CCTV检测结果，采用层次分析法进行指标赋权与筛选，构建包含环境影响、排水能力、适应及修复能力3个影响要素及管龄和维护管理水平等14个子指标的健康状况评估体系。利用遗传算法优化BP神经网络，建立基于数据驱动的污水管道系统健康状况评估模型，并以北方某市污水管道系统为例进行仿真模拟，结果表明，研究区域内污水管道系统健康度Ⅰ、Ⅱ、Ⅲ、Ⅳ级管道占比分别为28.28%、62.39%、7.00%和2.33%；评估结果与实际情况比对，预测准确率91.63%。
关键词：污水管道健康状况评估层次分析法遗传算法BP神经网络
尊敬的用户，本篇文章需要20元，点击支付交费后阅读
限时优惠福利：领取VIP会员
全年期刊、VIP视频免费!
全年期刊、VIP视频免费!
参考文献[1] 巴振宁，梁建文，王鸣铄.基于改进F-ANP方法的市政排水管网运行安全风险评估[J].安全与环境工程，2020,27,132(6):212-220.
[2] REED E C,CULLEN N,DARLING R S,et al.Restoration of sewerage systems proceedings of an international conference Held in London on 22-24 June 1981[J].Corrosion,1982.
[3] KETTLER A J,GOULTER I C.An analysis of pipe breakage in urban water distribution networks[J].Revue Canadienne De Gnie Civil,1985,12(2):286-293.
[4] 罗同顺，左剑恶，黄霞等.基于模糊综合评判模型的污水管道缺陷定量化评价方法[J].环境科学学报，2011,31(10):2204-2209.
[5] SALMAN B,SALEM O.Modeling failure of wastewater collection lines using various section-level regression models[J].Journal of Infrastructure Systems,2012,18(2):146-154.
[6] 范小花，丁允超.城市污水管网气体爆炸风险评估[J].工业安全与环保，2016,42(8):32-34.
[7] HAWARI A,ALKADOUR F,ELMASRY M,et al.Condition assessment model for sewer pipelines using fuzzy-based evidential reasoning[J].Australian Journal of Civil Engineering,2018,16(1):1-15.
[8] HAWARI A,ALKADOUR F,ELMASRY M,et al.Simulation-based condition assessment model for sewer pipelines[J].Journal of Performance of Constructed Facilities,2016:4016066.
[9] MOHAMMADI M M,NAJAFI M,SALEHABADI N,et al.Predicting condition of sanitary sewer pipes with gradient boosting tree[C].2020.
[10] 刘威，董婉琪.基于AHP-熵权法组合赋权的排水管网风险评估方法研究[J].安全与环境学报，2021,21(3):949-956.
[11] 徐得潜，张倩.基于AHP-GRA的合流制污水管道风险评估[J].安全与环境学报.2019,19(4):1149-1154.
[12] YIN X,CHEN Y,BOUFERGUENE A,et al.A deep learning-based framework for an automated defect detection system for sewer pipes[J].Automation in Construction,2019,109(2020):102967.
[13] ROGHANI B,CHERQUI F,AHMADI M,et al.Dealing with uncertainty in sewer condition assessment:impact on inspection programs[J].Automation in Construction,2019,103(6):117-126.
[14] ANBARI M J,TABESH M,ROOZBAHANI A.Risk assessment model to prioritize sewer pipes inspection in wastewater collection networks[J].Journal of Environmental Management,2017.
[15] Hydrology;Reports from Aalborg University Describe Recent Advances in Hydrology(Analysis and integrated modelling of groundwater infiltration to sewer networks)[J].Science Letter,2016.
[16] HAWARI A,ALKADOUR F,ELMASRY M,et al.A state of the art review on condition assessment models developed for sewer pipelines[J].Engineering Applications of Artificial Intelligence,2020,93:103721.
[17] Hydrology;Researchers from Tsinghua University Report Recent Findings in Hydrology (Quantifying rainfall-derived inflow and infiltration in sanitary sewer systems based on conductivity monitoring)[J].Science Letter,2018.
[18] HU Y,SCAVIA D,KERKEZ B.Are all data useful?inferring causality to predict flows across sewer and drainage systems using directed information and boosted regression trees[J].Water Research,2018,145(15):697-706.
[19] 王威尧，刘莹昕，刘飒.层次分析法的权重计算及其应用[J].沈阳大学学报（自然科学版），2014,26(5):372-375.
[20] 王海英，李顺安，韩乐，等.南宁市排水管道健康状况评估分析[J].给水排水，2020,56(5):132-137.
[21] 徐祖信，汪玲玲，李怀正，等.基于特征因子的排水管网地下水入渗分析方法[J].同济大学学报（自然科学版），2016,44(4):593-599.
[22] 吴慧英，江凯兵，李天兵，等.基于SWMM的市政排水管道泥沙淤积对溢流积水影响的模拟分析[J].给水排水，2019,45(11):135-139.
[23] 顾永钢，高丹，刘操，等.北京市城区典型餐饮废水分类调查及对策[C].2019.
[24] 北京工业废水和城市污水环境激素污染状况调查[J].环境科学研究，2007(6):1-7.
[25] 高思，于燕.西安市二级及以下公立医疗机构污水处理情况调查[J].中国卫生产业，2018,15(22):154-156.
[26] 白萍，王峰.室外排水工程采用塑料管和钢筋混凝土管的比较[J].给水排水，2004,30(6):86-88.
[27] 刘少非，郑茂辉.GA优化ELM神经网络的排水管道缺陷诊断[J].哈尔滨工业大学学报，2021,53(5):59-64.
[28] LEI H Y L C.Design of decision tree structure with improved BPNN nodes for high-accuracy locomotion mode recognition using a single IMU[J].Sensors,2021.
[29] LI X H G Z.Theory study and application of the BP-ANNmethod for power grid short-term load forecasting[J].ZTECommunications,2015,13(3):2-5.
[30] 胡海涛.基于BP神经网络和遗传算法的并行迭代优化研究[J].机械与电子，2019,37,316(1):28-34.
[31] 王波，林济铿，任怡，等.基于Logistic回归深层神经网络的电力系统故障概率诊断[J].天津大学学报（自然科学与工程技术版），2021,54(2):186-195.
[32] 鲍长春，崔子豪.基于广义合成分析和深度神经网络的自回归系数估计方法[J].电子学报，2021,49(1):29-39.
[33] 齐利华，祖士卿，马骥.珠海市某区域污水管网CCTV检测结果与建议[J].中国给水排水，2017(33):135-138.
[34] 蒋瑞，储征伟.城市排水管道健康状况检测与评估内外业流程一体化方案设计与应用[J].测绘通报，2016.
[35] 巴振宁，梁建文，韩亚鑫.基于改进AHP和模糊综合评价法的燃气管道腐蚀风险评价[J].安全与环境学报，2018,18(6):2103-2109.
[36] KHAIRUDDIN S H,HASAN M H,HASHMANI M A,et al.Generating clustering-based interval fuzzy type-2triangular and trapezoidal membership functions:a structured literature review[J].Symmetry,2021,13(2):239.
[2] REED E C,CULLEN N,DARLING R S,et al.Restoration of sewerage systems proceedings of an international conference Held in London on 22-24 June 1981[J].Corrosion,1982.
[3] KETTLER A J,GOULTER I C.An analysis of pipe breakage in urban water distribution networks[J].Revue Canadienne De Gnie Civil,1985,12(2):286-293.
[4] 罗同顺，左剑恶，黄霞等.基于模糊综合评判模型的污水管道缺陷定量化评价方法[J].环境科学学报，2011,31(10):2204-2209.
[5] SALMAN B,SALEM O.Modeling failure of wastewater collection lines using various section-level regression models[J].Journal of Infrastructure Systems,2012,18(2):146-154.
[6] 范小花，丁允超.城市污水管网气体爆炸风险评估[J].工业安全与环保，2016,42(8):32-34.
[7] HAWARI A,ALKADOUR F,ELMASRY M,et al.Condition assessment model for sewer pipelines using fuzzy-based evidential reasoning[J].Australian Journal of Civil Engineering,2018,16(1):1-15.
[8] HAWARI A,ALKADOUR F,ELMASRY M,et al.Simulation-based condition assessment model for sewer pipelines[J].Journal of Performance of Constructed Facilities,2016:4016066.
[9] MOHAMMADI M M,NAJAFI M,SALEHABADI N,et al.Predicting condition of sanitary sewer pipes with gradient boosting tree[C].2020.
[10] 刘威，董婉琪.基于AHP-熵权法组合赋权的排水管网风险评估方法研究[J].安全与环境学报，2021,21(3):949-956.
[11] 徐得潜，张倩.基于AHP-GRA的合流制污水管道风险评估[J].安全与环境学报.2019,19(4):1149-1154.
[12] YIN X,CHEN Y,BOUFERGUENE A,et al.A deep learning-based framework for an automated defect detection system for sewer pipes[J].Automation in Construction,2019,109(2020):102967.
[13] ROGHANI B,CHERQUI F,AHMADI M,et al.Dealing with uncertainty in sewer condition assessment:impact on inspection programs[J].Automation in Construction,2019,103(6):117-126.
[14] ANBARI M J,TABESH M,ROOZBAHANI A.Risk assessment model to prioritize sewer pipes inspection in wastewater collection networks[J].Journal of Environmental Management,2017.
[15] Hydrology;Reports from Aalborg University Describe Recent Advances in Hydrology(Analysis and integrated modelling of groundwater infiltration to sewer networks)[J].Science Letter,2016.
[16] HAWARI A,ALKADOUR F,ELMASRY M,et al.A state of the art review on condition assessment models developed for sewer pipelines[J].Engineering Applications of Artificial Intelligence,2020,93:103721.
[17] Hydrology;Researchers from Tsinghua University Report Recent Findings in Hydrology (Quantifying rainfall-derived inflow and infiltration in sanitary sewer systems based on conductivity monitoring)[J].Science Letter,2018.
[18] HU Y,SCAVIA D,KERKEZ B.Are all data useful?inferring causality to predict flows across sewer and drainage systems using directed information and boosted regression trees[J].Water Research,2018,145(15):697-706.
[19] 王威尧，刘莹昕，刘飒.层次分析法的权重计算及其应用[J].沈阳大学学报（自然科学版），2014,26(5):372-375.
[20] 王海英，李顺安，韩乐，等.南宁市排水管道健康状况评估分析[J].给水排水，2020,56(5):132-137.
[21] 徐祖信，汪玲玲，李怀正，等.基于特征因子的排水管网地下水入渗分析方法[J].同济大学学报（自然科学版），2016,44(4):593-599.
[22] 吴慧英，江凯兵，李天兵，等.基于SWMM的市政排水管道泥沙淤积对溢流积水影响的模拟分析[J].给水排水，2019,45(11):135-139.
[23] 顾永钢，高丹，刘操，等.北京市城区典型餐饮废水分类调查及对策[C].2019.
[24] 北京工业废水和城市污水环境激素污染状况调查[J].环境科学研究，2007(6):1-7.
[25] 高思，于燕.西安市二级及以下公立医疗机构污水处理情况调查[J].中国卫生产业，2018,15(22):154-156.
[26] 白萍，王峰.室外排水工程采用塑料管和钢筋混凝土管的比较[J].给水排水，2004,30(6):86-88.
[27] 刘少非，郑茂辉.GA优化ELM神经网络的排水管道缺陷诊断[J].哈尔滨工业大学学报，2021,53(5):59-64.
[28] LEI H Y L C.Design of decision tree structure with improved BPNN nodes for high-accuracy locomotion mode recognition using a single IMU[J].Sensors,2021.
[29] LI X H G Z.Theory study and application of the BP-ANNmethod for power grid short-term load forecasting[J].ZTECommunications,2015,13(3):2-5.
[30] 胡海涛.基于BP神经网络和遗传算法的并行迭代优化研究[J].机械与电子，2019,37,316(1):28-34.
[31] 王波，林济铿，任怡，等.基于Logistic回归深层神经网络的电力系统故障概率诊断[J].天津大学学报（自然科学与工程技术版），2021,54(2):186-195.
[32] 鲍长春，崔子豪.基于广义合成分析和深度神经网络的自回归系数估计方法[J].电子学报，2021,49(1):29-39.
[33] 齐利华，祖士卿，马骥.珠海市某区域污水管网CCTV检测结果与建议[J].中国给水排水，2017(33):135-138.
[34] 蒋瑞，储征伟.城市排水管道健康状况检测与评估内外业流程一体化方案设计与应用[J].测绘通报，2016.
[35] 巴振宁，梁建文，韩亚鑫.基于改进AHP和模糊综合评价法的燃气管道腐蚀风险评价[J].安全与环境学报，2018,18(6):2103-2109.
[36] KHAIRUDDIN S H,HASAN M H,HASHMANI M A,et al.Generating clustering-based interval fuzzy type-2triangular and trapezoidal membership functions:a structured literature review[J].Symmetry,2021,13(2):239.
Evaluation of the health status of sewage pipeline system based on GA optimized BP neural network model
Abstract: Health assessment of sewage pipeline system is the core and basis for solving urban water pollution,waterlogging disaster and other urban diseases in the background of black-odor water treatment and urban physical examination.Taking the sewerage system as the research object,according to CCTV(closed-circuit television)test results,using Analytic Hierarchy Process(AHP)for weighting and selection,environmental impact,drainage ability,adapt to the building contains and three influence factors of the ability to repair,and 14 sub-indexes of the health of the evaluation system such as pipe age,maintenance management level.A genetic algorithm(GA)was used to optimize BP neural network,and a data-driven health status assessment model of the sewage pipeline system was established.The pipeline systems in northern cities as an example to carry on the simulation,the results show that the study area in the sewer system health Ⅰ,Ⅱ,Ⅲ,Ⅳ piping proportion were 28.28%,62.39%,7.00%,and 2.33%.Compared with the actual situation,the prediction accuracy is 91.63%,which has good applicability and generalization.
Keywords: Sewage pipeline; Health status evaluation; Analytic hierarchy process; Genetic algorithm; BP neural network;
727
0
0