| 673 | 1 | 128 |
| 下载次数 | 被引频次 | 阅读次数 |
【目的】在我国“双碳”背景下，污水处理厂进水水质的准确预测对于节能减排和降低能耗具有重要意义。【方法】针对传统污水进水水质预测方法(如人工神经网络、循环神经网络及长短期记忆网络)在处理污水水质特征的随机性和非线性时精度不足的问题，提出了一种基于卷积注意力时序网络(CAT-NN)的预测模型。该模型结合了多尺度信息融合与混合注意力机制，并采用时序解码模块，有效捕捉污水水质指标的长期趋势与短期突变特性。【结果】通过对陕西省延安市某污水处理厂进水COD、NH3-N、TN和TP四项典型水质指标数据的预测分析，CAT-NN模型展现了优越的预测性能，其均方根误差(RMSE)为4.50%,平均绝对误差(MAE)为5.00%。与传统模型(如ANN、LSTM和门控循环单元GRU)相比，RMSE和MAE分别提升了16.13%和20.00%以上。【结论】结果表明：CAT-NN模型在污水处理厂进水水质预测中具有更高的精度和更强的鲁棒性。该模型不仅为污水处理厂的精确控制与高效运维提供了有力支撑，也为实现节能减排目标提供了重要的技术保障。
Abstract：[Objective]Under the “dual carbon” goals in China, the accurate prediction of influent water quality in wastewater treatment plants is crucial for energy conservation, emission reduction, and energy consumption reduction.[Methods]To address the insufficient accuracy of traditional influent water quality prediction method(such as artificial neural networks, recurrent neural networks, and long short-term memory networks) in handling the randomness and nonlinearity of wastewater water quality characteristics, a prediction model based on convolutional attention temporal neural network(CAT-NN) was proposed. The model integrated multi-scale information fusion and a hybrid attention mechanism, along with a temporal decoding module, to effectively capture the long-term trends and short-term abrupt changes in wastewater water quality indicators.[Results]Through the predictive analysis of four typical water quality indicators—COD, NH3-N, TN, and TP—of influent water data from a wastewater treatment plant in Yan'an City, Shaanxi Province, the CAT-NN model demonstrated excellent prediction perfor-mance, with a root mean square error(RMSE) of 4.50% and a mean absolute error(MAE) of 5.00%. Compared to traditional models(such as ANN, LSTM, and gated recurrent units(GRU)), the RMSE and MAE improved by over 16.13% and 20.00%, respectively.[Conclusion]The result indicate that the CAT-NN model achieves higher accuracy and stronger robustness in predicting influent water quality in wastewater treatment plants. The model not only provides strong support for the precise control and efficient operation of wastewater treatment plants, but also serves as a key technological solution for achieving energy conservation and emission reduction goals.
[1] 孟红旗，李红霞，赵爱平，等.市政污水厂典型A2O工艺低碳运行的系统性评估[J].环境科学，2023,44(2):1174-1180.MENG H Q,LI H X,ZHAO A P,et al.Systematic evaluation of low-carbon operation of typical A2O processes in municipal sewage plant [J].Environmental Science,2023,44(2):1174-1180.
[2] 余娇，赵荣钦，肖连刚，等.基于 “水—能—碳” 关联的城市污水处理系统碳排放研究[J].资源科学，2020,42(6):1052-1062.YU J,ZHAO R Q,XIAO L G,et al.Carbon emissions of urban wastewater treatment system based on the “water-energy-carbon” nexus [J].Resources Science,2020,42(6):1052-1062.
[3] 习近平.在第七十五届联合国大会一般性辩论上的讲话[N].人民日报，2020-09-23(3).DOI:10.28655/n.cnki.nrmrb.2020.009319.XI J P.Speech at the general debate of the 75th session of the United Nations General Assembly [N].People’s Daily,2020-09-23(3).DOI:10.28655/n.cnki.nrmrb.2020.009319.
[4] 谢琤琤，刘刚.城市污水处理厂碳中和路径解析[J].环境工程，2023,41(9):181-186.XIE C C,LIU G.Analysis of carbon neutrality pathways for urban wastewater treatment plants [J].Environmental Engineering,2023,41(9):181-186.
[5] AGHDAM E,MOHANDES S R,MANU P,et al.Predicting quality parameters of wastewater treatment plants using artificial intelligence techniques [J].Journal of Cleaner Production,2023,405:137019.
[6] QIONGHUA Z,QI W,YADONG X,et al.A novel carbon emission evaluation model for anaerobic-anoxic-oxic urban sewage treatment[J].Journal of Environmental Management,2024,350:119640.
[7] XIAN C,GONG C,LU F,et al.The evaluation of greenhouse gas emissions from sewage treatment with urbanization:Understanding the opportunities and challenges for climate change mitigation in China’s low-carbon pilot city,Shenzhen[J].Science of The Total Environment,2023,855:158629.
[8] ZHANG C,ZHAO G,JIAO Y,et al.Critical analysis on the transformation and upgrading strategy of Chinese municipal wastewater treatment plants:Towards sustainable water remediation and zero carbon emissions [J].Science of the Total Environment,2023,858:165201.
[9] ZHANG Y,GE T,LIU J,et al.The comprehensive measurement method of energy conservation and emission reduction in the whole process of urban sewage treatment based on carbon emission [J].Environmental Science and Pollution Research,2021,28(42):56727-56740.
[10] MENG H Q,LI H X,ZHAO A P,et al.Systematic evaluation of low-carbon operation of typical A2O processes in municipal sewage plant [J].Environmental Science,2023,44(2):1174-1180.
[11] PAKROU S,MEHRDADI N,BAGHVAND A.ANN modeling to predict the COD and efficiency of waste pollutant removal from municipal wastewater treatment plants[J].Current World Environ-ment,2015,10:873-881.
[12] ZHANG Y,LI C,DUAN H,et al.Deep learning based data-driven model for detecting time-delay water quality indicators of wastewater treatment plant influent [J].Chemical Engineering Journal,2023,467:143483.
[13] 邹可可，李中原，穆小玲，等.基于LSTM-GRU的污水水质预测模型研究[J].能源与环保，2021,43(12):59-63.ZOU K K,LI Z Y,MU X L,et al.Study on sewage quality prediction model based on LSTM-GRU [J].China Energy and Environmental Protection,2021,43(12):59-63.
[14] LY Q V,TRUONG V H,JI B X,et al.Exploring potential machine learning application based on big data for prediction of wastewater quality from different full-scale wastewater treatment plants [J].Science of the Total Environment,2022,832:154930.
[15] 姚怡帆，荆玉姝，王丽艳，等.基于集成模型的污水处理厂出水总氮预测方法[J].Industrial Water Treatment,2023,43(9):187-194.YAO Y F,JING Y S,WANG L Y,et al.Prediction method of total nitrogen in effluent from sewage treatment plants based on integrated model [J].Industrial Water Treatment,2023,43(9):187-194.
[16] 黄学平，吴留兴，辛攀，等.基于3种机器学习模型的污水处理厂出水总氮预测分析 [J].能源研究与管理，2023,(2):100-105.HUANG X P,WU L X,XIN P,et al.Prediction and analysis of total nitrogen in effluent from wastewater treatment plants based on three machine learning models [J].Energy Research and Management,2023,(2):100-105.
[17] 张净，窦慧芸，蒋武，等.基于PIWT-IPSO-BP的污水厂出水COD含量的预测模型[J].China Rural Water & Hydropower,2024(9):15-20.ZHANG J,DOU H Y,JIANG W,et al.Prediction model of effluent COD concentration in wastewater treatment plant based on PIWT-IPSO-BP [J].China Rural Water & Hydropower,2024(9):15-20.
[18] 王朱贺，李楠，张希瑞，等.基于机器学习的深基坑三维土层重建[J].重庆大学学报，2021,44(5):135-145.WANG Z H,LI N,ZHANG X R,et al.3D soil layer reconstruction of deep foundation pit based on machine learning [J].Journal of Chongqing University,2021,44(5):135-145.
[19] BI J,LIN Y,DONG Q,et al.Large-scale water quality prediction with integrated deep neural network [J].Information Sciences,2021,571:191-205.
[20] LIU H,JIAN H.ANN-based prediction of ammonia nitrogen for wastewater discharge indicators under carbon neutral trend [J].Frontiers in Ecology and Evolution,2023,11.doi:10.3389/fevo.2023.1199870.
[21] BERTONE E,STEWART R A,ZHANG H,et al.Hybrid water treatment cost prediction model for raw water intake optimization [J].Environmental Modelling & Software,2016,75:230-242.
[22] HAO X,LIU R,HUANG X.Evaluation of the potential for operating carbon neutral WWTPs in China [J].Water Research,2015,87:424-431.
[23] KAMRAN J M,SHAH H,WHITE M,et al.GVFs in the real world:Making predictions online for water treatment [J].Machine Learning,2023,113(8):1-31.
[24] KHALIL M,ALSAYED A,LIU Y,et al.Machine learning for modeling N2O emissions from wastewater treatment plants:Aligning model performance,complexity,and interpretability [J].Water Research,2023,245:120667.
[25] LI K,DUAN H,LIU L,et al.An integrated first-principal and deep learning approach for modeling nitrous oxide emissions from wastewater treatment plants [J].Environmental Science & Technology,2022,56(4):2816-2826.
[26] 马创，王尧，李林峰.基于遗传算法与支持向量机的水质预测模型[J].重庆大学学报，2021,44(7):108-114.MA C,WANG Y,LI L F.Water quality prediction model based on genetic algorithm and support vector machine [J].Journal of Chongqing University,2021,44(7):108-114.
[27] 涂吉昌，陈超波，王景成，等.基于深度学习的水质预测模型研究[J].自动化与仪表，2019,34(6):96-100.TU J C,CHEN C B,WANG J C,et al.Research on water quality prediction model based on deep learning [J].Automation and Instrumentation,2019,34(6):96-100.
[28] 叶蕾，耿敬华，方文，等.基于深度学习的排污口污染物浓度预测研究[J].环境科学学报，2024,44(4):429-439.YE L,GENG J H,FANG W,et al.Predicting concentrations of water contaminates from sewage outlet based on deep learning algorithms[J].Acta Scientiae Circumstantiae,44(4):429-439.
[29] 王红晨，马俊，陈博行.基于进化算法优化的CNN-EA-ConvLSTM水质预测模型[J].水电能源科学，2023,41(8):73-76.WANG H C,MA J,CHEN F X.CNN-EA-Conv LSTM water quality prediction model based on evolutionary algorithm optimization[J].Water Resources and Power,2023,41(8):73-76.
[30] CHENG T,HARROU F,KADRI F,et al.Forecasting of wastewater treatment plant key features using deep learning-based models:A case study [J].IEEE Access,2020,8:184475-184485.
[31] HAO X,LIU R,HUANG X.Evaluation of the potential for operating carbon neutral WWTPs in China [J].Water Research,2015,87:424-431.
[32] 方国华，张钰，袁婷，等.基于灰色关联-长短时记忆网络的水质预测研究[J].安全与环境学报，2023,23(12):4557-4568.FANG G H,ZHANG Y,YUAN T,et al.Study on the effect andpath ways of phosphorus removal bymodified constructed rapidinfiltration system[J].Journal of Safety and Environment,2023,23(12):4557-4568.
[33] ZHANG Y,LI C,JIANG Y,et al.Accurate prediction of water quality in urban drainage network with integrated EMD-LSTM model[J].Journal of Cleaner Production,2022,354:131724.
[34] PU F,DING C,CHAO Z,et al.Water-quality classification of inland lakes using Landsat-8 images by convolutional neural networks [J].Remote Sensing,2019,11(14):1674.
[35] 张铭玮，李正权，方志豪.基于量子粒子群优化的CNN-LSTM水质预测模型[J].中国计量大学学报，2022,33(3):303-310.ZHANG M W,LI Z Q,FANG Z H,et al.A CNN-LSTM water quality prediction model based on quantum particle swarm optimization[J].Journal of China University of Metrology,2022,33(3):303-310.
[36] YINGYI C,LIHUA S,YEQI L,et al.A review of the artificial neural network models for water quality prediction [J].Applied Sciences,2020,10(17):5776.
[37] YANG Y,KIM K R,KOU R,et al.Prediction of effluent quality in a wastewater treatment plant by dynamic neural network modeling [J].Process Safety and Environmental Protection,2022,158:515-524.
[38] WAN X,LI X,WANG X,et al.Water quality prediction model using Gaussian process regression based on deep learning for carbon neutrality in papermaking wastewater treatment system[J].Environmental Research,2022,211:112942.
基本信息:
DOI：10.13928/j.cnki.wrahe.2025.12.002
中图分类号:TP183;X703
引用信息:
[1]杨利伟,屈鑫,蒙怡筱,等.基于深度卷积注意力时序网络的污水处理厂进水水质预测[J].水利水电技术(中英文),2025,56(12):15-26.DOI:10.13928/j.cnki.wrahe.2025.12.002.
基金信息:
国家重点研发计划(2018YFE0103800); 陕西省住建节能能力建设课题项目(2022-03514)