[1]王昕妍,庞维亮,冯丽霞,等.基于可解释机器学习的污水厂碳源投加预测模型[J].中国给水排水,2026,42(7):44-50.
　WANGXinyan,PANGWeiliang,FENGLixia,et al.Prediction Model for Carbon Source Dosing in Wastewater Treatment Plants Based on Explainable Machine Learning[J].China Water & Wastewater,2026,42(7):44-50.
点击复制

基于可解释机器学习的污水厂碳源投加预测模型

中国给水排水[ISSN:1000-4062/CN:12-1073/TU] 卷: 第42卷 期数: 2026年第7期 页码: 44-50 栏目: 出版日期: 2026-04-01
Title:
Prediction Model for Carbon Source Dosing in Wastewater Treatment Plants Based on Explainable Machine Learning
作者:
王昕妍1,2， 庞维亮3， 冯丽霞4， 王晨晨1,2， 王少坡1,2， 曲申5,6
（1.天津城建大学 环境与市政工程学院，天津 300384；2.天津城建大学 天津市水质科学与技术重点实验室，天津 300384；3.天津市生态环境科学研究院，天津 300191；4.天津市联合环保工程设计有限公司，天津 300191；5.北京理工大学 能源与环境政策研究中心，北京 100081；6.北京理工大学 管理学院，北京 100081）
Author(s):
WANG　Xinyan1，2， PANG　Weiliang3， FENG　Lixia4， WANG　Chenchen1，2， WANG　Shaopo1，2， QU　Shen5，6
（1. School of Environmental and Municipal Engineering， Tianjin Chengjian University， Tianjin 300384， China； 2. Tianjin Key Laboratory of Aquatic Science and Technology， Tianjin Chengjian University， Tianjin 300384， China； 3. Tianjin Academy of Environmental Sciences， Tianjin 300191， China； 4. Tianjin United Environmental Protection Engineering Design Co. Ltd.， Tianjin 300191， China； 5. Center for Energy & Environmental Policy Research， Beijing Institute of Technology， Beijing 100081， China； 6. School of Management， Beijing Institute of Technology， Beijing 100081， China）
关键词:
污水处理厂;  碳源投加预测;  机器学习;  可解释性;  Shapley加法解释（SHAP）;  部分依赖图（PDP）
Keywords:
wastewater treatment plant;  carbon source dosing prediction;  machine learning;  explainability;  Shapley additive explanations (SHAP);  partial dependence plot (PDP)
摘要:
针对污水处理厂碳源精准投加问题，采用自动机器学习方法，筛选出梯度提升机（GBM）作为最佳算法，构建两座典型工艺污水处理厂的乙酸钠投加强度（即处理单位污水的乙酸钠投加量，SADI）预测模型，模型达到了强拟合预测效果。进一步采用可解释机器学习方法探究SADI与水质因素之间的关联，结果表明，对于采用A2/O工艺的JG污水厂，进水B/N值是影响SADI的首要因素，且有机负荷较低导致SADI显著上升；而对于采用A2/O+MBBR工艺的SZ污水厂，其生物膜强化除磷工艺以及进水高有机负荷降低了外加碳源需求，出水TP成为SADI预测的主要影响因素。SADI与各类水质指标之间呈现出复杂的非线性关联。本研究可为深入剖析不同污水处理工艺中碳源投加的影响因素及处理效果差异提供参考。
Abstract:
To enhance the precision of carbon source dosing in the wastewater treatment plant (WWTP), this study employs an automated machine learning approach, identifying the gradient boosting machine (GBM) as the optimal algorithm. Predictive models for sodium acetate dosing intensity (SADI), defined as the amount of sodium acetate added per unit volume of treated wastewater, were developed for two WWTPs with typical treatment processes. The models achieved a strong predictive fit. Furthermore, an explainable machine learning approach was adopted to explore the relationship between SADI and water quality factors. The results indicated that, for the JG WWTP, which utilized the A2/O process, the influent B/N ratio served as the principal determinant of SADI, with a low organic load substantially increasing SADI. In contrast, for the SZ WWTP employing the A2/O+MBBR process, the enhanced phosphorus removal capability of the biofilm process, coupled with the high influent organic loading, reduced the demand for external carbon sources, thereby making effluent TP the principal determinant of SADI. SADI demonstrated intricate nonlinear relationships with multiple water quality indicators. This study offers a valuable reference for examining the factors governing carbon source dosing and treatment performance across various wastewater treatment processes.

相似文献/References:

[1]王 亮.马来西亚Pantai地埋式污水厂环网供配电结构设计[J].中国给水排水,2018,34(22):63.
　WANG Liang.Power Supply and Distribution Structure Design of Ring Network for Pantai Underground Wastewater Treatment Plantin Malaysia[J].China Water & Wastewater,2018,34(7):63.
[2]侯晓庆,邓 磊,高海英,等.MBR工艺在神定河污水处理厂升级改造工程中的应用[J].中国给水排水,2018,34(22):66.
　HOU Xiao-qing,DENG Lei,GAO Hai-ying,et al.Application of MBR Process in the Upgrading and Reconstruction Project of Shending River WastewaterTreatment Plant[J].China Water & Wastewater,2018,34(7):66.
[3]邱明海.北京市垡头污水处理厂改扩建工程设计技术方案[J].中国给水排水,2018,34(20):13.
　QIU Ming hai.Reconstruction and Expansion Design Technical Plan of Beijing Fatou Wastewater Treatment Plant[J].China Water & Wastewater,2018,34(7):13.
[4]郝二成,郭毅,刘伟岩,等.基于数学模拟的污水厂运行分析——建模与体检[J].中国给水排水,2020,36(15):23.
　HAO Er-cheng,GUO Yi,LIU Wei-yan,et al.Operation Analysis of Wastewater Treatment Plant Based on Mathematical Simulation: Modeling and Examination[J].China Water & Wastewater,2020,36(7):23.
[5]张月,王阳,张宏伟,等.阳泉市污水处理二期工程BARDENPHO工艺设计和运行[J].中国给水排水,2020,36(16):64.
　ZHANG Yue,WANG Yang,ZHANG Hong-wei,et al.Design and Operation of BARDENPHO Process in Phase Ⅱ Project of Yangquan Wastewater Treatment Plant[J].China Water & Wastewater,2020,36(7):64.
[6]祝新军,蔡芝斌,姚斌,等.绍兴污水处理厂气浮设备的优化改造[J].中国给水排水,2020,36(16):101.
　ZHU Xin-jun,CAI Zhi-bin,YAO Bin,et al.Optimization and Modification of Air Floatation Equipment in Shaoxing Wastewater Treatment Plant[J].China Water & Wastewater,2020,36(7):101.
[7]王文明,杨淇椋,蔡依廷,等.MSBR工艺在高排放标准污水处理厂的应用[J].中国给水排水,2020,36(16):111.
　WANG Wen-ming,YANG Qi-liang,CAI Yi-ting,et al.Application of MSBR Process in Wastewater Treatment Plant with Stringent Discharge Standard[J].China Water & Wastewater,2020,36(7):111.
[8]郝二成,郭毅,刘伟岩,等.基于数学模拟的污水厂运行分析——控制与优化[J].中国给水排水,2020,36(17):23.
　HAO Er-cheng,GUO Yi,LIU Wei-yan,et al.Operation Analysis of Wastewater Treatment Plant Based on Mathematical Simulation: Control and Optimization[J].China Water & Wastewater,2020,36(7):23.
[9]王阳,张月,王晓康,等.高排放标准下的改良AAO+深度处理工程案例[J].中国给水排水,2020,36(18):56.
　WANG Yang,ZHANG Yue,WANG Xiao-kang,et al.Project Case of Modified AAO and Advanced Treatment Process under High Emission Standards[J].China Water & Wastewater,2020,36(7):56.
[10]郑枫,慕杨,孙逊.MBR工艺用于山东省某污水处理厂扩建工程[J].中国给水排水,2020,36(18):81.
　ZHENG Feng,MU Yang,SUN Xun.MBR Process Used in Expansion Project of a Sewage Treatment Plant in Shandong Province[J].China Water & Wastewater,2020,36(7):81.

更新日期/Last Update: 2026-04-01