机器学习在污泥处理典型工艺中的应用与研究进展

曹依航; 宋鑫; 张驰; 罗景阳

doi:10.13205/j.hjgc.202607021

机器学习在污泥处理典型工艺中的应用与研究进展

doi: 10.13205/j.hjgc.202607021

曹依航^1,2,
宋鑫^1,2,
张驰^1,2,
罗景阳^1,2, ,

1. 河海大学浅水湖泊综合治理与资源开发教育部重点实验室, 南京 210098;
2. 河海大学环境学院, 南京 210098

基金项目:

国家自然科学基金面上项目（52470146）；江苏省省级大学生创新创业训练计划（S202510294037）

详细信息

作者简介:
曹依航（2006—），女，本科生，主要研究方向为有机废物的资源化利用。2314010109@hhu.edu.cn

通讯作者:
罗景阳（1989—），男，工学博士，教授，博士生导师，主要研究方向为有毒有害污染物控制理论与技术及有机废物的资源化利用。luojy2016@hhu.edu.cn

计量
- 文章访问数: 6
- HTML全文浏览量: 0
- PDF下载量: 1
- 被引次数: 0
出版历程
- 收稿日期: 2026-03-11
- 网络出版日期: 2026-09-01

Research progress of machine learning in typical sludge treatment technologies

CAO Yihang^1,2,
SONG Xin^1,2,
ZHANG Chi^1,2,
LUO Jingyang^{1,2
, ,}

1. Key Laboratory of Integrated Regulation and Resource Development on Shallow Lakes of the Ministry of Education, Hohai University, Nanjing 210098, China;
2. College of Environment, Hohai University, Nanjing 210098, China

摘要

摘要: 随着城镇污水处理规模的不断扩大，污泥产生量持续增加，其高效处理处置与资源化利用成为环境工程领域的重要研究方向。机器学习因能够从复杂运行数据中提取非线性特征，在污泥处理领域的预测与优化中具有强大应用潜力。围绕污泥脱水、污泥资源化利用（如厌氧消化）与污泥终端处置（如焚烧、填埋）等典型工艺，从数据集准备、算法选择与模型评估3个层面梳理了机器学习建模的一般流程及关键研究进展。比较分析了支持向量机（SVM）、随机森林（RF）、人工神经网络（ANN）及其他深度学习模型在不同污泥处理场景中的适用性与局限性：SVM在中小样本与高维数据条件下的表现更为稳定，RF通常具有较强泛化能力并可提供变量重要性线索，ANN及深度学习在大规模数据及典型时序或图像任务中更具优势，但对数据质量提出了更高要求。最后，从多源数据融合、模型可解释性以及机器学习与机理模型耦合等方面对未来研究方向进行展望，以期为污泥处理领域的智能化与精细化管理提供参考。
- 污泥处理 /
- 机器学习 /
- 污泥脱水 /
- 厌氧消化 /
- 终端处置
Abstract: With the continuous expansion of urban sewage treatment capacity， the sludge generation continues to increase， making its efficient treatment， disposal， and resource recovery as significant research focus. Machine learning holds substantial application potential in sludge treatment prediction and optimization due to its capacity to extract non-linear features from complex operational data. Focusing on typical processes such as sludge dewatering， resource recovery （i.e.， anaerobic digestion）， and final disposal （i.e.， incineration and landfill）， the general workflow and key research advances in machine learning modeling are summarized across three dimensions： dataset preparation， algorithm selection， and model evaluation. A comparative analysis examines the applicability and limitations of support vector machines （SVM）， random forests （RF）， artificial neural networks （ANN）， and other deep learning models across diverse sludge treatment scenarios. The results show that SVMs demonstrate greater stability with small-to-medium sample sizes and high-dimensional data， while RFs typically exhibit strong generalization capabilities and provide insights into variable importance. ANNs and deep learning models show advantages in handling large-scale data and typical time-series or image tasks， though they impose higher demands on data quality. Finally， future research directions are explored through multi-source data fusion， model interpretability， and the coupling of machine learning with mechanistic models， aiming to provide guidance on the intelligent and refined management of sludge treatment.
- sludge treatment /
- machine learning /
- sludge dewatering /
- anaerobic digestion /
- terminal disposal

HTML全文

参考文献(46)

[1]	Ministry of Ecology and Environment of the People's Republic of China. 2024 Report on the state of the ecology and environment in China[R]. Beijing：Ministry of Ecology and Environment of the People's Republic of China，2025. 中华人民共和国生态环境部. 中国生态环境状况公报（2024年）[R]. 北京：中华人民共和国生态环境部，2025.
[2]	AHMAD T，AHMAD K，ALAM M. Sustainable management of water treatment sludge through 3'R' concept[J]. Journal of Cleaner Production，2016，124：1-13.
[3]	RUI D N，MA Y Y，YE L. Application of machine learning methods in wastewater treatment systems[J]. Environmental Engineering，2022，40（6）：145-153. 芮栋妮，马燕燕，叶林. 机器学习方法在污水处理系统中的应用[J]. 环境工程，2022，40（6）：145-153.
[4]	WEI X S，GAO H J，CHEN Y H，CHANG Ming. Research progress of artificial intelligence technology in the field of water pollution control[J]. Journal of Environmental Engineering Technology，2022，12（6）：2057-2063. 魏潇淑，高红杰，陈远航，等. 人工智能技术在水污染治理领域的研究进展[J]. 环境工程技术学报，2022，12（6）：2057-2063.
[5]	LIU S S，ZHANG B，LI X Y，et al. Recent advances in the application of machine learning in environmental analysis and detection[J]. Journal of Instrumental Analysis，2024，43（8）：1105-1116. 刘思思，张波，李星颖，等. 机器学习在环境分析检测中的应用研究进展[J]. 分析测试学报，2024，43（8）：1105-1116.
[6]	MA H Z，LIU Y C，ZHAO J H，et al. Advances in machine learning applications to resource technology for organic solid waste[J]. Chinese Journal of Engineering，2025，47（3）：550-561. 马鸿志，刘忆婵，赵继华，等. 机器学习在有机固体废物资源化的应用进展[J]. 工程科学学报，2025，47（3）：550-561.
[7]	YANG Y X，FU L，WEI Q J，et al. CABNas-nir：A near-infrared classification for urban pipe network sludge on the fusion algorithm of NAS framework and active learning[J]. Plos One，2025，20（12）：e0339347.
[8]	HU Y M，XU D D，ZHANG M，et al. Research on the denitrification efficiency of anammox sludge based on machine vision and machine learning[J]. Water，2025，17（14）：2084.
[9]	CHEN H X，KUANG S N，CHEN X Y，et al. Synergistic reduction of pollution abatement and carbon in wastewater treatment plants based on multi-objective optimization：a case study of a plant in Beijing[J]. Research of Environmental Sciences，2023，36（11）：2148-2158. 陈惠鑫，旷森楠，陈昕悦，等. 基于多目标优化的污水处理厂减污降碳协同路径研究：以北京市某厂为例[J]. 环境科学研究，2023，36（11）：2148-2158
[10]	ZENG J C，BAI H，WANG S，et al. Experiment of mechanical dewatering effectiveness of river and lake sediments based on machine learning[J]. Water Purification Technology，2023，42（11）：159-165. 曾嘉辰，白鹤，王盛，等. 基于机器学习的河湖底泥机械脱水效果试验[J]. 净水技术，2023，42（11）：159-165.
[11]	DING C C，SHEN L，LIANG Q Y，et al. Machine learning in flocculant research and application：toward smart and sustainable water treatment[J]. Separations，2025，12（8）：203.
[12]	SHAO S，FU D Z，YANG T J，et al. Analysis of machine learning models for wastewater treatment plant sludge output prediction[J]. Sustainability，2023，15（18）：13380.
[13]	SALEHIN I，KANG D K. A review on dropout regularization approaches for deep neural networks within the scholarly domain[J]. Electronics，2023，12（14）：3106.
[14]	KOHEN E，FARHI N，SHAVITT Y，et al. Prediction of a full scale WWTP activated sludge SVI test using an LSTM neural network[J]. Environmental Science-Water Research& Technology，2022，8（11）：2786-2795.
[15]	LI Y，KONG B，YU W W，et al. An attention-based CNN-LSTM method for effluent wastewater quality prediction[J]. Applied Sciences-Basel，2023，13（12）：7011.
[16]	ZHU J W，SHENG Q，LIU W，et al. Study on HBA-SVM regression model for heat drying sludge moisture content real-time monitoring[J]. Energy Environmental Protection，2023，37（4）：149-156. 朱建伟，盛强，刘威，等. 污泥热干化含水率实时监测的HBA-SVM回归模型研究[J]. 能源环境保护，2023，37（4）：149-156.
[17]	BIN N F，LI J. Understanding machine learning predictions of wastewater treatment plant sludge with explainable artificial intelligence[J]. Water Environment Research，2024，96（10）：e11136.
[18]	ABUBAKAR U A，LEMAR G S，BELLO A A D，et al. Evaluation of traditional and machine learning approaches for modeling volatile fatty acid concentrations in anaerobic digestion of sludge：potential and challenges[J]. Environmental science and pollution research international，2025，32（49）：28239-28252.
[19]	ADIBIMANESH B，POLESEK-KARCZEWSKA S，BAGHERZADEH F，et al. Energy consumption optimization in wastewater treatment plants：Machine learning for monitoring incineration of sewage sludge[J]. Sustainable Energy Technologies and Assessments，2023，56：103040.
[20]	BORZOOEI S，SCABINI L，MIRANDA G，et al. Evaluation of activated sludge settling characteristics from microscopy images with deep convolutional neural networks and transfer learning[J]. Journal of Water Process Engineering，2024，64：105692.
[21]	WANI A A. Comprehensive analysis of clustering algorithms：exploring limitations and innovative solutions[J]. Peerj Computer Science，2024，10：e2286.
[22]	JOLLIFFE I T，CADIMA J. Principal component analysis：a review and recent developments[J]. Philosophical Transactions of the Royal Society A-Mathematical Physical and Engineering Sciences，2016，374（2065）：20150202.
[23]	ALONSO J M，de ABREU A H M，ANDREOLI C V，et al. Chemical characteristics and valuation of sewage sludge from four different wastewater treatment plants[J]. Environmental Monitoring and Assessment，2024，196（1）：34.
[24]	YE G，WAN J Q，DENG Z C，et al. Prediction of effluent total nitrogen and energy consumption in wastewater treatment plants：Bayesian optimization machine learning methods[J]. Bioresource Technology，2024，395：130361.
[25]	RAINIO O，TEUHO J，KLÉN R. Evaluation metrics and statistical tests for machine learning[J]. Scientific Reports，2024，14（1）：6086.
[26]	WANG X H，LI Y，QIAO Q，et al. Water quality prediction based on machine learning and comprehensive weighting methods[J]. Entropy，2023，25（8）：e25081186.
[27]	YANG S，KIM J，EOM J，et al. Machine learning based prediction of waste activated sludge generation for optimization of WWTP operational efficiency[J]. Environmental Research，2025，286：122990.
[28]	DAI W，PANG J W，DING J，et al. Integrated real-time intelligent control for wastewater treatment plants：Data-driven modeling for enhanced prediction and regulatory strategies[J]. Water Research，2025，274：123099.
[29]	CAO B D，ZHANG T，ZHANG W J，et al. Enhanced technology based for sewage sludge deep dewatering：A critical review[J]. Water Research，2021，189：116650.
[30]	CHEN D，DOU Y，LU P，et al. A review on sludge deep dewatering technology[J]. Chemical Industry and Engineering Progress，2019，38（10）：4722-4746.
[31]	FACCHINI F，RANIERI L，VITTI M. A neural network model for decision-making with application in sewage sludge management[J]. Applied Sciences-Basel，2021，11（12）：5434.
[32]	LI H W，LI C J，ZHOU K，et al. Intelligent upgrade of waste-activated sludge dewatering process based on artificial neural network model：Core influential factor identification and non-experimental prediction of sludge dewatering performance[J]. Journal of Environmental Management，2023，346：118971.
[33]	KOWALCZYK M，KAMIZELA T. Artificial neural networks in modeling of dewaterability of sewage sludge[J]. Energies，2021，14（6）：1682.
[34]	AHMAD Yasmin N S，WAHAB N A，ANUAR A N，et al. Performance comparison of SVM and ANN for aerobic granular sludge[J]. 2019，2019，8（4）：1080-1089.
[35]	De CLERCQ D，JALOTA D，SHANG R X，et al. Machine learning powered software for accurate prediction of biogas production：A case study on industrial-scale Chinese production data[J]. Journal of Cleaner Production，2019，218：390-399.
[36]	LI T，LI J. Simulation research of sewage sludge anaerobic digestion based on data mining technology[J]. Journal of Beijing University of Technology，2016，42（12）：1888-1894. 李佟，李军. 基于数据挖掘技术的污泥厌氧消化模拟研究[J]. 北京工业大学学报，2016，42（12）：1888-1894.
[37]	FARD M G，KOUPAIE E H. Machine learning assisted modelling of anaerobic digestion of waste activated sludge coupled with hydrothermal pre-treatment[J]. Bioresource Technology，2024，394：130255.
[38]	MANZOOR M. Process upset detection in wastewater treatment plants using clustering and deep learning[J]. IIP Series，2024，3（20）：118-168.
[39]	NIE E R，HE P J，ZHANG H，et al. Microbial volatile organic compounds as microecological stability indicators in response to temperature changes during anaerobic digestion[J]. Environmental Science& Technology，2025，59（13）：6696-6707.
[40]	WANG L G，LONG F，LIAO W，et al. Prediction of anaerobic digestion performance and identification of critical operational parameters using machine learning algorithms[J]. Bioresource Technology，2020，298：122495.
[41]	HUBERT C，KRAUSE S，SCHAUM C. Patterns in the course of gas production rates in anaerobic digestion—prediction of gas production rates based on deconvolution and linear regression[J]. Water，2023，15（4）：614.
[42]	GHAZIZADE-FARD M，KOUPAIE E H. Anaerobic co-digestion of wastewater sludge and food waste：A machine learning approach to process modeling and optimization[J]. Journal of Environmental Management，2025，393：126985.
[43]	ORGANIŚCIAK P，MASŁOŃ A A，KOWAL B，et al. Machine learning-based prediction of biogas production from sludge characteristics in four anaerobic digesters：development of the AD2Biogas prediction tool[J]. Advances in Science and Technology Research Journal，2024，18（8）：1-15.
[44]	KARAMI A，KARIMI-JASHNI A，NIKOO M R，et al. Simulation of anaerobic digestion process under variable feeding sludge using a hybrid machine learning model[J]. Chemosphere，2025，387：144672.
[45]	WANG D，XIANG J，YANG B，et al. Machine learning in sludge treatment：applications，mechanisms，and prospects[J]. Journal of Cleaner Production，2025，514：145710.
[46]	SZELĄG B，GAWDZIK J. Application of selected methods of artificial intelligence to activated sludge settleability predictions[J]. Polish Journal of Environmental Studies，2016，25（4）：1709-1714.