| 引用本文: | 贲雅雯,张欢,周琪,庞宏娇,宋怡藩,荆家琪,曲申.基于集成学习的饮用水处理预测模型[J].哈尔滨工业大学学报,2026,58(6):15.DOI:10.11918/202510068 |
| BEN Yawen,ZHANG Huan,ZHOU Qi,PANG Hongjiao,SONG Yifan,JING Jiaqi,QU Shen.Prediction model for drinking water treatment based on ensemble learning[J].Journal of Harbin Institute of Technology,2026,58(6):15.DOI:10.11918/202510068 |
|
| |
|
|
| 本文已被：浏览 1031次 下载 110次 |
码上扫一扫！ |
|
|
| 基于集成学习的饮用水处理预测模型 |
|
贲雅雯1,2,张欢1,2,周琪1,2,庞宏娇3,宋怡藩1,2,荆家琪1,2,曲申1,2
|
|
(1．北京理工大学 能源与环境政策研究中心,北京 100081; 2．北京理工大学 管理学院,北京 100081; 3．环境水质学国家重点实验室(中国科学院生态环境研究中心),北京 100085)
|
|
| 摘要: |
| 为解决传统单一模型在应对复杂水质预测等现实挑战时面临的局限性,提出模型简单平均法与两种Stacking集成策略,即基于最小二乘法（Least Square,LS）的加权集成、以极端随机森林回归（Extra Trees Regressor,ETR）为元学习器的Stacking集成。实地采集了某饮用水处理厂的全流程小时级监测数据,并对原始数据集进行了严格的预处理。在此基础上,在测试集上对所有单一模型和集成模型的预测性能进行综合评估与比较。结果表明,提出的3种集成模型在所有4项水质指标的预测上,其性能均显著优于任何单一模型,预测误差大幅降低。其中,LS加权模型在平均误差上表现最优,平均绝对百分比误差（MAPE）约为1.08%,ETR加权模型在平均误差略高0.02%。此外,探究了两种Stacking模型对基学习器的权重分配,结果表明,ETR加权模型具有较高的适应性。该模型在浊度骤增等高风险事件中,通过非线性的动态权重调整,能快速响应水质的复杂变化。本研究为饮用水处理的智能化管理提供了新视角,所提出的Stacking集成模型可为水厂的平稳运行与效率优化提供可靠的数据支撑,其强大的适应性则为工艺扰动和水质异常提供了关键的风险预警,有利于后续处理的及时调整。 |
| 关键词: 饮用水处理 水质预测 集成学习 时间序列预测 药剂投加 Stacking集成学习 |
| DOI：10.11918/202510068 |
| 分类号:TU991 |
| 文献标识码:A |
| 基金项目:国家杰出青年科学基金(52425005)；国家科技重大专项(2025ZD1202203)；国家自然科学基金(52370189) |
|
| Prediction model for drinking water treatment based on ensemble learning |
|
BEN Yawen1,2,ZHANG Huan1,2,ZHOU Qi1,2,PANG Hongjiao3,SONG Yifan1,2,JING Jiaqi1,2,QU Shen1,2
|
|
(1.BIT Center for Energy and Environmental Policy Research, Beijing 100081, China; 2.School of Management, Beijing Institute of Technology, Beijing 100081, China; 3.Key Laboratory of Environmental Aquatic Chemistry (Research Center for Eco-Environmental Sciences, Chinese Academy of Sciences), Beijing 100085, China)
|
| Abstract: |
| To address the limitations of traditional single models when dealing with complex water quality prediction and other real-world challenges, this study proposed the model simple averaging method and two Stacking integration strategies, namely the weighted integration based on the Least Square (LS) method and the Stacking integration with the Extra Trees Regressor (ETR) as the meta-learner. The full-process hourly monitoring data of a certain drinking water treatment plant were collected on-site, and the original data set was subjected to strict preprocessing. On this basis, the predictive performance of all individual models and ensemble models was comprehensively evaluated and compared on the test set. Results indicate that the three proposed ensemble models consistently outperform all single models across all four water quality indicators. Notably, these models achieve a substantial reduction in prediction error. Among these, the LS-weighted model performs the best in terms of average error, with an MAPE value of approximately 1.08%, while the ETR-weighted model has an average error that is slightly higher by 0.02%. Furthermore, this study investigates the weight allocation of base learners in the two Stacking models, revealing that the ETR-weighted model demonstrates greater adaptability. Specifically, this model demonstrates the ability to respond rapidly to complex water quality variations through nonlinearly dynamic weight adjustment, particularly during high-risk events such as sudden turbidity spikes. This study provides a new perspective for the intelligent management of drinking water treatment. The proposed Stacking ensemble model can provide reliable data support for the stable operation and efficiency optimization of water treatment plants. Its strong adaptability offers crucial risk warnings for process disturbances and water quality anomalies, facilitating timely adjustments in subsequent treatment processes. |
| Key words: drinking water treatment water quality prediction ensemble learning time series forecasting chemical dosing Stacking ensemble learning |
|
|
|
|
