当前位置: X-MOL 学术Water Res. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Attention-based Deep learning Models for Predicting Anomalous Shock of Wastewater Treatment Plants
Water Research ( IF 11.4 ) Pub Date : 2025-01-23 , DOI: 10.1016/j.watres.2025.123192
Yituo Zhang, Jihong Wang, Chaolin Li, Hengpan Duan, Wenhui Wang

Quickly grasping the time-consuming water quality indicators (WQIs) such as total nitrogen (TN) and total phosphorus (TP) of influent is an essential prerequisite for wastewater treatment plants (WWTPs) to prompt respond to sudden shock loads. Soft detection methods based on machine learning models, especially deep learning models, perform well in predicting the normal fluctuations of these time-consuming WQIs but hardly predict their sudden fluctuations mainly due to the lack of extreme fluctuation data for model training. This work employs attention mechanisms to aid deep learning models in learning patterns of anomalous water quality. The lack of interpretability has always hindered deep learning models from optimizing for different application scenarios. Therefore, the local and global sensitivity analyses are performed based on the best-performing attention-based deep learning and ordinary machine learning models, respectively, allowing for reliable feature importance quantification with a small computational burden. In the case study, three types of attention-based deep learning models were developed, including attention-based multilayer perceptron (A-MLP), Transformer composed of stacked A-MLP encoder and A-MLP decoder, and feature-temporal attention-based long short-term memory (FTA-LSTM) neural network with encoder-decoder architecture. These developed attention-based deep learning models consistently outperform the corresponding baseline models in predicting the testing set of TN, TP, and chemical oxygen demand (COD) time series and the anomalous values therein, clearly demonstrating the positive effect of the integrated attention mechanism. Among them, the prediction performance of FTA-LSTM outperforms A-MLP and Transformer (2.01-38.48% higher R2, 0-85.14% higher F1-score, 0-62.57% higher F2-score). Predicting anomalous water quality using attention-based deep learning models is a novel attempt that drives the WWTPs’ operation towards being safer, cleaner, and more cost-efficient.

中文翻译:


基于注意力的深度学习模型,用于预测污水处理厂的异常冲击



快速掌握进水总氮 (TN) 和总磷 (TP) 等耗时的水质指标 (WQI) 是污水处理厂 (WWTP) 迅速响应突发冲击负荷的重要前提。基于机器学习模型的软检测方法,尤其是深度学习模型,在预测这些耗时的 WQI 的正常波动方面表现良好,但很难预测它们的突然波动,这主要是由于缺乏用于模型训练的极端波动数据。这项工作采用注意力机制来帮助深度学习模型学习异常水质的模式。缺乏可解释性一直阻碍深度学习模型针对不同的应用场景进行优化。因此,局部和全局敏感性分析分别基于性能最好的基于注意力的深度学习和普通机器学习模型进行,从而以较小的计算负担实现可靠的特征重要性量化。在案例研究中,开发了三种类型的基于注意力的深度学习模型,包括基于注意力的多层感知器 (A-MLP)、由堆叠 A-MLP 编码器和 A-MLP 解码器组成的 Transformer 以及具有编码器-解码器架构的基于特征时间注意力的长短期记忆 (FTA-LSTM) 神经网络。这些开发的基于注意力的深度学习模型在预测 TN、TP 和化学需氧量 (COD) 时间序列的测试集及其中的异常值方面始终优于相应的基线模型,清楚地证明了集成注意力机制的积极作用。其中,FTA-LSTM 的预测性能优于 A-MLP 和 Transformer (2.01-38.R48 高 2%,F1 分数高 0-85.14%,F2 分数高 0-62.57%)。使用基于注意力的深度学习模型预测异常水质是一种新颖的尝试,它推动污水处理厂的运营朝着更安全、更清洁和更具成本效益的方向发展。
更新日期:2025-01-23
down
wechat
bug