Shyu Hsiang-Yang, Castro Cynthia J, Bair Robert A, Lu Qing, Yeh Daniel H
Civil & Environmental Engineering, University of South Florida, 4202 E. Fowler Avenue, Tampa, Florida 33620, United States.
ACS Environ Au. 2023 Jun 30;3(5):308-318. doi: 10.1021/acsenvironau.2c00072. eCollection 2023 Sep 20.
Developing advanced onsite wastewater treatment systems (OWTS) requires accurate and consistent water quality monitoring to evaluate treatment efficiency and ensure regulatory compliance. However, off-line parameters such as chemical oxygen demand (COD), total suspended solids (TSS), and () require sample collection and time-consuming laboratory analyses that do not provide real-time information of system performance or component failure. While real-time COD analyzers have emerged in recent years, they are not economically viable for onsite systems due to cost and chemical consumables. This study aimed to design and implement a real-time remote monitoring system for OWTS by developing several multi-input and single-output soft sensors. The soft sensor integrates data that can be obtained from well-established in-line sensors to accurately predict key water quality parameters, including COD, TSS, and concentrations. The temporal and spatial water quality data of an existing field-tested OWTS operated for almost two years ( = 56 data points) were used to evaluate the prediction performance of four machine learning algorithms. These algorithms, namely, partial least square regression (PLS), support vector regression (SVR), cubist regression (CUB), and quantile regression neural network (QRNN), were chosen as candidate algorithms for their prior application and effectiveness in wastewater treatment predictions. Water quality parameters that can be measured in-line, including turbidity, color, pH, NH, NO, and electrical conductivity, were selected as model inputs for predicting COD, TSS, and . The results revealed that the trained SVR model provided a statistically significant prediction for COD with a mean absolute percentage error (MAPE) of 14.5% and of 0.96. The CUB model provided the optimal predictive performance for TSS, with a MAPE of 24.8% and of 0.99. None of the models were able to achieve optimal prediction results for ; however, the CUB model performed the best with a MAPE of 71.4% and of 0.22. Given the large fluctuation in the concentrations of COD, TSS, and within the OWTS wastewater dataset, the proposed soft sensor models adequately predicted COD and TSS, while prediction was comparatively less accurate and requires further improvement. These results indicate that although water quality datasets for the OWTS are relatively small, machine learning-based soft sensors can provide useful predictive estimates of off-line parameters and provide real-time monitoring capabilities that can be used to make adjustments to OWTS operations.
开发先进的现场污水处理系统（OWTS）需要准确且一致的水质监测，以评估处理效率并确保符合监管要求。然而，诸如化学需氧量（COD）、总悬浮固体（TSS）等离线参数，以及（此处原文括号内容缺失）需要进行样品采集和耗时的实验室分析，无法提供系统性能或部件故障的实时信息。尽管近年来出现了实时COD分析仪，但由于成本和化学消耗品，它们对于现场系统在经济上并不可行。本研究旨在通过开发多个多输入单输出软传感器，为OWTS设计并实施一个实时远程监测系统。该软传感器整合了可从成熟的在线传感器获取的数据，以准确预测关键水质参数，包括COD、TSS以及（此处原文括号内容缺失）浓度。利用一个经过近两年现场测试的OWTS的时空水质数据（n = 56个数据点）来评估四种机器学习算法的预测性能。这些算法，即偏最小二乘回归（PLS）、支持向量回归（SVR）、Cubist回归（CUB）和分位数回归神经网络（QRNN），因其先前在废水处理预测中的应用和有效性而被选为候选算法。可在线测量的水质参数，包括浊度、颜色、pH值、NH、NO以及电导率，被选作预测COD、TSS和（此处原文括号内容缺失）的模型输入。结果表明，经过训练的SVR模型对COD提供了具有统计学意义的预测，平均绝对百分比误差（MAPE）为14.5%，相关系数（此处原文相关系数表示符号缺失）为0.96。CUB模型对TSS提供了最佳预测性能，MAPE为24.8%，相关系数为0.99。没有一个模型能够对（此处原文括号内容缺失）实现最佳预测结果；然而，CUB模型表现最佳，MAPE为71.4%，相关系数为0.22。鉴于OWTS废水数据集中COD、TSS和（此处原文括号内容缺失）浓度的大幅波动，所提出的软传感器模型对COD和TSS进行了充分预测，而（此处原文括号内容缺失）预测相对不太准确，需要进一步改进。这些结果表明，尽管OWTS的水质数据集相对较小，但基于机器学习的软传感器可以提供离线参数的有用预测估计，并提供可用于调整OWTS运行的实时监测能力。
