Advances in soft sensors for Wastewater Treatment Plants: A systematic review (original) (raw)

2021, Journal of Water Process Engineering

Software (soft) sensors have been developed by using mathematical modelling to translate easy-to-measure parameters or existing sensors into other important operating parameters. This review surveys the advancements of soft sensor development for water resource recovery facilities (WRRFs) with the intention of establishing a baseline for these soft sensor models. Although a variety of data-driven modelling approaches have been proposed, it is difficult to identify the state-of-the-art. This is because each study uses a unique WRRF dataset, which differ based on statistical attributes (e.g., range, distribution) and qualitative attributes (e.g., supporting on-line sensors, nature of the wastewater). This is a problem as certain methods may only be effective for datasets with specific attributes. Moreover, it makes direct comparison based on common performance measures inadequate and misleading. To address this, the current review summarized (1) the different supporting on-line sensors that have been used in soft sensor development; (2) the methods applied in soft sensor development as well as the specific problem addressed by these methods; and (3) model performance in relation to the source and size of the datasets.

The impact of bad sensors on the water industry and possible alternatives

J. Inf. Technol. Constr., 2008

Advanced monitoring of water quality in order to perform a real-time hazard analysis prior to Water Treatment Works (WTW) is more important nowadays, both to give warning of contamination and also to avoid downtime of the WTW. Downtimes could be a major contributor to risk. Any serious accident will cause a significant loss in customer and investor confidence. In this paper, two treatment plants (case studies) were examined. One was a groundwater WTW and the other a river WTW. The results showed that good correlations existed between the controlling parameters measured at the river WTW, but not at the Groundwater Treatment Works (GWTW), where there was a lack of good correlation between warning parameters. Results emphasised the value of backup monitoring and self-adjusting automation processes that are needed to counteract the rise in power costs. The study showed that a relationship between the different types of sensors and/or measured parameters can be deduced in order to cross-...

Data-Based Modelling of Chemical Oxygen Demand for Industrial Wastewater Treatment

Applied Sciences

The aim of wastewater treatment plants (WWTPs) is to clean wastewater before it is discharged into the environment. Real-time monitoring and control will become more essential as the regulations for effluent discharges are likely to become stricter in the future. Model-based soft sensors provide a promising solution for estimating important process variables such as chemical oxygen demand (COD) and help in predicting the performance of WWTPs. This paper explores the possibility of using interpretable model structures for monitoring the influent and predicting the effluent of paper mill WWTPs by systematically finding the best model parameters using an exhaustive algorithm. Experimentation was conducted with regression models such as multiple linear regression (MLR) and partial least squares regression (PLSR), as well as LASSO regression with a nonlinear scaling function to account for nonlinearities. Some autoregressive time series models were also built. The results showed decent m...

Dynamic soft sensors for detecting factors affecting turbidity in drinking water

Journal of Hydroinformatics, 2013

Effective monitoring of water quality is critical for water safety. In particular, online monitoring based on modeling is useful in several applications such as process assessment, hazardous event detection or common fault diagnostics in the water processes. Soft sensors have lately established themselves as a good alternative for different tasks of process control such as the acquisition of critical process variables and process monitoring. In this paper, we introduce a dynamic method for predicting turbidity in drinking water. The goals of the work were to construct a dynamic real-time data-driven model to predict the turbidity in treated water and to find the most significant variables affecting turbidity. Both linear and non-linear regression methods are used in modeling. Our results show that the static linear or non-linear model (r = 0.40 and r = 0.52, respectively) is not able to follow the changes in turbidity, whereas the dynamic method can produce a reasonable estimate for...

Loading...

Loading Preview

Sorry, preview is currently unavailable. You can download the paper by clicking the button above.