Abstract
The complicated characteristics of wastewater treatment plants (WWTPs) significantly hinder the monitoring of industrial processes, and thus much attention has been paid to process modeling and prediction. A fuzzy partial least squares-based dynamic Bayesian networks (FPLS-DBN) is proposed to improve the modeling ability in WWTPs. To adapt the nonlinear process data, fuzzy partial least squares (FPLS) is introduced by using a fuzzy system to extract nonlinear features from process data. In addition, a dynamic extension is included by embedding augmented matrices into Bayesian networks to fit the uncertainty and time-varying characteristics. Regarding the quality indices for effluent suspended solid in the WWTP, the root mean square error of the FPLS-DBN model is decreased by 28.63% and 69.47%, respectively, in comparison with that for partial least squares and Bayesian networks. The results demonstrate the superiority of FPLS-DBN in modeling performance for an actual industrial WWTP application.
Highlights
In recent years, more attention is focused on wastewater treatment processes (WWTPs) and stricter requirements for wastewater discharge standards have been prompted to ensure the accurate monitoring of key quality indices
To illustrate the performance of the fuzzy partial least squares (FPLS)-DBN, the key quality index SS is used for prediction
In this paper, a dynamic probability model based on the nonlinear method denoted FPLS-DBN has been developed for industrial process modeling, which aims to improve the prediction accuracy of the key quality indices in WWTPs
Summary
More attention is focused on wastewater treatment processes (WWTPs) and stricter requirements for wastewater discharge standards have been prompted to ensure the accurate monitoring of key quality indices. The effluent quality indices are often measured by online instruments or off-line laboratory analysis. These methods are difficult to measure the quality indices for real-time monitoring owing to continuous maintenance, insufficient accuracy, measurement delay, and aged deterioration [1], [2]. To improve the monitoring in WWTPs, it is necessary to structure an accurate process model, especially the real-time monitoring for the key process effluent indices [2]. To quickly and accurately obtain key variables, data-driven models have been widely concerned in many engineering fields, which could extract valid information from easy-tomeasure auxiliary variables to predict difficult-to-measure. May lead to overfitting and inefficiency, and it is necessary to provide auxiliary variables that have lower dimensions for modeling
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
