A hybrid machine learning–based multi-objective supervisory control strategy of a full-scale wastewater treatment for cost-effective and sustainable operation under varying influent conditions. (1st April 2021)

• Record Type: Journal Article
• Authors: Heo, SungKu; Nam, KiJeon; Tariq, Shahzeb; Lim, Juin Yau; Park, Junkyu; Yoo, ChangKyoo
• Is Part Of: Journal of cleaner production. Volume 291(2021)
• Publication Date: 2021-04-01
• Subjects: Supervisory control -- Multi-objective control -- Deep learning -- Machine learning -- Sustainable operation -- TKN/COD ratio; Factory and trade waste -- Management -- Periodicals; Manufactures -- Environmental aspects -- Periodicals; Déchets industriels -- Gestion -- Périodiques; Usines -- Aspect de l'environnement -- Périodiques; 628.5
• DOI: 10.1016/j.jclepro.2021.125853
• Languages: English
• ISSNs: 0959-6526

Abstract

Abstract: This study develops a multi-objective supervisory control (MOSC) strategy for wastewater treatment based on hybrid machine-learning algorithms that search optimal setpoints of multiple controllers under varying influent conditions. A wastewater treatment plant (WWTP) operation was modeled by Benchmark Simulation Model No. 2 (BSM2), and influent conditions were generated in consideration of a H-WWTP in South Korea. Two proportional-integral (PI) controllers for dissolved oxygen and biogas, and one cascade-PI controller for nitrate were used as local control loops. The MOSC strategy identified five influent scenarios using fuzzy c-means algorithms and nitrogen-to-carbon ratios. Then, the control performance according to influent changes was gauged employing a deep-learning-based approximation model, and optimal setpoints for the controllers were determined by a non-dominated sorting genetic algorithm. The results demonstrate that an intelligent MOSC strategy can identify optimal setpoints to improve WWTP performance and outperform a reference control across a range of possible ratios of total Kjeldahl nitrogen to chemical oxygen demand (TKN/COD) in influent disturbances. The MOSC strategy was also able to accommodate extreme influent conditions, reduce operational costs by 8%, maintain effluent quality, and produce biogas for sustainable WWTP operation. Graphical abstract: Image 1 Highlights: MOSC was developed to search the optimal setpoints under various influent conditions. FCM algorithm was utilized to cluster and identify the influent load conditions. DL predicted the control objectives from the influent conditions and setpoints. Optimal setpoints were determined by NSGA-II to meet the control objectives. It guidelines sustainable WWTP for varying TKN/COD and extreme influent conditions.