Data-Driven Adaptive Critic Designs for Hybrid Lifelong Learning in Wastewater Treatment Processes
- 1 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 22 (7) , 6058-6069
Abstract
Wastewater treatment yields significant societal benefits in resource recycling, economic development, and public health. Dissolved oxygen (DO) concentration during the wastewater treatment process serves as a critical indicator for assessing effluent quality. Therefore, maintaining DO within an appropriate range is essential. This study proposes a data-driven tracking controller based on an action-dependent heuristic dynamic programming (ADHDP) approach incorporating lifelong learning (LL) to achieve precise DO concentration tracking. First, the LL-ADHDP controller, acting as an auxiliary controller, is integrated with a prior-knowledge-based controller to achieve model-free tracking control. The online LL-ADHDP approach enhances the approximation accuracy of both the critic and action networks. Second, integrating the LL mechanism into these networks mitigates catastrophic forgetting and improves overall robustness. Third, the method is applied to the benchmark simulation model no. 1. Experimental results demonstrate its superior tracking performance. Finally, simulations with diverse reference trajectories confirm the good dynamic performance and effectively reduce the tracking error of the proposed LL-ADHDP method.Keywords
Funding Information
- National Natural Science Foundation of China (62473012)
- National Natural Science Foundation of China (62222301)
- Natural Science Foundation of Beijing Municipality (F251019)
- National Science and Technology Major Project (2021ZD0112302)
- National Science and Technology Major Project (2021ZD0112301)
- Outstanding Youth Project of Guangdong Basic and Applied Basic Research Foundation (2023B1515020064)
This publication has 30 references indexed in Scilit:
- Perturbation-Resilient for Temporal-Camouflaged IoT AttacksIEEE Internet of Things Journal, 2025
- Adaptive critic design with weight allocation for intelligent learning control of wastewater treatment plantsEngineering Applications of Artificial Intelligence, 2024
- Self-Organizing Fuzzy Terminal Sliding Mode Control for Wastewater Treatment ProcessesIEEE Transactions on Automation Science and Engineering, 2023
- Offline Data-Driven Adaptive Critic Design With Variational Inference for Wastewater Treatment Process ControlIEEE Transactions on Automation Science and Engineering, 2023
- Event-triggered PID control for wastewater treatment plantsJournal of Water Process Engineering, 2020
- Continual lifelong learning with neural networks: A reviewNeural Networks, 2019
- Combined $\mathcal{L}_2$ -Stable Feedback and Feedforward Aeration Control in a Wastewater Treatment PlantIEEE Transactions on Control Systems Technology, 2019
- Adaptive fuzzy neural network control of wastewater treatment process with multiobjective operationNeurocomputing, 2018
- Complete stability analysis of a heuristic approximate dynamic programming control designAutomatica, 2015
- A boundedness result for the direct heuristic dynamic programmingNeural Networks, 2012