Autonomous real-time control for membrane capacitive deionization

•LSTM-based simulation models were established to simulate the actual MCDI operation.•RL agents were examined in the actual MCDI system using a telecommunication system.•A2C was the best agent, with the largest desalination goal and longer operation.•SHAP analysis explained the contribution of input...

Full description

Saved in:
Bibliographic Details
Published in:Water research (Oxford) 2024-09, Vol.262, p.122086, Article 122086
Main Authors: Shim, Jaegyu, Lee, Suin, Yun, Nakyeong, Son, Moon, Chae, Sung Ho, Cho, Kyung Hwa
Format: Article
Language:English
Subjects:
Artificial Intelligence
Electric Conductivity
Membrane capacitive deionization
Membranes, Artificial
Models, Theoretical
Optimization
Process control
Real-time
Reinforcement learning
Water Purification - methods
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•LSTM-based simulation models were established to simulate the actual MCDI operation.•RL agents were examined in the actual MCDI system using a telecommunication system.•A2C was the best agent, with the largest desalination goal and longer operation.•SHAP analysis explained the contribution of input parameters to the model decisions. Artificial intelligence has been employed to simulate and optimize the performance of membrane capacitive deionization (MCDI), an emerging ion separation process. However, a real-time control for optimal MCDI operation has not been investigated yet. In this study, we aimed to develop a reinforcement learning (RL)-based control model and investigate the model to find an energy-efficient MCDI operation strategy. To fulfill the objectives, we established three long-short term memory models to predict applied voltage, outflow pH, and outflow electrical conductivity. Also, four RL agents were trained to minimize outflow concentration and energy consumption simultaneously. Consequently, actor-critic (A2C) and proximal policy optimization (PPO2) achieved the ion separation goal (
ISSN:0043-1354
1879-2448
1879-2448
DOI:10.1016/j.watres.2024.122086