Artificial intelligence-based modeling of capacitive deionization for process optimization and cost contribution analysis of electrode features

Abdelrahman K. A. Khalil; Mohammad Al-Shabi; Khalil Abdelrazek Khalil

doi:10.1117/12.2664473

15 June 2023 Artificial intelligence-based modeling of capacitive deionization for process optimization and cost contribution analysis of electrode features

Abdelrahman K. A. Khalil, Mohammad Al-Shabi, Khalil Abdelrazek Khalil

Author Affiliations +

Proceedings Volume 12513, Energy Harvesting and Storage: Materials, Devices, and Applications XIII; 1251309 (2023) https://doi.org/10.1117/12.2664473
Event: SPIE Defense + Commercial Sensing, 2023, Orlando, Florida, United States

Abstract

Capacitive deionization is a promising electrochemical technology employed in water treatment applications. Among the various water desalination and treatment technologies, capacitive deionization technology has many advantages and appreciably increases desalination efficiency. CDI desalinates the Water via the electrosorption of ions inside the porous structure of two oppositely charged electrodes. The electrodes are considered the core of the CDI system. The carbon flow electrode is a new design for improving salt removal efficiency (SRE). Thus, developing a numerical model to predict CDI salt removal efficiency (SRE) and understanding how electrodes jointly contribute to desalination is crucial for rational FCDI system design. This paper demonstrates the concept of using Artificial intelligence-based modeling to predict the electrosorption capacity of FCDI with reasonable accuracy based on the important flow electrode and process features. The contribution and relative importance of each feature in deionization and the cost analysis framework of FCDI are determined and validated. This study shows that artificial neural networks (ANN) have strong abilities in predicting the nonlinear behavior of the CDI system and in revealing each feature’s role of the electrode in desalination. Two hidden layers with 14 and 11 neurons in the first and second hidden layers have been used. The model has good regression of 100% for training, 99.67% for validation 99.809% for testing, and 99.908% for the overall system. The 𝑅𝑀𝑆𝐸, 𝑀𝐴𝐸, and 𝑅𝑀𝑆𝐸_{%𝐸𝑟𝑟𝑜𝑟} were significantly small.

Conference Presentation

Citation Download Citation

Abdelrahman K. A. Khalil, Mohammad Al-Shabi, and Khalil Abdelrazek Khalil "Artificial intelligence-based modeling of capacitive deionization for process optimization and cost contribution analysis of electrode features", Proc. SPIE 12513, Energy Harvesting and Storage: Materials, Devices, and Applications XIII, 1251309 (15 June 2023); https://doi.org/10.1117/12.2664473

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available