Journal of Science and Innovative Development ISSN 2181-4317

ARTIFICIAL NEURAL NETWORK-BASED MODELING OF HEAT-STABLE SALT REMOVAL FROM MDEA/DEA AMINE SOLUTIONS VIA ION-EXCHANGE TECHNOLOGY

Norqulov Jonibek Farxod o‘g‘li, Muradov Raxmatulla Sobirjonovich, Kodirov Orifjon Sharipovich September 13, 2025 DOI: https://doi.org/10.36522/ILM-FAN/8-5-2025-a421a

Abstract

<p>The degradation of amine-based solvents, such as methyldiethanolamine&nbsp;(MDEA) and diethanolamine (DEA), due to the accumulation of heat-stable salts&nbsp;(HSS), poses a significant challenge to the efficiency, safety, and sustainability&nbsp;of acid gas removal systems. Ion exchange using strong-base anion resins has&nbsp;been widely adopted as a practical method for HSS removal; however, the&nbsp;optimization and control of this process remain challenging due to its nonlinear&nbsp;and multivariable nature. In this study, a predictive model based on artificial&nbsp;neural networks was developed to estimate the residual HSS concentration and&nbsp;final solution pH following ion exchange purification. A comprehensive dataset&nbsp;<br /> representing industrially relevant variations in key process parameters-initial&nbsp;HSS concentration, amine strength, flow rate, initial pH, and temperature-was generated and used for model training in MATLAB. The ANN architecture&nbsp;consisted of a two-hidden-layer feedforward network trained using Bayesian&nbsp;regularization, enabling robust learning without overfitting. The model achieved&nbsp;high correlation coefficients of R = 0.9586 for overall prediction, R = 0.9173 for HSS&nbsp;concentration, and R = 0.9898 for pH prediction. Error histograms demonstrated&nbsp;low and symmetrically distributed residuals, confirming the model&rsquo;s accuracy&nbsp;and generalization capabilities. These results confirm that ANNs can serve as a&nbsp;reliable surrogate model for real-time monitoring and predictive control in solvent&nbsp;purification systems. The proposed methodology contributes to the development of&nbsp;intelligent process optimization in chemical engineering, enhancing operational&nbsp;efficiency and reduced environmental impact.</p>

Cite this article
Norqulov Jonibek Farxod o‘g‘li, Muradov Raxmatulla Sobirjonovich, Kodirov Orifjon Sharipovich (2025). ARTIFICIAL NEURAL NETWORK-BASED MODELING OF HEAT-STABLE SALT REMOVAL FROM MDEA/DEA AMINE SOLUTIONS VIA ION-EXCHANGE TECHNOLOGY. Journal of Science and Innovative Development. https://doi.org/https://doi.org/10.36522/ILM-FAN/8-5-2025-a421a