Artificial Intelligence-Based Modelling and Optimization of the Green Methanol Production Process

Abstract

Technological advancements in machine learning (ML), Artificial Intelligence (AI), and data science have brought industries to the era of the fourth industrial revolution. The application of ML in chemical engineering is in the domains of process modeling, optimization, and predictive analysis. Traditional process modeling relies heavily on first-principal methods, which, while accurate, are computationally demanding and are non-flexible for variable process conditions. Renewable methanol produced through the power-to-liquid (PtL) process has gained significant popularity due to its various applications in household items, as a raw material for manufacturing valuable chemicals, and as a fuel both in blend or pure form. In today's competitive and uncertain chemical industry market, fast and accurate models are required to predict the plant output. This work aims to develop a data-driven surrogate model for methanol production process using ML to predict energy requirements, final product purity, and methanol production process. The effect of the sampling size and sampling technique (mainly Latin-Hypercube Sampling (LHS), Monte Carlo, and SOBOL) on the performance of the surrogate model is evaluated. A comparative analysis of different ML (e.g., XG-Boost, Random Forest, Decision Tree, Support Vector Regression) and Deep learning models (e.g., Artificial Neural Networks) is conducted using metrics such as coefficient of determination (R²), mean-squared error (MSE), and mean-absolute-error (MAE). Additionally, the applications of these trained ML models are explored in optimizion of process conditions to maximize production rate, enhance product purity, and reduce energy consumption rate. The results highlight that LHS performed significantly better than SOBOL and Monte Carlo techniques, and the surrogate model developed with the ANN technique shows superior performance with R 2 values of 0.9846, 0.9743, and 0.9750 for the energy, production rate, and final product purity predictions, respectively. Optimization results using the Differential Evolution Algorithm (DEA) reveal that the production rate can be increased by 33% with competitive purity but with an expense of 18% higher energy requirement from the base conditions.

Date of Award	8 May 2024
Original language	American English
Supervisor	ALI ALMANSOORI (Supervisor)