In this study, an integrated framework of artificial neural networks (ANNs) and metaheuristic algorithms have been developed for the prediction of biochar yield using biomass characteristics and pyrolysis process conditions. Comparative analysis of six different metaheuristic algorithms was performed to optimize the ANN architecture and select important features. The results suggested that the ANN model coupled with the Rao-2 algorithm outperformed (R² ∼ 0.93, RMSE ∼ 1.74%) all other models. Furthermore, the detailed information behind the models was acquired, identifying the most influencing factors as follows: pyrolysis temperature (56%), residence time (23%), and heating rate (8%). The partial dependence plot analysis revealed how each influencing factor affected the target variable. Finally, an easy-to-use software tool for predicting biochar yield was built using the ANN-Rao-2 model. This study demonstrates huge potential that machine learning presents in predictive modelling of complex pyrolysis processes, and reduces the time-consuming and expensive experimental work for estimating the biochar yield.

The Claus process is one of the promising technologies for acid gas processing and sulfur recovery. Hydrogen sulfide primarily exists as a byproduct in the gas processing unit. It must be removed from natural gas. The Environmental Protection Agency (EPA) notices that increasing SO₂ and CO₂ in the air harms the environment. Sulfur generally has an elemental content of 0.1–6 wt % in crude oil, but the value could be higher than 14% for some crude oils and asphalts. It produces SO₂ and CO₂ gases, which damage the environment and atmosphere of the earth, called primary pollutants. When SO₂ gas is reacted with water in the atmosphere, it causes sulphur and nitric acid, called a secondary pollutant. The world countries started desulphurization in 1962 to reduce the amount of sulfur in petroleum products. In this research, the Claus process was modeled in Aspen Plus software (AspenTech, Bedford, MA, USA) and industrial data validated it. The Peng–Robinson method is used for the simulation of hydrocarbon components. The influence of oxygen gas concentration, furnace temperature, the temperature of the first catalytic reactor, and temperature of the second catalytic reactor on the Claus process were studied. The first objective of the research is process modeling and simulation of a chemical process. The second objective is optimizing the process. The optimization tool in the Aspen Plus is used to obtain the best operating parameters. The optimization results show that sulfur recovery increased to 18%. Parametric analysis is studied regarding operating parameters and design parameters for increased production of sulfur. Due to pinch analysis on the Claus process, the operating cost of the heat exchangers is reduced to 40%. The third objective is the cost analysis of the process. Before optimization, it is shown that the production of sulfur recovery increased. In addition, the recovery of sulfur from hydrogen sulfide gas also increased. After optimizing the process, it is shown that the cost of heating and cooling utilities is reduced. In addition, the size of equipment is reduced. The optimization causes 2.5% of the profit on cost analysis.