Gasification of different biomass types: Modelling of final pyrolysis gases through a simulation study and artificial neural networks

The rapid depletion of fossil fuels and the increasing environmental problems caused by their use have significantly heightened global interest in sustainable and clean energy sources. In this context, among renewable energy alternatives, biomass stands out due to its environmental sustainability and economic advantages. The biomass gasification process is an effective thermochemical technology that converts solid biomass into synthesis gas (H₂, CO, CO₂, CH₄) under controlled atmospheric conditions. This process promotes the utilization of renewable resources in energy production and has the potential to reduce the overall carbon footprint. The present study aims to predict the yields of major gas components in the biomass gasification process and to determine the key parameters influencing these yields. Gasification processes were comprehensively modeled using simulation software. Data obtained under various temperature and oxygen-to-equivalence ratio (OER) conditions were thoroughly analyzed. The simulation results were processed using Artificial Neural Network (ANN) models, and their predictive performance was evaluated through statistical metrics such as Mean Squared Error (MSE) and the coefficient of determination (R²). Furthermore, the Analysis of Variance (ANOVA) method was applied to test the statistical significance of temperature and OER parameters on the yields of the gas components. The results demonstrated that the ANN model could predict gas yields with very high accuracy (R²>0.99). According to the ANOVA analysis, temperature and OER parameters had a statistically significant effect on H₂, CO, and CO₂ yields (p<0.05). Particularly, hydrogen yield increased markedly at higher temperatures and lower OER values, whereas CO and CH₄ yields decreased under these conditions, while CO₂ yield increased. These findings highlight the critical importance of selecting appropriate parameters for optimizing gasification performance. In conclusion, the results reveal that ANN and ANOVA are powerful and complementary tools for optimizing biomass gasification processes. These methods provide a reliable scientific basis for enhancing hydrogen production efficiency from biomass and contribute to the development of sustainable approaches in renewable energy production. This study aligns with global energy transition goals by supporting carbon neutrality and reducing dependency on fossil fuels.