Research on gas emission quantity prediction model based on EDA-IGA.

Area of Science:

• Mining Engineering
• Computational Intelligence
• Environmental Science

Background:

• Accurate prediction of gas emission quantity in coal mines is critical for ensuring operational safety and preventing accidents.
• Existing prediction models may lack the necessary accuracy and efficiency for real-time mine management.
• Gas emission is a significant hazard in coal mining, impacting worker safety and economic viability.

Purpose of the Study:

• To develop and validate a novel prediction model for coal mine gas emission quantity.
• To enhance the accuracy and efficiency of gas emission prediction using a hybrid algorithm approach.
• To provide a reliable tool for guiding safe mining practices and mitigating risks.

Main Methods:

• A hybrid model integrating the Immune Genetic Algorithm (IGA) with the Estimation of Distribution Algorithm (EDA) was developed.
• Multi-thread calculation and vaccine injection were employed within the IGA framework.
• The EDA was utilized to optimize population generation and selection processes within the IGA.

Main Results:

• The developed EDA-IGA model demonstrated high prediction accuracy (94.93%) for coal mine gas emissions.
• Compared to IGA alone, the EDA-IGA model improved prediction accuracy by 9.51% and reduced iterations by 67%.
• Model predictions showed strong consistency with on-site gas emission data from a Chinese coal mine.

Conclusions:

• The EDA-IGA model offers a superior and accurate method for predicting coal mine gas emission quantities.
• This advanced prediction capability can significantly enhance mine safety protocols and reduce accident risks.
• The model serves as a valuable new tool for the mining industry, improving safety and reducing economic losses.