Research on Coal Dust Wettability Identification Based on GA-BP Model

Area of Science:

• Mining Engineering
• Environmental Science
• Computational Intelligence

Background:

• Coal mine dust wettability is crucial for dust control but its influencing factors are unclear.
• Existing identification processes for coal dust wettability are complex and inefficient.

Purpose of the Study:

• To develop an accurate and efficient method for identifying coal mine dust wettability.
• To address the challenges of unclear influencing factors and complicated identification processes in coal dust wettability.

Main Methods:

• A genetic algorithm-optimized back propagation neural network (GA-BP) model was developed.
• Thirteen physical and chemical properties of coal dust were used as input parameters.
• The GA-BP model's performance was compared against Extreme Learning Machine (ELM) and Particle Swarm Optimization-ELM (PSO-ELM) models.

Main Results:

• The GA-BP model achieved the highest identification accuracy for coal mine dust wettability at 96.6%.
• The accuracy ranking was GA-BP > PSO-ELM > ELM > BP.
• While GA-BP had the highest accuracy, its running time was longer than ELM and BP models.

Conclusions:

• The GA-BP model offers a superior method for coal mine dust wettability identification.
• This advancement is significant for effective coal mine dust prevention and control.
• The study contributes to occupational safety and health in mining environments.