A Dynamic Health Assessment Approach for Shearer Based on Artificial Immune Algorithm

Area of Science:

• Engineering
• Computer Science
• Artificial Intelligence

Background:

• Coal shearers are critical in mining, but their dynamic health is difficult to assess accurately.
• Operating troubles and production accidents in shearers reduce efficiency and pose safety risks.

Purpose of the Study:

• To propose a novel dynamic health assessment approach for coal shearers using an artificial immune algorithm.
• To enhance coal production efficiency and reduce operational failures and accidents.

Main Methods:

• Developed a system framework for dynamic health assessment.
• Identified key indicators for assessing shearer health.
• Designed a health assessment model based on artificial immune algorithms.
• Created a flowchart for the proposed approach.

Main Results:

• Achieved a simulation accuracy of 96% using industrial production data.
• Demonstrated superior classification accuracy compared to back propagation-neural network (BP-NN) and support vector machine (SVM) methods.
• Validated the feasibility and performance through industrial application.

Conclusions:

• The artificial immune algorithm-based approach is effective for dynamic health assessment of coal shearers.
• The method can be integrated with automated control systems in fully mechanized coal faces.
• The research contributes to improved safety and efficiency in coal mining operations.