Scholarlink

<p>Human safety is essential in the mining industry, particularly during blasting operations, due to hazards such as rockfall, shockwaves, and hazardous chemical emissions. Existing methods for determining evacuation times rely on manual calibration or standalone optimization techniques, which often lack precision and adaptability to dynamic mining conditions. This study proposes an integrated Grey Relational Analysis (GRA) and Adaptive Neuro-Fuzzy Inference System (ANFIS) approach to optimize the performance of mechanical evacuation timers, addressing the limitations of traditional methods. The GRA-ANFIS framework enables multi-parameter optimization (pallet weight, Torque, and angular twist) while minimizing time delay errors, achieving a 0.04-minute (2.4-second) delay in evacuation timing —a significant improvement over conventional techniques. Experimental results demonstrate that the optimal configuration (pallet weight = 820&#xa0;mg, torque = 85&#xa0;N · mm, angular twist = 280°) maximizes evacuation accuracy and reliability. Compared to prior studies using standalone ANFIS or GRA, this hybrid method enhances predictive accuracy by 32% (validated via ANOVA, R² = 0.9985) and ensures robust performance under variable mining conditions. The findings highlight the potential of GRA-ANFIS as a scalable solution for improving worker safety in blasting operations.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Integrated Grey Relational Analysis and Adaptive Neuro-Fuzzy Inference-Based Approach for Mechanical Evacuation Timer Performance Analysis: Application Is Mining Worker Safety Evacuation

  • 期刊论文

  • 发表日期：

    2026年2月20日

查看全文
  • Mayuri B. Ardak,
  • Mangesh Ravindra Phate,
  • Anilkumar Sathe

摘要

Human safety is essential in the mining industry, particularly during blasting operations, due to hazards such as rockfall, shockwaves, and hazardous chemical emissions. Existing methods for determining evacuation times rely on manual calibration or standalone optimization techniques, which often lack precision and adaptability to dynamic mining conditions. This study proposes an integrated Grey Relational Analysis (GRA) and Adaptive Neuro-Fuzzy Inference System (ANFIS) approach to optimize the performance of mechanical evacuation timers, addressing the limitations of traditional methods. The GRA-ANFIS framework enables multi-parameter optimization (pallet weight, Torque, and angular twist) while minimizing time delay errors, achieving a 0.04-minute (2.4-second) delay in evacuation timing —a significant improvement over conventional techniques. Experimental results demonstrate that the optimal configuration (pallet weight = 820 mg, torque = 85 N · mm, angular twist = 280°) maximizes evacuation accuracy and reliability. Compared to prior studies using standalone ANFIS or GRA, this hybrid method enhances predictive accuracy by 32% (validated via ANOVA, R² = 0.9985) and ensures robust performance under variable mining conditions. The findings highlight the potential of GRA-ANFIS as a scalable solution for improving worker safety in blasting operations.