Scholarlink

<p>Port operations face significant safety challenges in their material handling processes, particularly in the design, installation, operation, and maintenance phases. This paper applies a fuzzy-model reference learning (FMRL) based framework to assess conveyor motor health and safety risks in ports, demonstrated through a case study. The system utilizes fuzzy inference integrated with a model reference learning strategy to effectively identify hazards related to conveyor motors and predict system failures in port environments. By analyzing sensor data from operational conveyor motors over extended periods (15.5&#xa0;h under normal conditions and 38&#xa0;h under faulty conditions), the system demonstrated superior hazard detection capabilities. Experimental results show that the FMRL approach achieved a 9.452% reduction in RMSE compared to conventional Fuzzy-PSO methods. The framework proved particularly effective at identifying potential failure modes, evaluating risk factors, and prioritizing protective measures for conveyor motors in port facilities. The application of this approach enhances predictive maintenance capabilities, enabling ports to minimize unanticipated downtime through early problem detection, thereby improving safety, increasing productivity, and reducing operational costs.</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

Fuzzy model reference learning control for hazard identification for material handling operations and maintenance in the ports

  • 期刊论文

  • 发表日期：

    2025年12月15日

查看全文
  • Udhayakumar Palanivel,
  • Rajkumar K,
  • Richa Ahuja,
  • Revathi S

摘要

Port operations face significant safety challenges in their material handling processes, particularly in the design, installation, operation, and maintenance phases. This paper applies a fuzzy-model reference learning (FMRL) based framework to assess conveyor motor health and safety risks in ports, demonstrated through a case study. The system utilizes fuzzy inference integrated with a model reference learning strategy to effectively identify hazards related to conveyor motors and predict system failures in port environments. By analyzing sensor data from operational conveyor motors over extended periods (15.5 h under normal conditions and 38 h under faulty conditions), the system demonstrated superior hazard detection capabilities. Experimental results show that the FMRL approach achieved a 9.452% reduction in RMSE compared to conventional Fuzzy-PSO methods. The framework proved particularly effective at identifying potential failure modes, evaluating risk factors, and prioritizing protective measures for conveyor motors in port facilities. The application of this approach enhances predictive maintenance capabilities, enabling ports to minimize unanticipated downtime through early problem detection, thereby improving safety, increasing productivity, and reducing operational costs.