Scholarlink

<p>This study proposes a comprehensive, data-driven framework for evaluating maintenance crew performance in fertilizer manufacturing units. The framework integrates key performance indicators (KPIs), real-time monitoring, and workforce assessment to enhance operational efficiency and decision-making. Unlike prior research that focuses primarily on AI-driven predictive maintenance and equipment reliability, this study bridges the gap between machine performance and human efficiency. A mixed-methods approach is adopted, combining statistical validation, real-time condition monitoring, and workforce analytics. The study incorporates benchmarking techniques and data from IoT-enabled systems and maintenance logs. Performance evaluation is conducted through a structured scoring system that considers response time, task completion rate, cost adherence, and equipment reliability. Statistical techniques, including paired t-tests, ANOVA, and regression analysis, are used to validate the significance of improvements in maintenance efficiency. The proposed framework enables a holistic evaluation of maintenance crew performance, demonstrating measurable improvements in response time (30.5% reduction in MTTR), cost efficiency (18.4% reduction in CoM), and equipment reliability (25% increase in MTBF). Comparative analysis with approaches such as condition-based maintenance (CBM) and reliability-centered maintenance (RCM) highlights the framework’s effectiveness in balancing operational metrics with workforce accountability. The implementation also led to a 6.1% increase in Overall Equipment Effectiveness (OEE), improving from 77.6 to 83.7%. By integrating workforce assessment with data-driven maintenance practices, this framework provides actionable insights for plant managers aiming to improve reliability, reduce downtime, and optimize maintenance operations. Its modular structure and reliance on real-time monitoring support proactive planning, enhance resource utilization, and improve decision-making. The model is adaptable to sectors such as oil and gas, power generation, and automotive manufacturing. This study introduces a novel, structured evaluation mechanism that complements existing AI-based predictive maintenance tools by incorporating quantitative workforce performance assessment. By aligning human and machine dimensions within a unified evaluation model, the framework addresses key gaps in current maintenance strategies and offers a scalable solution for enhancing operational excellence and industrial reliability.</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

A data-driven framework for evaluating maintenance crews in fertilizer manufacturing units

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月6日

查看全文
  • Prasada Rao Y V S S S V

摘要

This study proposes a comprehensive, data-driven framework for evaluating maintenance crew performance in fertilizer manufacturing units. The framework integrates key performance indicators (KPIs), real-time monitoring, and workforce assessment to enhance operational efficiency and decision-making. Unlike prior research that focuses primarily on AI-driven predictive maintenance and equipment reliability, this study bridges the gap between machine performance and human efficiency. A mixed-methods approach is adopted, combining statistical validation, real-time condition monitoring, and workforce analytics. The study incorporates benchmarking techniques and data from IoT-enabled systems and maintenance logs. Performance evaluation is conducted through a structured scoring system that considers response time, task completion rate, cost adherence, and equipment reliability. Statistical techniques, including paired t-tests, ANOVA, and regression analysis, are used to validate the significance of improvements in maintenance efficiency. The proposed framework enables a holistic evaluation of maintenance crew performance, demonstrating measurable improvements in response time (30.5% reduction in MTTR), cost efficiency (18.4% reduction in CoM), and equipment reliability (25% increase in MTBF). Comparative analysis with approaches such as condition-based maintenance (CBM) and reliability-centered maintenance (RCM) highlights the framework’s effectiveness in balancing operational metrics with workforce accountability. The implementation also led to a 6.1% increase in Overall Equipment Effectiveness (OEE), improving from 77.6 to 83.7%. By integrating workforce assessment with data-driven maintenance practices, this framework provides actionable insights for plant managers aiming to improve reliability, reduce downtime, and optimize maintenance operations. Its modular structure and reliance on real-time monitoring support proactive planning, enhance resource utilization, and improve decision-making. The model is adaptable to sectors such as oil and gas, power generation, and automotive manufacturing. This study introduces a novel, structured evaluation mechanism that complements existing AI-based predictive maintenance tools by incorporating quantitative workforce performance assessment. By aligning human and machine dimensions within a unified evaluation model, the framework addresses key gaps in current maintenance strategies and offers a scalable solution for enhancing operational excellence and industrial reliability.