Scholarlink

Population burst, electronification, and rapid digital advancements is leading to exponential growth of electrical and electronics market demand resulting in electronic waste generation up to 50 million metric tons annually. Whereas e-waste collection and recycling is just one fifth of it. Rest being dumped in landfills is major cause of economic loss, environment contamination and health impact. This research introduces a novel technoeconomic framework based supervised machine learning with Countvectorizer and Multinomial Naïve Bayes classifier methodologies, productivity, efficiency parameters to evaluate the most preemptive cause of e-waste by considering weighted mean statistical ranking method of risk and cost priority numbers. Results showed “Moisture and Humidity” being the most preemptive technoeconomic cause of e-waste over “Excessive Heat” although it has the highest risk priority number. This framework also reduced e-waste analysis time from 45 days of manual effort to just 16 s. This model is customizable and scalable for any industry, extendable, adaptable, portable across other domains, and data sources.

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

Enhanced Technoeconomic Framework to Detect Preemptive Root Causes of E-waste Using AI/ML, FMEA, Countvectorizer, Multinomial Naive Bayes, Weighted Risk and Cost Priority Numbers, Productivity, and Efficiency Data

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Siba Ram Baral

摘要

Population burst, electronification, and rapid digital advancements is leading to exponential growth of electrical and electronics market demand resulting in electronic waste generation up to 50 million metric tons annually. Whereas e-waste collection and recycling is just one fifth of it. Rest being dumped in landfills is major cause of economic loss, environment contamination and health impact. This research introduces a novel technoeconomic framework based supervised machine learning with Countvectorizer and Multinomial Naïve Bayes classifier methodologies, productivity, efficiency parameters to evaluate the most preemptive cause of e-waste by considering weighted mean statistical ranking method of risk and cost priority numbers. Results showed “Moisture and Humidity” being the most preemptive technoeconomic cause of e-waste over “Excessive Heat” although it has the highest risk priority number. This framework also reduced e-waste analysis time from 45 days of manual effort to just 16 s. This model is customizable and scalable for any industry, extendable, adaptable, portable across other domains, and data sources.