Scholarlink

<p>The Indian auto component manufacturing sector has long struggled with inefficient decision-making and limited real-time data use. This research investigates how Industry 4.0 technologies, specifically the Internet of Things (IoT), digital twins, generative artificial intelligence, and advanced neural networks can revolutionize this sector. IoT-enabled smart sensors support real-time monitoring and predictive maintenance. Digital twins replicate physical assets virtually, aiding scenario simulation and process improvement. Generative AI facilitates defect detection, process optimization, and intelligent decision-making. A novel Bayesian Network-Stacked Encoder-Puma Optimizer (BN-SE-PO) model further improves anomaly detection, pattern recognition, and automation. Empirical results show that IoT-based systems achieve 85% efficiency, 30% downtime, 40% cost savings, and 90% quality significantly outperforming conventional approaches. This study provides a robust framework for implementing AI-driven technologies to transform productivity, reliability, and supply chain efficiency in the Indian auto component industry.</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

Productivity Enhancement in the Indian Auto Component Manufacturing Supply Chain Through IoT, Digital Twins with Generative AI, and Stacked Encoder-Enhanced Neural Networks

  • 期刊论文

  • 发表日期：

    2025年9月20日

查看全文
  • Tushar D. Bhoite,
  • Rajesh B. Buktar,
  • Parikshit N. Mahalle,
  • Mohan P. Khond,
  • Ganesh S. Pise,
  • Yogeshrao Y. More

摘要

The Indian auto component manufacturing sector has long struggled with inefficient decision-making and limited real-time data use. This research investigates how Industry 4.0 technologies, specifically the Internet of Things (IoT), digital twins, generative artificial intelligence, and advanced neural networks can revolutionize this sector. IoT-enabled smart sensors support real-time monitoring and predictive maintenance. Digital twins replicate physical assets virtually, aiding scenario simulation and process improvement. Generative AI facilitates defect detection, process optimization, and intelligent decision-making. A novel Bayesian Network-Stacked Encoder-Puma Optimizer (BN-SE-PO) model further improves anomaly detection, pattern recognition, and automation. Empirical results show that IoT-based systems achieve 85% efficiency, 30% downtime, 40% cost savings, and 90% quality significantly outperforming conventional approaches. This study provides a robust framework for implementing AI-driven technologies to transform productivity, reliability, and supply chain efficiency in the Indian auto component industry.