Scholarlink

<p>The advancements in manufacturing industries led to the increasing adoption of Digital Twin (DT) and Machine Learning (ML) technologies, to increase production systems, and enable real-time decision-making process. However, challenges continue in producing precise manufacturing processes as DTs and applying them for fully autonomous decision-making. Thus, a new DT-ML framework is developed for enhancing performance of production system. The Elephant Swarm Water Search Driven Light Gradient Boosting Machine (ESWS-LightGBM) is introduced to detect the critical process parameters, allowing workflow adjustments and adaptive scheduling. This suggested model processes real-time data and produces optimal decisions to empower production efficacy. The input data is collected from Industrial Internet of Things sensors, and were preprocessed involving noise filtering, missing value imputation, and feature scaling to clean and standardize the dataset accordingly. The incorporation of DTs enables real-time virtual simulations, while ML algorithms refine continuous decision-making models. The results showed that the ESWS-LightGBM model greatly enhances the efficiency of the production system by reducing downtime, enabling proactive adjustments, improving overall equipment effectiveness, and minimizing material loss. Therefore, the research exhibits how DT technology can improve efficiency and productivity in manufacturing processes, promoting its extensive applications in the manufacturing industries.</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

Application of Combination of Digital Twin and Machine Learning in Production System Optimization

  • 期刊论文

  • 发表日期：

    2025年9月2日

查看全文
  • Jiaqiang Wang,
  • Dingzhen Zhang,
  • Rengui Ma,
  • Xiaojing Liu

摘要

The advancements in manufacturing industries led to the increasing adoption of Digital Twin (DT) and Machine Learning (ML) technologies, to increase production systems, and enable real-time decision-making process. However, challenges continue in producing precise manufacturing processes as DTs and applying them for fully autonomous decision-making. Thus, a new DT-ML framework is developed for enhancing performance of production system. The Elephant Swarm Water Search Driven Light Gradient Boosting Machine (ESWS-LightGBM) is introduced to detect the critical process parameters, allowing workflow adjustments and adaptive scheduling. This suggested model processes real-time data and produces optimal decisions to empower production efficacy. The input data is collected from Industrial Internet of Things sensors, and were preprocessed involving noise filtering, missing value imputation, and feature scaling to clean and standardize the dataset accordingly. The incorporation of DTs enables real-time virtual simulations, while ML algorithms refine continuous decision-making models. The results showed that the ESWS-LightGBM model greatly enhances the efficiency of the production system by reducing downtime, enabling proactive adjustments, improving overall equipment effectiveness, and minimizing material loss. Therefore, the research exhibits how DT technology can improve efficiency and productivity in manufacturing processes, promoting its extensive applications in the manufacturing industries.