Scholarlink

<p>Discovering novel materials with desired properties is essential for driving innovation across industries. Industry 4.0 and smart manufacturing have promised transformative advances in this area through real-time data integration and automated production planning and control. However, the reliance on automation alone has often fallen short, lacking the flexibility and innovation needed for this complex process. Automation, constrained by predefined processes, is unable to adapt to real-time changes. To fully unlock the potential of smart manufacturing, we must evolve from automation to autonomous systems that go beyond rigid programming and can dynamically adjust and optimize the search for solutions in real time. Current discovery approaches are often slow, requiring numerous trials to find optimal combinations, and costly, particularly when optimizing multiple properties simultaneously. To address this challenge, this paper proposes a Bayesian multi-objective sequential decision-making (BMSDM) framework that can intelligently select experiments as manufacturing progresses, guiding us toward the discovery of optimal design faster and more efficiently. The framework leverages sequential learning through a Bayesian Optimization (BO) framework, which iteratively refines a statistical model representing the underlying manufacturing process. This statistical model, a Gaussian Process (GP), acts as a surrogate, allowing for efficient exploration and optimization without requiring numerous real-world experiments. This approach has the potential to significantly reduce the time and cost of data collection required by traditional experimental designs. To prove our hypothesis, the proposed BMSDM is compared with traditional Design of Experiments (DoE) methods and two state-of-the-art multi-objective optimization methods. Using a real manufacturing dataset, we evaluate and compare the performance of these approaches across five key evaluation metrics. Our results demonstrate that BMSDM comprehensively outperforms the competing methods in multi-objective decision-making (MODM) scenarios. Our proposed approach represents a significant leap forward in creating a futuristic intelligent autonomous platform capable of novel material discovery, moving from rigid automation to adaptive, autonomous systems.</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

From automation to autonomy in smart manufacturing: a Bayesian optimization framework for modeling multi-objective experimentation and sequential decision making

  • 期刊论文

  • 发表日期：

    2025年4月1日

查看全文
  • Avijit Saha Asru,
  • Hamed Khosravi,
  • Imtiaz Ahmed,
  • Abdullahil Azeem

摘要

Discovering novel materials with desired properties is essential for driving innovation across industries. Industry 4.0 and smart manufacturing have promised transformative advances in this area through real-time data integration and automated production planning and control. However, the reliance on automation alone has often fallen short, lacking the flexibility and innovation needed for this complex process. Automation, constrained by predefined processes, is unable to adapt to real-time changes. To fully unlock the potential of smart manufacturing, we must evolve from automation to autonomous systems that go beyond rigid programming and can dynamically adjust and optimize the search for solutions in real time. Current discovery approaches are often slow, requiring numerous trials to find optimal combinations, and costly, particularly when optimizing multiple properties simultaneously. To address this challenge, this paper proposes a Bayesian multi-objective sequential decision-making (BMSDM) framework that can intelligently select experiments as manufacturing progresses, guiding us toward the discovery of optimal design faster and more efficiently. The framework leverages sequential learning through a Bayesian Optimization (BO) framework, which iteratively refines a statistical model representing the underlying manufacturing process. This statistical model, a Gaussian Process (GP), acts as a surrogate, allowing for efficient exploration and optimization without requiring numerous real-world experiments. This approach has the potential to significantly reduce the time and cost of data collection required by traditional experimental designs. To prove our hypothesis, the proposed BMSDM is compared with traditional Design of Experiments (DoE) methods and two state-of-the-art multi-objective optimization methods. Using a real manufacturing dataset, we evaluate and compare the performance of these approaches across five key evaluation metrics. Our results demonstrate that BMSDM comprehensively outperforms the competing methods in multi-objective decision-making (MODM) scenarios. Our proposed approach represents a significant leap forward in creating a futuristic intelligent autonomous platform capable of novel material discovery, moving from rigid automation to adaptive, autonomous systems.