Scholarlink

This research explores new paradigms that help with the critical obstacles faced in the discovery of novel lightweight alloysLightweight alloys by integrating machine learningMachine learning models and quantum computingQuantum computing. We explore a suite of quantum-enhanced computational techniques, including the variational quantum eigensolver (VQE), quantum annealing, quantum support vector machines (QSVM), and quantum neural networks (QNN). The efficiency of this hybrid model is demonstrated with the help of targeted case studies, including the accurate prediction of phase stability in high-entropy alloys, the determination of stacking fault energies in magnesiumMagnesium-based alloys with over 90% (Theoretical) validation accuracy, and high-fidelity simulationsSimulation of corrosionCorrosion inhibitor binding on aluminium surfaces. The full-scale discovery of these models is still a future goal; these models serve as a powerful tool, solving computationally prohibitive subproblems to accelerate the materials characterizationCharacterization pipeline drastically. This work establishes a transferable and viable workflow, paving the way for the accelerated design of next-generation structural materials.

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

Quantum Computers and Hybrid Machine Learning Models for the Discovery of Lightweight Structural Alloys

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Soham Panchal,
  • Megh Raval,
  • Raj Pandya,
  • Vishvesh Badheka

摘要

This research explores new paradigms that help with the critical obstacles faced in the discovery of novel lightweight alloysLightweight alloys by integrating machine learningMachine learning models and quantum computingQuantum computing. We explore a suite of quantum-enhanced computational techniques, including the variational quantum eigensolver (VQE), quantum annealing, quantum support vector machines (QSVM), and quantum neural networks (QNN). The efficiency of this hybrid model is demonstrated with the help of targeted case studies, including the accurate prediction of phase stability in high-entropy alloys, the determination of stacking fault energies in magnesiumMagnesium-based alloys with over 90% (Theoretical) validation accuracy, and high-fidelity simulationsSimulation of corrosionCorrosion inhibitor binding on aluminium surfaces. The full-scale discovery of these models is still a future goal; these models serve as a powerful tool, solving computationally prohibitive subproblems to accelerate the materials characterizationCharacterization pipeline drastically. This work establishes a transferable and viable workflow, paving the way for the accelerated design of next-generation structural materials.