Scholarlink

<p>The growing use of ionizing radiation across medical and industrial fields has intensified the demand for lead-free, flexible, and sustainable radiation shielding materials. However, current development strategies remain heavily reliant on empirical trial-and-error, which is both time-consuming and resource-intensive. Here, we report a machine learning-assisted Monte Carlo simulation strategy that enables rapid and accurate optimization of metal filler compositions for efficient X-ray attenuation across a broad energy range (40–120 kV). Guided by this artificial intelligence (AI)-driven approach, we developed polyvinyl alcohol (PVA)-based gels containing uniformly dispersed Bi/W/Gd<sub>2</sub>O<sub>3</sub> nanoparticles, which form within 1 min at −20°C using a PVA-DMSO/H<sub>2</sub>O co-solvent system. The optimized gel with 50 wt% metal loading exhibits exceptional mechanical strength (1.76 MPa), toughness (6.3 MJ m<sup>−3</sup>), and elongation (600%), together with &gt;98% X-ray shielding efficiency at 5 mm thickness, outperforming lead composites at 120 kV. The physically cross-linked network endows the material with recyclability and anti-freezing capability, retaining flexibility at −50°C. This study establishes an intelligent, data-driven paradigm for designing high-performance radiation-shielding materials, demonstrating how AI accelerates materials discovery and enables scalable fabrication of eco-friendly protective 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

Machine learning-assisted rapid development of high performance flexible lead-free radiation shielding gels

  • 期刊论文

  • 发表日期：

    2026年4月29日

查看全文
  • Wenjie Ma,
  • Mingxu Zheng,
  • Runchuan Wang,
  • Xuefei Wu,
  • Tianyu Wang,
  • Xinjing You,
  • Yujiao Jiang,
  • Hao Zhang,
  • Yueping Li,
  • Silei Chen,
  • Yan Yan,
  • Lihua Zhang,
  • Xiaozhuang Zhou,
  • Boyuan Fan,
  • Xiaju Cheng,
  • Jiale Han,
  • Liang Sun,
  • Shuwang Wu

摘要

The growing use of ionizing radiation across medical and industrial fields has intensified the demand for lead-free, flexible, and sustainable radiation shielding materials. However, current development strategies remain heavily reliant on empirical trial-and-error, which is both time-consuming and resource-intensive. Here, we report a machine learning-assisted Monte Carlo simulation strategy that enables rapid and accurate optimization of metal filler compositions for efficient X-ray attenuation across a broad energy range (40–120 kV). Guided by this artificial intelligence (AI)-driven approach, we developed polyvinyl alcohol (PVA)-based gels containing uniformly dispersed Bi/W/Gd2O3 nanoparticles, which form within 1 min at −20°C using a PVA-DMSO/H2O co-solvent system. The optimized gel with 50 wt% metal loading exhibits exceptional mechanical strength (1.76 MPa), toughness (6.3 MJ m−3), and elongation (600%), together with >98% X-ray shielding efficiency at 5 mm thickness, outperforming lead composites at 120 kV. The physically cross-linked network endows the material with recyclability and anti-freezing capability, retaining flexibility at −50°C. This study establishes an intelligent, data-driven paradigm for designing high-performance radiation-shielding materials, demonstrating how AI accelerates materials discovery and enables scalable fabrication of eco-friendly protective systems.