用智能优化方法高效设计聚合物微粒，4次实验就达成目标尺寸。
Constrained composite Bayesian optimization for rational synthesis of polymeric particles
- 结合约束与复合优化，智能避开无效实验条件。
- 仅用4次迭代实现300nm和3μm两种目标粒径，媲美专家水平。
- 适合材料合成、纳米制造等需精准控制的科研团队使用。
聚合物纳米/微粒在医疗与能源领域具有关键作用，但其合成过程传统上依赖专家经验与高成本试错。本文首次提出约束性复合贝叶斯优化（CCBO），在黑箱可行性约束和数据有限条件下，高效优化目标性能。通过模拟电喷雾制造过程的合成问题，CCBO有效规避不可行条件，快速逼近预设粒径目标，优于标准贝叶斯优化流程，决策能力接近人类专家。实验室实验进一步验证了该方法对聚乳酸-乙醇酸共聚物（PLGA）颗粒的理性设计能力：在初始数据极少且未知实验约束的情况下，仅用4次迭代即成功制备出直径为300 nm和3.0 μm的颗粒。整体而言，CCBO为下一代人工智能驱动的目标导向颗粒合成提供了一种通用且全面的优化范式。
原文摘要 · Abstract (English)
Polymeric nano- and micro-scale particles have critical roles in tackling critical healthcare and energy challenges with their miniature characteristics. However, tailoring their synthesis process to meet specific design targets has traditionally depended on domain expertise and costly trial-and-errors. Recently, modeling strategies, particularly Bayesian optimization (BO), have been proposed to aid materials discovery for maximized/minimized properties. Coming from practical demands, this study for the first time integrates constrained and composite Bayesian optimization (CCBO) to perform efficient target value optimization under black-box feasibility constraints and limited data for laboratory experimentation. Using a synthetic problem that simulates electrospraying, a model nanomanufacturing process, CCBO strategically avoided infeasible conditions and efficiently optimized particle production towards predefined size targets, surpassing standard BO pipelines and providing decisions comparable to human experts. Further laboratory experiments validated CCBO capability to guide the rational synthesis of poly(lactic-co-glycolic acid) (PLGA) particles with diameters of 300 nm and 3.0 $μ$m via electrospraying. With minimal initial data and unknown experiment constraints, CCBO reached the design targets within 4 iterations. Overall, the CCBO approach presents a versatile and holistic optimization paradigm for next-generation target-driven particle synthesis empowered by artificial intelligence (AI).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。