This paper presents an inverse design methodology that utilizes artificial intelligence (AI)-driven experiments to optimize the chemoenzymatic epoxidation of soyabean oil using hydrogen peroxide and lipase (Novozym 435). First, experiments are conducted using a systematic 3-level, 5-factor Box-Behnken design to explore the effect of input parameters on oxirane oxygen content (OOC (%)). Based on these experiments, various AI models are trained, with the support vector regression (SVR) model being found to be the most accurate. SVR is then used as a fitness function in particle swarm optimization, and the suggested optimal conditions, upon experimental validation, resulted in a maximum OOC of 7.19 % (∼98.5 % relative conversion of oil to epoxy). The results demonstrate the superiority of the proposed approach over existing methods. This framework offers a general intensified process optimization strategy with minimal resource utilization that can be applied to any other process.

中文翻译：

---

通过人工智能驱动的实验方法逆向设计大豆油化学酶环氧化反应


本文提出了一种逆向设计方法，利用人工智能 (AI) 驱动的实验来优化使用过氧化氢和脂肪酶 (Novozym 435) 的大豆油化学酶环氧化反应。首先，使用系统的 3 水平、5 因素 Box-Behnken 设计进行实验，以探索输入参数对环氧乙烷氧含量 (OOC (%)) 的影响。基于这些实验，训练了各种人工智能模型，其中支持向量回归（SVR）模型被发现是最准确的。然后，SVR 被用作粒子群优化中的适应度函数，并且经实验验证，建议的最佳条件导致最大 OOC 为 7.19%（油到环氧树脂的相对转化率约为 98.5%）。结果证明了所提出的方法相对于现有方法的优越性。该框架提供了一种通用的强化流程优化策略，具有最小的资源利用率，可应用于任何其他流程。