{"title":"基于机器学习监督多物理场模型的微波食品三维几何设计,实现最佳加热均匀性","authors":"","doi":"10.1016/j.fbp.2024.07.017","DOIUrl":null,"url":null,"abstract":"<div><p>Multiphysics models can assist in geometric design of frozen microwaveable foods, but the conventional 'parametric-sweeping' strategy is computationally intensive. This study develops an online machine learning (ML)-supervised multiphysics modeling strategy to simultaneously optimize multiple geometrical parameters (e.g., top surface width, top surface length, and the ratio of top-to-bottom dimensions) for optimal microwave heating uniformity. First, one or more paired geometric dimensional parameters and heating uniformity results obtained from multiphysics modeling are used as initial training data for the ML optimization process that integrates Gaussian Process Regression (GPR) and Bayesian optimization. Then, the multiphysics modeling procedure is supervised by an ML process to generate new paired geometry-heating uniformity results to expand the training dataset. The loop of multiphysics modeling and ML optimization is conducted to effectively identify geometry designs with good heating uniformity. Results indicate that the ML-supervised optimization strategy can efficiently identify good geometric designs with low heating uniformity by using much fewer multiphysics models than the parametric sweep approach. The ML-supervised approach also exhibits great robustness, delivering good performance even with small (as little as one model) and randomly selected initial training data. This ML-supervised approach is flexible and can be modified to meet specific needs for broad industrial implementation in the development of microwaveable food.</p></div>","PeriodicalId":12134,"journal":{"name":"Food and Bioproducts Processing","volume":null,"pages":null},"PeriodicalIF":3.5000,"publicationDate":"2024-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"3-D geometric design of microwaveable food products for optimal heating uniformity based on machine learning-supervised multiphysics models\",\"authors\":\"\",\"doi\":\"10.1016/j.fbp.2024.07.017\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Multiphysics models can assist in geometric design of frozen microwaveable foods, but the conventional 'parametric-sweeping' strategy is computationally intensive. This study develops an online machine learning (ML)-supervised multiphysics modeling strategy to simultaneously optimize multiple geometrical parameters (e.g., top surface width, top surface length, and the ratio of top-to-bottom dimensions) for optimal microwave heating uniformity. First, one or more paired geometric dimensional parameters and heating uniformity results obtained from multiphysics modeling are used as initial training data for the ML optimization process that integrates Gaussian Process Regression (GPR) and Bayesian optimization. Then, the multiphysics modeling procedure is supervised by an ML process to generate new paired geometry-heating uniformity results to expand the training dataset. The loop of multiphysics modeling and ML optimization is conducted to effectively identify geometry designs with good heating uniformity. Results indicate that the ML-supervised optimization strategy can efficiently identify good geometric designs with low heating uniformity by using much fewer multiphysics models than the parametric sweep approach. The ML-supervised approach also exhibits great robustness, delivering good performance even with small (as little as one model) and randomly selected initial training data. This ML-supervised approach is flexible and can be modified to meet specific needs for broad industrial implementation in the development of microwaveable food.</p></div>\",\"PeriodicalId\":12134,\"journal\":{\"name\":\"Food and Bioproducts Processing\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.5000,\"publicationDate\":\"2024-08-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Food and Bioproducts Processing\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0960308524001421\",\"RegionNum\":2,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"BIOTECHNOLOGY & APPLIED MICROBIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Food and Bioproducts Processing","FirstCategoryId":"97","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0960308524001421","RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"BIOTECHNOLOGY & APPLIED MICROBIOLOGY","Score":null,"Total":0}
引用次数: 0
摘要
多物理场模型有助于冷冻微波食品的几何设计,但传统的 "参数扫描 "策略需要大量计算。本研究开发了一种在线机器学习(ML)监督多物理场建模策略,可同时优化多个几何参数(如顶面宽度、顶面长度和顶底尺寸比),以获得最佳微波加热均匀性。首先,多物理场建模获得的一个或多个成对几何尺寸参数和加热均匀性结果被用作集成高斯过程回归(GPR)和贝叶斯优化的 ML 优化过程的初始训练数据。然后,多物理场建模过程在 ML 过程的监督下生成新的成对几何尺寸-加热均匀性结果,以扩展训练数据集。多物理场建模和 ML 优化的循环可有效识别具有良好加热均匀性的几何设计。结果表明,与参数扫描方法相比,多物理场建模和 ML 监督优化策略使用的多物理场模型要少得多,因此能有效识别加热均匀性低的良好几何设计。ML 监督方法还表现出很强的鲁棒性,即使在初始训练数据较小(只有一个模型)和随机选择的情况下,也能提供良好的性能。这种 ML 监督方法非常灵活,可以根据具体需要进行修改,以便在微波食品开发中广泛应用。
3-D geometric design of microwaveable food products for optimal heating uniformity based on machine learning-supervised multiphysics models
Multiphysics models can assist in geometric design of frozen microwaveable foods, but the conventional 'parametric-sweeping' strategy is computationally intensive. This study develops an online machine learning (ML)-supervised multiphysics modeling strategy to simultaneously optimize multiple geometrical parameters (e.g., top surface width, top surface length, and the ratio of top-to-bottom dimensions) for optimal microwave heating uniformity. First, one or more paired geometric dimensional parameters and heating uniformity results obtained from multiphysics modeling are used as initial training data for the ML optimization process that integrates Gaussian Process Regression (GPR) and Bayesian optimization. Then, the multiphysics modeling procedure is supervised by an ML process to generate new paired geometry-heating uniformity results to expand the training dataset. The loop of multiphysics modeling and ML optimization is conducted to effectively identify geometry designs with good heating uniformity. Results indicate that the ML-supervised optimization strategy can efficiently identify good geometric designs with low heating uniformity by using much fewer multiphysics models than the parametric sweep approach. The ML-supervised approach also exhibits great robustness, delivering good performance even with small (as little as one model) and randomly selected initial training data. This ML-supervised approach is flexible and can be modified to meet specific needs for broad industrial implementation in the development of microwaveable food.
期刊介绍:
Official Journal of the European Federation of Chemical Engineering:
Part C
FBP aims to be the principal international journal for publication of high quality, original papers in the branches of engineering and science dedicated to the safe processing of biological products. It is the only journal to exploit the synergy between biotechnology, bioprocessing and food engineering.
Papers showing how research results can be used in engineering design, and accounts of experimental or theoretical research work bringing new perspectives to established principles, highlighting unsolved problems or indicating directions for future research, are particularly welcome. Contributions that deal with new developments in equipment or processes and that can be given quantitative expression are encouraged. The journal is especially interested in papers that extend the boundaries of food and bioproducts processing.
The journal has a strong emphasis on the interface between engineering and food or bioproducts. Papers that are not likely to be published are those:
• Primarily concerned with food formulation
• That use experimental design techniques to obtain response surfaces but gain little insight from them
• That are empirical and ignore established mechanistic models, e.g., empirical drying curves
• That are primarily concerned about sensory evaluation and colour
• Concern the extraction, encapsulation and/or antioxidant activity of a specific biological material without providing insight that could be applied to a similar but different material,
• Containing only chemical analyses of biological materials.