Peter Jul-Rasmussen , Arijit Chakraborty , Venkat Venkatasubramanian , Xiaodong Liang , Jakob Kjøbsted Huusom
{"title":"用于中试规模气泡塔曝气的混合人工智能建模技术:比较研究","authors":"Peter Jul-Rasmussen , Arijit Chakraborty , Venkat Venkatasubramanian , Xiaodong Liang , Jakob Kjøbsted Huusom","doi":"10.1016/j.compchemeng.2024.108655","DOIUrl":null,"url":null,"abstract":"<div><p>With increased accessibility of process data from the production lines in chemical and biochemical production plants, the use of data-based modeling methods is gaining interest. In this work, three different data-based modeling approaches are applied for modeling aeration in a pilot scale bubble column. In all three modeling approaches the same serial hybrid-model structure is used, combining a species conservation balance based on first-principles with different data-based models for the overall volumetric mass transfer coefficient (<span><math><mrow><msub><mrow><mi>K</mi></mrow><mrow><mi>L</mi></mrow></msub><mi>a</mi></mrow></math></span>). Simple empirical correlations with parameters fit to process data provide transparent models but lack the accuracy of Artificial Neural Networks (ANNs). ANNs provide models with high accuracy within the operation regimes used for training, however, the models are prone to overfitting, and their black-box nature results in models that are difficult to interpret. As an alternative, a symbolic regression-inspired technique is used for discovering symbolic equations, resulting in interpretable models with accuracy that is comparable to that of the ANN.</p></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":null,"pages":null},"PeriodicalIF":3.9000,"publicationDate":"2024-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0098135424000735/pdfft?md5=3477d1f0e4cfdb2734621b49ea7ff3f6&pid=1-s2.0-S0098135424000735-main.pdf","citationCount":"0","resultStr":"{\"title\":\"Hybrid AI modeling techniques for pilot scale bubble column aeration: A comparative study\",\"authors\":\"Peter Jul-Rasmussen , Arijit Chakraborty , Venkat Venkatasubramanian , Xiaodong Liang , Jakob Kjøbsted Huusom\",\"doi\":\"10.1016/j.compchemeng.2024.108655\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>With increased accessibility of process data from the production lines in chemical and biochemical production plants, the use of data-based modeling methods is gaining interest. In this work, three different data-based modeling approaches are applied for modeling aeration in a pilot scale bubble column. In all three modeling approaches the same serial hybrid-model structure is used, combining a species conservation balance based on first-principles with different data-based models for the overall volumetric mass transfer coefficient (<span><math><mrow><msub><mrow><mi>K</mi></mrow><mrow><mi>L</mi></mrow></msub><mi>a</mi></mrow></math></span>). Simple empirical correlations with parameters fit to process data provide transparent models but lack the accuracy of Artificial Neural Networks (ANNs). ANNs provide models with high accuracy within the operation regimes used for training, however, the models are prone to overfitting, and their black-box nature results in models that are difficult to interpret. As an alternative, a symbolic regression-inspired technique is used for discovering symbolic equations, resulting in interpretable models with accuracy that is comparable to that of the ANN.</p></div>\",\"PeriodicalId\":286,\"journal\":{\"name\":\"Computers & Chemical Engineering\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.9000,\"publicationDate\":\"2024-03-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S0098135424000735/pdfft?md5=3477d1f0e4cfdb2734621b49ea7ff3f6&pid=1-s2.0-S0098135424000735-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computers & Chemical Engineering\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0098135424000735\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computers & Chemical Engineering","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0098135424000735","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0
摘要
随着化工和生化生产厂生产线工艺数据的可获取性不断提高,基于数据的建模方法的使用越来越受到关注。在这项工作中,我们采用了三种不同的基于数据的建模方法,对中试规模气泡塔中的曝气进行建模。这三种建模方法都采用了相同的串行混合模型结构,将基于第一原理的物种守恒平衡与不同的基于数据的总体积传质系数(KLa)模型相结合。与工艺数据参数拟合的简单经验相关性提供了透明的模型,但缺乏人工神经网络(ANN)的准确性。人工神经网络可在用于训练的运行条件下提供高精确度的模型,但模型容易过度拟合,其黑箱性质导致模型难以解释。作为一种替代方法,我们采用了一种受符号回归启发的技术来发现符号方程,从而得到可解释的模型,其准确性可与 ANN 相媲美。
Hybrid AI modeling techniques for pilot scale bubble column aeration: A comparative study
With increased accessibility of process data from the production lines in chemical and biochemical production plants, the use of data-based modeling methods is gaining interest. In this work, three different data-based modeling approaches are applied for modeling aeration in a pilot scale bubble column. In all three modeling approaches the same serial hybrid-model structure is used, combining a species conservation balance based on first-principles with different data-based models for the overall volumetric mass transfer coefficient (). Simple empirical correlations with parameters fit to process data provide transparent models but lack the accuracy of Artificial Neural Networks (ANNs). ANNs provide models with high accuracy within the operation regimes used for training, however, the models are prone to overfitting, and their black-box nature results in models that are difficult to interpret. As an alternative, a symbolic regression-inspired technique is used for discovering symbolic equations, resulting in interpretable models with accuracy that is comparable to that of the ANN.
期刊介绍:
Computers & Chemical Engineering is primarily a journal of record for new developments in the application of computing and systems technology to chemical engineering problems.