发动机排放建模的深度核学习方法

IF 2.4 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Changmin Yu, M. Seslija, George Brownbridge, S. Mosbach, M. Kraft, M. Parsi, Mark Davis, Vivian J. Page, A. Bhave
{"title":"发动机排放建模的深度核学习方法","authors":"Changmin Yu, M. Seslija, George Brownbridge, S. Mosbach, M. Kraft, M. Parsi, Mark Davis, Vivian J. Page, A. Bhave","doi":"10.1017/dce.2020.4","DOIUrl":null,"url":null,"abstract":"Abstract We apply deep kernel learning (DKL), which can be viewed as a combination of a Gaussian process (GP) and a deep neural network (DNN), to compression ignition engine emissions and compare its performance to a selection of other surrogate models on the same dataset. Surrogate models are a class of computationally cheaper alternatives to physics-based models. High-dimensional model representation (HDMR) is also briefly discussed and acts as a benchmark model for comparison. We apply the considered methods to a dataset, which was obtained from a compression ignition engine and includes as outputs soot and NOx emissions as functions of 14 engine operating condition variables. We combine a quasi-random global search with a conventional grid-optimization method in order to identify suitable values for several DKL hyperparameters, which include network architecture, kernel, and learning parameters. The performance of DKL, HDMR, plain GPs, and plain DNNs is compared in terms of the root mean squared error (RMSE) of the predictions as well as computational expense of training and evaluation. It is shown that DKL performs best in terms of RMSE in the predictions whilst maintaining the computational cost at a reasonable level, and DKL predictions are in good agreement with the experimental emissions data.","PeriodicalId":34169,"journal":{"name":"DataCentric Engineering","volume":null,"pages":null},"PeriodicalIF":2.4000,"publicationDate":"2020-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1017/dce.2020.4","citationCount":"12","resultStr":"{\"title\":\"Deep kernel learning approach to engine emissions modeling\",\"authors\":\"Changmin Yu, M. Seslija, George Brownbridge, S. Mosbach, M. Kraft, M. Parsi, Mark Davis, Vivian J. Page, A. Bhave\",\"doi\":\"10.1017/dce.2020.4\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract We apply deep kernel learning (DKL), which can be viewed as a combination of a Gaussian process (GP) and a deep neural network (DNN), to compression ignition engine emissions and compare its performance to a selection of other surrogate models on the same dataset. Surrogate models are a class of computationally cheaper alternatives to physics-based models. High-dimensional model representation (HDMR) is also briefly discussed and acts as a benchmark model for comparison. We apply the considered methods to a dataset, which was obtained from a compression ignition engine and includes as outputs soot and NOx emissions as functions of 14 engine operating condition variables. We combine a quasi-random global search with a conventional grid-optimization method in order to identify suitable values for several DKL hyperparameters, which include network architecture, kernel, and learning parameters. The performance of DKL, HDMR, plain GPs, and plain DNNs is compared in terms of the root mean squared error (RMSE) of the predictions as well as computational expense of training and evaluation. It is shown that DKL performs best in terms of RMSE in the predictions whilst maintaining the computational cost at a reasonable level, and DKL predictions are in good agreement with the experimental emissions data.\",\"PeriodicalId\":34169,\"journal\":{\"name\":\"DataCentric Engineering\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.4000,\"publicationDate\":\"2020-06-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://sci-hub-pdf.com/10.1017/dce.2020.4\",\"citationCount\":\"12\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"DataCentric Engineering\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1017/dce.2020.4\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"DataCentric Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1017/dce.2020.4","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 12

摘要

摘要我们将深度核学习(DKL)应用于压燃式发动机排放,并将其性能与同一数据集上的其他替代模型进行比较。深度核学习可以被视为高斯过程(GP)和深度神经网络(DNN)的组合。代孕模型是基于物理模型的一类计算成本较低的替代品。还简要讨论了高维模型表示(HDMR),并将其作为比较的基准模型。我们将所考虑的方法应用于数据集,该数据集是从压燃式发动机获得的,包括作为14个发动机工况变量函数的烟灰和NOx排放量作为输出。我们将准随机全局搜索与传统的网格优化方法相结合,以确定几个DKL超参数的合适值,这些参数包括网络架构、内核和学习参数。根据预测的均方根误差(RMSE)以及训练和评估的计算费用,比较了DKL、HDMR、纯GP和纯DNN的性能。结果表明,在预测中,DKL在RMSE方面表现最好,同时将计算成本保持在合理水平,并且DKL预测与实验排放数据非常一致。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Deep kernel learning approach to engine emissions modeling
Abstract We apply deep kernel learning (DKL), which can be viewed as a combination of a Gaussian process (GP) and a deep neural network (DNN), to compression ignition engine emissions and compare its performance to a selection of other surrogate models on the same dataset. Surrogate models are a class of computationally cheaper alternatives to physics-based models. High-dimensional model representation (HDMR) is also briefly discussed and acts as a benchmark model for comparison. We apply the considered methods to a dataset, which was obtained from a compression ignition engine and includes as outputs soot and NOx emissions as functions of 14 engine operating condition variables. We combine a quasi-random global search with a conventional grid-optimization method in order to identify suitable values for several DKL hyperparameters, which include network architecture, kernel, and learning parameters. The performance of DKL, HDMR, plain GPs, and plain DNNs is compared in terms of the root mean squared error (RMSE) of the predictions as well as computational expense of training and evaluation. It is shown that DKL performs best in terms of RMSE in the predictions whilst maintaining the computational cost at a reasonable level, and DKL predictions are in good agreement with the experimental emissions data.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
DataCentric Engineering
DataCentric Engineering Engineering-General Engineering
CiteScore
5.60
自引率
0.00%
发文量
26
审稿时长
12 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信