检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Maass, Alejandro I. Manzie, Chris Shames, Iman Nakada, Hayato Department of Electrical and Electronic Engineering The University of Melbourne Australia College of Engineering & Computer Science The Australian National University Australia Advanced Unit Management System Development Division Toyota Motor Corporation Japan

This paper provides a zeroth-order optimisation framework for non-smooth and possibly non-convex cost functions with matrix parameters that are real and symmetric. We provide complexity bounds on the number of iterations required to ensure a given accuracy level for both the convex and non-convex case. The derived complexity bounds for the convex case are less conservative than available bounds in the literature since we exploit the symmetric structure of the underlying matrix space. Moreover, the non-convex complexity bounds are novel for the class of optimisation problems we consider. The utility of the framework is evident in the suite of applications that use symmetric matrices as tuning parameters. Of primary interest here is the challenge of tuning the gain matrices in model predictive controllers, as this is a challenge known to be inhibiting industrial implementation of these architectures. To demonstrate the framework we consider the problem of MIMO diesel air-path control, and consider implementing the framework iteratively "in-the-loop" to reduce tracking error on the output channels. Both simulations and experimental results are included to illustrate the effectiveness of the proposed framework over different engine drive cycles. Copyright © 2021, The Authors. All rights reserved.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Tuning of model predictive engine controllers over transient drive cycles ⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 14022-14027页

作者： Alejandro I. Maass Chris Manzie Iman Shames Robert Chin Dragan Nešić Nalika Ulapane Hayato Nakada Department of Electrical and Electronic Engineering The University of Melbourne Victoria 3010 Australia School of Computer Science The University of Birmingham United Kingdom Advanced Unit Management System Development Division Toyota Motor Corporation Japan

A framework for tuning the parameters of model predictive controllers (MPCs) based on gradient-free optimisation (GFO) is proposed. Efficient calibration of MPCs is often a difficult task given the large number of tuning parameters and their non-intuitive correlation with the output response. We propose an efficient and systematic framework for the tuning of MPC parameters that can be implemented iteratively within the closed-loop setting. The performance of the proposed GFO-based algorithm is evaluated through its application to air-path control for diesel engines over simulations and experiments. We illustrate that the tuned parameters provide satisfactory tracking of reference trajectories over engine drive cycles with only a few iterations. Thereby, we extend existing MPC tuning approaches that calibrate parameters using step responses on the fuel rate and engine speed onto tuning over a full drive cycle response.

关键词： Gradient-free optimisation model-based control controller calibration diesel engines automotive control

来源：评论

学校读者我要写书评

暂无评论

Creep behavior of carbon fiber reinforced plastic sheet anchor embedded in concrete with epoxy resin

引用

Zairyo/Journal of the Society of Materials Science, Japan 2021年第4期70卷 293-299页

作者： Yamashita, Ryo Hiroi, Yukio Arazoe, Masaki Yamamoto, Takashi Miyagawa, Toyoaki Engineering Dept. PC Division IHI Construction Service Co. Ltd Koto-ku Tokyo135-0016 Japan Research & Development Dept. IHI Infrastructure Systems Co. Ltd Minato-ku Tokyo108-0023 Japan Infrastructural Use Dept. Composite Division Nippon Steel Chemical & Material Co. Ltd. Chuo-ku Tokyo103-0027 Japan Dept. of Civil and Earth Resource Engineering Graduate School of Engineering Kyoto University Nishikyo-ku Kyoto615-8540 Japan Infra-System Management Research Unit Kyoto University Nishikyo-ku Kyoto615-8540 Japan

来源：评论

学校读者我要写书评

暂无评论

Tuning of multivariable model predictive controllers through expert bandit feedback

arXiv

引用

arXiv 2020年

作者： Ira, Alex S. Manzie, Chris Shames, Iman Chin, Robert Nešić, Dragan Nakada, Hayato Sano, Takeshi Department of Electrical and Electronic Engineering University of Melbourne Parkville Australia University of Birmingham United Kingdom Advanced Unit Management System Development Division Toyota Motor Corporation Higashi-Fuji Technical Center 1200 Mishuku Susono-city Shizuoka410-1193

For certain industrial control applications an explicit function capturing the nontrivial trade-off between competing objectives in closed loop performance is not available. In such scenarios it is common practice to use the human innate ability to implicitly learn such a relationship and manually tune the corresponding controller to achieve the desirable closed loop performance. This approach has its deficiencies because of individual variations due to experience levels and preferences in the absence of an explicit calibration metric. Moreover, as the complexity of the underlying system and/or the controller increase, in the effort to achieve better performance, so does the tuning time and the associated tuning cost. To reduce the overall tuning cost, a tuning framework is proposed herein, whereby a supervised machine learning is used to extract the human-learned cost function and an optimization algorithm that can efficiently deal with a large number of variables, is used for optimizing the extracted cost function. Given the interest in the implementation across many industrial domains and the associated high degree of freedom present in the corresponding tuning process, a Model Predictive Controller applied to air path control in a diesel engine is tuned for the purpose of demonstrating the potential of the *** Codes 93C83, 93C85, 93C95, 90C56, 90C90 Copyright © 2020, The Authors. All rights reserved.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Active Learning for Linear Parameter-Varying system Identification ⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 989-994页

作者： Robert Chin Alejandro I. Maass Nalika Ulapane Chris Manzie Iman Shames Dragan Nešić Jonathan E. Rowe Hayato Nakada Department of Electrical & Electronic Engineering The University of Melbourne Australia & School of Computer Science University of Birmingham UK Department of Electrical & Electronic Engineering The University of Melbourne Australia School of Computer Science University of Birmingham UK & The Alan Turing Institute UK Advanced Unit Management System Development Division Toyota Motor Corporation Japan

Active learning is proposed for selection of the next operating points in the design of experiments, for identifying linear parameter-varying systems. We extend existing approaches found in literature to multiple-input multiple-output systems with a multivariate scheduling parameter. Our approach is based on exploiting the probabilistic features of Gaussian process regression to quantify the overall model uncertainty across locally identified models. This results in a flexible framework which accommodates for various techniques to be applied for estimation of local linear models and their corresponding uncertainty. We perform active learning in application to the identification of a diesel engine air-path model, and demonstrate that measures of model uncertainty can be successfully reduced using the proposed framework.

关键词： Machine learning system identification Parameter estimation Uncertainty Diesel engines

来源：评论

学校读者我要写书评

暂无评论

Coupling Gas Purging with Inorganic Carbon Supply to Enhance Biohydrogen Production with Clostridium Thermocellum

SSRN

引用

SSRN 2022年

作者： Kim, Changman Wolf, Isaac Dou, Chang Magnusson, Lauren Maness, Pin-Ching Chou, Katherine J. Singer, Steven Sundstrom, Eric Advanced Biofuel and Bioproducts Process Development Unit Lawrence Berkeley National Laboratory EmeryvilleCA94608 United States Department of Biotechnology and Bioengineering Chonnam National University Gwangju61186 Korea Republic of Biosciences Center National Renewable Energy Laboratory GoldenCO80401 United States Joint BioEnergy Institute 5885 Hollis street 4th floor EmeryvilleCA94608 United States Biological System Engineering Division Lawrence Berkeley National Laboratory 1 Cyclotron Road BerkeleyCA94702 United States

Clostridium thermocellum is a desirable biocatalyst for biohydrogen production, with a native ability to simultaneously saccharify cellulose and to metabolize released cellodextrins for hydrogen production. During fermentation with C. thermocellum , partial pressures of two gases - CO 2 and H 2 - are critical drivers of overall reaction kinetics. Biohydrogen production is enhanced by maintaining a low hydrogen partial pressure, while high concentrations of dissolved CO 2 promote microbial biomass synthesis. Our study evaluates the inherent trade-offs between hydrogen stripping and inorganic carbon supply for optimized biohydrogen synthesis. We find that nitrogen sparging at low flow rates increases hydrogen production when compared with an equivalent nitrogen overlay, but that high rates of nitrogen sparging inhibit cell growth and hydrogen production. Decreasing dissolved hydrogen partial pressure via nitrogen sparging also lowers production of reduced metabolites, including lactate and ethanol. To address potential stripping of inorganic carbon from the production medium, we supplemented CO 2 to the sparging gas and co-optimized for gas flow rate and for the CO 2 fraction of the sparging gas. Total hydrogen production increased from 50 mmol∙L −1 in the base condition, when the bioreactor was sparged with 0.1 vvm of pure nitrogen, to 181.3 mmol∙L −1 when sparged with 1.3 vvm of 33% CO 2 , demonstrating that biohydrogen production is highly sensitive to both parameters. Fine sensitivity of biohydrogen production to sparging conditions highlights the critical importance of bioreactor design and operation to achieve maximum H 2 removal without compromising inorganic carbon supply to bacterial central metabolism. © 2022, The Authors. All rights reserved.

关键词： Gases

来源：评论

学校读者我要写书评

暂无评论

Cancellation and Resumption of Elective Surgeries Over Time Across a National Sample of US Hospitals During the COVID-19 Pandemic

CHEST Critical Care

引用

CHEST Critical Care 2024年第3期2卷 100080-100080页

作者： Vranas, Kelly C. Costa, Deena Kelly Davis, Billie S. Admon, Andrew J. Zhao, Bo Kahn, Jeremy M. Kerlin, Meeta Prasad Center to Improve Veteran Involvement in Care Health Services Research & Development VA Portland Health Care System Portland OR Division of Pulmonary Allergy and Critical Care Medicine Department of Medicine Oregon Health & Science University Portland OR Palliative and Advanced Illness Research Center Philadelphia PA Pulmonary Allergy and Critical Care Division Department of Medicine Perelman School of Medicine University of Pennsylvania Philadelphia PA Department of Critical Care and Clinical Research Investigation and Systems Modeling of Acute Illness (CRISMA) Center University of Pittsburgh School of Medicine Pittsburgh PA United States Section of Pulmonary Critical Care & Sleep Medicine Yale School of Medicine New Haven CT Yale School of Nursing New Haven CT Division of Pulmonary and Critical Care Medicine Department of Internal Medicine University of Michigan School of Medicine Ann Arbor MI United States Department of Epidemiology University of Michigan School of Public Health Ann Arbor MI United States VA Center for Clinical Management Research VA Ann Arbor Health Care System Ann Arbor MI United States Department of Geography University of Washington Seattle WA United States

来源：评论

学校读者我要写书评

暂无评论

Active learning for linear parameter-varying system identification

arXiv

引用

arXiv 2020年

作者： Chin, Robert Maass, Alejandro I. Ulapane, Nalika Manzie, Chris Shames, Iman Nešić, Dragan Rowe, Jonathan E. Nakada, Hayato Department of Electrical & Electronic Engineering University of Melbourne Australia & School of Computer Science University of Birmingham United Kingdom Department of Electrical & Electronic Engineering University of Melbourne Australia School of Computer Science University of Birmingham United Kingdom Alan Turing Institute United Kingdom Advanced Unit Management System Development Division Toyota Motor Corporation Japan

关键词： Diesel engines

来源：评论

学校读者我要写书评

暂无评论

EP01.21: Performance evaluation study of an artificial intelligence-based support system for fetal cardiac ultrasound screening

引用

Ultrasound in Obstetrics & Gynecology 2024年第S1期64卷 113-113页

作者： R. Komatsu M. Komatsu N. Harada R. Matsuoka A. Sakai N. Teraya R. Aoyama K. Takeda K. Takasawa H. Katayama T. Shibata K. Iwamoto A. Sekizawa R. Hamamoto Department of Obstetrics and Gynecology Showa University School of Medicine Tokyo Japan Cancer Translational Research Team RIKEN Center for Advanced Intelligence Project Tokyo Japan Division of Medical AI Research and Development National Cancer Center Research Institute Tokyo Japan Solution Transformation Unit Fujitsu Ltd. Kawasaki Japan NCC Cancer Science Graduate School of Medical and Dental Sciences Tokyo Medical and Dental University Tokyo Japan Artificial Intelligence Laboratory Fujitsu Ltd. Kawasaki Japan Research Management Division Clinical Research Support Office National Cancer Center Hospital Tokyo Japan Biostatistics Division Center for Research Administration and Support National Cancer Center Tokyo Japan

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Approach for Tuning Model Predictive Controllers

A Machine Learning Approach for Tuning Model Predictive Cont...

引用

International Conference on Control, Automation, Robotics and Vision

作者： Alex S. Ira Iman Shames Chris Manzie Robert Chin Dragan Nesic Hayato Nakada Takeshi Sano The University of Melbourne Australia Advanced Unit Management System Development Division Higashi-Fuji Technical Center Susono-city Shizuoka Japan

Many industrial domains are characterized by Multiple-Input-Multiple-Output (MIMO) systems for which an explicit relationship capturing the nontrivial trade-off between the competing objectives is not available. Human experts have the ability to implicitly learn such a relationship, which in turn enables them to tune the corresponding controller to achieve the desirable closed-loop performance. However, as the complexity of the MIMO system and/or the controller increase, so does the tuning time and the associated tuning cost. To reduce the tuning cost, a framework is proposed in which a machine learning method for approximating the human-learned cost function along with an optimization algorithm for optimizing it, and consequently tuning the controller, are employed. In this work the focus is on the tuning of Model Predictive Controllers (MPCs), given both the interest in their implementations across many industrial domains and the associated high degrees of freedom present in the corresponding tuning process. To demonstrate the proposed approach, simulation results for the tuning of an air path MPC controller in a diesel engine are presented.

关键词： Tuning Cost function Diesel engines Atmospheric modeling Manifolds Steady-state

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：