检索结果-内蒙古大学图书馆

A data-driven optimization algorithm for differential algebraic equations with numerical infeasibilities

AICHE JOURNAL 2020年第10期66卷 e16657页

作者： Beykal, Burcu Onel, Melis Onel, Onur Pistikopoulos, Efstratios N. Texas A&M Univ Artie McFerrin Dept Chem Engn College Stn TX 77843 USA Texas A&M Univ Texas A&M Energy Inst College Stn TX USA Princeton Univ Dept Chem & Biol Engn Princeton NJ 08544 USA

Support vector machines (SVMs) based optimization framework is presented for the data-driven optimization of numerically infeasible differential algebraic equations (DAEs) without the full discretization of the underlying first-principles model. By formulating the stability constraint of the numerical integration of a DAE system as a supervised classification problem, we are able to demonstrate that SVMs can accurately map the boundary of numerical infeasibility. The necessity of this data-driven approach is demonstrated on a two-dimensional motivating example, where highly accurate SVM models are trained, validated, and tested using the data collected from the numerical integration of DAEs. Furthermore, this methodology is extended and tested for a multidimensional case study from reaction engineering (i.e., thermal cracking of natural gas liquids). The data-driven optimization of this complex case study is explored through integrating the SVM models with a constrained global grey-box optimization algorithm, namely the ARGONAUT framework.

关键词： data-driven optimization differential algebraic equations dynamic optimization steam cracking support vector machines

来源：评论

学校读者我要写书评

暂无评论

Lean Modular Integrated Construction Production Phase Planning under Uncertainties: A Big data-driven optimization Approach

引用

JOURNAL OF CONSTRUCTION ENGINEERING AND MANAGEMENT 2024年第6期150卷

作者： Yang, Zhongze Lu, Weisheng Univ Hong Kong Dept Real Estate & Construct Pokfulam Hong Kong 999077 Peoples R China

Phase planning is one of the most important components of lean-based production planning that provides basic guidelines for the entire production process. In modular integrated construction (MiC) projects, the complicated and drawn-out features of the manufacturing or production process pose difficulties for informed phase planning decisions under uncertainties. However, owing to the nascent nature of MiC, traditional approaches have little prior knowledge of the uncertainties. This research aimed to address this problem by proposing a data-driven optimization method based on a set of valuable historical production data to hedge against uncertainties during production. A real-life case study was then conducted to validate this optimization approach. The planning solution, including the (1) critical production path, (2) detailed production schedules, and (3) simulated production process, balances production schedules and uncertainties to ensure feasible and robust phase planning. This optimization method can make full use of historical production data rather than approximations of the probability distributions to handle uncertainties in the phase planning process. This research provides an innovative and robust solution for MiC production managers to efficiently conduct phase planning under uncertainties. It enriches the literature on phase planning and contributes to lean MiC manufacturing. The biggest novelty of this research is to open up a window for researchers and practitioners to look into MiC production in factories, which are traditionally like a "black box" unknown to us.

关键词： Modular integrated construction (MiC) Production process optimization Production phase planning data-driven optimization Decision-making under uncertainties Lean construction

来源：评论

学校读者我要写书评

暂无评论

A data-driven optimization model for the workover rig scheduling problem: Case study in an oil company

引用

COMPUTERS & CHEMICAL ENGINEERING 2023年 170卷

作者： Santos, Iuri Martins Hamacher, Silvio Oliveira, Fabricio Pontificia Univ Catolica Rio de Janeiro Dept Ind Engn Rua Marques Sao Vicente 225 BR-22451900 Rio de Janeiro RJ Brazil Tecgraf Inst Rua Marques Sao Vicente 225 BR-22451900 Rio De Janeiro RJ Brazil Aalto Univ Dept Math & Syst Anal Otakaari 1POB 11100 Espoo 00076 Finland

After completion, oil wells often require intervention services to increase productivity, correct oil flow losses, and solve mechanical failures. These interventions, known as workovers, are made using oil rigs, an expensive and scarce resource. The workover rig scheduling problem (WRSP) comprises deciding which wells demanding workovers will be attended to, which rigs will serve them, and when the operations must be performed, minimizing the rig fleet costs and the oil production loss associated with the workover delay. This study presents a data-driven optimization methodology for the WRSP using text mining and regression models to predict the duration of the workover activities and a mixed-integer linear programming model to obtain the solutions for the model. A sensitivity analysis is performed using simulation to measure the impact of the regression error in the solution.

关键词： Oil and gas Workover rig scheduling problem data-driven optimization Simulation

来源：评论

学校读者我要写书评

暂无评论

Smart data-driven optimization of Powered Prosthetic Ankles Using Surface Electromyography

引用

SENSORS 2018年第8期18卷 2705页

作者： Atri, Roozbeh Marquez, J. Sebastian Leung, Connie Siddiquee, Masudur R. Murphy, Douglas P. Gorgey, Ashraf S. Lovegreen, William T. Fei, Ding-Yu Bai, Ou Florida Int Univ Human Cyber Phys Syst Lab Miami FL 33174 USA Hunter Holmes McGuire VA Med Ctr Dept Vet Affairs Richmond VA 23249 USA Virginia Commonwealth Univ Dept Biomed Engn Richmond VA 23220 USA

The advent of powered prosthetic ankles provided more balance and optimal energy expenditure to lower amputee gait. However, these types of systems require an extensive setup where the parameters of the ankle, such as the amount of positive power and the stiffness of the ankle, need to be setup. Currently, calibrations are performed by experts, who base the inputs on subjective observations and experience. In this study, a novel evidence-based tuning method was presented using multi-channel electromyogram data from the residual limb, and a model for muscle activity was built. Tuning using this model requires an exhaustive search over all the possible combinations of parameters, leading to computationally inefficient system. Various data-driven optimization methods were investigated and a modified Nelder-Mead algorithm using a Latin Hypercube Sampling method was introduced to tune the powered prosthetic. The results of the modified Nelder-Mead optimization were compared to the Exhaustive search, Genetic Algorithm, and conventional Nelder-Mead method, and the results showed the feasibility of using the presented method, to objectively calibrate the parameters in a time-efficient way using biological evidence.

关键词： electromyography powered prosthetic ankle parameter tuning data-driven optimization Nelder-Mead Latin Hypercube Sampling

来源：评论

学校读者我要写书评

暂无评论

Modeling the Operation of Small-Scale Integrated Energy Systems Based on data-driven Robust optimization

引用

IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING 2020年第3期15卷 442-450页

作者： Han, Dong Yang, Ce Sun, Weiqing Yan, Zheng Univ Shanghai Sci & Technol Dept Elect Engn Shanghai 200093 Peoples R China Minist Educ Key Lab Control Power Transmiss & Convers SJTU Shanghai 200240 Peoples R China

To facilitate energy system integration, it is imperative that a multienergy system produce and deliver in a coordinated way the energy in its different component forms. In particular, a small-scale integrated energy system must accommodate renewable energy resources, flexible loads, and energy coupling technologies, which creates new challenges to the interactions between the energy vectors. Hence, an energy management model for a microenergy system in grid-connected mode under uncertainties is proposed to perform the decision-making for shifting energy modes for all energy sources and end-use applications with the aim of optimally scheduling controllable energy resources in the system and minimizing the net management cost under uncertainty. To address the stochastic nature of the price of electricity, a data-driven robust optimization approach is introduced. It uses the available sample data to design the appropriate uncertainty set using statistical hypothesis tests, and a combination of conditional value-at-risk and a worst-case optimization problem is used to formulate the energy management problem under uncertainty. We explore a computationally tractable robust counterpart of the original optimization problem. The optimal energy scheduling solution obtained from the proposed approach is immune against any worst-case realizations. Numerical results demonstrate the effectiveness of the proposed approach and its performance of less conservation. (c) 2019 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

关键词： integrated energy system multienergy coupling coordinated operation data-driven optimization robust optimization

来源：评论

学校读者我要写书评

暂无评论

Surrogate-Assisted Evolutionary Framework for data-driven Dynamic optimization

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2019年第2期3卷 137-150页

作者： Luo, Wenjian Yi, Ruikang Yang, Bin Xu, Peilan Univ Sci & Technol China Sch Comp Sci & Technol Hefei 230027 Peoples R China Univ Sci & Technol China Anhui Prov Key Lab Software Engn Comp & Commun Hefei 230027 Peoples R China

Recently, dynamic optimization has received much attention from the swarm and evolutionary computation community. However, few studies have investigated data-driven evolutionary dynamic optimization, and most algorithms for evolutionary dynamic optimization are based on analytical mathematical functions. In this paper, we investigate data-driven evolutionary dynamic optimization. First, we develop a surrogate-assisted evolutionary framework for solving data-driven dynamic optimization problems (DD-DOPs). Second, we employ a benchmark based on the typical dynamic optimization problems set in order to verify the performance of the proposed framework. The experimental results demonstrate that the proposed framework is effective for solving DD-DOPs.

关键词： data-driven optimization dynamic optimization surrogate-assisted evolutionary algorithm surrogate model

来源：评论

学校读者我要写书评

暂无评论

data-driven surrogate optimization for deploying heterogeneous multi-energy storage to improve demand response performance at building cluster level

引用

APPLIED ENERGY 2024年 356卷

作者： Ren, Haoshan Gao, Dian-ce Ma, Zhenjun Zhang, Sheng Sun, Yongjun City Univ Hong Kong Dept Architecture & Civil Engn Hong Kong Peoples R China Sun Yat Sen Univ Sch Intelligent Syst Engn Guangzhou Peoples R China Univ Wollongong Sustainable Bldg Res Ctr Wollongong NS 2522 Australia Xi An Jiao Tong Univ Sch Human Settlements & Civil Engn Xian Peoples R China

Energy storage such as battery and thermal energy storage is an effective approach to shift building peak load and alleviate grid stress at a building cluster level. However, due to the heterogeneous performance of different types of storage (e.g., response speed, charge/discharge efficiency and rate, storage capacity) and highly diversified energy use patterns of individual buildings, the multi-energy storage should be properly selected and optimally designed for individual buildings to achieve effective load shifting. The optimal deployment of multi-energy storage at a cluster level is a challenging optimization problem due to the nonlinear dynamic performance of the multi-energy storage and the high dimensionality as a result of a large number of buildings. To tackle the challenges, this study proposes a data-driven surrogate optimization method that optimally deploys multi-energy storage at a cluster level to minimize the building cluster energy bill under demand response programs. The method utilizes data-driven surrogate models to accurately predict demand response performance of individual buildings with multi-energy storage. An iterative optimization with automated energy-storage-option screening is developed to optimize the multi-energy storage configurations and design parameters. For a case study including 21 buildings, by optimally deploying multi-energy storage including battery, cooling TES tank, and building-integrated TES, the method reduced the building cluster energy bill by 8%-181% as compared to baseline cases. The optimal deployment method effectively identifies the buildings with better potential to adopt demand-side management and balances the pros and cons of the energy storage options, increasing demand response incentives by 12%-31%. The proposed method can be used in practice to facilitate the deployment of energy storage and improve engagement of buildings in demand response.

关键词： Energy storage Demand response Optimal deployment Energy flexibility Building cluster data-driven optimization

来源：评论

学校读者我要写书评

暂无评论

A BAYESIAN RISK APPROACH TO data-driven STOCHASTIC optimization: FORMULATIONS AND ASYMPTOTICS

引用

SIAM JOURNAL ON optimization 2018年第2期28卷 1588-1612页

作者： Wu, Di Zhu, Helin Zhou, Enlu Georgia Inst Technol Sch Ind & Syst Engn Atlanta GA 30332 USA

A large class of stochastic programs involve optimizing an expectation taken with respect to an underlying distribution that is unknown in practice. One popular approach to addressing the distributional uncertainty, known as the distributionally robust optimization, is to hedge against the worst case over an uncertainty set of candidate distributions. However, it has been observed that inappropriate construction of the uncertainty set can sometimes result in overconservative solutions. To explore the middle ground between optimistically ignoring the distributional uncertainty and pessimistically fixating on the worst-case scenario, we propose a Bayesian risk optimization (BRO) framework for parametric underlying distributions, which is to optimize a risk functional applied to the posterior distribution of an unknown distribution parameter. Of our particular interest are four risk functionals: mean, mean-variance, value-at-risk, and conditional value-at-risk. To unravel the implication of BRO, we establish the consistency of objective functions and optimal solutions, as well as the asymptotic normality of objective functions and optimal values. More importantly, our analysis reveals a hidden interpretation: the objectives of BRO can be approximately viewed as a weighted sum of posterior mean objective and the (squared) half-width of the true objective's confidence interval.

关键词： data-driven optimization risk measures Bayesian asymptotics

来源：评论

学校读者我要写书评

暂无评论

data-driven robust optimization

引用

MATHEMATICAL PROGRAMMING 2018年第2期167卷 235-292页

作者： Bertsimas, Dimitris Gupta, Vishal Kallus, Nathan MIT Sloan Sch Management 77 Massachusetts Ave Cambridge MA 02139 USA Univ Southern Calif Marshall Sch Business Los Angeles CA 90029 USA Cornell Univ Sch Operat Res & Informat Engn New York NY 10011 USA Cornell Tech New York NY 10011 USA

The last decade witnessed an explosion in the availability of data for operations research applications. Motivated by this growing availability, we propose a novel schema for utilizing data to design uncertainty sets for robust optimization using statistical hypothesis tests. The approach is flexible and widely applicable, and robust optimization problems built from our new sets are computationally tractable, both theoretically and practically. Furthermore, optimal solutions to these problems enjoy a strong, finite-sample probabilistic guarantee whenever the constraints and objective function are concave in the uncertainty. We describe concrete procedures for choosing an appropriate set for a given application and applying our approach to multiple uncertain constraints. Computational evidence in portfolio management and queueing confirm that our data-driven sets significantly outperform traditional robust optimization techniques whenever data are available.

关键词： Robust optimization data-driven optimization Chance-constraints Hypothesis testing

来源：评论

学校读者我要写书评

暂无评论

Enhancing DNN Models for EEG/ECoG BCI With a Novel data-driven Offline optimization Method

引用

IEEE ACCESS 2023年 11卷 35888-35900页

作者： Tragoudaras, Antonios Antoniadis, Charalampos Massoud, Yehia King Abdullah Univ Sci & Technol KAUST Comp Elect & Math Sci & Engn CEMSE Div Thuwal 23955 Saudi Arabia

A better understanding of ElectroEncephaloGraphy (EEG) and ElectroCorticoGram (ECoG) signals would get us closer to comprehending brain functionality, creating new avenues for treating brain abnormalities and developing novel Brain-Computer Interface (BCI)-related applications. Deep Neural Networks (DNN)s have lately been employed with remarkable success to decode EEG/ECoG signals for BCI. However, the optimal architectural/training parameter values in these DNN architectures have yet to receive much attention. In addition, new data-driven optimization methodologies that leverage significant advancements in Machine Learning, such as the Transformer model, have recently been proposed. Because an exhaustive search on all possible architectural/training parameter values of the state-of-the-art DNN model (our baseline model) decoding the motor imagery EEG and finger tension ECoG signals comprising the BCI IV 2a and 4 datasets, respectively, would require prohibitively much time, this paper proposes an offline model-based optimization technique based on the Transformer model for the discovery of the optimal architectural/training parameter values for that model. Our findings indicate that we could pick better values for the baseline model's architectural/training parameters, enhancing the baseline model's performance by up to 14.7% in the BCI IV 2a dataset and by up to 61.0% in the BCI IV 4 dataset.

关键词： Brain modeling Biological system modeling Electroencephalography optimization Decoding Electrodes Recording ECoG EEG signals BCI CNN self-attention model deep learning data-driven optimization

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：