2023 American Control Conference (ACC)最新文献_第5页

Learning MPC for Process Dynamic Working Condition Change Tasks under Model Mismatch 模型不匹配下过程动态工况变化任务的MPC学习

2023 American Control Conference (ACC) Pub Date : 2023-05-31 DOI: 10.23919/ACC55779.2023.10155993

Guanghui Yang, Rui Wang, Zuhua Xu, Zhijiang Shao

引用次数: 0

LSR-BO: Local Search Region Constrained Bayesian Optimization for Performance Optimization of Vapor Compression Systems 蒸汽压缩系统性能优化的局部搜索域约束贝叶斯优化

2023 American Control Conference (ACC) Pub Date : 2023-05-31 DOI: 10.23919/ACC55779.2023.10155821

J. Paulson, Farshud Sorourifar, C. Laughman, A. Chakrabarty

{"title":"LSR-BO: Local Search Region Constrained Bayesian Optimization for Performance Optimization of Vapor Compression Systems","authors":"J. Paulson, Farshud Sorourifar, C. Laughman, A. Chakrabarty","doi":"10.23919/ACC55779.2023.10155821","DOIUrl":"https://doi.org/10.23919/ACC55779.2023.10155821","url":null,"abstract":"Bayesian optimization (BO) has recently been demonstrated as a powerful tool for efficient derivative-free optimization of expensive black-box functions, such as those prevalent in performance optimization of complex energy systems. Classical BO algorithms ignore the relationship between consecutive optimizer candidates, resulting in jumps in the admissible search space which can lead to fail-safe mechanisms being triggered, or undesired transient dynamics that violate operational constraints. In this paper, we propose LSR-BO, a novel global optimization methodology that enforces local search region (LSR) constraints by design, which restricts how much the optimizer candidate can be changed at every iteration. We demonstrate that naively incorporating LSR constraints into BO causes the algorithm to get stuck in local suboptimal solutions, and overcome this challenge through the development a novel exploration strategy that can gracefully navigate the trade-off between short-term \"local\", and long-term \"global\", performance improvement. Furthermore, we provide theoretical guarantees on the convergence of LSR-BO. Finally, we verify the effectiveness of our proposed LSR-BO method on an illustrative benchmark and a real-world energy minimization problem for a commercial vapor compression system.","PeriodicalId":397401,"journal":{"name":"2023 American Control Conference (ACC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124205689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

A Distributed Time-Varying Optimization Algorithm For Networked Lagrangian Agents Generating Continuous Control Torques 网络拉格朗日智能体产生连续控制转矩的分布式时变优化算法

2023 American Control Conference (ACC) Pub Date : 2023-05-31 DOI: 10.23919/ACC55779.2023.10156384

Yong Ding, H. Wang, Jie Mei, W. Ren

引用次数: 0

Differentiable Control for Adaptive Wake Steering 自适应尾流转向的可微控制

2023 American Control Conference (ACC) Pub Date : 2023-05-31 DOI: 10.23919/ACC55779.2023.10156112

C. Adcock, G. Iaccarino, J. King

{"title":"Differentiable Control for Adaptive Wake Steering","authors":"C. Adcock, G. Iaccarino, J. King","doi":"10.23919/ACC55779.2023.10156112","DOIUrl":"https://doi.org/10.23919/ACC55779.2023.10156112","url":null,"abstract":"Wake steering yaws upstream wind turbines to deflect their wakes from downstream turbines, increasing the total power produced by the wind farm. Most wake steering methods generate lookup tables offline which map a set of wind farm conditions, such as wind speed, to yaw offset angles for each turbine in a farm. These tables assume all turbines are operational and can be significantly non-optimal when one or more turbines shutdown–as they often do because of low wind speed, routine maintenance, or emergency maintenance. We present a new wake steering method that adapts to turbine status. Using a hybrid model- and learning-based method, differentiable control, we train a neural network to determine yaw offset angles from conditions including turbine status (active/inactive). Unlike the lookup table approach, differentiable control does not solve an optimization problem for each combination of turbine status in a farm; including learning in the method allows it to generalize. We present results for both standard wake steering (all turbines active) and adaptive wake steering (some turbines active). We find that differentiable control has comparable accuracy as and an order of magnitude faster offline compute time than the lookup table approach. Differentiable control enables adaptive wake steering through computationally efficient training and rapid online evaluation.","PeriodicalId":397401,"journal":{"name":"2023 American Control Conference (ACC)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114449467","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Transmissibility-based Kalman Filtering For Systems With Non-Gaussian Process Noise 非高斯过程噪声系统的透射率卡尔曼滤波

2023 American Control Conference (ACC) Pub Date : 2023-05-31 DOI: 10.23919/ACC55779.2023.10155922

A. Khalil, Almuatazbellah M. Boker, Khaled F. Aljanaideh, M. Al Janaideh

引用次数: 0

Symbolic Regression for Fault Prognosis and Remaining Useful Life Estimation* 故障预测和剩余使用寿命估计的符号回归*

2023 American Control Conference (ACC) Pub Date : 2023-05-31 DOI: 10.23919/ACC55779.2023.10156572

Efi Safikou, G. Bollas

引用次数: 0

Modeling Blade-Pitch Actuation Power Use in Wind Turbines 叶片-俯仰驱动动力在风力涡轮机中的应用

2023 American Control Conference (ACC) Pub Date : 2023-05-31 DOI: 10.23919/ACC55779.2023.10156073

Aoife Henry, M. Pusch, L. Pao

{"title":"Modeling Blade-Pitch Actuation Power Use in Wind Turbines","authors":"Aoife Henry, M. Pusch, L. Pao","doi":"10.23919/ACC55779.2023.10156073","DOIUrl":"https://doi.org/10.23919/ACC55779.2023.10156073","url":null,"abstract":"Estimating the levelized cost of energy (LCOE) of a wind turbine is useful for performing a cost-benefit analysis of potential designs. The power consumed by blade-pitch actuation is an often neglected, but nontrivial factor in LCOE estimation. The peak power consumption determines the required rating of the actuation motors and the mean power consumption impacts the net annual energy production (nAEP) of the turbine. The closed-loop blade-pitch actuation and the power consumed by its motors are complex functions of the wind field disturbance and internal turbine states. They can only be predicted well with reasonably high-fidelity and computationally expensive simulations or field tests. We present an alternative approach to modeling these signals using the Sparse Identification of Nonlinear Dynamics with Control (SINDyC) methodology. It is computationally tractable to generate these models for large datasets and to efficiently evaluate the required pitching power for a given wind field. Furthermore, the models provide intuition as to how the wind disturbance and blade pitch contribute to the signal dynamics. By generating a closed-form dynamic state equation for the blade-pitch actuation and an algebraic equation for the blade-pitch motor power, we can efficiently predict the mean and maximum power required for a given turbulent wind field and turbine design. The model is trained and validated using data generated from the open-source aero-servo-hydro-elastic wind turbine simulation tool OpenFAST.","PeriodicalId":397401,"journal":{"name":"2023 American Control Conference (ACC)","volume":"239 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123445877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Learning Based Optimal Sensor Selection for Linear Quadratic Control with Unknown Sensor Noise Covariance * 基于学习的未知传感器噪声协方差线性二次控制最优传感器选择*

2023 American Control Conference (ACC) Pub Date : 2023-05-31 DOI: 10.23919/ACC55779.2023.10156247

Jinna Li, Xinru Wang, Xiangyu Meng

引用次数: 0

Free Will Arbitrary Time Consensus-Based Cooperative Salvo Guidance over Leader-Follower Network 基于自由意志任意时间共识的领导-追随者网络合作齐射制导

2023 American Control Conference (ACC) Pub Date : 2023-05-31 DOI: 10.23919/ACC55779.2023.10156111

R. S. Pal, S. R. Kumar, Dwaipayan Mukherjee

引用次数: 0

An integrated deep learning - short term production scheduling - optimal control framework for batch processes 一个集成的深度学习-短期生产调度-批处理的最优控制框架

2023 American Control Conference (ACC) Pub Date : 2023-05-31 DOI: 10.23919/ACC55779.2023.10155963

Omar Santander, Ioannis Giannikopoulos, M. Baldea

引用次数: 0