Pub Date : 2024-10-22DOI: 10.1016/j.conengprac.2024.106136
Hafiz Mian Muhammad Adil, Hassan Abbas Khan
On-board chargers within electric vehicles (EVs) must efficiently manage grid-to-vehicle (G2V), vehicle-to-grid (V2G), and vehicle-to-vehicle (V2V) modes for sustainable EV operation. This paper introduces a modified hybrid nonlinear control approach that utilizes the whale optimization algorithm-tuned supertwisted synergetic (WOA-ST-syn) technique for a multipurpose on-board charger (MP-OBC). The whale optimization algorithm(WOA) adjusts the parameters of supertwisted synergetic controller using the integral time absolute error, reducing the need for exhaustive trial-and-error adjustments. The controller employs the state space model of a two-stage on-board electric vehicle charging system, ensuring stability through the Lyapunov stability criterion. Simulations in MATLAB/Simulink evaluate the performance of the proposed controller across various operational modes, testing robustness against varying load currents and mode-switching conditions. Results indicate significant improvements over state-of-the-art nonlinear controllers, with minimal chattering, shortest rise time (0.0007 s for AC-DC, 1.5520 s for DC-DC), fastest settling time (0.0447 s for AC-DC, 2.0550 s for DC-DC), and minimal steady-state error (0.0010% for AC-DC, 0.0004% for DC-DC). Controller Hardware-in-the-Loop (C-HIL) experiments were also performed to confirm the real-time applicability of the controller.
{"title":"WOA-tuned supertwisted synergetic control of multipurpose on-board charger for G2V/V2G/V2V operational modes of electric vehicles","authors":"Hafiz Mian Muhammad Adil, Hassan Abbas Khan","doi":"10.1016/j.conengprac.2024.106136","DOIUrl":"10.1016/j.conengprac.2024.106136","url":null,"abstract":"<div><div>On-board chargers within electric vehicles (EVs) must efficiently manage grid-to-vehicle (G2V), vehicle-to-grid (V2G), and vehicle-to-vehicle (V2V) modes for sustainable EV operation. This paper introduces a modified hybrid nonlinear control approach that utilizes the whale optimization algorithm-tuned supertwisted synergetic (WOA-ST-syn) technique for a multipurpose on-board charger (MP-OBC). The whale optimization algorithm(WOA) adjusts the parameters of supertwisted synergetic controller using the integral time absolute error, reducing the need for exhaustive trial-and-error adjustments. The controller employs the state space model of a two-stage on-board electric vehicle charging system, ensuring stability through the Lyapunov stability criterion. Simulations in MATLAB/Simulink evaluate the performance of the proposed controller across various operational modes, testing robustness against varying load currents and mode-switching conditions. Results indicate significant improvements over state-of-the-art nonlinear controllers, with minimal chattering, shortest rise time (0.0007 s for AC-DC, 1.5520 s for DC-DC), fastest settling time (0.0447 s for AC-DC, 2.0550 s for DC-DC), and minimal steady-state error (0.0010% for AC-DC, 0.0004% for DC-DC). Controller Hardware-in-the-Loop (C-HIL) experiments were also performed to confirm the real-time applicability of the controller.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"154 ","pages":"Article 106136"},"PeriodicalIF":5.4,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142532934","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-21DOI: 10.1016/j.conengprac.2024.106120
Yongze Jin , Xiaohao Song , Yanxi Yang , Xinhong Hei , Nan Feng , Xubo Yang
To improve the fault diagnosis accuracy of rolling bearings under diverse working conditions, an improved domain adversarial neural network is proposed, the feature extraction module is reconstructed by multi-channel and multi-scale CNN-LSTM-ECA (MMCLE) in the proposed network. The MMCLE module consists of several key components. Firstly, the multi-channel multi-scale Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) are established to extract spatial features and temporal dependencies of the input data. Then, the Efficient Channel Attention (ECA) module is introduced to weight the effective feature channels. Finally, the domain adversarial training is employed to extract common features from both the source and target domains. By minimizing the domain offset between these domains, the faults of rolling bearing under diverse working conditions can be accurately diagnosed. The simulation results show that, based on the proposed MMCLE model, the domain offset issue can be effectively addressed, and the fault diagnosis accuracy can be improved for samples in the target domain under diverse working conditions. The accuracy and feasibility of the proposed method can be effectively verified.
{"title":"An improved multi-channel and multi-scale domain adversarial neural network for fault diagnosis of the rolling bearing","authors":"Yongze Jin , Xiaohao Song , Yanxi Yang , Xinhong Hei , Nan Feng , Xubo Yang","doi":"10.1016/j.conengprac.2024.106120","DOIUrl":"10.1016/j.conengprac.2024.106120","url":null,"abstract":"<div><div>To improve the fault diagnosis accuracy of rolling bearings under diverse working conditions, an improved domain adversarial neural network is proposed, the feature extraction module is reconstructed by multi-channel and multi-scale CNN-LSTM-ECA (MMCLE) in the proposed network. The MMCLE module consists of several key components. Firstly, the multi-channel multi-scale Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) are established to extract spatial features and temporal dependencies of the input data. Then, the Efficient Channel Attention (ECA) module is introduced to weight the effective feature channels. Finally, the domain adversarial training is employed to extract common features from both the source and target domains. By minimizing the domain offset between these domains, the faults of rolling bearing under diverse working conditions can be accurately diagnosed. The simulation results show that, based on the proposed MMCLE model, the domain offset issue can be effectively addressed, and the fault diagnosis accuracy can be improved for samples in the target domain under diverse working conditions. The accuracy and feasibility of the proposed method can be effectively verified.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"154 ","pages":"Article 106120"},"PeriodicalIF":5.4,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142532941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-19DOI: 10.1016/j.conengprac.2024.106128
Georg Janisch , Andreas Kugi , Wolfgang Kemmetmüller
Induction machines are widely used in electric vehicles due to their high reliability and low costs. Controlling these machines to meet the high-performance demands presents a significant challenge since they are often operated at high speed and within operating ranges where magnetic saturation plays a significant role. Furthermore, specific motor parameters are not accurately known or vary during operation, e.g., due to temperature changes. Therefore, there is still a demand for control strategies to meet these demands systematically. This paper proposes a novel control strategy combining a model predictive control (MPC) concept with a fast feedback controller and a nonlinear observer. The proposed MPC strategy is based on a magnetic nonlinear model and allows for a long prediction horizon. It features high torque dynamics while ensuring energy optimality in the steady state. The results also show excellent performance for high rotational speeds and the operation at the system limits, outperforming state-of-the-art control concepts.
{"title":"A high-performance model predictive torque control concept for induction machines for electric vehicle applications","authors":"Georg Janisch , Andreas Kugi , Wolfgang Kemmetmüller","doi":"10.1016/j.conengprac.2024.106128","DOIUrl":"10.1016/j.conengprac.2024.106128","url":null,"abstract":"<div><div>Induction machines are widely used in electric vehicles due to their high reliability and low costs. Controlling these machines to meet the high-performance demands presents a significant challenge since they are often operated at high speed and within operating ranges where magnetic saturation plays a significant role. Furthermore, specific motor parameters are not accurately known or vary during operation, e.g., due to temperature changes. Therefore, there is still a demand for control strategies to meet these demands systematically. This paper proposes a novel control strategy combining a model predictive control (MPC) concept with a fast feedback controller and a nonlinear observer. The proposed MPC strategy is based on a magnetic nonlinear model and allows for a long prediction horizon. It features high torque dynamics while ensuring energy optimality in the steady state. The results also show excellent performance for high rotational speeds and the operation at the system limits, outperforming state-of-the-art control concepts.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"153 ","pages":"Article 106128"},"PeriodicalIF":5.4,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142534103","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Representation learning approaches have achieved great success in fault diagnosis of large-scale mechanical data, among which the popular auto-encoder method has developed a series of effective variants. In the existing variants, the encoder network is re-employed to encode feature representations of the data, while the decoder network is directly discarded after training, leading to a regrettable waste of computational resources. Instead of proposing advanced variants of the auto-encoder, this paper explicitly penalizes the decoder network with group lasso, thereby transforming waste into treasure. Specifically, the group lasso constrains the column vectors of the decoder network’s weight matrix at the group level, making them reusable for feature selection. Moreover, a smooth function is utilized to approximate the group lasso to prevent numerical oscillations when computing the gradients. The simulated data and experimental gear data are sequentially used to verify the effectiveness of the smooth group lasso through investigations on two representative auto-encoder variants. The results show that the decoder network penalized by smooth group lasso can be re-utilized to guide selection of a subset of key features for training a classifier, exhibiting an extraordinary feature selection capability.
{"title":"A reusable decoder network penalized by smooth group lasso and its applications to large-scale fault diagnosis of machinery","authors":"Zhiqiang Zhang, Hongji He, Shuiqing Xu, Lisheng Yin, Xueping Dong","doi":"10.1016/j.conengprac.2024.106127","DOIUrl":"10.1016/j.conengprac.2024.106127","url":null,"abstract":"<div><div>Representation learning approaches have achieved great success in fault diagnosis of large-scale mechanical data, among which the popular auto-encoder method has developed a series of effective variants. In the existing variants, the encoder network is re-employed to encode feature representations of the data, while the decoder network is directly discarded after training, leading to a regrettable waste of computational resources. Instead of proposing advanced variants of the auto-encoder, this paper explicitly penalizes the decoder network with group lasso, thereby transforming waste into treasure. Specifically, the group lasso constrains the column vectors of the decoder network’s weight matrix at the group level, making them reusable for feature selection. Moreover, a smooth function is utilized to approximate the group lasso to prevent numerical oscillations when computing the gradients. The simulated data and experimental gear data are sequentially used to verify the effectiveness of the smooth group lasso through investigations on two representative auto-encoder variants. The results show that the decoder network penalized by smooth group lasso can be re-utilized to guide selection of a subset of key features for training a classifier, exhibiting an extraordinary feature selection capability.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"153 ","pages":"Article 106127"},"PeriodicalIF":5.4,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142446180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-16DOI: 10.1016/j.conengprac.2024.106105
Liang Han , Yue Wang , Ziwei Yan , Xiaoduo Li , Zhang Ren
This study investigates time-varying formation control with communication constraint for general discrete-time multi-agent systems (MASs), which aims to control a swarm of agents to maintain a desired formation while avoiding obstacles in the scenario with spatial constraint. The event-triggered mechanism is introduced to effectively reduce the system communication frequency and an artificial potential field function is incorporated into the proposed controller to achieve obstacle avoidance in formation. The obtained results are applied to solve obstacle avoidance problems for multiple unmanned aerial vehicles (UAVs) in formation flight. Physical simulations are completed with four UAV models on a 3-D visualization simulation platform integrated by Robot Operating System (ROS) and Gazebo. Then, practical experiments are carried out with four quadrotors in a complex experimental scenario combined with the motion capture system. The physical simulation and practical experiments are implemented to verify the effectiveness of the theoretical results.
{"title":"Event-triggered formation control with obstacle avoidance for multi-agent systems applied to multi-UAV formation flying","authors":"Liang Han , Yue Wang , Ziwei Yan , Xiaoduo Li , Zhang Ren","doi":"10.1016/j.conengprac.2024.106105","DOIUrl":"10.1016/j.conengprac.2024.106105","url":null,"abstract":"<div><div>This study investigates time-varying formation control with communication constraint for general discrete-time multi-agent systems (MASs), which aims to control a swarm of agents to maintain a desired formation while avoiding obstacles in the scenario with spatial constraint. The event-triggered mechanism is introduced to effectively reduce the system communication frequency and an artificial potential field function is incorporated into the proposed controller to achieve obstacle avoidance in formation. The obtained results are applied to solve obstacle avoidance problems for multiple unmanned aerial vehicles (UAVs) in formation flight. Physical simulations are completed with four UAV models on a 3-D visualization simulation platform integrated by Robot Operating System (ROS) and Gazebo. Then, practical experiments are carried out with four quadrotors in a complex experimental scenario combined with the motion capture system. The physical simulation and practical experiments are implemented to verify the effectiveness of the theoretical results.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"153 ","pages":"Article 106105"},"PeriodicalIF":5.4,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142442895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-16DOI: 10.1016/j.conengprac.2024.106126
Wenqiang Zhao , Hongqian Wei , Qiang Ai , Nan Zheng , Chen Lin , Youtong Zhang
The path following function is a critical component of functional safety for autonomous vehicles, and following precision has garnered increased attention in practical applications. However, control performance can be compromised due to uncertainties in vehicle parameters and discrepancies between the control model and the actual vehicle to be controlled. To address this, a real-time model predictive control for path following of autonomous vehicles is proposed, incorporating an estimation of model mismatch. An adaptive extended Kalman filter is developed to estimate the potential model mismatch terms, and state deviations are compensated accordingly. Subsequently, a parameter-varying model predictive controller is formulated to achieve unbiased path-following control while maintaining robustness to parameter variations. Simulation results demonstrate a significant improvement in lateral following accuracy, with enhancements of 53.85%, 47.83%, and 42.86% compared to the nonlinear model predictive control, robust model predictive control, and learning-based control, respectively. The hardware-in-the-loop and real-road experiments further validate the excellent real-time executability, with a maximum time cost of 12.4 ms, accounting for 62% of the sampling period.
{"title":"Real-time model predictive control of path-following for autonomous vehicles towards model mismatch and uncertainty","authors":"Wenqiang Zhao , Hongqian Wei , Qiang Ai , Nan Zheng , Chen Lin , Youtong Zhang","doi":"10.1016/j.conengprac.2024.106126","DOIUrl":"10.1016/j.conengprac.2024.106126","url":null,"abstract":"<div><div>The path following function is a critical component of functional safety for autonomous vehicles, and following precision has garnered increased attention in practical applications. However, control performance can be compromised due to uncertainties in vehicle parameters and discrepancies between the control model and the actual vehicle to be controlled. To address this, a real-time model predictive control for path following of autonomous vehicles is proposed, incorporating an estimation of model mismatch. An adaptive extended Kalman filter is developed to estimate the potential model mismatch terms, and state deviations are compensated accordingly. Subsequently, a parameter-varying model predictive controller is formulated to achieve unbiased path-following control while maintaining robustness to parameter variations. Simulation results demonstrate a significant improvement in lateral following accuracy, with enhancements of 53.85%, 47.83%, and 42.86% compared to the nonlinear model predictive control, robust model predictive control, and learning-based control, respectively. The hardware-in-the-loop and real-road experiments further validate the excellent real-time executability, with a maximum time cost of 12.4 ms, accounting for 62% of the sampling period.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"153 ","pages":""},"PeriodicalIF":5.4,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142438250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-15DOI: 10.1016/j.conengprac.2024.106129
Zhenhong Liao , Ce Xu , Wen Chen , Feng Wang , Jinhua She
Grinding in mineral processing is used to control the ore at the technically feasible and economically optimum particle size to achieve mineral liberation for separation. A circulating-load ratio (CLR) during a semi-autogenous grinding (SAG) milling process is critical for controlling particle size and energy consumption. This paper presents a CLR-prediction model based on clustering SAG milling operating conditions. First, operating parameters affecting the CLR are identified by comprehensively analyzing the complex mechanism and characteristics of a typical industrial SAG milling process. Next, a method is developed to cluster operating conditions of the SAG milling process based on the power consumption and CLR of the process. The method reveals the actual physical significance of each operating condition. Then, support vector regression (SVR) is used to model the CLR in each operating condition. After that, a distance-based model integration strategy is designed to determine the weights of each SVR model to predict the CLR. Finally, integrating the SVR submodels yields a CLR prediction model. Actual run data demonstrated the accuracy and effectiveness of the model in predicting CLR. This method has significant practical value for improving SAG milling efficiency via its utilization in control system design.
矿物加工中的磨矿是将矿石控制在技术上可行、经济上最佳的粒度，以实现矿物分离。半自磨机（SAG）研磨过程中的循环负荷率（CLR）对于控制粒度和能耗至关重要。本文提出了一种基于 SAG 研磨操作条件聚类的 CLR 预测模型。首先，通过全面分析典型工业 SAG 研磨过程的复杂机理和特征，确定了影响 CLR 的操作参数。然后，根据 SAG 磨工艺的功耗和 CLR，开发了一种对 SAG 磨工艺操作条件进行聚类的方法。该方法揭示了每个运行条件的实际物理意义。然后，使用支持向量回归（SVR）对每种操作条件下的 CLR 进行建模。然后，设计一种基于距离的模型集成策略，以确定每个 SVR 模型的权重，从而预测 CLR。最后，对 SVR 子模型进行整合，得出 CLR 预测模型。实际运行数据证明了该模型预测 CLR 的准确性和有效性。这种方法在控制系统设计中的应用对于提高 SAG 磨矿效率具有重要的实用价值。
{"title":"Multi-model integration for predicting circulating load ratio based on clustering SAG milling operating conditions","authors":"Zhenhong Liao , Ce Xu , Wen Chen , Feng Wang , Jinhua She","doi":"10.1016/j.conengprac.2024.106129","DOIUrl":"10.1016/j.conengprac.2024.106129","url":null,"abstract":"<div><div>Grinding in mineral processing is used to control the ore at the technically feasible and economically optimum particle size to achieve mineral liberation for separation. A circulating-load ratio (CLR) during a semi-autogenous grinding (SAG) milling process is critical for controlling particle size and energy consumption. This paper presents a CLR-prediction model based on clustering SAG milling operating conditions. First, operating parameters affecting the CLR are identified by comprehensively analyzing the complex mechanism and characteristics of a typical industrial SAG milling process. Next, a method is developed to cluster operating conditions of the SAG milling process based on the power consumption and CLR of the process. The method reveals the actual physical significance of each operating condition. Then, support vector regression (SVR) is used to model the CLR in each operating condition. After that, a distance-based model integration strategy is designed to determine the weights of each SVR model to predict the CLR. Finally, integrating the SVR submodels yields a CLR prediction model. Actual run data demonstrated the accuracy and effectiveness of the model in predicting CLR. This method has significant practical value for improving SAG milling efficiency via its utilization in control system design.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"153 ","pages":"Article 106129"},"PeriodicalIF":5.4,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142438252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-15DOI: 10.1016/j.conengprac.2024.106124
Longyan Wang , Qiang Dong , Yanxia Fu , Bowen Zhang , Meng Chen , Junhang Xie , Jian Xu , Zhaohui Luo
Wind farm wake interactions are critical determinants of overall power generation efficiency. To address these challenges, coordinated yaw control of turbines has emerged as a highly effective strategy. While conventional approaches have been widely adopted, the application of contemporary machine learning techniques, specifically reinforcement learning (RL), holds great promise for optimizing wind farm control performance. Considering the scarcity of comparative analyses for yaw control approaches, this study implements and evaluates classical greedy, optimization-based, and RL policies for in-line multiple wind turbine under various wind scenario by an experimentally validated analytical wake model. The results unambiguously establish the superiority of RL over greedy control, particularly below rated wind speeds, as RL optimizes yaw trajectories to maximize total power capture. Furthermore, the RL-controlled policy operates without being hampered by iterative modeling errors, leading to a higher cumulative power generation compared to the optimized control scheme during the control process. At lower wind speeds (5 m/s), it achieves a remarkable 32.63 % improvement over the optimized strategy. As the wind speed increases, the advantages of RL control gradually diminish. In consequence, the model-free adaptation offered by RL control substantially bolsters robustness across a spectrum of changing wind scenarios, facilitating seamless transitions between wake steering and alignment in response to evolving wake physics. This analysis underscores the significant advantages of data-driven RL for wind farm yaw control when compared to traditional methods. Its adaptive nature empowers the optimization of total power production across a range of diverse operating regimes, all without the need for an explicit model representation.
{"title":"Effectiveness of cooperative yaw control based on reinforcement learning for in-line multiple wind turbines","authors":"Longyan Wang , Qiang Dong , Yanxia Fu , Bowen Zhang , Meng Chen , Junhang Xie , Jian Xu , Zhaohui Luo","doi":"10.1016/j.conengprac.2024.106124","DOIUrl":"10.1016/j.conengprac.2024.106124","url":null,"abstract":"<div><div>Wind farm wake interactions are critical determinants of overall power generation efficiency. To address these challenges, coordinated yaw control of turbines has emerged as a highly effective strategy. While conventional approaches have been widely adopted, the application of contemporary machine learning techniques, specifically reinforcement learning (RL), holds great promise for optimizing wind farm control performance. Considering the scarcity of comparative analyses for yaw control approaches, this study implements and evaluates classical greedy, optimization-based, and RL policies for in-line multiple wind turbine under various wind scenario by an experimentally validated analytical wake model. The results unambiguously establish the superiority of RL over greedy control, particularly below rated wind speeds, as RL optimizes yaw trajectories to maximize total power capture. Furthermore, the RL-controlled policy operates without being hampered by iterative modeling errors, leading to a higher cumulative power generation compared to the optimized control scheme during the control process. At lower wind speeds (5 m/s), it achieves a remarkable 32.63 % improvement over the optimized strategy. As the wind speed increases, the advantages of RL control gradually diminish. In consequence, the model-free adaptation offered by RL control substantially bolsters robustness across a spectrum of changing wind scenarios, facilitating seamless transitions between wake steering and alignment in response to evolving wake physics. This analysis underscores the significant advantages of data-driven RL for wind farm yaw control when compared to traditional methods. Its adaptive nature empowers the optimization of total power production across a range of diverse operating regimes, all without the need for an explicit model representation.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"153 ","pages":"Article 106124"},"PeriodicalIF":5.4,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142438251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-12DOI: 10.1016/j.conengprac.2024.106102
Gaohua Wu , Yiling Yang , Yuguo Cui , Guoping Li , Yanding Wei
This paper presents multivariable switching control of a piezoelectric microgripper regarding its output displacement, gripping force, and manipulated position. Unlike existing microgripper control, it simultaneously regulates force/position variables. Meanwhile, force/position interaction interferences and signal itself overshooting are suppressed. Firstly, a symmetrical microgripper with two independent gripping arms is introduced. Then, a generalized dynamic model is established by considering structural dynamics, electromechanical coupling, and force/position interaction. After that, multivariable switching control is proposed to achieve clamp-carry-release manipulation using dual-input and dual-output (DIDO) perturbation displacement and force/position controllers. Finally, various switching experiments are conducted, demonstrating that force/position interaction interferences are reduced by 83.76 % and 87.51 %, and interference-suppression time is shortened from 0.86 s and 0.70 s to 0.49 s and 0.41 s. Also, overshoots of gripping force and position are eliminated with a smaller settling time. The proposed multivariable switching control exhibits superior regulation performance, guaranteeing manipulation accuracy and stability.
{"title":"Multivariable switching control of a compliant piezoelectric microgripper with force/position interaction interferences","authors":"Gaohua Wu , Yiling Yang , Yuguo Cui , Guoping Li , Yanding Wei","doi":"10.1016/j.conengprac.2024.106102","DOIUrl":"10.1016/j.conengprac.2024.106102","url":null,"abstract":"<div><div>This paper presents multivariable switching control of a piezoelectric microgripper regarding its output displacement, gripping force, and manipulated position. Unlike existing microgripper control, it simultaneously regulates force/position variables. Meanwhile, force/position interaction interferences and signal itself overshooting are suppressed. Firstly, a symmetrical microgripper with two independent gripping arms is introduced. Then, a generalized dynamic model is established by considering structural dynamics, electromechanical coupling, and force/position interaction. After that, multivariable switching control is proposed to achieve clamp-carry-release manipulation using dual-input and dual-output (DIDO) perturbation displacement and force/position controllers. Finally, various switching experiments are conducted, demonstrating that force/position interaction interferences are reduced by 83.76 % and 87.51 %, and interference-suppression time is shortened from 0.86 s and 0.70 s to 0.49 s and 0.41 s. Also, overshoots of gripping force and position are eliminated with a smaller settling time. The proposed multivariable switching control exhibits superior regulation performance, guaranteeing manipulation accuracy and stability.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"153 ","pages":"Article 106102"},"PeriodicalIF":5.4,"publicationDate":"2024-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142423369","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-10DOI: 10.1016/j.conengprac.2024.106112
Karl Berntorp, Marcus Greiff
This paper presents a modeling framework for joint estimation of a host vehicle state and a map of the road based on global navigation satellite system (GNSS) and camera measurements. We model the road using a spline representation based on lower-dimensional Bézier curves parametrized in generalized endpoints (GEPs) with implicit guarantees of continuous lane boundaries. We model the GEPs by a parameter vector having a Gaussian prior representing the uncertainty of the prior map, and provide a systematic way of defining this prior from generic map representations. Both GNSS and camera measurements, such as lane-mark measurements, have noise characteristics that vary in time. To adapt to the changing noise levels and hence improve positioning performance, we formulate the problem as a joint vehicle state, map parameter, and noise covariance estimation problem and present two noise-adaptive linear-regression Kalman filters (LRKFs); (i) an interacting multiple-model (IMM) LRKF and (ii) a variational-Bayes (VB) LRKF. We conduct a Monte-Carlo study and compare the two approaches in terms of estimation precision and computation times. Embedded implementations in an automotive-grade dSpace Micro Autobox-II indicate the real-time validity of both approaches, with turn-around times of between 2–, depending on the problem size and if the map is updated. The results indicate that while the IMM-LRKF shows marginally better estimation accuracy, the VB-LRKF is at least a factor of 2 faster.
{"title":"A framework for joint vehicle localization and road mapping using onboard sensors","authors":"Karl Berntorp, Marcus Greiff","doi":"10.1016/j.conengprac.2024.106112","DOIUrl":"10.1016/j.conengprac.2024.106112","url":null,"abstract":"<div><div>This paper presents a modeling framework for joint estimation of a host vehicle state and a map of the road based on global navigation satellite system (GNSS) and camera measurements. We model the road using a spline representation based on lower-dimensional Bézier curves parametrized in <em>generalized endpoints</em> (GEPs) with implicit guarantees of continuous lane boundaries. We model the GEPs by a parameter vector having a Gaussian prior representing the uncertainty of the prior map, and provide a systematic way of defining this prior from generic map representations. Both GNSS and camera measurements, such as lane-mark measurements, have noise characteristics that vary in time. To adapt to the changing noise levels and hence improve positioning performance, we formulate the problem as a joint vehicle state, map parameter, and noise covariance estimation problem and present two noise-adaptive linear-regression Kalman filters (LRKFs); (i) an interacting multiple-model (IMM) LRKF and (ii) a variational-Bayes (VB) LRKF. We conduct a Monte-Carlo study and compare the two approaches in terms of estimation precision and computation times. Embedded implementations in an automotive-grade dSpace Micro Autobox-II indicate the real-time validity of both approaches, with turn-around times of between 2–<span><math><mrow><mn>80</mn><mspace></mspace><mi>ms</mi></mrow></math></span>, depending on the problem size and if the map is updated. The results indicate that while the IMM-LRKF shows marginally better estimation accuracy, the VB-LRKF is at least a factor of 2 faster.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"153 ","pages":"Article 106112"},"PeriodicalIF":5.4,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142423367","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号