Control Engineering Practice最新文献_第7页

Enhanced deep reinforcement learning model with bird’s eye view design strategy for decision control in vehicle-road collaboration 基于鸟瞰图设计策略的深度强化学习模型用于车路协同决策控制

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2025-03-14 DOI: 10.1016/j.conengprac.2025.106315

Yitao Luo , Runde Zhang , Zhuyun Chen , Chong Xie , Shaowu Zheng , Shanhu Yu , Weihua Li

{"title":"Enhanced deep reinforcement learning model with bird’s eye view design strategy for decision control in vehicle-road collaboration","authors":"Yitao Luo , Runde Zhang , Zhuyun Chen , Chong Xie , Shaowu Zheng , Shanhu Yu , Weihua Li","doi":"10.1016/j.conengprac.2025.106315","DOIUrl":"10.1016/j.conengprac.2025.106315","url":null,"abstract":"<div><div>Autonomous driving in complex traffic scenarios is a vital challenge, and deep reinforcement learning (DRL) has been extensively applied to address this issue. The recent advancement of vehicle-to-everything (V2X) technology has provided abundant perceptual information for DRL agents, improving the accuracy and safety of decision control. However, existing research on green wave traffic scenes has difficulty adapting to multi-signal scenarios with single-signal countdown models, which lack complete signal state information. To address this limitation, an enhanced DRL model with bird’s eye view (BEV) design strategy is proposed for vehicle-road collaborative autonomous driving scenarios. The constructed model introduces a state prediction fusion strategy to compensate for state information. Specifically, state information is first predicted by fusing perception results from vehicles and roadside units (RSUs) at different moments. Then, the recommended velocity is derived for green wave passage, called the green wave velocity belt, and incorporate it into the state space as two variables in the state vector. Finally, a relevant reward term in the reward function is designed to guide agent learning strategies. The proposed method is trained on the basis of the parallel DreamerV3 framework. The results show that the proposed approach can effectively integrate multi-source perceptual information, improving training efficiency and control performance, and demonstrating great effectiveness and practical application value.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"159 ","pages":"Article 106315"},"PeriodicalIF":5.4,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143620563","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}

引用次数: 0

A robust distributed fault detection scheme for interconnected systems based on subspace identification technique 基于子空间识别技术的互联系统鲁棒分布式故障检测方案

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2025-03-14 DOI: 10.1016/j.conengprac.2025.106301

Caixin Fu , Changhong Jiang , Zhiwei Wan , Qiang Wang , Shenquan Wang

{"title":"A robust distributed fault detection scheme for interconnected systems based on subspace identification technique","authors":"Caixin Fu , Changhong Jiang , Zhiwei Wan , Qiang Wang , Shenquan Wang","doi":"10.1016/j.conengprac.2025.106301","DOIUrl":"10.1016/j.conengprac.2025.106301","url":null,"abstract":"<div><div>This paper proposes a robust data-driven distributed fault detection (FD) method for interconnected systems with stochastic noises, addressing the challenges posed by stochastic noises and the limitations of centralized designs on real industrial systems. The proposed method utilizes the process data from a sensor network to generate robust residual signals for FD. The method performs distributed calculations of residual signals and test statistics at each sensor node using the subspace identification technique and the average consensus algorithm. To ensure satisfactory detection performance and robustness against uncertainties caused by stochastic noises, the paper integrates the performance index and the Mahalanobis distance into the FD framework. Unlike existing FD methods that rely on the Mahalanobis distance, this study also explores improving detection performance through the consensus algorithm and performance index. It is worth noting that this method not only mitigates the negative effects of stochastic noises in FD, but also eliminates global communication costs and complex information interactions. The developed method is validated through an experimental study on a real traction drive system to assess its feasibility and effectiveness.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"159 ","pages":"Article 106301"},"PeriodicalIF":5.4,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143620564","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}

引用次数: 0

Adaptive aircraft anti-skid braking control for runway disturbance compensation 跑道扰动补偿的自适应飞机防滑制动控制

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2025-03-14 DOI: 10.1016/j.conengprac.2025.106314

Xiaochao Liu , Xuefeng Sun , Zhuangzhuang Wang , Ning Bai , Yaoxing Shang

{"title":"Adaptive aircraft anti-skid braking control for runway disturbance compensation","authors":"Xiaochao Liu , Xuefeng Sun , Zhuangzhuang Wang , Ning Bai , Yaoxing Shang","doi":"10.1016/j.conengprac.2025.106314","DOIUrl":"10.1016/j.conengprac.2025.106314","url":null,"abstract":"<div><div>During aircraft braking, the wheels are often in a high-slip state, making them prone to repeated skidding under the influence of internal and external disturbances. Therefore, designing a disturbance-resistant anti-skid braking control system is key to achieving efficient braking. This paper proposes an adaptive runway disturbance-resistant anti-skid braking control law that addresses the problem of skidding caused by various disturbances during aircraft braking, thereby improving braking efficiency. By studying the internal and external disturbances affecting the aircraft during braking, these disturbances are classified based on their impact on the balance point of the wheel slip system. A method based on the induced ideal limit cycle is proposed to detect disturbances. An adaptive braking control strategy incorporating runway recognition technology was developed, enabling the braking system to adjust the target deceleration rate according to real-time disturbances. Finally, simulation tests and inertial platform tests confirmed that the proposed control law significantly improves efficiency compared to the PBM (Press Bias Module) control method.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"159 ","pages":"Article 106314"},"PeriodicalIF":5.4,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143620645","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}

引用次数: 0

Induction heating using MPC and state estimation for safe acceleration of compressor tests 基于MPC和状态估计的压缩机安全加速试验感应加热

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2025-03-13 DOI: 10.1016/j.conengprac.2025.106317

Guilherme da F. Pereira , Rodolfo C.C. Flesch , Gabriel Thaler

{"title":"Induction heating using MPC and state estimation for safe acceleration of compressor tests","authors":"Guilherme da F. Pereira , Rodolfo C.C. Flesch , Gabriel Thaler","doi":"10.1016/j.conengprac.2025.106317","DOIUrl":"10.1016/j.conengprac.2025.106317","url":null,"abstract":"<div><div>Induction heating (IH) systems normally do not use closed-loop temperature control, but the results in some applications can be considerably improved by using a controller. The objective of this work is to experimentally assess the use of zone model-based predictive controllers (ZMPCs) for temperature control in an IH prototype used to heat a compressor in performance tests with constraints on unmeasured states. This choice was motivated by the importance of such tests in industry, the potential to shorten the transient duration using IH, and the existence of safety constraints on non-measurable temperatures. A test rig with an instrumented compressor was built to test the proposed framework with different controllers from the literature, including a reference-tracking model-based predictive controller (MPC) predictive controller (MPC) and a PI controller. A state-space model was identified using measured temperatures as states to describe the thermal dynamics of the compressor. Since the temperature required for ensuring safety constraints is not measurable in a regular compressor, a Kalman filter was used for state estimation. Experimental results show that all controllers satisfy the constraints and can track a reference step with zero steady-state error. The best result was achieved by ZMPC, where the heating time of the evaluated compressor was reduced from 70min to less than 10min while maintaining safe internal temperature conditions, which represents a reduction of approximately 90% in transient time.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"159 ","pages":"Article 106317"},"PeriodicalIF":5.4,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143620644","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}

引用次数: 0

Two-stage three-phase photovoltaic grid-connected inverter control method based on off-policy integral reinforcement learning 基于非策略积分强化学习的两级三相光伏并网逆变器控制方法

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2025-03-12 DOI: 10.1016/j.conengprac.2025.106313

He Ren , Min Zhuang , Lingfang Sun , Huichao Ji , Xiuyu Zhang , Chun-Yi Su

{"title":"Two-stage three-phase photovoltaic grid-connected inverter control method based on off-policy integral reinforcement learning","authors":"He Ren , Min Zhuang , Lingfang Sun , Huichao Ji , Xiuyu Zhang , Chun-Yi Su","doi":"10.1016/j.conengprac.2025.106313","DOIUrl":"10.1016/j.conengprac.2025.106313","url":null,"abstract":"<div><div>In this article, a novel control method of the grid-connected inverter (GCI) based on the off-policy integral reinforcement learning (IRL) method is presented to solve two-stage three-phase photovoltaic (TTP) power quality degradation problem of the grid connection caused by unknown system dynamics. Firstly, the voltage-current dual-loop control (VDC) structure is adopted, where the model of the current loop is restructured benefitting from the current tracking principle. Secondly, the grid-connected power quality problem is turned into a zero-sum game (ZSG) problem, which can be completed by solving the Hamilton–Jacobi-Bellman (HJB) equations using the off-policy IRL method only with the collected input and output (I/O) data. Thirdly, the off-policy IRL method is improved on the basis of the traditional policy iteration method and the equivalence between them is demonstrated. Finally, the presented method is verified by StarSim Modeling Tech power electronic simulation experiment platform to satisfy the standard of the grid connection and the total harmonic distortion of the current is less than 5%.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"159 ","pages":"Article 106313"},"PeriodicalIF":5.4,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143600935","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}

引用次数: 0

Three-time-scale control for discharging rate consensus and large-signal stability analysis in AC-bus microgrids 交流母线微电网放电速率一致性三时间尺度控制及大信号稳定性分析

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2025-03-10 DOI: 10.1016/j.conengprac.2025.106299

Maria Camila Merchán-Riveros, Carolina Albea, Franciso Salas

{"title":"Three-time-scale control for discharging rate consensus and large-signal stability analysis in AC-bus microgrids","authors":"Maria Camila Merchán-Riveros, Carolina Albea, Franciso Salas","doi":"10.1016/j.conengprac.2025.106299","DOIUrl":"10.1016/j.conengprac.2025.106299","url":null,"abstract":"<div><div>A distributed control scheme for islanded AC-bus microgrids is proposed, based on multi-agent system and singular perturbation theory. The goal is to achieve a balanced State Of Charge (SOC) for each Battery Energy Storage System (BESS) in discharging mode, ensuring stability properties of a large-signal model that considers the primary and secondary control loop dynamics. The power inverters are controlled through a voltage and current loop. Moreover, a droop control and consensus algorithm are proposed to ensure that the SOC of these BESSs are balanced. Furthermore, large-signal stability analysis is assessed for the complete network system by using singular perturbation theory. Indeed, through an appropriate selection of the parameters, the dynamics exhibit three-time-scale separation to fit each control goal (power converter control, droop control and consensus control). Experimental results on an Imperix power test bench validate the proposed control scheme, and verify the reliability and robustness with respect to any connection/disconnection event or communication failure through different scenarios.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"159 ","pages":"Article 106299"},"PeriodicalIF":5.4,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143590355","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}

引用次数: 0

Real-time kinematics-based sensor-fault detection for autonomous vehicles using single and double transport with adaptive numerical differentiation 基于自适应数值微分的单、双运输自动驾驶车辆实时运动学传感器故障检测

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2025-03-08 DOI: 10.1016/j.conengprac.2025.106304

Shashank Verma, Dennis S. Bernstein

{"title":"Real-time kinematics-based sensor-fault detection for autonomous vehicles using single and double transport with adaptive numerical differentiation","authors":"Shashank Verma, Dennis S. Bernstein","doi":"10.1016/j.conengprac.2025.106304","DOIUrl":"10.1016/j.conengprac.2025.106304","url":null,"abstract":"<div><div>Sensor-fault detection is crucial for the safe operation of autonomous vehicles. This paper introduces a novel kinematics-based approach for detecting and identifying faulty sensors, which is model-independent, rule-free, and applicable to ground and aerial vehicles. This method, called kinematics-based sensor fault detection (KSFD), relies on kinematic relations, sensor measurements, and real-time single and double numerical differentiation. Using onboard data from radar, rate gyros, magnetometers, and accelerometers, KSFD identifies a single faulty sensor in real time. To achieve this, adaptive input and state estimation (AISE) is used for real-time single and double numerical differentiation of the sensor data, and the kinematically exact single and double transport theorems are used to evaluate the consistency of the data. Unlike model-based and knowledge-based methods, KSFD relies solely on sensor signals, kinematic relations, and AISE for real-time numerical differentiation. For ground vehicles, KSFD requires six kinematics-based error metrics, whereas, for aerial vehicles, nine error metrics are needed. Simulated and experimental examples are provided to evaluate the effectiveness of KSFD.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"159 ","pages":"Article 106304"},"PeriodicalIF":5.4,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143579524","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}

引用次数: 0

FPGA implementation of edge-side motor fault diagnosis using a Kalman filter-based empirical mode decomposition algorithm 基于卡尔曼滤波的经验模态分解算法在FPGA上实现边缘电机故障诊断

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2025-03-07 DOI: 10.1016/j.conengprac.2025.106312

Jiaxin Li, Maosong Cheng, Yongbo Wei, Zhimin Dai

引用次数: 0

A parallel weighted ADTC-Transformer framework with FUnet fusion and KAN for improved lithium-ion battery SOH prediction 基于FUnet融合和KAN的并联加权ADTC-Transformer框架改进了锂离子电池SOH预测

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2025-03-05 DOI: 10.1016/j.conengprac.2025.106302

Chuang Chen , Yuheng Wu , Jiantao Shi , Dongdong Yue , Ge Shi , Dongzhen Lyu

{"title":"A parallel weighted ADTC-Transformer framework with FUnet fusion and KAN for improved lithium-ion battery SOH prediction","authors":"Chuang Chen , Yuheng Wu , Jiantao Shi , Dongdong Yue , Ge Shi , Dongzhen Lyu","doi":"10.1016/j.conengprac.2025.106302","DOIUrl":"10.1016/j.conengprac.2025.106302","url":null,"abstract":"<div><div>This paper delves into the extraction and integration of local and global features for lithium-ion battery State of Health (SOH) prediction, proposing an innovative parallel weighted architecture—ADTC-Transformer. This framework combines Adaptive Dilated Temporal Convolution (ADTC) with a Transformer encoder to effectively capture and balance local and global dependencies while dynamically optimizing feature contributions through a weighted fusion mechanism. Additionally, the traditional U-shaped network (Unet) is enhanced by incorporating a Feature Pyramid Network (FPN), forming the FUnet module, which significantly strengthens the fusion and utilization of multi-scale features. Building on this, the Kolmogorov–Arnold Network (KAN) is introduced as the final prediction module, leveraging Kolmogorov–Arnold representation theory to model complex high-dimensional features through local interpolation and global nonlinear transformations. This enables the KAN module to capture intricate temporal dependencies and interactions across a wide range of feature scales, thus improving the model’s ability to predict long-term SOH. Experimental results demonstrate that the proposed method markedly improves prediction accuracy across NASA, CALCE, and WRBD datasets, excelling particularly in long-term SOH prediction for lithium-ion batteries. This provides robust support for battery health management and performance optimization.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"159 ","pages":"Article 106302"},"PeriodicalIF":5.4,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143550994","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}

引用次数: 0

U-control-based active disturbance-rejection control revealed by the sliding mode for USV heading control 基于u控制的滑模自抗扰控制在无人潜航器航向控制中的应用

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2025-03-04 DOI: 10.1016/j.conengprac.2025.106288

Jiabin Yu , Yuxiang Wei , Yang Chen , Huiyan Zhang , Jiping Xu , Zhiyao Zhao

引用次数: 0