Control Engineering Practice最新文献_第3页

Prescribed performance control with adaptive erupting funnel function for a class of unknown discrete-time systems and undefined disturbances 一类未知离散系统和未定义扰动的自适应爆发漏斗函数的预定性能控制

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2025-07-17 DOI: 10.1016/j.conengprac.2025.106483

Chidentree Treesatayapun

引用次数: 0

Real-time classification and early warning of industrial alarm floods using modified TF-IDF methods 基于改进TF-IDF方法的工业报警洪水实时分类预警

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2025-07-17 DOI: 10.1016/j.conengprac.2025.106485

Md Habibur Rahaman, Haniyeh Seyed Alinezhad, Tongwen Chen

{"title":"Real-time classification and early warning of industrial alarm floods using modified TF-IDF methods","authors":"Md Habibur Rahaman, Haniyeh Seyed Alinezhad, Tongwen Chen","doi":"10.1016/j.conengprac.2025.106485","DOIUrl":"10.1016/j.conengprac.2025.106485","url":null,"abstract":"<div><div>In complex industrial processes, the activation of a single alarm can trigger a cascade of consequences, affecting multiple interconnected components and rapidly increasing the number of active alarms. This phenomenon, known as an alarm flood, imposes a significant operational burden on operators by overwhelming them with high volumes of alarm notifications. This paper addresses these challenges by advancing real-time fault detection and monitoring systems. The contributions of this paper are twofold. First, it introduces a similarity analysis using a modified term frequency–inverse document frequency (TF-IDF) method to form clusters of alarm floods. Parameter optimization techniques are then applied to achieve the optimal <em>n</em>-gram size for improved clustering performance. Second, a novel method is proposed for real-time fault detection and a machine learning predictive model is further applied to assign real-time <em>n</em>-gram sequences to historical alarm floods, ensuring continuity in fault identification. Finally, an optimal alert threshold is designed to generate early warnings, enhancing operators’ responses to potential alarm floods and thus improving industrial process safety and efficiency.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"164 ","pages":"Article 106485"},"PeriodicalIF":5.4,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144655087","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

Learning-based real-time model predictive tracking control for autonomous vehicles with path-pattern adaptability 基于学习的路径模式自适应自动驾驶汽车实时模型预测跟踪控制

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2025-07-16 DOI: 10.1016/j.conengprac.2025.106480

Wentong Shi , Shiying Dong , Chao Zhang , Dele Meng , Jinlong Hong , Hongqing Chu , Bingzhao Gao

{"title":"Learning-based real-time model predictive tracking control for autonomous vehicles with path-pattern adaptability","authors":"Wentong Shi , Shiying Dong , Chao Zhang , Dele Meng , Jinlong Hong , Hongqing Chu , Bingzhao Gao","doi":"10.1016/j.conengprac.2025.106480","DOIUrl":"10.1016/j.conengprac.2025.106480","url":null,"abstract":"<div><div>Real-time implementation of nonlinear model predictive control (NMPC) for path tracking in autonomous vehicles (AVs) remains challenging due to the computational complexity of solving high-dimensional, nonlinear optimization problems under dynamic constraints. To address this issue, this paper proposes a novel end-to-end training framework, called the neural network optimizer (NN Optimizer), which significantly reduces the computational burden of NMPC, enabling real-time implementation. Specifically, the NN Optimizer integrates low-fidelity, interpretable physical models with neural networks (NNs), utilizing automatic differentiation to backpropagate the NMPC loss function through a differentiable dynamics model to obtain policy gradients. As opposed to traditional imitation learning (IL)-based approaches, usually reliant on expert knowledge, the proposed method does not rely on extensive labeled data, offering greater interpretability and path-pattern adaptability. During online implementation, it just involves simple function evaluation, avoiding the computation of gradient information and multiple iterations. In two validation scenarios during co-simulation, the NN Optimizer achieves a solving speed over 70 times faster than interior point optimizer (<span>IPOPT</span>), while improving closed-loop control performance by more than 10% compared to IL. In real-vehicle tests, the NN optimizer outperforms the linear quadratic regulator (LQR), achieving improvements in control performance of over 30% in the weave scenario and over 60% in the double lane change (DLC) scenario.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"164 ","pages":"Article 106480"},"PeriodicalIF":5.4,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144633973","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

An overview of Unmanned Surface Vehicles: Methods, practices, and applications 无人水面车辆概述：方法、实践和应用

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2025-07-16 DOI: 10.1016/j.conengprac.2025.106479

Huarong Zheng , Chenguang Liu

{"title":"An overview of Unmanned Surface Vehicles: Methods, practices, and applications","authors":"Huarong Zheng , Chenguang Liu","doi":"10.1016/j.conengprac.2025.106479","DOIUrl":"10.1016/j.conengprac.2025.106479","url":null,"abstract":"<div><div>Over the past few decades, Unmanned Surface Vehicles (USVs) have transitioned from concept to reality at an impressive pace. This rapid development is fueled by advances in technology and emerging demands in science, engineering, and military applications. The emphasis on USVs has evolved from purely research-focused activities to practical commercial and engineering applications. This paper presents insights gained from a decade of USV development, providing an overview of the latest methodologies, design practices, and applications. We review and compare various USVs currently in use, including those for research and field applications. In addition, we categorize and update the state-of-the-art navigation, guidance, and control methodologies that form the core capabilities of USVs, with a particular emphasis on the growing trend of learning-based and data-driven systems. As a crucial aspect, we also discuss the architectural design, implementation, and field testing of USVs. Finally, we explore their applications in three key areas: military operations, oceanographic observation, and intelligent waterborne transportation. Given that technological and practical challenges for USVs remain, we outline considerations and highlight relevant future directions.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"164 ","pages":"Article 106479"},"PeriodicalIF":5.4,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144633974","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 formation drillability sensing-based hybrid online prediction method for the rate of penetration (ROP) and its industrial application for drilling processes 基于地层可钻性实时感知的机械钻速混合在线预测方法及其在钻井过程中的工业应用

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2025-07-15 DOI: 10.1016/j.conengprac.2025.106487

Chao Gan , Yao Wang , Wei-Hua Cao , Kang-Zhi Liu , Min Wu

{"title":"Real-time formation drillability sensing-based hybrid online prediction method for the rate of penetration (ROP) and its industrial application for drilling processes","authors":"Chao Gan , Yao Wang , Wei-Hua Cao , Kang-Zhi Liu , Min Wu","doi":"10.1016/j.conengprac.2025.106487","DOIUrl":"10.1016/j.conengprac.2025.106487","url":null,"abstract":"<div><div>Real-time prediction of the rate of penetration (ROP) is crucial for enhancing drilling efficiency. Formation drillability (FD), a key factor that reflects the formation characteristics is rarely considered in common studies. In this paper, a real-time FD sensing-based hybrid online prediction method of ROP and its industrial application for the drilling process is proposed, which contains two main stages (FD soft sensing and online ROP prediction). In the first stage, the FD of the bottom hole is predicted in real-time based on the soft sensing techniques, which is set as one of the input parameters of the ROP prediction model. In the second stage, five parameters that have close relationships with the ROP are pre-processed online using limiting filtering and Savitzky Golay (SG) filtering first. After that, the hybrid modeling method and incremental learning strategy are introduced to establish the ROP prediction model. Finally, the proposed method is applied in the Gedian area, Central China. Compared with six well-known ROP prediction methods, the prediction accuracy is improved by at least 19%, which validates the effectiveness of the proposed method and lays a foundation for intelligent optimization control of the drilling process.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"164 ","pages":"Article 106487"},"PeriodicalIF":5.4,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144632016","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

Hierarchical NMPC for energy-efficient torque vectoring in four in-wheel motor electric vehicles 四轮电机电动汽车节能转矩矢量的分级NMPC

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2025-07-14 DOI: 10.1016/j.conengprac.2025.106477

Suyong Park , Junghyo Kim , Duc Giap Nguyen , Minsoo Woo , Daekwang Kim , Kyoungseok Han

{"title":"Hierarchical NMPC for energy-efficient torque vectoring in four in-wheel motor electric vehicles","authors":"Suyong Park , Junghyo Kim , Duc Giap Nguyen , Minsoo Woo , Daekwang Kim , Kyoungseok Han","doi":"10.1016/j.conengprac.2025.106477","DOIUrl":"10.1016/j.conengprac.2025.106477","url":null,"abstract":"<div><div>This paper presents a hierarchical torque vectoring (TV) framework that integrates vehicle dynamics enhancement and energy efficiency improvement using nonlinear model predictive control (NMPC) for four in-wheel motor electric vehicles (4WMEVs). TV systems offer significant potential for enhancing both handling performance and energy economy by optimally distributing torque among the wheels. However, effectively balancing these two objectives remains a critical challenge. To address this, we propose a simplified hierarchical control structure that simultaneously improves handling performance and reduces energy consumption. The top-layer controller computes the desired longitudinal tire forces to generate accurate yaw moments, enhancing handling performance. The bottom-layer controller ensures energy-optimal torque allocation while preserving the control objectives of the top-layer. Simulation results demonstrate that the proposed strategy achieves a 11.27% reduction in energy consumption without compromising handling performance.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"164 ","pages":"Article 106477"},"PeriodicalIF":5.4,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144623509","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 compound Bayesian networks gas prediction and scheduling method for blast furnace systems under various scenarios 基于复合贝叶斯网络的高炉瓦斯预测与调度方法

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2025-07-14 DOI: 10.1016/j.conengprac.2025.106463

Junyan Fan, Dinghui Wu, Shenxin Lu

{"title":"A compound Bayesian networks gas prediction and scheduling method for blast furnace systems under various scenarios","authors":"Junyan Fan, Dinghui Wu, Shenxin Lu","doi":"10.1016/j.conengprac.2025.106463","DOIUrl":"10.1016/j.conengprac.2025.106463","url":null,"abstract":"<div><div>Changes in the production scenarios of the blast furnace system disrupt the established production rhythm and gas balance. The complex characteristics of equipment in different scenarios and the temporal coupling resulting from the interactions between scenarios present challenges in prediction and scheduling. To address this issue, a compound Bayesian networks (CBN) gas prediction and scheduling method is proposed. In light of the characteristics of gas production and consumption data from different equipment, a monotonic variable-step size sliding window event extraction algorithm is designed to extract event information and construct state and delay event sets. By integrating the physical production structure with these event sets, state Bayesian networks, delay Bayesian networks, and an inter-network state representation layer are constructed, forming a complete CBN. Meanwhile, a prediction and scheduling inference procedure with temporal decoupling is proposed. It decouples the energy states of production equipment across successive scenarios and incorporates the objective function to enable scheduling inference and decision-making. Actual data from the steel production process are used for experimental analysis. The results demonstrate that the proposed method enhances prediction accuracy by 4.93% and reduces delay by 5.97%. In scheduling, it decreases the proportion of instances exceeding the safety tank level by 16.67% and lowers the comprehensive energy consumption per ton of steel by 0.0054%.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"164 ","pages":"Article 106463"},"PeriodicalIF":5.4,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144623510","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

Globally smooth lemniscate trajectory with adaptive integral terminal sliding mode control and inversion-based hysteresis compensation for pi ezoelectric stage precise tracking 基于自适应积分末端滑模控制和逆滞后补偿的全局光滑运动轨迹，实现了压电级的精确跟踪

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2025-07-12 DOI: 10.1016/j.conengprac.2025.106486

Jim-Wei Wu (Senior Member IEEE) , Ting-Kuei Hsu , Jia-Cheng Li , Yu-Han Lin , Sung-Hua Chen

{"title":"Globally smooth lemniscate trajectory with adaptive integral terminal sliding mode control and inversion-based hysteresis compensation for pi ezoelectric stage precise tracking","authors":"Jim-Wei Wu (Senior Member IEEE) , Ting-Kuei Hsu , Jia-Cheng Li , Yu-Han Lin , Sung-Hua Chen","doi":"10.1016/j.conengprac.2025.106486","DOIUrl":"10.1016/j.conengprac.2025.106486","url":null,"abstract":"<div><div>High-precision measurement systems use an <em>xy</em>-axis piezoelectric scanner following a pre-determined trajectory to achieve three-dimensional scanning at micro/nano-scales. Most systems employ a raster scanning trajectory due to ease of implementation; however, raster scanning generates infinite odd harmonics, which can induce mechanical resonance leading to image distortion. Moreover, the nonlinear response characteristics of piezoelectric materials frequently result in unexpected displacements. This paper presents a novel sequential scanning trajectory that eliminates the need for a step function and minimizes the risk of mapping errors. An advanced controller combining an inverse hysteresis model with adaptive integral terminal sliding mode control (AITSMC) was developed and first applied in the piezoelectric scanner through theoretical derivation and stability analysis to prove its feasibility. In simulations and experiments, the proposed controller significantly mitigated the effects of hysteresis during trajectory tracking and achieved superior tracking accuracy and lower RMSE compared to existing sliding mode controllers.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"164 ","pages":"Article 106486"},"PeriodicalIF":5.4,"publicationDate":"2025-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144606156","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

Intuitive hand motion-based teleoperation system for human-mobile manipulator interaction using mixed reality 基于直观手部动作的混合现实人机交互遥操作系统

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2025-07-11 DOI: 10.1016/j.conengprac.2025.106467

Hua-Hsuan Yeh, Yu-Wei Chang, Yen-Chen Liu

{"title":"Intuitive hand motion-based teleoperation system for human-mobile manipulator interaction using mixed reality","authors":"Hua-Hsuan Yeh, Yu-Wei Chang, Yen-Chen Liu","doi":"10.1016/j.conengprac.2025.106467","DOIUrl":"10.1016/j.conengprac.2025.106467","url":null,"abstract":"<div><div>This paper presents an intuitive teleoperation interface for human-mobile manipulator interaction, addressing the challenges posed by unstructured, dynamic environments and the inherent uncertainties in robot dynamics. Traditional teleoperation systems often lack intuitiveness and immersiveness, particularly when controlling high-DoF (degree-of-freedom) robotic systems. The proposed approach integrates IMU (Inertial Measurement Unit)-based hand motion tracking with mixed reality technology, enabling seamless control in both Manipulation and Locomotion modes. In Manipulation mode, a torque-based controller regulates the motion of the manipulator’s end-effector, while a radial basis function neural network compensates for dynamic uncertainties. The null-space projection method further provides self-autonomous redundancy resolution. In Locomotion mode, a velocity-based control strategy is implemented to govern the motion of the mobile platform. The mixed reality environment, constructed using SLAM (Simultaneous Localization and Mapping), 3D point-cloud data, and real-time 2D visual streaming, provides immersive and comprehensive visual feedback through a head-mounted display device. Stability of the Manipulation mode is analyzed via Lyapunov stability theorem and validated through numerical studies. Experiments conducted on a mobile manipulator, comprising a differential-drive base and a 7-DoF manipulator, demonstrate effective performance in complex scenarios. Additionally, comparative experiments with multiple input devices show that the proposed system offers superior usability and imposes a lower operator workload than alternative interfaces. These results highlight the robustness, intuitiveness, and practical applicability of the proposed method in dynamic and hazardous environments.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"164 ","pages":"Article 106467"},"PeriodicalIF":5.4,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144596252","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

Fault detection for electric magnesium melting furnace based on cooperative modeling 基于协同建模的电熔镁炉故障检测

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2025-07-11 DOI: 10.1016/j.conengprac.2025.106490

Yunpeng Fan , Yingwei Zhang , Chaomin Luo , Zhuming Bi

引用次数: 0