Control Engineering Practice最新文献

{"title":"TimeGPT-based multi-step-ahead key quality indicator forecasting for industrial processes","authors":"Xinmin Zhang ,&nbsp;Yuwei Chen ,&nbsp;Bocun He ,&nbsp;Zhihuan Song ,&nbsp;Manabu Kano","doi":"10.1016/j.conengprac.2025.106410","DOIUrl":"10.1016/j.conengprac.2025.106410","url":null,"abstract":"<div><div>Multi-step prediction is one of the most challenging problems in the field of industrial soft sensing. Recently, large language models have been widely used in various fields. Inspired by TimeGPT, a popular large-scale model for time series forecasting, this paper proposes a novel multi-step key quality indicator forecasting method for industrial processes, namely the TimeGPT-based Multi-step-ahead Forecasting (TiMF) model. The proposed TiMF model is designed based on pre-trained TimeGPT, and historical process variable information is integrated into the prediction model as an auxiliary guide to improve the utilization of industrial data information. To evaluate the effectiveness of the proposed method, it was applied to the debutanizer industrial process and the sintering industrial process. The application results show that the proposed TiMF can achieve better prediction accuracy than other existing methods. This work provides a new attempt for the industrial soft sensing application of the large-scale time series prediction model.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"164 ","pages":"Article 106410"},"PeriodicalIF":5.4,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144203852","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}

{"title":"Resonance suppression of a piezo-actuated nanopositioning stage based on recursive positive velocity feedback control","authors":"Suan Xu ,&nbsp;Tengfei Chen ,&nbsp;Kaixing Hong ,&nbsp;Lushuai Qian ,&nbsp;Yaping Xu ,&nbsp;Luc Chassagne","doi":"10.1016/j.conengprac.2025.106422","DOIUrl":"10.1016/j.conengprac.2025.106422","url":null,"abstract":"<div><div>The piezo-actuated nanopositioning stage is widely used in the applications requiring precise motion and control at the nanometer level, which determines whether the system is capable of high precision and fast response. In order to suppress the low-damping resonance of the one-dimensional nanopositioning stage, this paper proposes a novel dual-loop control method that combines recursive positive velocity feedback (RPVF) control and displacement tracking control. The RPVF-based inner control loop is proposed to mitigate the resonance mode of the nanopositioning stage, and the softplus function and simulated annealing are used to improve the flamingo search algorithm for parameter configuration. The proportional–integral (PI) controller is introduced in the outer loop to overcome the problems remain in the system after vibration compensation, such as hysteresis and creep. The experimental results show that the proposed controller combining RPVF and PI effectively suppresses the low-damping resonance modes of the nanopositioning stage and achieves outstanding performance in control bandwidth, step response and trajectory tracking.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"164 ","pages":"Article 106422"},"PeriodicalIF":5.4,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144203851","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}

{"title":"Adjust to reality: LLM-driven test-time semantic adjustment for zero-shot fault diagnosis","authors":"Jiancheng Zhao ,&nbsp;Jiaqi Yue ,&nbsp;Chunhui Zhao ,&nbsp;Chen Chen","doi":"10.1016/j.conengprac.2025.106406","DOIUrl":"10.1016/j.conengprac.2025.106406","url":null,"abstract":"<div><div>Zero-shot fault diagnosis methods identify unseen faults by predicting semantic knowledge from samples. However, existing studies require labor-intensive tasks of training domain experts and annotating semantic knowledge in a specified format. Moreover, due to the domain shift problem (DSP), models trained solely on seen faults experience a decrease in performance when transferred to unseen faults. To reduce the annotation burden and address the DSP, we propose a test-time semantic adjustment method driven by the large language models (LLMs), which focuses on annotating and optimizing semantic knowledge. Firstly, with carefully designed prompts, semantic knowledge is automatically annotated by the LLM based on unstructured professional corpora. Secondly, to overcome the DSP caused by the lack of unseen faults, this study introduces the concept of test-time adjustment for zero-shot diagnosis. Specifically, we design a dual-view semantic knowledge adjustment strategy that employs information on unseen faults from unlabeled test data to adjust the semantic knowledge. This simple yet effective strategy can also be applied to other zero-shot diagnosis methods. Last but not least, we propose the class-agnostic feature extraction to enhance the cross-category transferability of extracted features for preventing overfitting to seen faults. We conduct experiments on the Tennessee-Eastman process (TEP) and a real thermal power plant (TPP), and the proposed method achieves an average improvement of 11.34% in terms of the accuracy of unseen faults on the TEP dataset, and 6.87% on the TPP dataset.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"164 ","pages":"Article 106406"},"PeriodicalIF":5.4,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144194495","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}

{"title":"Robust prediction-based control for unknown time-varying delays and disturbances in spherical motion platform","authors":"Seong-Min Lee ,&nbsp;Sangheon Lee ,&nbsp;Hungsun Son","doi":"10.1016/j.conengprac.2025.106400","DOIUrl":"10.1016/j.conengprac.2025.106400","url":null,"abstract":"<div><div>This paper presents a new prediction-based controller utilizing enhanced preview and state prediction methods to deal with unknown time-varying delays and disturbances. In practice, uncertain and variable time delays in virtual reality applications can lead to control instability and a significant reduction in the overall sense of realism. In this paper, a robust prediction-based control (RPC) is proposed for the spherical motion platform (SMP) to compensate for the effects of the time-varying delays and disturbances. The RPC comprises a preview strategy and state/disturbance prediction methods with an estimator to handle unknown time-varying delays. In addition, a newly proposed preview method improves the system’s ability to follow a time-varying reference trajectory. The stability analysis for the time-delayed system incorporating the RPC is conducted using the Lyapunov–Krasovskii approach. Numerical simulations and various experiments demonstrate that the RPC effectively leads the state to converge to the desired trajectory within an error bound under various conditions of time-varying delays in the presence of disturbances, whereas the existing controllers have limitations in reducing the desired control errors. Consequently, the results validate the feasibility and effectiveness of the RPC in real-world applications, demonstrating its robustness in handling time-varying delays through practical implementation on the SMP.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"163 ","pages":"Article 106400"},"PeriodicalIF":5.4,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144185602","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}

{"title":"Exponential decay adaptive robust control for electron spin magnetization in atomic spin gyroscopes","authors":"Feng Li ,&nbsp;Zhuo Wang ,&nbsp;Ruigang Wang ,&nbsp;Haoying Pang ,&nbsp;Wenfeng Fan ,&nbsp;Xinxiu Zhou ,&nbsp;Xusheng Lei ,&nbsp;Wei Quan","doi":"10.1016/j.conengprac.2025.106405","DOIUrl":"10.1016/j.conengprac.2025.106405","url":null,"abstract":"<div><div>As the demand for high-precision navigation and stability in engineering grows, traditional mechanical and optical gyroscopes face performance and size limitations. Atomic Spin Gyroscopes (ASGs) offer exceptional precision and stability, with potential for miniaturization. However, electron spin magnetization (ESM) is sensitive to interference from various physical fields, and its stability is crucial for ASGs performance. Current research lacks effective closed-loop control solutions to stabilize ESM under parameter fluctuation and external disturbance. In this study, we develop an affine nonlinear system model with non-autonomous characteristics for ESM and propose an exponential decay adaptive robust control (EDARC) strategy to address this challenge. In addition, an innovative hardware architecture for direct measurement and control of ESM is implemented. Comparative simulations reveal that the EDARC outperforms existing approaches, while experimental results show substantial improvements in system stability. The proposed method demonstrates a significant enhancement in ESM stabilization by reducing the Integral of Absolute Error (IAE) by over 95%, effectively mitigating the impact of magnetic and thermal disturbances. Allan deviation analysis further confirms the improvement in long-term stability, with reductions exceeding 90%, highlighting the robustness of the proposed strategy in maintaining precise ESM control over extended periods.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"163 ","pages":"Article 106405"},"PeriodicalIF":5.4,"publicationDate":"2025-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144185673","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}

{"title":"Hierarchical optimal planning and real-time tracking of parking trajectories based on risk field","authors":"Dongxu Su,&nbsp;Zhiguo Zhao,&nbsp;Kun Zhao,&nbsp;Kaichong Liang,&nbsp;Qin Yu","doi":"10.1016/j.conengprac.2025.106423","DOIUrl":"10.1016/j.conengprac.2025.106423","url":null,"abstract":"<div><div>In order to improve the safety, smoothness and robustness of the automatic parking trajectory for light commercial vehicles in dynamic environments, this paper designs a novel real-time parking trajectory planning and tracking control architecture. A parking risk field (PRF) is established to reflect the guiding role and constraints of the parking environment on the vehicle. Nonlinear Model Predictive Control (NMPC) incorporating the PRF is proposed to realize the trajectory smooth optimization and real-time dynamic obstacle avoidance while tracking the global trajectory. Firstly, in the global parking trajectory planning layer, the initial trajectory is generated based on hybrid A*, path quadratic smoothing and speed planning algorithms. The parking problem is then formulated as an optimization problem, with the global trajectory planned based on the initial one. Secondly, in the real-time tracking control layer, considering the influence of trajectory guidance, drivable area modeling and dynamic obstacle avoidance, the PRF is constructed, comprising the trajectory attraction field, parking boundary field and vehicle repulsion field. Based on the PRF, the NMPC cost function is formulated. Additionally, vehicle ellipse constraints are designed and work with the boundary field to confine the vehicle within the parking space. Finally, the proposed optimal planning and dynamic tracking method based on the PRF is verified through simulation and real vehicle experiments. Both simulation and experiment results demonstrate that the designed trajectory planning and control architecture can enable the vehicle to park safely, smoothly and accurately in the parking space, while avoiding dynamic obstacles in real time through NMPC.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"163 ","pages":"Article 106423"},"PeriodicalIF":5.4,"publicationDate":"2025-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144178694","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}

{"title":"A comprehensive control architecture for semi-autonomous dual-arm robots in agriculture settings","authors":"Jozsef Palmieri,&nbsp;Paolo Di Lillo,&nbsp;Stefano Chiaverini,&nbsp;Alessandro Marino","doi":"10.1016/j.conengprac.2025.106394","DOIUrl":"10.1016/j.conengprac.2025.106394","url":null,"abstract":"<div><div>The adoption of mobile robotic platforms in complex environments, such as agricultural settings, requires these systems to exhibit a flexible yet effective architecture that integrates perception and control. In such scenarios, several tasks need to be accomplished simultaneously, ranging from managing robot limits to performing operational tasks and handling human inputs. The purpose of this paper is to present a comprehensive control architecture for achieving complex tasks such as robotized harvesting in vineyards within the framework of the European project CANOPIES. In detail, a 16-DOF dual-arm mobile robot is employed, controlled via a Hierarchical Quadratic Programming (HQP) approach capable of handling both equality and inequality constraints at various priorities to harvest grape bunches selected by the perception system developed within the project. Furthermore, given the complexity of the scenario and the uncertainty in the perception system, which could potentially lead to collisions with the environment, the handling of interaction forces is necessary. Remarkably, this was achieved using the same HQP framework. This feature is further leveraged to enable semi-autonomous operations, allowing a human operator to assist the robotic counterpart in completing harvesting tasks. Finally, the obtained results are validated through extensive testing conducted first in a laboratory environment to prove individual functionalities, then in a real vineyard, encompassing both autonomous and semi-autonomous grape harvesting operations.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"163 ","pages":"Article 106394"},"PeriodicalIF":5.4,"publicationDate":"2025-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144185674","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}

{"title":"Time-delay assisted mechanism and adaptive LSTM hybrid train braking model of heavy haul trains","authors":"Qiang Liu ,&nbsp;Kexuan Xu ,&nbsp;Yating Fu ,&nbsp;Jiang Liu ,&nbsp;Ling Liu","doi":"10.1016/j.conengprac.2025.106392","DOIUrl":"10.1016/j.conengprac.2025.106392","url":null,"abstract":"<div><div>The train braking model (TBM) that describes the dynamic relations of operation speed, mileage, and control force is essential for achieving stable operation and precise stopping of heavy haul trains (HHTs). However, it is difficult to establish the TBM of HHTs due to complex characteristics: (i) the long body and air braking process of the HHTs may lead to unexpected time-delays of control force; and (ii) there are significant unmodeled dynamics caused by rough tracks and external poor environment. Traditional TBM does not take into account the unmodeled dynamics and time-delays caused by air transmission during braking. To address these issues, this study proposes a data mechanism hybrid modeling strategy, which incorporates a braking time-delay assisted mechanism model and an adaptive long and short-term memory (LSTM) model. A new Bayesian optimization based time-delay estimation method is first proposed to determine unknown time-delays of each carriage and the estimated time-delays are incorporated to generate the multi-point-mass kinetic mechanism model. Moreover, the error of the mechanism-driven model is adaptively compensated by a sliding window LSTM model to conduct the unmodeled dynamics. The effectiveness of the proposed method is demonstrated using the field data.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"163 ","pages":"Article 106392"},"PeriodicalIF":5.4,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144167807","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}

{"title":"Optimization-based trajectory planning for autonomous vehicles in scenarios with multiple reference lines","authors":"Xi Zhang ,&nbsp;Zheng Zang ,&nbsp;Xinran Chen ,&nbsp;Yaomin Lu ,&nbsp;Jianyong Qi ,&nbsp;Jianwei Gong","doi":"10.1016/j.conengprac.2025.106407","DOIUrl":"10.1016/j.conengprac.2025.106407","url":null,"abstract":"<div><div>Enabling autonomous vehicles to adhere to the reference line as much as possible is a regulatory consensus that ensures predictability in vehicle’s behavior within mixed traffic flow, thereby reducing the risk of accidents. State-of-the-art Cartesian-based trajectory planning methods overcome limitations inherent in traditional Frenet-based approaches, particularly regarding constraint violations in high-curvature scenarios. However, these methods encounter theoretical challenges in handling reference line constraints, hindering their direct application in road scenarios. In this paper, an optimization-based trajectory planning method in Cartesian Frame is proposed to address road scenarios with multiple reference lines. The main work can be summarized into three parts. In the first part, The on-road trajectory planning task is reframed as an Optimal Control Problem (OCP) with multiple-reference lines constraints (MRLC), where the nominal OCP ensures safety and feasibility. The incorporation of nominal MRLC ensures that the generated trajectory closely follows the reference lines while maintaining the trajectory’s longitudinal deformation capability. However, nominal MRLC, which involves a minimum optimization problem when describing the distance between the trajectory and reference lines, cannot be directly embedded into an OCP. To address this issue, in the second part, an approximate calculation method is proposed to explicitly describe MRLC. The MRLC constructed in this way not only preserves the trajectory’s good deformability but also handles the generation of continuous lane-changing trajectories. In the third part, an improved dynamic programming approach tailored for multi-reference line scenarios is proposed, providing high-quality initial guesses for OCP-MRLC to enhance its convergence speed. Finally, comprehensive benchmarking against state-of-the-art methods is presented, showcasing the significance of the proposed OCP-MRLC in meeting reference line constraints and ensuring trajectory quality. Experiments conducted with real-world datasets validate the practicality of the algorithm.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"163 ","pages":"Article 106407"},"PeriodicalIF":5.4,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144167806","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}

{"title":"Event-triggered active return-to-center control for steer-by-wire system by a time-window algorithmic framework","authors":"Xiaodong Wu ,&nbsp;Shuhan Liu ,&nbsp;Jinjie Wang ,&nbsp;Baoran Shi","doi":"10.1016/j.conengprac.2025.106382","DOIUrl":"10.1016/j.conengprac.2025.106382","url":null,"abstract":"<div><div>Since the mechanical decoupling of the steer-by-wire system, the self-aligning torque from the vehicle tire cannot be transmitted to the steering wheel. As a result, the steering wheel does not automatically return to the center position after the driver releases the steering wheel. In order to design an active return-to-center (RTC) steering system, this paper proposes an event-triggered active RTC control for the steer-by-wire system by a time-window algorithmic framework. The active return state is worked by the slide mode control to track the steering wheel RTC speed reference. For the SBW system, an RTC speed reference model is designed to obtain referable kinematic characteristics of an ideal mechanical steering system. Additionally, an active return transition module for RTC state switching is designed by a time-state sequence transfer mechanism, which is used to reduce the jerking sensation during the transition between normal steering and active returning states. To evaluate the effectiveness of the proposed algorithms, a hardware-in-the-loop test platform with a steer-by-wire system is established. Based on the different experimental scenarios, the performance of the proposed active RTC control approach is verified by comparative analysis.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"163 ","pages":"Article 106382"},"PeriodicalIF":5.4,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144134656","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}