ISA transactions最新文献_第7页

One-class transformer-based feature disentanglement with clustering-driven semisupervised learning for the fault diagnosis of reciprocating machinery 基于一类变压器的特征解纠集与聚类驱动半监督学习的往复机械故障诊断。

IF 6.5 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

ISA transactions

Pub Date : 2025-12-01 DOI: 10.1016/j.isatra.2025.10.032

Diego Cabrera , Yuliang Feng , Fernando Sancho , Mariela Cerrada , René-Vinicio Sánchez , Chuan Li

In industrial machinery, fault diagnosis is crucial for preventing significant economic losses and ensuring operational safety. Traditional approaches often rely on extensive datasets containing both healthy and faulty data across various operating conditions, which can be challenging to obtain, especially for high-tech equipment that operates reliably for extended periods. This paper presents a novel decoupled transformer-based domain generalization approach that addresses this limitation by leveraging exclusively healthy operational data, thereby significantly simplifying deployment compared to existing methods that require comprehensive datasets of both healthy and faulty data. Our method employs a clustering-based semi-supervised learning procedure, which not only decouples domain generalization from fault diagnosis training but also efficiently operates without domain information during inference. Notably, our proposal requires only a small amount of labeled data under faulty categories, which can become available after the domain-generalization phase has been completed, further enhancing practical applicability. Experimental results demonstrate promising performance in 46 domain generalization tasks involving a reciprocating compressor with valve-related faults, highlighting the practical industrial value and deployment simplicity of our proposed method.

在工业机械中，故障诊断对于防止重大经济损失和保证运行安全至关重要。传统的方法通常依赖于大量的数据集，其中包含各种运行条件下的健康和故障数据，这些数据集很难获得，特别是对于长时间可靠运行的高科技设备。本文提出了一种新的基于解耦变压器的域泛化方法，该方法通过仅利用健康运行数据来解决这一限制，从而与需要健康和故障数据的综合数据集的现有方法相比，大大简化了部署。该方法采用了一种基于聚类的半监督学习方法，不仅将故障诊断训练与领域泛化解耦，而且在推理过程中可以有效地进行无领域信息的操作。值得注意的是，我们的建议只需要少量错误类别下的标记数据，这些数据可以在领域泛化阶段完成后使用，进一步增强了实用性。实验结果表明，该方法在包含阀门相关故障的往复式压缩机的46个领域泛化任务中具有良好的性能，突出了该方法的实际工业价值和部署简单性。

{"title":"One-class transformer-based feature disentanglement with clustering-driven semisupervised learning for the fault diagnosis of reciprocating machinery","authors":"Diego Cabrera , Yuliang Feng , Fernando Sancho , Mariela Cerrada , René-Vinicio Sánchez , Chuan Li","doi":"10.1016/j.isatra.2025.10.032","DOIUrl":"10.1016/j.isatra.2025.10.032","url":null,"abstract":"<div><div>In industrial machinery, fault diagnosis is crucial for preventing significant economic losses and ensuring operational safety. Traditional approaches often rely on extensive datasets containing both healthy and faulty data across various operating conditions, which can be challenging to obtain, especially for high-tech equipment that operates reliably for extended periods. This paper presents a novel decoupled transformer-based domain generalization approach that addresses this limitation by leveraging exclusively healthy operational data, thereby significantly simplifying deployment compared to existing methods that require comprehensive datasets of both healthy and faulty data. Our method employs a clustering-based semi-supervised learning procedure, which not only decouples domain generalization from fault diagnosis training but also efficiently operates without domain information during inference. Notably, our proposal requires only a small amount of labeled data under faulty categories, which can become available after the domain-generalization phase has been completed, further enhancing practical applicability. Experimental results demonstrate promising performance in 46 domain generalization tasks involving a reciprocating compressor with valve-related faults, highlighting the practical industrial value and deployment simplicity of our proposed method.</div></div>","PeriodicalId":14660,"journal":{"name":"ISA transactions","volume":"167 ","pages":"Pages 1925-1937"},"PeriodicalIF":6.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145380604","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

Resilient output containment control of heterogeneous linear parameter-varying multi-agent systems under external disturbances and composite attacks 外部干扰和复合攻击下异构线性变参数多智能体系统的弹性输出控制。

IF 6.5 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

ISA transactions

Pub Date : 2025-12-01 DOI: 10.1016/j.isatra.2025.10.013

Yanjie Liu, Zhi Li

This paper investigates the resilient output containment control problem of heterogeneous linear parameter-varying (LPV) multi-agent systems facing external disturbances and composite attacks, such as denial-of-service (DoS) and false-data injection (FDI) attacks. DoS attacks target communication channels, preventing followers from directly accessing the information of the exosystem and leader. To address this issue, resilient distributed observers and estimators are constructed to asymptotically estimate the matrix and state of the exosystem and leader, respectively. Based on the reconstructed leader dynamics, a decentralized solver is designed to solve an LPV output regulation equation. To reduce the effects of FDI attacks on follower information, a local adaptive compensator is constructed. Considering the two situations where the follower’s states are either unavailable or available, two corresponding control protocols are proposed to ensure that the output of each follower converges to the convex hull spanned by the outputs of the leaders. Finally, three simulation examples are introduced to demonstrate the effectiveness of obtained results.

研究了异构线性变参数（LPV）多智能体系统面对外部干扰和复合攻击（如拒绝服务（DoS）和假数据注入（FDI）攻击）时的弹性输出遏制控制问题。DoS攻击的目标是通信渠道，阻止追随者直接访问外部系统和领导者的信息。为了解决这一问题，构造了弹性分布式观测器和估计器，分别对外系统和前导系统的矩阵和状态进行渐近估计。基于重构的领导者动力学，设计了一个分散求解器来求解LPV输出调节方程。为了减少FDI攻击对跟踪信息的影响，构造了局部自适应补偿器。针对follower状态不可用和可用的两种情况，提出了两种相应的控制协议，以保证follower的输出收敛于leader输出所跨越的凸包。最后，通过三个仿真实例验证了所得结果的有效性。

{"title":"Resilient output containment control of heterogeneous linear parameter-varying multi-agent systems under external disturbances and composite attacks","authors":"Yanjie Liu, Zhi Li","doi":"10.1016/j.isatra.2025.10.013","DOIUrl":"10.1016/j.isatra.2025.10.013","url":null,"abstract":"<div><div>This paper investigates the resilient output containment control problem of heterogeneous linear parameter-varying (LPV) multi-agent systems facing external disturbances and composite attacks, such as denial-of-service (DoS) and false-data injection (FDI) attacks. DoS attacks target communication channels, preventing followers from directly accessing the information of the exosystem and leader. To address this issue, resilient distributed observers and estimators are constructed to asymptotically estimate the matrix and state of the exosystem and leader, respectively. Based on the reconstructed leader dynamics, a decentralized solver is designed to solve an LPV output regulation equation. To reduce the effects of FDI attacks on follower information, a local adaptive compensator is constructed. Considering the two situations where the follower’s states are either unavailable or available, two corresponding control protocols are proposed to ensure that the output of each follower converges to the convex hull spanned by the outputs of the leaders. Finally, three simulation examples are introduced to demonstrate the effectiveness of obtained results.</div></div>","PeriodicalId":14660,"journal":{"name":"ISA transactions","volume":"167 ","pages":"Pages 1264-1276"},"PeriodicalIF":6.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145446990","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

High-gain fuzzy observer based quantized input control for uncertain nonlinear systems with sensor and actuator failures 基于高增益模糊观测器的不确定非线性系统的量化输入控制。

IF 6.5 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

ISA transactions

Pub Date : 2025-12-01 DOI: 10.1016/j.isatra.2025.07.059

Yue Sun , Chuang Gao , Yonghui Yang , Libing Wu

In this paper, we propose a control scheme for a class of nonlinear systems with both sensor and actuator failures. Different from the published results, a novel compensation failure gain mechanism is proposed, where an adaptive compensation term is applied to the high gain fuzzy observer to cope with the influence of sensor failures on the system. Concurrently, the command filtered technique and quantitative input control are taken into account to simplify the design process and improve the utilization of communication resources. The proposed scheme ensures that the output of system follows a reference signal whether the system experiences a failure or not. Finally, the practicality and advantages of the controller are illustrated through two simulation examples.

本文针对一类传感器和执行器均失效的非线性系统，提出了一种控制方案。与已发表的结果不同，提出了一种新的补偿失效增益机制，在高增益模糊观测器中加入自适应补偿项，以应对传感器失效对系统的影响。同时考虑了命令滤波技术和定量输入控制，简化了设计过程，提高了通信资源的利用率。该方案保证了无论系统是否发生故障，系统的输出都遵循参考信号。最后，通过两个仿真实例说明了该控制器的实用性和优越性。

引用次数: 0

Superharmonic resonance study and fault diagnosis induced by slant crack in rotor-bearing system 转子-轴承系统斜裂纹诱发的超谐波共振研究及故障诊断。

IF 6.5 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

ISA transactions

Pub Date : 2025-12-01 DOI: 10.1016/j.isatra.2025.07.056

Weipeng Sun , Kaicheng Zhang , Shen Hu , Daoli Zhao , Yusen Jiang , Wei Ma , Qiuhong Huang

Crack faults in rotor-bearing systems can cause major safety hazards, which makes it necessary to monitor and diagnose them promptly. This paper investigates the crack fault mechanism and further proposes a diagnosis between crack faults and others. A cracked stiffness model was developed based on fracture mechanics, and the cracked rotor was analyzed in detail for stresses. The multi-failure rotor test bench was established and related experiments were carried out to verify the model’s accuracy. The results show that the critical rotational speed decreases obviously as the crack angle increases for crack depth ratios from 0.8 to 1. For the slant cracked rotor-bearing system with crack depth coefficient of a/R (Ratio of crack depth to shaft radius) = 1 and angle of 45

^{\circ}

, superharmonic resonance and horizontal resonance were observed around 1/3

ω_{n}

(critical speed), and the resonance peaks were hysteretic in horizontal direction. Based on the harmonic resonance characteristics, three neural networks, Back Propagation (BP), Kernel Extreme Learning Machine (KELM) and Random Forest (RF), are used to classify different faults including cracks, and they are optimized by Sparrow Search Algorithm (SSA). The results show that all three models have high classification accuracy, while the optimized KELM model is the most efficient.

转子轴承系统的裂纹故障会造成重大的安全隐患，需要对其进行及时的监测和诊断。本文对裂纹故障机理进行了研究，并进一步提出了裂纹故障与其它故障的诊断方法。基于断裂力学建立了裂纹刚度模型，并对裂纹转子进行了详细的应力分析。建立了多故障转子试验台，并进行了相关实验，验证了模型的准确性。结果表明：裂纹深度比为0.8 ~ 1时，随着裂纹角的增大，临界转速明显降低；对于裂纹深度系数为a/R（裂纹深度与轴半径之比）= 1、角为45°的斜裂纹转子-轴承系统，在1/3ωn（临界转速）附近出现超谐波共振和水平共振，且共振峰在水平方向上存在滞后。基于谐波共振特性，采用BP （Back Propagation）、KELM （Kernel Extreme Learning Machine）和RF （Random Forest）三种神经网络对包括裂纹在内的不同故障进行分类，并采用SSA （Sparrow Search Algorithm）对其进行优化。结果表明，三种模型均具有较高的分类精度，其中优化后的KELM模型分类效率最高。

{"title":"Superharmonic resonance study and fault diagnosis induced by slant crack in rotor-bearing system","authors":"Weipeng Sun , Kaicheng Zhang , Shen Hu , Daoli Zhao , Yusen Jiang , Wei Ma , Qiuhong Huang","doi":"10.1016/j.isatra.2025.07.056","DOIUrl":"10.1016/j.isatra.2025.07.056","url":null,"abstract":"<div><div>Crack faults in rotor-bearing systems can cause major safety hazards, which makes it necessary to monitor and diagnose them promptly. This paper investigates the crack fault mechanism and further proposes a diagnosis between crack faults and others. A cracked stiffness model was developed based on fracture mechanics, and the cracked rotor was analyzed in detail for stresses. The multi-failure rotor test bench was established and related experiments were carried out to verify the model’s accuracy. The results show that the critical rotational speed decreases obviously as the crack angle increases for crack depth ratios from 0.8 to 1. For the slant cracked rotor-bearing system with crack depth coefficient of a/R (Ratio of crack depth to shaft radius) = 1 and angle of 45<span><math><msup><mspace></mspace><mrow><mo>∘</mo></mrow></msup></math></span>, superharmonic resonance and horizontal resonance were observed around 1/3<span><math><msub><mi>ω</mi><mi>n</mi></msub></math></span> (critical speed), and the resonance peaks were hysteretic in horizontal direction. Based on the harmonic resonance characteristics, three neural networks, Back Propagation (BP), Kernel Extreme Learning Machine (KELM) and Random Forest (RF), are used to classify different faults including cracks, and they are optimized by Sparrow Search Algorithm (SSA). The results show that all three models have high classification accuracy, while the optimized KELM model is the most efficient.</div></div>","PeriodicalId":14660,"journal":{"name":"ISA transactions","volume":"167 ","pages":"Pages 761-774"},"PeriodicalIF":6.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144812756","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

Finite-time moving target circumnavigation based on dual sliding-mode estimator using bearing-only measurements 基于方位测量的双滑模估计的有限时间运动目标环球导航。

IF 6.5 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

ISA transactions

Pub Date : 2025-12-01 DOI: 10.1016/j.isatra.2025.07.043

Yingjing Shi, Rui Li, Ce Yu

Utilizing incomplete measurements to localize and circumnavigate a moving target in finite time is still a challenging problem. This paper presents an innovative sliding-mode control framework to tackle this issue, which combines a single parameter estimator with a control protocol based on bearing measurements. For a stationary target, the agent will eventually move on a circle with the specified radius, adhering to a maximum time constraint for localization and circumnavigation. In the case of the moving target with unknown speed, the agent achieves the circumnavigation in a ring, and relationship between the system parameters and the speed of the target is established. Additionally, the paper outlines the circumnavigation zone and the quantitative relationship between this zone and the system parameters. The proposed solution’s effectiveness is demonstrated through extensive numerical simulations and a physical experiment.

利用不完全测量在有限时间内对运动目标进行定位和绕航仍然是一个具有挑战性的问题。本文提出了一种创新的滑模控制框架来解决这一问题，该框架将单参数估计器与基于轴承测量的控制协议相结合。对于静止目标，agent最终将在指定半径的圆周上运动，并在最大时间约束下进行定位和环游。在运动目标速度未知的情况下，智能体实现环形绕航，建立了系统参数与目标速度的关系。此外，本文还概述了环航区及其与系统参数之间的定量关系。通过大量的数值模拟和物理实验证明了该方法的有效性。

引用次数: 0

Anti-disturbance trajectory tracking event-triggered control for underactuated surface vessels: A novel switching self-tuning mechanism 欠驱动水面舰船抗扰动轨迹跟踪事件触发控制：一种新型开关自调谐机制。

IF 6.5 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

ISA transactions

Pub Date : 2025-12-01 DOI: 10.1016/j.isatra.2025.08.019

Simeng Song , Zhilin Liu , Shouzheng Yuan , Lin Yang , Yingkai Ma

Prescribed performance control has garnered significant interest for its capability to predefine system performance indicators. However, some unresolved challenges persist in prescribed performance control for underactuated surface vessels (USVs) under disturbances and input saturation. To address these issues, this paper proposes a fixed-time trajectory tracking scheme for underactuated surface vessels, where external disturbances, input saturation, and prescribed performance are considered. Specifically, the underactuated control challenge is first solved by a coordinate system transformation. A smooth saturation model addresses the actuator input saturation. Then, a dynamic event-triggering mechanism is proposed to reduce the unnecessary communication burden. Meanwhile, a non-fragile prescribed performance function is designed to avoid the serious degradation of the tracking accuracy caused by the trigger mechanism and to ensure that the tracking error converges within a prescribed range even when the desired trajectory switches. Next, we employ a command filter to avoid the "explosion of complexity" and design the compensation system for the filtering error to guarantee control accuracy. Furthermore, by designing a switching self-tuning mechanism, the negative effect of the uncertainty term on the USV can be compensated in real time, requiring no a priori knowledge of uncertainty terms. Finally, based on the Lyapunov theory, we demonstrate that our scheme is theoretically reasonable. Further simulations verify that the underactuated surface vessel can still guarantee the prescribed tracking performance under our scheme, even under external disturbances and input saturation, while significantly reducing the unnecessary communication burden.

规定的性能控制因其预先定义系统性能指标的能力而获得了极大的兴趣。然而，在干扰和输入饱和的情况下，欠驱动水面船舶（usv）的规定性能控制仍然存在一些未解决的挑战。为了解决这些问题，本文提出了一种针对欠驱动水面舰船的固定时间轨迹跟踪方案，该方案考虑了外部干扰、输入饱和和规定性能。具体地说，欠驱动控制挑战首先通过坐标系变换来解决。平滑饱和模型处理致动器输入饱和。然后，提出了一种动态事件触发机制，以减少不必要的通信负担。同时，设计了非脆弱的规定性能函数，避免了触发机构对跟踪精度的严重影响，保证了在期望轨迹切换时跟踪误差收敛在规定范围内。其次，我们采用命令滤波来避免“复杂度爆炸”，并设计了滤波误差补偿系统以保证控制精度。此外，通过设计切换自调谐机构，可以实时补偿不确定性项对无人潜航器的负面影响，而无需先验的不确定性项知识。最后，基于李雅普诺夫理论，我们证明了我们的方案在理论上是合理的。进一步的仿真验证了在我们的方案下，欠驱动水面舰船即使在外部干扰和输入饱和的情况下仍能保证规定的跟踪性能，同时显著减少了不必要的通信负担。

{"title":"Anti-disturbance trajectory tracking event-triggered control for underactuated surface vessels: A novel switching self-tuning mechanism","authors":"Simeng Song , Zhilin Liu , Shouzheng Yuan , Lin Yang , Yingkai Ma","doi":"10.1016/j.isatra.2025.08.019","DOIUrl":"10.1016/j.isatra.2025.08.019","url":null,"abstract":"<div><div>Prescribed performance control has garnered significant interest for its capability to predefine system performance indicators. However, some unresolved challenges persist in prescribed performance control for underactuated surface vessels (USVs) under disturbances and input saturation. To address these issues, this paper proposes a fixed-time trajectory tracking scheme for underactuated surface vessels, where external disturbances, input saturation, and prescribed performance are considered. Specifically, the underactuated control challenge is first solved by a coordinate system transformation. A smooth saturation model addresses the actuator input saturation. Then, a dynamic event-triggering mechanism is proposed to reduce the unnecessary communication burden. Meanwhile, a non-fragile prescribed performance function is designed to avoid the serious degradation of the tracking accuracy caused by the trigger mechanism and to ensure that the tracking error converges within a prescribed range even when the desired trajectory switches. Next, we employ a command filter to avoid the \"explosion of complexity\" and design the compensation system for the filtering error to guarantee control accuracy. Furthermore, by designing a switching self-tuning mechanism, the negative effect of the uncertainty term on the USV can be compensated in real time, requiring no a priori knowledge of uncertainty terms. Finally, based on the Lyapunov theory, we demonstrate that our scheme is theoretically reasonable. Further simulations verify that the underactuated surface vessel can still guarantee the prescribed tracking performance under our scheme, even under external disturbances and input saturation, while significantly reducing the unnecessary communication burden.</div></div>","PeriodicalId":14660,"journal":{"name":"ISA transactions","volume":"167 ","pages":"Pages 155-167"},"PeriodicalIF":6.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144984155","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 reliable UAV tracking system with online re-detection network 具有在线再检测网络的可靠无人机跟踪系统。

IF 6.5 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

ISA transactions

Pub Date : 2025-12-01 DOI: 10.1016/j.isatra.2025.08.045

Xin Lu , Yulong Duan , Fusheng Li

Failures in long-term tracking have been frequently reported, posing significant challenges for the practical implementation of UAV tracking systems. Previous research has often employed a metric based on the current tracking state to assess reliability, coupled with a time-consuming re-detection network designed to recover the lost target. However, this approach lacks sufficient robustness and flexibility when dealing with unknown factors present in complex tracking scenarios. To address this issue, we propose a reliable UAV tracking system that incorporates a temporal consistency deviation index and an online re-detection network. The former takes into account the temporal consistency of consecutive frames and estimates tracking uncertainty using the confidence deviation caused by interference factors. The latter applies a series of linear transformations, inspired by Ghost operations, to reduce computational load and expedite inference. Additionally, a channel-spatial attention module is integrated into the re-detection component to enhance the extraction of valuable feature information. Results from the long-term dataset UAV20L demonstrate that the proposed algorithm outperforms the baseline trackers, particularly in scenarios involving full occlusion and viewpoint change situations. Furthermore, a physically constructed UAV tracking system is utilized to validate the effectiveness and real-time performance of the algorithm in handling occlusion events. Our code is released at https://anonymous.4open.science/r/Tracking-Redetection-F06F.

长期跟踪的失败经常被报道，对无人机跟踪系统的实际实施构成重大挑战。以前的研究通常采用基于当前跟踪状态的度量来评估可靠性，并结合耗时的重新检测网络来恢复丢失的目标。然而，这种方法在处理复杂跟踪场景中存在的未知因素时，缺乏足够的鲁棒性和灵活性。为了解决这一问题，我们提出了一种可靠的无人机跟踪系统，该系统结合了时间一致性偏差指标和在线再检测网络。前者考虑连续帧的时间一致性，利用干扰因素引起的置信度偏差估计跟踪不确定性。后者应用一系列线性变换，灵感来自Ghost操作，以减少计算负荷和加快推理。此外，在重检测组件中集成了通道空间注意模块，以增强对有价值特征信息的提取。来自长期数据集UAV20L的结果表明，该算法优于基线跟踪器，特别是在涉及完全遮挡和视点变化的情况下。最后，利用实际构建的无人机跟踪系统验证了该算法处理遮挡事件的有效性和实时性。我们的代码发布在https://anonymous.4open.science/r/Tracking-Redetection-F06F。

{"title":"A reliable UAV tracking system with online re-detection network","authors":"Xin Lu , Yulong Duan , Fusheng Li","doi":"10.1016/j.isatra.2025.08.045","DOIUrl":"10.1016/j.isatra.2025.08.045","url":null,"abstract":"<div><div>Failures in long-term tracking have been frequently reported, posing significant challenges for the practical implementation of UAV tracking systems. Previous research has often employed a metric based on the current tracking state to assess reliability, coupled with a time-consuming re-detection network designed to recover the lost target. However, this approach lacks sufficient robustness and flexibility when dealing with unknown factors present in complex tracking scenarios. To address this issue, we propose a reliable UAV tracking system that incorporates a temporal consistency deviation index and an online re-detection network. The former takes into account the temporal consistency of consecutive frames and estimates tracking uncertainty using the confidence deviation caused by interference factors. The latter applies a series of linear transformations, inspired by Ghost operations, to reduce computational load and expedite inference. Additionally, a channel-spatial attention module is integrated into the re-detection component to enhance the extraction of valuable feature information. Results from the long-term dataset UAV20L demonstrate that the proposed algorithm outperforms the baseline trackers, particularly in scenarios involving full occlusion and viewpoint change situations. Furthermore, a physically constructed UAV tracking system is utilized to validate the effectiveness and real-time performance of the algorithm in handling occlusion events. Our code is released at <span><span>https://anonymous.4open.science/r/Tracking-Redetection-F06F</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":14660,"journal":{"name":"ISA transactions","volume":"167 ","pages":"Pages 941-954"},"PeriodicalIF":6.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145002259","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

Safety-constrained transient control for aero-engines: A data-driven diffeomorphic ADP framework 航空发动机安全约束的瞬态控制：数据驱动的差分ADP框架。

IF 6.5 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

ISA transactions

Pub Date : 2025-12-01 DOI: 10.1016/j.isatra.2025.08.004

Shuoshuo Liu , Tao Sun , Peng Li , Ning Xu , Xudong Zhao

To enable safety-constrained control of aero-engines under wide-range transient conditions, a novel data-driven diffeomorphic adaptive dynamic programming (ADP) framework is developed to explicitly enforce the state and input safety constraints. The approach begins by employing diffeomorphic transformations coupled with a dynamic control law to effectively eliminate explicit state constraints. This transformation reformulates the original constrained problem into an optimal control framework subject solely to virtual input saturation. Subsequently, to handle input constraints, an inverse hyperbolic tangent barrier function is designed, thereby facilitating the application of Bellman’s optimality principle. Leveraging this framework, a data-driven policy iteration method is developed to efficiently approximate the solution of the Hamilton-Jacobi-Bellman equation and derive the optimal control law. Rigorous theoretical analysis confirms the feasibility and stability of the proposed approach. Extensive simulations on a JT9D engine validate the proposed method’s capability in achieving safe and rapid operating condition transitions. Compared to traditional PID control and particle swarm optimization based model predictive control, the proposed method achieves superior control performance, reduces the acceleration time by 24.6 %, and significantly lowers computational complexity. This research presents a promising and practical solution for advanced aero-engine control.

为了实现航空发动机在大范围瞬态条件下的安全约束控制，提出了一种数据驱动的差分自适应动态规划（ADP）框架，以显式执行状态约束和输入安全约束。该方法首先采用微分同态变换与动态控制律相结合，以有效地消除显式状态约束。这种转换将原来的约束问题重新表述为仅受虚拟输入饱和影响的最优控制框架。随后，为了处理输入约束，设计了一个逆双曲正切势垒函数，便于Bellman最优性原理的应用。利用该框架，开发了一种数据驱动的策略迭代方法，以有效地逼近Hamilton-Jacobi-Bellman方程的解并推导出最优控制律。严格的理论分析证实了该方法的可行性和稳定性。在JT9D发动机上进行的大量仿真验证了该方法实现安全和快速工况转换的能力。与传统的PID控制和基于粒子群优化的模型预测控制相比，该方法具有更好的控制性能，加速时间缩短24.6 %，计算复杂度显著降低。该研究为先进航空发动机控制提供了一种有前途的实用解决方案。

{"title":"Safety-constrained transient control for aero-engines: A data-driven diffeomorphic ADP framework","authors":"Shuoshuo Liu , Tao Sun , Peng Li , Ning Xu , Xudong Zhao","doi":"10.1016/j.isatra.2025.08.004","DOIUrl":"10.1016/j.isatra.2025.08.004","url":null,"abstract":"<div><div>To enable safety-constrained control of aero-engines under wide-range transient conditions, a novel data-driven diffeomorphic adaptive dynamic programming (ADP) framework is developed to explicitly enforce the state and input safety constraints. The approach begins by employing diffeomorphic transformations coupled with a dynamic control law to effectively eliminate explicit state constraints. This transformation reformulates the original constrained problem into an optimal control framework subject solely to virtual input saturation. Subsequently, to handle input constraints, an inverse hyperbolic tangent barrier function is designed, thereby facilitating the application of Bellman’s optimality principle. Leveraging this framework, a data-driven policy iteration method is developed to efficiently approximate the solution of the Hamilton-Jacobi-Bellman equation and derive the optimal control law. Rigorous theoretical analysis confirms the feasibility and stability of the proposed approach. Extensive simulations on a JT9D engine validate the proposed method’s capability in achieving safe and rapid operating condition transitions. Compared to traditional PID control and particle swarm optimization based model predictive control, the proposed method achieves superior control performance, reduces the acceleration time by 24.6 %, and significantly lowers computational complexity. This research presents a promising and practical solution for advanced aero-engine control.</div></div>","PeriodicalId":14660,"journal":{"name":"ISA transactions","volume":"167 ","pages":"Pages 144-154"},"PeriodicalIF":6.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145002262","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

Design and complexity analysis of marginalized Gaussian filtering for nonlinear systems with multi-step random measurement delays and packet dropouts 具有多步随机测量延迟和丢包的非线性系统边缘高斯滤波的设计与复杂性分析。

IF 6.5 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

ISA transactions

Pub Date : 2025-12-01 DOI: 10.1016/j.isatra.2025.08.022

Yuxin Zhang , Yunqi Chen , Zhibin Yan , Zheyuan Wang

For nonlinear systems with multi-step random measurement delays and packet dropouts, the existing state-augmented Gaussian filtering (SAGF) has a high computational complexity in the case of large delay steps as the dimension of augmented state increases with delay step. To overcome this drawback, this paper firstly points out that there exist analytical linear substructures in the augmented systems. Then by applying the marginalization technique to these substructures, a marginalized Gaussian filtering (MGF) is developed, where integrals are w.r.t. a single original state rather than w.r.t. the augmented state. Further, on the premise that sigma-point methods are applied to integrals in both SAGF and MGF, a quantitative computational complexity analysis is provided by counting floating-point operations, showing that MGF has a lower theoretical computational complexity than SAGF. Finally, a simulation experiment on target tracking illustrates that MGF has the same estimation accuracy as SAGF, but requires less running time.

对于具有多步随机测量延迟和丢包的非线性系统，现有的状态增强高斯滤波（SAGF）在大延迟步长的情况下计算复杂度很高，因为随着延迟步长的增加，增强状态的维数也会增加。为了克服这一缺点，本文首先指出增广系统中存在解析线性子结构。然后将边缘化技术应用到这些子结构中，提出了一种边缘高斯滤波（MGF）方法，该方法中积分只对单个原始状态进行加权，而不是对增广状态进行加权。此外，在SAGF和MGF均采用sigma点方法进行积分的前提下，通过对浮点运算进行计数，对计算复杂度进行了定量分析，结果表明MGF的理论计算复杂度低于SAGF。最后，通过对目标跟踪的仿真实验表明，MGF具有与SAGF相同的估计精度，但所需的运行时间更短。

{"title":"Design and complexity analysis of marginalized Gaussian filtering for nonlinear systems with multi-step random measurement delays and packet dropouts","authors":"Yuxin Zhang , Yunqi Chen , Zhibin Yan , Zheyuan Wang","doi":"10.1016/j.isatra.2025.08.022","DOIUrl":"10.1016/j.isatra.2025.08.022","url":null,"abstract":"<div><div>For nonlinear systems with multi-step random measurement delays and packet dropouts, the existing state-augmented Gaussian filtering (SAGF) has a high computational complexity in the case of large delay steps as the dimension of augmented state increases with delay step. To overcome this drawback, this paper firstly points out that there exist analytical linear substructures in the augmented systems. Then by applying the marginalization technique to these substructures, a marginalized Gaussian filtering (MGF) is developed, where integrals are w.r.t. a single original state rather than w.r.t. the augmented state. Further, on the premise that sigma-point methods are applied to integrals in both SAGF and MGF, a quantitative computational complexity analysis is provided by counting floating-point operations, showing that MGF has a lower theoretical computational complexity than SAGF. Finally, a simulation experiment on target tracking illustrates that MGF has the same estimation accuracy as SAGF, but requires less running time.</div></div>","PeriodicalId":14660,"journal":{"name":"ISA transactions","volume":"167 ","pages":"Pages 513-528"},"PeriodicalIF":6.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144984204","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

Dynamic surface-based distributed practical predefined-time cooperative control for flight formation of a novel small tandem-rotor wheeled UAV 一种新型小型串联旋翼轮式无人机飞行编队基于动态表面的分布式实用预定义时间协同控制。

IF 6.5 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

ISA transactions

Pub Date : 2025-12-01 DOI: 10.1016/j.isatra.2025.08.053

Xiaolu Li, Changqing Wang, Yong Guo, Aijun Li

A novel practical predefined-time sliding mode control strategy is proposed for the flight formation of a small tandem-rotor wheeled UAV (TRW-UAV) with unknown upper bound external disturbances and uncertainties in this paper. Firstly, a new predefined-time sliding mode surface is proposed to guide all errors of the position and velocity loops to converge to the origin in a predefined-time. Furthermore, a dynamic surface control approach is utilized to circumvent the higher-order differentiation when controlling the actuator loop. Secondly, a predefined-time adaptive law is designed for estimating external disturbances and uncertainties during the controller design process to construct a distributed practical predefined-time formation cooperative control strategy. Thirdly, a novel practical predefined-time criterion is utilized to rigorously demonstrate the stability of the proposed control strategy. Finally, the simulation results indicate that the proposed control strategy can deliver the practical predefined-time control when there are external disturbances and model uncertainties, and with higher convergence accuracies compared to some of the existing methods.

针对具有未知上界外部干扰和不确定性的小型串联旋翼轮式无人机（TRW-UAV）的飞行编队问题，提出了一种新颖实用的预定义时间滑模控制策略。首先，提出了一种新的预定义时间滑模曲面，用于引导位置和速度环路的所有误差在预定义时间收敛到原点；此外，在控制作动器回路时，采用了一种动态曲面控制方法来规避高阶微分。其次，设计了一种预定义时间自适应律，用于估计控制器设计过程中的外部干扰和不确定性，构建了一种实用的分布式预定义时间编队协同控制策略；第三，利用一种新颖实用的预定义时间判据严格证明了所提控制策略的稳定性。仿真结果表明，在存在外部干扰和模型不确定性的情况下，所提出的控制策略能够实现实际的预定义时间控制，并且与现有的一些方法相比具有更高的收敛精度。

{"title":"Dynamic surface-based distributed practical predefined-time cooperative control for flight formation of a novel small tandem-rotor wheeled UAV","authors":"Xiaolu Li, Changqing Wang, Yong Guo, Aijun Li","doi":"10.1016/j.isatra.2025.08.053","DOIUrl":"10.1016/j.isatra.2025.08.053","url":null,"abstract":"<div><div>A novel practical predefined-time sliding mode control strategy is proposed for the flight formation of a small tandem-rotor wheeled UAV (TRW-UAV) with unknown upper bound external disturbances and uncertainties in this paper. Firstly, a new predefined-time sliding mode surface is proposed to guide all errors of the position and velocity loops to converge to the origin in a predefined-time. Furthermore, a dynamic surface control approach is utilized to circumvent the higher-order differentiation when controlling the actuator loop. Secondly, a predefined-time adaptive law is designed for estimating external disturbances and uncertainties during the controller design process to construct a distributed practical predefined-time formation cooperative control strategy. Thirdly, a novel practical predefined-time criterion is utilized to rigorously demonstrate the stability of the proposed control strategy. Finally, the simulation results indicate that the proposed control strategy can deliver the practical predefined-time control when there are external disturbances and model uncertainties, and with higher convergence accuracies compared to some of the existing methods.</div></div>","PeriodicalId":14660,"journal":{"name":"ISA transactions","volume":"167 ","pages":"Pages 575-588"},"PeriodicalIF":6.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145031666","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