IEEE Transactions on Industrial Informatics最新文献_第10页

Surface Constraint Policy for Learning Surface-Constrained and Dynamically Feasible Robot Skills 基于曲面约束的动态可行机器人技能学习策略

IF 9.8 1区计算机科学

IEEE Transactions on Industrial Informatics Pub Date : 2026-10-01 Epub Date: 2026-06-15 DOI: 10.1109/TII.2026.3694400

Shuai Ke;Jiexin Zhang;Huan Zhao;Zhiao Wei;Yikun Guo;Jie Pan;Han Ding

{"title":"Surface Constraint Policy for Learning Surface-Constrained and Dynamically Feasible Robot Skills","authors":"Shuai Ke;Jiexin Zhang;Huan Zhao;Zhiao Wei;Yikun Guo;Jie Pan;Han Ding","doi":"10.1109/TII.2026.3694400","DOIUrl":"10.1109/TII.2026.3694400","url":null,"abstract":"Diffusion-based imitation learning methods have driven rapid progress in robot dexterous manipulation tasks. However, they have limitations when applied to tasks that involve complex free-form surface constraints because of their lack of explicit surface geometry constraint modeling and the dynamic feasibility issue, resulting in stochastic action generation that fails to achieve reliable surface alignment and maintain stable contact. To address these limitations, we propose a novel surface constraint policy (SCP) for generating robot actions that satisfy free-form surface constraints on the basis of human demonstrations and real-time visual observations. First, the surface geometry constraint is encoded using a 2-D weighted Gaussian kernel function that is derived from demonstrations. Building on the encoded surface geometry constraints, the diffusion-based policy is used to infer task-level action intentions from multimodal sensory inputs, including visual observations and robot state feedback. These intentions are further transformed into surface-constrained dynamic movement primitives through a similarity-based action mapping method, thereby enabling smooth and compliant motion execution. The SCP achieves generation of structured surface geometric intent and dynamically admissible actions. The proposed method is validated on multiple surface manipulation tasks and compared with existing techniques. The experimental results demonstrate superior task success rates and contact stability under surface constraints.","PeriodicalId":13301,"journal":{"name":"IEEE Transactions on Industrial Informatics","volume":"22 10","pages":"8652-8662"},"PeriodicalIF":9.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148289257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Rejection and Mitigation of GNSS Time Synchronization Attacks Based on GNSS Receiver Iterative Model 基于GNSS接收机迭代模型的GNSS时间同步攻击抑制与缓解

IF 9.8 1区计算机科学

IEEE Transactions on Industrial Informatics Pub Date : 2026-10-01 Epub Date: 2026-07-02 DOI: 10.1109/TII.2026.3695961

Fan Feng;Chuhan Huang;Pengrui Mao;Jianjun Lu;Xinran Li;Xiangwei Zhu

{"title":"Rejection and Mitigation of GNSS Time Synchronization Attacks Based on GNSS Receiver Iterative Model","authors":"Fan Feng;Chuhan Huang;Pengrui Mao;Jianjun Lu;Xinran Li;Xiangwei Zhu","doi":"10.1109/TII.2026.3695961","DOIUrl":"10.1109/TII.2026.3695961","url":null,"abstract":"Industrial systems typically use global navigation satellite systems (GNSS) timing to maintain time synchronization across distributed nodes. The GNSS time synchronization attacks (TSAs) pose a significant threat to industrial systems, such as smart grids. The inconsistency of system time caused by TSAs can lead to system failures or even paralysis. Actually, TSAs and anti-TSAs are essentially an ongoing evolution of a cat-and-mouse game. To improve the generalizability of the TSA mitigation method, we start from the principle of the position, velocity, time (PVT) solution and develop a TSA rejection and mitigation method (TSARM-IM) based on the iterative least squares model used by GNSS receivers. We conducted a comparison of the proposed method with other methods in a real-world testbed. In 10 cases, the average clock bias root mean square errors of TSARM-IM are only 15.75, 22.49, and 11.41 m, which is significantly superior to 35.05, 229.32, and 1527.06 m of TSARM and 40.60, 216.99, and 472.07 m of TSARM-S under three TSA strategies. Furthermore, the method proposed in this article is not designed based on any TSA strategies, but rather on the PVT solution and the aim of TSAs. This implies that the proposed method may have certain effectiveness for future new TSA strategies.","PeriodicalId":13301,"journal":{"name":"IEEE Transactions on Industrial Informatics","volume":"22 10","pages":"8849-8859"},"PeriodicalIF":9.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148372349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Novel Collective Neural Dynamics-Driven Formation for Multiagent Systems 多智能体系统的新型集体神经动力学驱动编队

IF 9.8 1区计算机科学

IEEE Transactions on Industrial Informatics Pub Date : 2026-10-01 Epub Date: 2026-06-23 DOI: 10.1109/TII.2026.3701121

Bolin Liao;Tinglei Wang;Cheng Hua;Darong Huang;Zhuosong Fu;Shuai Li

引用次数: 0

Exosystem-Based Dynamic Input Control Strategy for Load Mitigation in Variable-Speed Wind Turbines Under Above-Rated Wind Conditions 额定风力条件下变速风力发电机组基于外系统的动态输入控制策略

IF 9.8 1区计算机科学

IEEE Transactions on Industrial Informatics Pub Date : 2026-10-01 Epub Date: 2026-06-12 DOI: 10.1109/TII.2026.3699013

Shaodong Wang;Qinmin Yang;Shuzong Xie;Wenchao Meng

{"title":"Exosystem-Based Dynamic Input Control Strategy for Load Mitigation in Variable-Speed Wind Turbines Under Above-Rated Wind Conditions","authors":"Shaodong Wang;Qinmin Yang;Shuzong Xie;Wenchao Meng","doi":"10.1109/TII.2026.3699013","DOIUrl":"https://doi.org/10.1109/TII.2026.3699013","url":null,"abstract":"Despite the significant progress in wind power generation in recent years, how to mitigate the structural fatigue loads on critical components while regulating power output, thereby extending the service life of wind turbines (WTs), remains a highly concerned and challenging research topic. In this article, an exosystem-based dynamic input control strategy is proposed for variable-speed WT (VSWT) systems operating above-rated wind speed to achieve this dual objective. Specifically, the nonlinear VSWT model describing the drive-train dynamics, tower dynamics, and pitch actuator dynamics is first linearized and represented as a linear parameter varying model. Subsequently, an exosystem for simulating the external disturbance signal and the desired reference signal is incorporated into the dynamic input control strategy, aiming to reduce the difficulty of solving multiobjective optimization control problems. In addition, to improve the accuracy and real-time performance of the measured wind speed, the continuous wave light detection and ranging (CW-LIDAR) simulator is used to provide the effective wind speed value, and exosystem dynamics are constructed using the CW-LIDAR measurement data. Finally, comprehensive comparative studies between the proposed scheme and several pitch controllers are conducted under multiple scenarios using the OpenFAST (fatigue, aerodynamics, structures, and turbulence) platform on the NREL 5-MW VSWT, thereby verifying the feasibility and effectiveness of the proposed strategy.","PeriodicalId":13301,"journal":{"name":"IEEE Transactions on Industrial Informatics","volume":"22 10","pages":"9302-9312"},"PeriodicalIF":9.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 Wearable Sensor-Driven Monitoring Framework for Hypoxic Respiratory Key Parameters Using Sensitivity-Based Estimation 基于灵敏度估计的可穿戴传感器驱动的缺氧呼吸关键参数监测框架

IF 9.8 1区计算机科学

IEEE Transactions on Industrial Informatics Pub Date : 2026-10-01 Epub Date: 2026-06-12 DOI: 10.1109/TII.2026.3695486

Meitong Li;Jing Chen;Dawei Shi;Shiyue Jia;Lingling Zhu

{"title":"A Wearable Sensor-Driven Monitoring Framework for Hypoxic Respiratory Key Parameters Using Sensitivity-Based Estimation","authors":"Meitong Li;Jing Chen;Dawei Shi;Shiyue Jia;Lingling Zhu","doi":"10.1109/TII.2026.3695486","DOIUrl":"https://doi.org/10.1109/TII.2026.3695486","url":null,"abstract":"Wearable sensors provide continuous physiological measurements, such as <inline-formula><tex-math>$text{SpO}_{2}$</tex-math></inline-formula> and heart rate. However, in hypoxic respiratory applications, such sensors primarily monitor superficial symptoms, while the key underlying parameters remain nonmeasurable. To address this issue, this work proposes a process monitoring framework driven by a novel sensitivity-based parameter estimation approach. The framework utilizes a physics-informed model with 18 key parameters as the monitoring target, where the change in two critical parameters is used to assess the hypoxic adaptation index (HAI). The estimation method incorporates a sensitivity-based groupwise optimization and an identifiability-based collective variational inference, which assigns greater trust weights to high-quality signals to mitigate the impact of low-quality data. Monitoring effectiveness is validated via an <italic>in silico</i> experiment, which demonstrates normalized mean absolute error reductions of 3.28% (individual) and 4.30% (population) over the baseline. The robustness of the framework and the effectiveness of the HAI are subsequently confirmed in a real-world intermittent hypoxic training experiment that involved noisy sensor data from 19 human subjects. This work provides a robust and generalizable framework for monitoring nonmeasurable key parameters in other complex dynamic systems.","PeriodicalId":13301,"journal":{"name":"IEEE Transactions on Industrial Informatics","volume":"22 10","pages":"8801-8812"},"PeriodicalIF":9.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Ethernet POWERLINK for Reconfigurable Robotics: Teaching an Old Fieldbus New Tricks 用于可重构机器人的以太网POWERLINK：教授旧现场总线的新技巧

IF 9.8 1区计算机科学

IEEE Transactions on Industrial Informatics Pub Date : 2026-10-01 Epub Date: 2026-06-11 DOI: 10.1109/TII.2026.3697941

Alexey M. Romanov

{"title":"Ethernet POWERLINK for Reconfigurable Robotics: Teaching an Old Fieldbus New Tricks","authors":"Alexey M. Romanov","doi":"10.1109/TII.2026.3697941","DOIUrl":"https://doi.org/10.1109/TII.2026.3697941","url":null,"abstract":"The concept of reconfigurable robots proposes the interconnection of dozens or even hundreds of modules, which poses a significant challenge to the communication system, which must be real-time, fast, small, inexpensive to implement, energy-efficient, and flexible in terms of allowed topologies. This article shows that legacy fieldbus solutions can be extended for applications that require additional flexibility, such as reconfigurable robotics. The example proposed in this article is based on Ethernet POWERLINK and extends the design with minimal additional hardware and communication effort. This article proposes a new field-programmable gate array (FPGA)-based smart hub that brings a new set of capabilities: seamless support for multiple loops in the topology, massive redundancy, automatic node numbering for any topology, and automatic topology recovery. The presented design has a compact footprint of 917 logical element (LE) for a 16-port hub, making it suitable for implementation with low-cost, low-power FPGAs, such as the Intel MAX10 series. Moreover, due to its low logical complexity, the power consumption of the intellectual property core implemented with MAX10 will be only 61.65 mW. The experimental studies, performed both using cycle-accurate simulation and real prototypes, confirmed that the Ethernet POWERLINK network created with smart hubs operates in topologies with multiple redundant lines and loops. The controlled nodes remained in operation mode even during rewiring “on the fly.” It was also clearly demonstrated that the PollRequest–PollResponse interval jitter of FPGA-based controlled nodes is only <inline-formula><tex-math>$pm 40$</tex-math></inline-formula> ns, which makes it possible to determine neighboring nodes and automatically recover the network topology using the method proposed in this article.","PeriodicalId":13301,"journal":{"name":"IEEE Transactions on Industrial Informatics","volume":"22 10","pages":"9131-9142"},"PeriodicalIF":9.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097974","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

QuantEIT: Ultra-Lightweight Quantum-Inspired Inference for Electrical Impedance Tomography QuantEIT：电阻抗断层成像的超轻量级量子启发推理

IF 12.3 1区计算机科学

IEEE Transactions on Industrial Informatics Pub Date : 2026-10-01 DOI: 10.1109/tii.2026.3731100

Hao Fang, Sihao Teng, Hao Yu, Zhe Liu, Siyi Yuan, Huaiwu He, Yunjie Yang

引用次数: 0

SCVP-Net: Enhancing Unsupervised Multiview 3-D Point Cloud Reconstruction via Shape Contrast and View Perception 基于形状对比和视图感知的无监督多视角三维点云重建

IF 12.3 1区计算机科学

IEEE Transactions on Industrial Informatics Pub Date : 2026-10-01 DOI: 10.1109/tii.2026.3728115

Jiahui Song, Yonghong Hou, Bo Peng, Yuxuan Yao, Qingming Huang, Jianjun Lei

引用次数: 0

STiC-AD: Spatio-Temporal Attention With Instance Normalization and Convolution for Anomaly Detection in Semiconductor Manufacturing 基于实例归一化和卷积的半导体制造异常检测时空关注

IF 12.3 1区计算机科学

IEEE Transactions on Industrial Informatics Pub Date : 2026-10-01 DOI: 10.1109/tii.2026.3733115

Jaeyoung Koh, Jung In Kim, Seoung Bum Kim

引用次数: 0

Bayesian Supervised Projection Multivariate Transform for Degradation Monitoring and Forecasting of Hydroelectric Turbines With Well-Calibrated Uncertainty Quantification 基于贝叶斯监督投影多元变换的水轮机退化监测与预测

IF 9.8 1区计算机科学

IEEE Transactions on Industrial Informatics Pub Date : 2026-10-01 Epub Date: 2026-07-01 DOI: 10.1109/TII.2026.3701547

Dominique Tapsoba;Xavier Emery;Quentin Dollon

{"title":"Bayesian Supervised Projection Multivariate Transform for Degradation Monitoring and Forecasting of Hydroelectric Turbines With Well-Calibrated Uncertainty Quantification","authors":"Dominique Tapsoba;Xavier Emery;Quentin Dollon","doi":"10.1109/TII.2026.3701547","DOIUrl":"10.1109/TII.2026.3701547","url":null,"abstract":"Degradation monitoring of hydroelectric turbines requires accurate forecasting with well-calibrated uncertainty quantification to support critical maintenance decisions. Traditional bootstrap and multivariate projection pursuit methods suffer from poor coverage calibration (75%–84% undercalibration for bootstrap methods, 99%–100% overcalibration for projection pursuit, versus target 90%), whereas deep learning approaches with Monte Carlo dropout or ensembles face calibration challenges under distribution shift and computational constraints limiting deployment in real-time supervisory control and data acquisition (SCADA) environments. We propose Bayesian supervised projection multivariate transform, which combines supervised dimensionality reduction with Bayesian conjugate inference to achieve well-calibrated prediction intervals. Validated on 81 048 observations from two operational turbines across contrasting degradation scenarios (progressive drift and brutal rupture), our method achieves 1.30%–1.95% mean absolute percentage error with 86%–95% coverage, outperforming both classical projection pursuit and bootstrap-based approaches. The method provides analytical Student-<inline-formula><tex-math>$t$</tex-math></inline-formula> prediction intervals compatible with real-time SCADA systems (<inline-formula><tex-math>$sim$</tex-math></inline-formula>40 floating-point operations per sample), decomposing uncertainty into aleatoric, epistemic, and variance-related (variance uncertainty) components with physical interpretability for maintenance decision support. Results demonstrate that the coupling of supervised projection and Bayesian inference restores coverage calibration, establishing a practical framework for industrial deployment in critical infrastructure monitoring.","PeriodicalId":13301,"journal":{"name":"IEEE Transactions on Industrial Informatics","volume":"22 10","pages":"9490-9501"},"PeriodicalIF":9.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11591431","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148372360","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0