IEEE Transactions on Industrial Cyber-Physical Systems最新文献

{"title":"Deep Learning-Based Intelligent Intrusion Detection With Optimized Feature Selection for IoT Network Security","authors":"Surendra Kumar;Avinash Kumar;Mridula Dwivedi;Mohit Kumar;Huaming Wu;Sukhpal Singh Gill","doi":"10.1109/TICPS.2026.3708811","DOIUrl":"https://doi.org/10.1109/TICPS.2026.3708811","url":null,"abstract":"Intrusion detection is crucial to network security, especially in Internet of Things (IoT) contexts with rising cyberthreats. Traditional Intrusion Detection Systems (IDSs) can cause false alerts and are difficult to detect new attack types. Metaheuristic optimization can enhance detection rate, model complexity, and feature selection, but it lacks scalability and flexibility to changing situations. Nature-inspired methods enable deep learning models to focus on key features. Current existing methods face challenges in securing the network from several attack types and adapting to evolving attack patterns effectively, identifying changing attack patterns in IoT networks with great accuracy. This paper presents a novel IoT-aware intrusion detection framework that integrates the Whale Optimization Algorithm (WOA), Dipper Throated Optimization (DTO), and Ant Lion Optimization (ALO) for optimized feature selection, alongside Long Short-Term Memory and eXtreme Gradient Boosting for accurate anomaly detection. The proposed method effectively balances exploration and exploitation to select informative features, while the learning models capture temporal and nonlinear patterns in network traffic. Experimental results evaluated on benchmark datasets, including NSL-KDD, KDDCup99, CICDDoS2019, and NF-UNSW-NB15-v2, demonstrate that the proposed framework achieves high detection performance with reduced false alarms. The proposed frameworkimproves computational efficiency and maintains strong detection capability across multiple attack categories,making it scalable and secure for real-time IoT intrusion detection.","PeriodicalId":100640,"journal":{"name":"IEEE Transactions on Industrial Cyber-Physical Systems","volume":"4 ","pages":"584-592"},"PeriodicalIF":7.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148481190","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cross-Scenario Robustness Analysis of Deep Reinforcement Learning–Based Energy Management in Wind-Integrated Flexible Smart Traction Power Supply System","authors":"Yiyan Sang;Xijiao Ren;Yichen Ying;Jiamin Sheng;Suhan Zhang;Lie Xu;Agustí Egea-Àlvarez;Jianbin Zhang","doi":"10.1109/TICPS.2026.3710873","DOIUrl":"https://doi.org/10.1109/TICPS.2026.3710873","url":null,"abstract":"The increasing penetration of distributed renewable energy in electrified railway systems has promoted the development of flexible smart traction power supply systems (FSTPSSs). However, the strong intermittency and scenario-dependent dynamics of wind power introduce substantial uncertainty, posing significant challenges to the robustness of energy management strategies. Although deep reinforcement learning (DRL) has shown promise in addressing short-term renewable variability in FSTPSS, its robustness across heterogeneous wind power scenarios has not been systematically investigated. This paper develops a scenario-oriented robustness evaluation framework for DRL-based energy management in wind-integrated FSTPSS. Representative wind power scenarios are identified using the K-medoids clustering method, and scenario-specific stochastic fluctuation parameters are extracted to characterize intra-scenario uncertainty. On this basis, the robustness of DRL agents trained under different scenario exposures is quantitatively evaluated and compared when deployed under previously unseen operating conditions. Simulation results indicate that agents trained with diversified scenario experience achieve significantly lower mean square error (MSE) and mean absolute percentage error (MAPE) in reference power tracking when facing new wind power scenarios. These results demonstrate that explicitly incorporating scenario diversity into the training process is essential for enhancing the robustness and generalization capability of DRL-based energy management strategies under dynamic wind environments.","PeriodicalId":100640,"journal":{"name":"IEEE Transactions on Industrial Cyber-Physical Systems","volume":"4 ","pages":"665-677"},"PeriodicalIF":7.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148612943","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep Learning Model-Based Spatiotemporal Causality-Inspired Fusion for Cyber Attack Behavior Identification","authors":"Yuchen Dai;Jiehao Chen;Dezhi Xu;Junyi Li;Liyan Zhang;Lei Li","doi":"10.1109/TICPS.2026.3709779","DOIUrl":"https://doi.org/10.1109/TICPS.2026.3709779","url":null,"abstract":"The precise identification of cyber attacks in Industrial Cyber-Physical Systems (ICPS) is critical to both production safety and infrastructure stability. However, existing identification methods face bottlenecks in spatiotemporal feature fusion accuracy, noise immunity, and feature importance differentiation, leading to high misclassification rates under complex attack scenarios. To address this, we propose a spatiotemporal causality-inspired fusion method for attack identification. The method employs a mutual information-driven dynamic weighting mechanism and a dual-stream architecture to decouple and extract long-range temporal dependencies and local spatial structures from attack traffic. Furthermore, it introduces a causality-inspired decoupled evaluation strategy for adaptive fusion, which independently quantifies the contribution of each branch and dynamically adjusts fusion weights via sample-level gating, thereby guiding the model to focus on task-relevant features during decision-making. Experimental results on the UNSW-NB15, CICIDS2018, and a real-world industrial control dataset (ICS-NAD) demonstrate that the proposed model achieves the best performance across all attack categories, and ablation studies confirm the indispensability of each core component. This work provides a causality-inspired spatiotemporal fusion approach for ICPS security. The proposed method effectively improves the robustness and cross-dataset generalization capability of attack identification systems in complex attack scenarios, offering a viable technical pathway toward more reliable intelligent attack identification in industrial networks.","PeriodicalId":100640,"journal":{"name":"IEEE Transactions on Industrial Cyber-Physical Systems","volume":"4 ","pages":"613-624"},"PeriodicalIF":7.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148612982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mixed-Action Reinforcement Learning for Energy Management of Renewable-Integrated Libraries","authors":"Lin Tan;Peilin Xie;Sen Tan","doi":"10.1109/TICPS.2026.3703365","DOIUrl":"https://doi.org/10.1109/TICPS.2026.3703365","url":null,"abstract":"Energy coordination for renewable-integrated public buildings involves coupled physical dynamics, operational uncertainty, and mixed decision variables. Conventional optimization methods rely on accurate forecasts and repeated online computation, whereas standard reinforcement learning (RL) methods with continuous action spaces are not well suited to hybrid scheduling tasks involving both binary and continuous decisions. To address this issue, a proximal policy optimization (PPO)-based approach is developed for a smart library energy system with photovoltaic generation, an energy storage system (ESS), electric vehicles (EVs), and flexible tasks. The energy scheduling is formulated as a sequential decision-making problem that incorporates electricity price variation, ESS and EV charging behavior, and task scheduling requirements. A mixed binary–continuous policy is designed to unify discrete task scheduling and continuous energy control within one policy architecture, enabling direct coordination of task execution. The effectiveness of the proposed method is validated through Python-based simulations. Compared with a conventional continuous-action method, the proposed approach achieves more effective price-responsive ESS scheduling, reduces electricity purchase during high-price periods, and yields a 26.1% improvement in the overall economic index.","PeriodicalId":100640,"journal":{"name":"IEEE Transactions on Industrial Cyber-Physical Systems","volume":"4 ","pages":"751-761"},"PeriodicalIF":7.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148781111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"LLM-Guided Hybrid Scheduling With Digital Twin Feedback for Heterogeneous Multi-Robot Aircraft Stringer Assembly","authors":"Yu Liu;Yun Feng;Yixuan Tong;Lei Wang;Yaonan Wang;Tingwen Huang","doi":"10.1109/TICPS.2026.3733876","DOIUrl":"https://doi.org/10.1109/TICPS.2026.3733876","url":null,"abstract":"The lack of deterministic guarantees under stringent physical constraints, combined with the curse of dimensionality, hinders the deployment of heterogeneous multi-robot systems (MRSs) in aircraft stringer assembly. To bridge the gap between high-level reasoning and low-level feasibility, this article proposes a hybrid scheduling architecture that synergizes large language models (LLMs), mixed-integer linear programming (MILP), and digital twins (DTs). Specifically, we leverage the semantic reasoning of LLMs to extract high-quality prior knowledge, which is then mapped by an adaptive selector to guide the MILP solver through three distinct refinement strategies: filter, warm, and hybrid. This approach transforms LLM-generated insights into kinematically feasible schedules. To enhance operational robustness, a DT-driven event-triggered mechanism is integrated to enable agile rescheduling upon detecting disturbances. Experimental results on FJSP benchmarks and an industrial instance (with up to 64 tasks) show that the proposed method improves the solving speed of the traditional MILP solver on large-scale instances and reliably obtains feasible schedules. Furthermore, the proposed method maintains an average dynamic recovery rate of approximately 80% under random perturbations. This article provides a scalable and resilient solution for complex multi-robot collaboration in high-precision aerospace manufacturing.","PeriodicalId":100640,"journal":{"name":"IEEE Transactions on Industrial Cyber-Physical Systems","volume":"4 ","pages":"1016-1025"},"PeriodicalIF":7.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149130705","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Smooth Dual-Mode Service Fee Mechanism With Negative-Impact Voltage Assessment for Grid-Friendly P2P Energy Trading","authors":"Zongyu Yao;Jing Qiu;Jiafeng Lin;Weiyi Tian;Sihai An;Zhe Yuan","doi":"10.1109/TICPS.2026.3726012","DOIUrl":"https://doi.org/10.1109/TICPS.2026.3726012","url":null,"abstract":"Peer-to-peer (P2P) energy trading can intensify voltage deviations in distribution networks, whereas conventional fixed service fees do not distinguish market participants according to their voltage impacts. This paper proposes a smooth dual-mode voltage-impact service-fee mechanism for bilateral-auction-based P2P energy trading. LinDistFlow-based Voltage Sensitivity Factors (VSFs), pre-clearing voltage states, and transaction-level Negative Impact Indicators (NIIs) are combined to identify voltage-adverse trading directions. The Negative Sensitivity-Based Fee (NSBF) forms the low-stress limiting state, while a node-wise activation factor continuously introduces Voltage-Aware Adaptive Fee (VAAF) weighting as pre-clearing voltage deviations enter a prescribed transition band, thereby avoiding abrupt mode switching. Adverse and beneficial voltage movements are evaluated separately to prevent mutual offsetting. The proposed fee is embedded into an auction-compatible two-stage framework that coordinates day-ahead network scheduling with rolling sequential intra-day clearing. The day-ahead stage establishes a grid-feasible operating baseline, whereas the intra-day stage incorporates the nodal service fee into participants’ effective bids and asks without reformulating the bilateral auction as a network-constrained optimal power flow. Studies on a modified IEEE 33-bus feeder show that cumulative adverse voltage movement is reduced by 32.91% and 39.47% relative to fixed fees under normal low- and high-voltage conditions, respectively. Under the voltage-stressed condition, the smooth mechanism reduces adverse voltage movement by 20.13% relative to NSBF while preserving the same total P2P trading volume. Nonlinear AC power-flow validation shows that the maximum error in the incremental P2P-induced voltage movement remains below <inline-formula><tex-math>$7.36 times {{10}^{ - 4}}$</tex-math></inline-formula> p.u., with a minimum Pearson correlation of 0.999473 and preserved comparative ordering among the evaluated mechanisms.","PeriodicalId":100640,"journal":{"name":"IEEE Transactions on Industrial Cyber-Physical Systems","volume":"4 ","pages":"917-934"},"PeriodicalIF":7.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148985163","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Alexis: Anomaly-Based Intrusion Detection in FPGA-Enabled Cyber-Physical Systems","authors":"Umara Hanif;Muhammad Naveed Aman;Biplab Sikdar","doi":"10.1109/TICPS.2025.3649161","DOIUrl":"https://doi.org/10.1109/TICPS.2025.3649161","url":null,"abstract":"Ensuring the security of FPGA-based systems is crucial, especially in cyber-physical environments where reliability and security are paramount. This paper introduces <italic>Alexis</i>, a novel anomaly detection framework leveraging autoencoder neural networks to identify hardware Trojans in FPGA bitstreams. <italic>Alexis</i> meticulously examines bitstream data for discrepancies, thereby providing a robust approach to mitigate security breaches. Experimental evaluations highlight the superiority of <italic>Alexis</i>, achieving an accuracy upto 91%, significantly outperforming traditional approaches. Moreover, the Mean Squared Error (MSE) and Mean Absolute Error (MAE) values consistently indicate minimal reconstruction errors, thereby demonstrating the reliability of the autoencoder's learning capabilities. The computational efficiency of <italic>Alexis</i>, with an average time overhead of less than 0.021 seconds and memory usage around 1.14 MiB, underscores its suitability for resource-constrained environments. Additionally, the high Area Under the Curve (AUC) values range upto 0.96, illustrate the model's exceptional performance in accurately distinguishing anomalies from normal bitstreams. These results establish <italic>Alexis</i> as a scalable and efficient solution for enhancing the security of FPGA-enabled cyber-physical systems.","PeriodicalId":100640,"journal":{"name":"IEEE Transactions on Industrial Cyber-Physical Systems","volume":"4 ","pages":"106-118"},"PeriodicalIF":0.0,"publicationDate":"2025-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146175806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Secure Control for Cyber-Physical Systems Under Stealthy Attacks via a Successive Convex Optimization Algorithm","authors":"Yufan Chen;Yingying Ren;Da-Wei Ding","doi":"10.1109/TICPS.2025.3643827","DOIUrl":"https://doi.org/10.1109/TICPS.2025.3643827","url":null,"abstract":"This article investigates the secure control scheme for discrete-time cyber-physical systems (CPSs) under stealthy attacks. The goal is to design a controller such that the system runs safely under attack. Firstly, the stealthiness of attacks is characterized by the Kullback-Leibler divergence (KLD), while the reachable set is introduced to quantify system safety. On this basis, an <inline-formula><tex-math>$H_infty$</tex-math></inline-formula> performance is introduced to attenuate the effects of noise and attacks on the controlled output. Based on the reachable set and the <inline-formula><tex-math>$H_infty$</tex-math></inline-formula> performance, the controller design can be depicted as a nonconvex optimization problem with bilinear matrix inequalities (BMIs) constraints. A successive convex optimization (SCO) algorithm is proposed to iteratively solve the problem, which ensures that the reachable set resides within a safe set while satisfying the required performance level. Eventually, numerical simulations and experiments validate the efficacy of the proposed method.","PeriodicalId":100640,"journal":{"name":"IEEE Transactions on Industrial Cyber-Physical Systems","volume":"4 ","pages":"71-81"},"PeriodicalIF":0.0,"publicationDate":"2025-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146082210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"2025 Index IEEE Transactions on Industrial Cyber-Physical Systems","authors":"","doi":"10.1109/TICPS.2025.3643651","DOIUrl":"https://doi.org/10.1109/TICPS.2025.3643651","url":null,"abstract":"","PeriodicalId":100640,"journal":{"name":"IEEE Transactions on Industrial Cyber-Physical Systems","volume":"3 ","pages":"665-682"},"PeriodicalIF":0.0,"publicationDate":"2025-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11299287","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145729282","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dynamic PID-Based Event-Triggered Robust MPC for Cyber-Physical Systems Under DoS Attacks","authors":"Yun Chen;Xinli Shi;Ying Wan;Jinde Cao","doi":"10.1109/TICPS.2025.3643803","DOIUrl":"https://doi.org/10.1109/TICPS.2025.3643803","url":null,"abstract":"In this article, a novel resilient and robust event-triggered model predictive control (ET-MPC) approach is proposed for discrete-time nonlinear cyber-physical systems (CPSs) subject to external disturbances and denial-of-service (DoS) attacks. By integrating system constraints, disturbances, and network attacks, the proposed method achieves a balance between system stability and security. Specifically, a nonlinear robust state constraint set is constructed to reduce conservativeness, ensuring state constraint satisfaction. A dynamic buffer mechanism is introduced to merge model predictive control (MPC) and feedback control, effectively removing the upper bound for inter-triggering intervals. Moreover, the event-triggered mechanism (ETM) is enhanced with PID and dynamic threshold, further reducing communication and computation costs. Theoretical results establish a lower bound on the triggering interval and an upper bound on the state deviation, proving recursive feasibility and input-to-state practical stability (ISpS). Simulation results demonstrate the superior robustness, stability, and resource efficiency of the proposed method.","PeriodicalId":100640,"journal":{"name":"IEEE Transactions on Industrial Cyber-Physical Systems","volume":"4 ","pages":"53-61"},"PeriodicalIF":0.0,"publicationDate":"2025-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929352","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}