Search Results (619)

Federated learning (FL) enables privacy-preserving fault diagnosis across distributed industrial devices, but most existing methods assume homogeneous model architectures and comparable client resources. This assumption is unrealistic in resource-constrained Industrial Internet of Things (IIoT) scenarios, where clients may have substantially different memory and computation capacities. To address this challenge, we propose FedAnchor, an anchored and adaptive FL framework for resource-heterogeneous fault diagnosis. FedAnchor decomposes each client submodel into a shared anchored core and a client-specific adaptive extension. The anchored core provides a common parameter subspace for consistent masked aggregation, while the adaptive extension is selected by a server-side reinforcement-guided policy under client memory budgets. This design couples resource-aware submodel allocation with structurally aligned aggregation. Experiments on four benchmark datasets and six heterogeneous memory configurations show that FedAnchor achieves competitive or superior accuracy compared with representative homogeneous and model-heterogeneous FL baselines. Under the evaluated non-IID settings, FedAnchor improves accuracy by up to 9.8 percentage points over the strongest baseline, while maintaining favorable communication–accuracy trade-offs and empirical stability. Full article

This paper presents the design and experimental validation of a hybrid architecture for the Industrial Internet of Things (IIoT), based on a Siemens LOGO! v8.4 programmable logic controller (PLC) (Siemens AG, Munich, Germany), Node-RED v3.1.3 (OpenJS Foundation, Wilmington, DE, USA), Microsoft Azure (Microsoft Corporation, Redmond, WA, USA), and Factory I/O v2.5.5 (Real Games Unipessoal Lda, Gondomar, Porto, Portugal). The proposal integrates three main functions—real-time telemetry, structured historical data storage and bidirectional remote control—over an automated tank level process. The architecture was organized into four functional layers: local automation, middleware integration, cloud services and web application. Validation was conducted using five performance metrics: end-to-end latency, remote command latency, successful delivery rate, update rate, and service recovery time. The results confirm the technical feasibility of the proposed architecture for remote monitoring and control, while also identifying the main bottlenecks in the transmission chain. Overall, the study provides an experimental basis for modular and reproducible IIoT solutions with a low adoption barrier and potential applicability to progressive digitalization scenarios in small- and medium-sized enterprises. Full article

Smart wearable biomedical sensors/devices provide the ability for continuous monitoring of physiological parameters in occupational settings. Industrial Internet of Things (IIoT)’s integration in wearable biomedical technology presents additional cybersecurity risks and privacy concerns as attack surfaces expand and sensitive biometric data is processed. This scoping review included studies published between 2020 and 2026, screened according to PRISMA-ScR guidelines, which identified 39 articles. The findings indicate that most systems rely on commercial wearables for monitoring fatigue, stress, and environmental conditions, often with limited consideration of the cybersecurity aspects. Common risks include insecure wireless communication, data interception, firmware and supply chain attacks, and vulnerabilities related to IT/OT integration. To address these challenges, this study proposes a multi-layer threat taxonomy covering sensing, communication, processing, AI/analytics, and organizational layers. The results highlight the need for end-to-end cyber-resilient architectures and privacy-by-design approaches in occupational wearable monitoring systems. Full article

Industrial Internet of Things (IIoT) networks require continuous, uninterrupted sensing operations despite the finite battery capacity of deployed IoT nodes. Conventional reactive energy management, where nodes switch to charging mode only after residual energy falls below a fixed threshold, cannot prevent depletion events and compromises network uptime. We propose a digital twin (DT)-enabled predictive scheduling framework in which a DT layer co-located with a multi-access edge computing (MEC) control center continuously mirrors the physical network state and generates H-slot look-ahead scheduling decisions before depletion can occur. The framework operates over a 5G network-sliced infrastructure with dedicated URLLC, eMBB, and mMTC slices. Two coupled integer programming problems are formulated, namely a predictive IoT node scheduling problem and a predictive energy transmitter scheduling problem. Optimal solutions are obtained via branch-and-bound with reliability branching (DT-PBB), and a low-complexity DT-Aware Greedy Priority Heuristic (DT-GPH) is also proposed. Evaluated against Earliest-Deadline-First (EDF-WPT), No-WPT (a baseline that disables wireless charging entirely), and Random baselines across three parameter configurations with K up to 200 nodes, DT-PBB achieves the highest sensing utility and the fewest energy depletion events in all scenarios. DT-GPH provides near-optimal depletion performance at substantially lower computation cost. EDF-WPT, the strongest reactive policy, incurs 2-4 times more depletion events than DT-PBB. Proactive DT-enabled look-ahead decisively outperforms reactive urgency-based scheduling, validating the zero-downtime paradigm for large-scale IIoT networks. Full article

Time synchronization plays a critical role in enabling coordinated control and accurate data fusion in the Industrial Internet of Things (IIoT). However, most existing time-triggered synchronization protocols rely on periodic information exchange, which leads to considerable communication and energy consumption, particularly in large-scale and resource-constrained deployments. To address these limitations, this study proposes an adaptive event-triggered time synchronization scheme that eliminates the need for periodic communication. Unlike conventional approaches that employ fixed or predefined time-varying thresholds, the proposed method constructs a fully distributed triggering mechanism based on both local clock evolution and synchronization discrepancies observed from neighboring nodes. The triggering threshold evolves automatically according to the network synchronization state and does not require additional coordination messages. Theoretical analysis shows that the logical clock skews asymptotically converge to a common value, while the logical clock offset disagreement is ultimately bounded within an explicitly characterized neighborhood. Simulation results demonstrate that the proposed scheme achieves a more effective balance between synchronization accuracy and communication overhead, while producing more evenly distributed triggering events than several representative event-triggered synchronization methods. Full article

Lightweight, privacy-aware and adversarial robust intrusion detection is required for the proliferation of Internet of Things (IoT) devices. In the Industrial Internet of Things (IIoT), centralized detectors can be compromised by adversarial perturbations via gradient-based attacks, making them susceptible to raw traffic. We suggest Federated Learning-Adaptive Gated Recurrent Unit (FL-AdGRU), a Federated approach that combines a lightweight Gated Recurrent Unit (GRU) classifier with alternating adversarial fine-tuning on each client using FGSM and PGD, without any communication overhead. A two-stage resampling scheme (UCAS-SMOTE) reduces the class-imbalance ratio from 4081:1 to ≈4:1, followed by 61 features being reduced to 40 by a mutual-information selector (MI-SelectK). Under this scenario, FL-AdGRU achieves 99.9% accuracy and 0.999 weighted F1 (+6.5 p.p. over the federated DNN baseline), with no loss of accuracy when facing clean attacks, and boosts Fast Gradient Sign Method FGSM/Projected Gradient Descent (PGD) robustness by +19.3/+19.0 p.p. at the same level of $ϵ$ = 0.1, thus effectively balancing the accuracy–robustness trade-off. It is robust (97.8%/84.2% on UNSW-NB15) and generalizes well to UNSW-NB15, while decaying slowly in skeptical scenarios (≈99.9% weighted F1 for moderate skew, 93.9%/86.7% for severe). Assuring data-locality privacy through exchange of only model weights; defenses against inference attack are left for future work. FL-AdGRU, with a total communication of 43.8 MB (≈50× less than centralized training), is deployable on bandwidth-constrained IIoT networks. Full article

The Industrial Internet of Things (IIoT) demands authentication that protects resource-constrained field devices, supports fine-grained access control, and reduces reliance on implicitly trusted gateways. Existing IIoT authentication and key agreement schemes mainly verify cryptographic identity and establish session keys, but provide limited support for zero-trust access decisions after authentication such as role-specific operation control, gateway-side relation protection, emergency override, and context-aware re-verification. This paper proposes a lightweight zero-trust authentication and key agreement scheme for IIoT. The scheme embeds role-, device-, environment-, and behavior-aware control points into the authentication flow, protects gateway-side authentication relations and operator–asset mappings using secGear-based confidential computing, and supports pseudonym-based identity protection and break-the-glass emergency access. To complement deterministic access control, an optional auxiliary risk evaluation module provides trust evidence from contextual and operator-state signals without becoming part of the cryptographic critical path. This module is used to trigger re-verification, privilege degradation, audit escalation, or session termination before high-risk control privileges are released; it does not replace cryptographic authentication or constitute a formal guarantee of coercion detection, and the cryptographic layer remains fully functional and formally analyzable even when the auxiliary risk evaluation module is disabled. BAN logic and AVISPA analyses verify the cryptographic authentication and key agreement layer, while a comparative overhead analysis under an analytical operation count basis indicates low computation and communication cost relative to representative resource-constrained IoT authentication schemes. Full article

Mobile robots used in edge-assisted Industrial Internet-of-Things (IIoT) settings generate coupled motion, LiDAR, edge-compute, and network telemetry. Public datasets that place these streams in one tabular format, with scenario labels suitable for machine-learning experiments, are still limited. This data descriptor presents a pilot-real-calibrated indoor robotic IoT benchmark dataset with 120,000 records sampled at 2 Hz across nominal navigation and nine anomaly scenarios. The benchmark rows are generated from physically constrained simulation rules and are explicitly labeled as synthetic benchmark data. Real pilot evidence is included separately: ROS Noetic runs on a TurtleBot3 Burger, successful LD08 LiDAR bringup after resolving a driver mismatch, and NVIDIA Jetson Nano tegrastats logs under normal-navigation workloads. The calibrated file aligns normal-navigation LiDAR and edge-compute distributions with these pilot measurements while keeping the multi-scenario structure needed for controlled anomaly-detection experiments. The package includes CSV files, metadata, a data dictionary, validation reports, baseline scripts, ROS collection utilities, and a plan for future fully physical data collection. The complete dataset is openly available on Zenodo. Full article

This paper addresses the challenge of Reduced Capability (RedCap) User Equipment (UE) positioning within indoor 5G networks. While conventional approaches rely on time-domain ranging, the limited signal bandwidth associated with RedCap devices compromises the capability of these methods to satisfy stringent accuracy requirements. To overcome this limitation, we propose a positioning framework based on uplink Angle-of-Arrival (AoA) measurements. By performing AoA estimation at the Transmission and Reception Point (TRP), the proposed approach maintains hardware simplicity, requiring only a single antenna at the UE. The framework incorporates a computationally efficient AoA estimation algorithm derived from the analysis of the spatial covariance matrix, eliminating the need for the exhaustive beam scanning typically required for angular grid search. This procedure inherently generates a link quality metric which, alongside the AoA estimate, is utilized for final UE localization. The localization algorithm employs a Weighted Least Squares (WLS) estimator to provide a unified approach to UE positioning in both 2D and 3D physical spaces. The framework’s efficacy is confirmed via numerical simulations under the dense multipath conditions defined by standard 5G Indoor Factory (InF) environments. Full article

Distributed Denial of Service (DDoS) attacks pose significant threats to Industrial Internet of Things (IIoT) environments, exacerbated by the resource constraints of IoT devices and the disruptive impact of such attacks. Conventional detection and prevention methods fall short of ensuring the availability and operational continuity required in industrial deployments. This article systematically analyses artificial intelligence (AI) techniques for detecting, preventing, and mitigating DDoS attacks in IIoT systems. We examine diverse AI-driven solutions, including machine learning (ML) and deep learning (DL) models, alongside hybrid approaches that enhance real-time threat identification, adaptive defence mechanisms, and decentralised trust management, addressing the evolving sophistication of DDoS attacks. This study highlights AI’s potential to strengthen IIoT security and resilience, particularly in critical national infrastructure (CNI), where uninterrupted operations are paramount. However, challenges such as computational overhead, model interpretability, and dataset scarcity in industrial settings remain critical barriers. Additionally, the dynamic IIoT topology and heterogeneous device ecosystems necessitate context-aware AI solutions. This analysis underscores the need for lightweight, explainable AI frameworks and collaborative defence strategies tailored to the IIoT’s unique constraints. It emphasises the integration of AI with emerging technologies like edge computing and federated learning to advance proactive, scalable DDoS defence mechanisms in industrial ecosystems. Full article

Dataset quality significantly affects the effectiveness of a machine learning (ML) model in an intrusion detection system (IDS) for cyber-physical industrial control systems (CPS/ICS) and Industrial Internet of Things (IIoT). Existing surveys compare datasets qualitatively or along limited dimensions, whereas this review introduces quantitative documentation and decision-aid scoring across 23 ICS/OT/IIoT datasets. These datasets are analyzed along seven measurable axes, with their attacks mapped to MITRE ATT&CK for ICS tactics. Quantitatively, 14 of the 23 datasets (60.9%) are built on physical testbeds, and 22 of the 23 map to MITRE ATT&CK for ICS, spanning 11 of the 12 tactics. We introduce a checklist for documentation completeness (0–7) and a decision-aid rubric (0–15) covering realism, attack diversity, class imbalance, documentation, and reproducibility. Protocol coverage across these datasets is skewed toward Modbus (13 of 23 datasets, 57%), while many other protocols (such as Profinet and OPC UA) are underrepresented relative to their industry deployment. The available datasets show structural gaps in capturing multi-stage adversary behavior. In practice, dataset selection should pair a realism-anchored dataset with a high-reproducibility one, and account for protocol diversity and APT representation. Full article

In embodied-intelligence Industrial Internet of Things (IIoT), multi-AGV intelligent warehousing requires continuous processing of latency-sensitive tasks, such as environmental perception, inventory monitoring, and anomaly detection. Due to limited onboard computing capability and energy capacity, purely local execution can hardly satisfy real-time requirements, whereas fully cloud-based processing may incur excessive transmission delay and backhaul overhead. To address this issue, this paper investigates the joint optimization of AGV service-point migration and task offloading under a cloud-edge-end collaborative architecture. Considering the impact of service-point selection on wireless access, MEC resources, movement delay, and energy consumption, as well as the effect of offloading decisions on transmission, computation, and AGV-side energy cost, a dual-time-scale optimization model is formulated to minimize the long-term accumulated system delay while satisfying task latency and AGV energy constraints. To solve the resulting mixed discrete problem, a DPSO-MAPPO algorithm is proposed, where DPSO searches service-point plans satisfying movement and conflict constraints at the slow time scale, and MAPPO learns coordinated multi-AGV offloading policies at the fast time scale. The delay and energy feedback further enables coordination between the two types of decisions. Simulation results show that the proposed algorithm converges stably, reduces system delay by 13.55% compared with benchmark algorithms, and improves total energy consumption and energy-violation control. Full article

Safety-critical Industrial Internet of Things (IIoT) sensor networks deployed in disaster scenarios require intelligent routing mechanisms that prioritize mission-critical packets without relying on centralized coordination. Federated learning on resource-constrained edge nodes presents three primary challenges: the absence of an interpretable supervisory signal, the inability to act conservatively based on per-inference confidence, and vulnerability to partial node availability. The proposed FedCARE framework addresses these issues by employing a Mamdani Fuzzy Inference System to generate traceable criticality labels from multi-modal sensor telemetry, a dropout-aware aggregation protocol that normalizes over only reachable nodes, and a confidence-gated resolver that defers to symbolic fuzzy classification when model confidence is insufficient, otherwise applying an auditable maximization rule to prevent under-prioritization of safety-critical data. Evaluation on 50-, 100-, and 200-node Watts–Strogatz topologies under fault rates up to 50%, using the Edge-IIoTset and WUSTL-IIoT-2021 benchmarks, demonstrates 99.00% critical recall and up to $1.8\times$ higher overall-packet delivery compared to RPL-RP under severe fault conditions. Routing improvements are primarily attributed to fuzzy criticality labeling and multi-path replication. These findings indicate that fuzzy-supervised federated inference offers a practical and interpretable solution for safety-critical IIoT routing, with an observed energy overhead of 7.8% per delivered packet. Full article

Small- and medium-sized enterprises, especially in the agricultural food sector, struggle to implement end-to-end product traceability systems, such as enterprise resource planning (ERP), due to the high costs and complexity involved for businesses of this scale. As customer expectations and regulatory requirements place an increasing emphasis on traceability and transparency, the combined use of industrial Internet of things (IIoT) technologies and blockchain-based smart contracts offers a promising pathway to cost-effective automation of supply chain processes. This paper develops a conceptual, multi-layer architecture that integrates sensing, communication, integration and smart-contract layers to support affordable, automated and extensible traceability for agri-food supply chains. Building on information processing theory and transaction cost economics, the framework explains how such architecture can reduce information uncertainty, lower monitoring costs and strengthen the organisational trust in agri-food supply chains. The framework is empirically illustrated and tested through an implementation that links distributed sensing infrastructure with a blockchain-based smart contract in a real agricultural supply chain setting. The evaluation assesses operational performance, data integrity and cost-efficiency, demonstrating that the proposed architecture can serve as a viable alternative or most importantly complement to traditional ERP solutions for small- and medium-sized enterprises that seek end-to-end traceability, transparency and automation. Full article

Reliable bearing fault diagnosis in induction motors is essential for predictive maintenance and Industrial Internet of Things (IIoT) applications. However, diagnostic models that perform well under random or measurement-wise data splits may fail when deployed under unseen operating conditions. This study presents a robustness-oriented comparative evaluation of induction motor bearing fault diagnosis models using vibration and phase-current signals from a controlled medium subset of the Paderborn bearing dataset. Raw temporal 1D-CNN models, STFT-based 2D-CNN representations, and vibration–current fusion strategies were evaluated under measurement-wise and operating-condition holdout protocols. Under measurement-wise validation, the 1D-CNN Early Fusion model achieved a Macro-F1 score of 0.9251. Under the stricter operating-condition holdout setting, the same model achieved the highest robustness among the evaluated CNN models. Multi-seed validation confirmed its stability, with a mean Macro-F1 of 0.8626, a worst-case Macro-F1 of 0.7159, and a robustness score of 0.7850. The selected model remained lightweight, requiring 73,891 trainable parameters and an estimated model size of 0.282 MB. Additional revision experiments were conducted to address bearing-identity sharing and classical baseline comparisons. In the bearing-code-disjoint validation test, both raw temporal models showed reduced performance, and early fusion did not significantly outperform vibration-only learning. The 1D-CNN Vibration model achieved a mean Macro-F1 of 0.5616, while the 1D-CNN Early Fusion model achieved 0.5485; the paired Wilcoxon test was not significant (p = 0.2016). Classical baselines using handcrafted time-domain, frequency-domain, envelope-inspired, and spectral-kurtosis features were also evaluated. The strongest classical baseline, vibration-feature XGBoost, achieved a mean Macro-F1 of 0.8582 under condition-holdout validation. Overall, the findings show that lightweight vibration–current early fusion provides a favorable robustness–complexity trade-off under operating-condition shift. However, the bearing-code-disjoint results indicate that complete generalization to unseen bearing identities remains challenging. Therefore, the deployment claims are limited to computational feasibility indicators, and further validation on embedded hardware, additional datasets, and stricter cross-domain protocols is required. Full article