Search

The article describes solutions in the field of diagnostics of a control system based on a CNC and the cooperation with an industrial robot. The industrial robot is controlled directly from the CNC. Data exchange between the CNC and the robot controller allows for collecting the most important process data from the robot. Then, calculations are performed in the PLC using a number of functions to obtain consumption indicators of individual robot components. The data were visualized on the HMI screens of the CNC. Additionally, a dedicated interface was prepared to share these data using the MQTT protocol for IIoT solutions. The entire solution was implemented and then deployed in a real station. The presented solution is an extension of the possibilities of operating an industrial robot by CNC towards diagnostics and early failure prevention. [ABSTRACT FROM AUTHOR]

The Industrial Internet of Things (IIoT) has significantly transformed manufacturing by enabling the integration of physical and digital systems, resulting in extensive data generation. However, extracting actionable insights from this heterogeneous data poses significant challenges due to its distributed nature and the varied architectures and formats from multiple vendors. A unified access method for data processing is essential to overcome these obstacles. This paper introduces the concept of an Independent Event Log Layer (IELL), leveraging the Resource Description Framework (RDF) and ontology-based knowledge representation to standardise and analyse event logs from disparate formats like eXtensible Event Stream (XES) and Comma-Separated Values (CSV). Utilising the RDF Mapping Language (RML), we propose a novel approach to convert event logs into RDF files, creating a unified knowledge base that enhances process mining capabilities. This semantic abstraction facilitates advanced knowledge retrieval and analysis, linking various events and attributes to optimise IIoT processes. A proof-of-concept implementation demonstrates the feasibility of our approach using openly available event log data and RML tooling. The findings underscore the potential of IELL to streamline process mining in IIoT environments, providing unified access for knowledge retrieval and process optimisation. [ABSTRACT FROM AUTHOR]

Critical Industries such as Manufacturing, Power, and Intelligent Transportation are increasingly using IIoT systems, making them more susceptible to cyberattacks. To counter these cyberattacks, policymakers have made strong guidelines, and various security provisions like secure authentication and encryption mechanisms as effective countermeasures for these systems. The exponential rise in cyberattacks has proven that all these measures are not sufficient to protect IIoT systems and have certain limitations. Considering the progress in Artificial Intelligence, it is widely acknowledged that Machine Learning (ML) based Intrusion Detection Systems (IDS) hold significant potential for identifying these cyberattacks. Numerous ML-based IDS have been proposed, which are capable of detecting known attacks but do not perform well in recognizing the "Unknown-Attacks" or Zero-Day Attacks (ZDAs) and Advanced Persistent Threats (APTs); hence, one of the most prominent concerns in the cyber industry is how threat intelligence could be used to protect against these exploits. The proposed "Hybrid Multi-Stage Intrusion Detection System" (HMS-IDS) is driven by supervised and unsupervised approaches to identify both known and unknown cyber-attacks in IIoT environments. By carefully evaluating the esteemed CIC-ToN-IoT dataset, the proposed IDS model attains staggering levels of accuracy, reaching an impressive 99.49% in detecting known attacks and an exceptional 98.936% in identifying unknown attacks. These compelling findings unequivocally substantiate the system's efficacy in real-time detection of malicious cyber incursions targeting IIoT devices, thereby underscoring its tremendous potential for wide-scale implementation and practical deployment. To validate the proposed model's reliability, the performance evaluation is also performed on state-of-the-art datasets, namely KDD-99 Cup, NSL-KDD, CICIDS 2017. [ABSTRACT FROM AUTHOR]

The Industrial Internet of Things (IIoT) has brought about a significant transformation across various industries, including transportation networks, smart factories, industrial power grids, and intelligent supply chains. By enabling intelligent communication among industrial machinery, this technology allows devices to autonomously connect and exchange operational data. However, despite its numerous advantages, IIoT faces major challenges, including data security vulnerabilities, high-energy consumption of sensors, significant latency in data transmission, limited scalability, high costs associated with network maintenance and development, inefficient resource allocation, susceptibility to cyberattacks, and fluctuations in Quality of Service (QoS) in dynamic environments. Addressing these challenges necessitates the development of comprehensive and adaptive solutions. This paper introduces an optimized hybrid architecture called EDBLSD-IIoT to tackle these challenges effectively. By integrating emerging technologies such as edge computing, blockchain, software-defined networking (SDN), and cloud computing, this architecture leverages their combined advantages to improve IIoT network performance. Edge computing reduces latency by processing data at locations closest to the source, while the SDN controller optimizes data traffic and minimizes energy consumption by employing the whale optimization algorithm (WOA) to select the best cluster head. Blockchain technology enhances data transmission security through a distributed ledger, addressing trust and tampering issues in IIoT networks. To evaluate the proposed framework, a case study was conducted in a smart car manufacturing factory. Various simulation scenarios were designed to assess parameters such as data transmission latency, bandwidth, throughput, CPU workload, energy consumption, and average end-to-end delay. The evaluation results indicate that the EDBLSD-IIoT architecture outperforms frameworks based on ant colony optimization (ACO) and genetic algorithm (GA). Specifically, this architecture achieves a latency of 0.45 ns in the largest network size, CPU usage of 3.1%, throughput of 18.4 Mbps in scenarios with the highest node count, a 72% reduction in energy consumption under the highest transaction request load, and a bandwidth of 0.3 KB per request per second at the highest packet input rate. Furthermore, the proposed method demonstrates superior average end-to-end delay performance compared to the routing protocol (RPL) and channel-aware routing protocol (CARP), underscoring its efficiency and robustness in addressing the multifaceted challenges of IIoT. [ABSTRACT FROM AUTHOR]

This paper proposes a credit-driven practical byzantine fault tolerance based on a consensus algorithm for sustainable 6G communication to address the potential threat of malicious activity in green and sustainable 6G-based Industrial Internet of Things (IIoT) applications. The dual-layer architecture allows for simultaneous verification of transactions and the execution of read-write operations. According to simulation studies, CD-PBFT enhances algorithm performance and stability while efficiently reducing validation time. Empirical findings demonstrate that CD-PBFT achieves both efficiency and security fault tolerance by reducing network transaction latency by an average of 34.8% and increasing throughput by 25.2% compared to PBFT. [ABSTRACT FROM AUTHOR]

This paper provides the complete details of current challenges and solutions in the cybersecurity of cyber-physical systems (CPS) within the context of the IIoT and its integration with edge computing (IIoT–edge computing). We systematically collected and analyzed the relevant literature from the past five years, applying a rigorous methodology to identify key sources. Our study highlights the prevalent IIoT layer attacks, common intrusion methods, and critical threats facing IIoT–edge computing environments. Additionally, we examine various types of cyberattacks targeting CPS, outlining their significant impact on industrial operations. A detailed taxonomy of primary security mechanisms for CPS within IIoT–edge computing is developed, followed by a comparative analysis of our approach against existing research. The findings underscore the widespread vulnerabilities across the IIoT architecture, particularly in relation to DoS, ransomware, malware, and MITM attacks. The review emphasizes the integration of advanced security technologies, including machine learning (ML), federated learning (FL), blockchain, blockchain–ML, deep learning (DL), encryption, cryptography, IT/OT convergence, and digital twins, as essential for enhancing the security and real-time data protection of CPS in IIoT–edge computing. Finally, the paper outlines potential future research directions aimed at advancing cybersecurity in this rapidly evolving domain. [ABSTRACT FROM AUTHOR]

In the industrial Internet of Things (IIoT), the interconnection between networks and hardware and between networks themselves produces a substantial volume of data. This leads to various security and privacy issues, greatly increasing the risk of data privacy breaches. Existing methods are not effective in ensuring secure storage of this data, and the effectiveness of intrusion detection is also not satisfactory. This paper proposes using blockchain and an attention-deep convolutional neural network (A-DCNN) based on deep learning to protect data security further and improve intrusion detection accuracy in IIoT. Firstly, blockchain is implemented using the hyperledger fabric framework in a consortium chain, combined with the interplanetary file system, to achieve distributed data storage. This prevents data poisoning attacks and ensures data immutability and traceability. Secondly, a deep variational autoencoder is employed for the purpose of re-encoding the original data into a novel format, thus deterring potential attackers from conducting inference attacks. In addition, in the data preprocessing stage, the synthetic minority over-sampling technique combined with edited nearest neighbors is applied to enhance the sample data, significantly improving the accuracy, precision, and other evaluation metrics for small samples. Finally, the A-DCNN model is used in the intrusion detection module to detect malicious intrusions in IIoT. We conducted experiments using the new generation IIoT 4.0 datasets TON_IoT and the IoT network traffic datasets BoT-IoT. In the BoT-IoT datasets, the five-class precision reached 97.03%, and the binary classification accuracy reached 98.50%. In the TON_IoT datasets, the ten-class precision reached 99.50%, and the binary classification accuracy reached 97.86%. Compared to several existing techniques, these experimental results demonstrate that this framework effectively protects IIoT data and detects malicious intrusions in IIoT. [ABSTRACT FROM AUTHOR]

Reconnaissance attacks serve as the initial phase of Advanced Persistent Threats (APTs). The study proposes CluSHAPify, an approach that integrates SHAP-based traffic metadata selection with hierarchical clustering interpretations to determine the most relevant features for attack detection across different attack flow classes. Unlike most studies that select the top-k features, the proposed study uses hierarchical clustering to justify the selection of features identified with the highest SHAP values ensuring the most relevant features are chosen for effective attack detection across different attack flow classes. Additionally, CluSHAPify leverages multiple learners, making it a crossmodel approach that also overcomes the limitations of SHAP-based feature selection, which is inherently model-dependent. The proposed approach uses multiple learners to improve feature selection robustness by capturing diverse perspectives, combining XAI for enhanced accuracy and explainability, a novel approach in existing research. This study uses performance metrics designed for unbalanced datasets, demonstrating its effectiveness with various learners, including XGBoost, Random Forest, Decision Tree, and Extra Trees. This makes CluSHAPify a reliable and adaptable solution for detecting reconnaissance attacks in IIoT environments. [ABSTRACT FROM AUTHOR]

Copyright of Radio Communications Technology is the property of 54th Research Institute of CETC and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The convergence of IT and OT networks has gained significant attention in recent years, facilitated by the increase in distributed computing capabilities, the widespread deployment of Internet of Things devices, and the adoption of Industrial Internet of Things. This convergence has led to a drastic increase in external access capabilities to previously air-gapped industrial systems for process control and monitoring. To meet the need for remote access to system information, protocols designed for the OT space were extended to allow IT networked communications. However, OT protocols often lack the rigor of cybersecurity capabilities that have become a critical characteristic of IT protocols. Furthermore, OT protocol implementations on individual devices can vary in performance, requiring the comprehensive evaluation of a device's reliability and capabilities before installation into a critical infrastructure production network. In this paper, the authors define a framework for identifying vulnerabilities within these protocols and their on-device implementations, utilizing formal modeling, hardware in the loop-driven network emulation, and fully virtual network scenario simulation. Initially, protocol specifications are modeled to identify any vulnerable states within the protocol, leveraging the Construction and Analysis of Distributed Processes (CADP) software (version 2022-d "Kista", which was created by Inria, the French Institute for Research in Computer Science and Automation, in France). Device characteristics are then extracted through automated real-time network emulation tests built on the OMNET++ framework, and all measured device characteristics are then used as a virtual device representation for network simulation tests within the OMNET++ software (version 6.0.1., a public-soucre, open-architecture software, initially developed by OpenSim Limited in Budapest, Hungary), to verify the presence of any potential vulnerabilities identified in the formal modeling stage. With this framework, the authors have thus defined an end-to-end process to identify and verify the presence and impact of potential vulnerabilities within a protocol, as shown by the presented results. Furthermore, this framework can test protocol compliance, performance, and security in a controlled environment before deploying devices in live production networks and addressing cybersecurity concerns. [ABSTRACT FROM AUTHOR]

The paper presents a novel LoRa-based IIoT system for monitoring the underground coal mine environment. Additionally, a new adaptive data rate algorithm for mesh network topology is proposed to optimize the data rate and maximize the coverage distance. Maximum coverage distance is achieved with a minimum number of repeaters. However, unlike previous works, the current work takes into account the power constraints in the underground coal mine environment, and most low-power consumption system is presented with an intelligent design approach. The implementation of the proposed adaptive data rate algorithm achieves 1.46 Kbps data rate at spreading factor 9, bandwidth 125 KHz, and transmitted power 11 dBm and extended the battery life of the deployed end nodes. The deployed end nodes achieved a maximum of 180 m under diffused line-of-sight condition at the roadway region of the operational mine. The relevant parameters are measured from the operational mine. Finally, the hardware is fabricated and the proposed system is validated in an operational underground coal mine.

The Internet of Things (IoT) and the Industrial Internet of Things (IIoT) have grown significantly in the last decade, underlining the increasing need for effective, secure, and reliable data communication protocols. The widely accepted Message Queuing Telemetry Transport (MQTT) protocol, with its structure that meets the needs of welding-oriented devices in IoT and IIoT applications, is a prime example. However, its user-friendly simplicity also makes it susceptible to threats such as Dispersed Services Rejection (DDOS), Brete-Force, and incorrectly shaped package attacks. This article introduces a robust and reliable framework for preventing and defending against such attacks in MQTT-based IIoT systems based on the theory of merging attacks. The expert system incorporates the Adaboost model and can detect anomalies by processing network traffic in a closed setting and identifying impending threats. With its robust design, the system was subjected to various attack scenarios during testing, and it consistently detected interventions with an average accuracy of 92.7%, demonstrating its potential for use in intervention detection systems. The research findings not only contribute to the theoretical and practical concerns about the effective protection of IIoT systems but also offer hope for the future of cybersecurity in these systems.

The classical OFDM multicarrier waveforms for transmission are adopted by the existing 5G/B5G URLLC standard (3GPP R17-18), and less attention is paid to the anti-interference strategy of URLLC-OFDM multicarrier transmission due to its operation in the licensed frequency band. In the future, unlicensed frequency bands will host most heterogeneous multi-QoS services for IIoT, resulting in complex wireless communication links. The stringent requirements of high reliability and low latency for IIoT information transmission can not be fully met by the existing URLLC-OFDM waveforms. Firstly, the more robust Sub-FH technique was applied to OFDMA based on subcarrier-configurable OFDMA (i.e., Sub-FH/OFDMA) to improve the signal transmission reliability. Additionally, the Sub-FH/OFDMA waveforms were incorporated into a scheduling strategy with mini-slots as the basic unit. Hamming coding + mini-slot hopping HARQ were utilized by this scheduling strategy to effectively reduce the amount of retransmissions, which aim to enhance the real-time transmission among IIoT nodes. The theoretical relationship between BER/BLER and transmission delay was derived and compromises were made. Simulation results demonstrate that the scheme can ensure stable transmission quality of IIoT nodes despite external electromagnetic interference and internal multi-user interference, achieving a transmission delay of milliseconds when the target BLER is 10-5. A feasible solution for the future practical application of B5G/6G communication in complex IIoT scenarios is provided through the cross-layer design of waveform design and MAC slot scheduling in this paper.

Due to its outstanding privacy-related characteristics, Federated Learning (FL) has recently become a popular solution for the IIoT’s data privacy and scalability issues. However, more research is needed to determine how unique streaming data in IIoT Settings affects FL-enabled IIoT architectures, with unique streaming data affecting accuracy and reducing convergence performance. To achieve this goal, this paper explains the streaming data learning problem in an IIoT framework enabled by FL. Afterward, it outlines two unique issues relevant to this situation: convergence and the catastrophic forgetting that occurs throughout training. This article presents FedStream, a practical FL framework for IIoT streaming data applications, considering these challenges. In particular, we develop a straightforward and effective pairwise similarity-based streaming data replacement training method that systematically replaces original data samples with ones that show high similarity during the iterative training process. This not only improves the accuracy but also reduces the convergence process and catastrophic forgetting problem. Comprehensive case studies support the effectiveness of the proposed method. Finally, the article recommends potential research areas, encouraging academics and industry professionals to explore these emerging topics further.

Abstract In recent years, with the application of Internet of Things (IoT) and cloud technology in smart industrialization, Industrial Internet of Things (IIoT) has become an emerging hot topic. The increasing amount of data and device numbers in IIoT poses significant challenges to its security issues, making anomaly detection particularly important. Existing methods for anomaly detection in the IIoT often fall short when dealing with data imbalance, and the huge amount of IIoT data makes feature selection challenging and computationally intensive. In this paper, we propose an optimal deep learning model for anomaly detection in IIoT. Firstly, by setting different thresholds of eXtreme Gradient Boosting (XGBoost) for feature selection, features with importance above the given threshold are retained, while those below are ignored. Different thresholds yield different numbers of features. This approach not only secures effective features but also reduces the feature dimensionality, thereby decreasing the consumption of computational resources. Secondly, an optimized loss function is designed to study its impact on model performance in terms of handling imbalanced data, highly similar categories, and model training. We select the optimal threshold and loss function, which are part of our optimal model, by comparing metrics such as accuracy, precision, recall, False Alarm Rate (FAR), Area Under the Receiver Operating Characteristic Curve (AUC-ROC), and Area Under the Precision–Recall Curve (AUC-PR) values. Finally, combining the optimal threshold and loss function, we propose a model named MIX_LSTM for anomaly detection in IIoT. Experiments are conducted using the UNSW-NB15 and NSL-KDD datasets. The proposed MIX_LSTM model can achieve 0.084 FAR, 0.984 AUC-ROC, and 0.988 AUC-PR values in the binary anomaly detection experiment on the UNSW-NB15 dataset. In the NSL-KDD dataset, it can achieve 0.028 FAR, 0.967 AUC-ROC, and 0.962 AUC-PR values. By comparing the evaluation indicators, the model shows good performance in detecting abnormal attacks in the Industrial Internet of Things compared with traditional deep learning models, machine learning models and existing technologies.

The paradigms of Industry 4.0 and Industrial Internet of Things (IIoT) require functional architectures to deploy and organize hardware and software taking advantage of modern digital technologies in industrial systems. In this sense, a lot of the literature proposes and describes this type of architecture with a conceptual angle, without providing experimental validation or with scarce details about the involved equipment under real operation. Aiming at overcoming these limitations, this paper presents the experimental application of an IIoT architecture divided into four functional layers, namely, Sensing, Network, Middleware and Application layers. Automation and IoT hardware and software are used to implement and apply the architecture. Special attention is put on the software Grafana, chosen in the top layer to deploy graphical user interfaces that are remotely accessible via web. A pilot microgrid integrating photovoltaic energy and hydrogen served as scenario to test and prove the suitability of the architecture in four application cases. [ABSTRACT FROM AUTHOR]

In the IIoT, billions of devices continually provide information that is extremely diverse, variable, and large-scale and presents significant hurdles for interpretation and analysis. Additionally, issues about data transmission, scaling, computation, and storage can result in data anomalies that significantly affect IIoT applications. This work presents a novel anomaly detection framework for the IIoT in the context of the challenges posed by vast, heterogeneous, and complex data streams. This paper proposes a two-staged multi-variate approach employing a composition of long short-term memory (LSTM) and a random forest (RF) Classifier. Our approach leverages the LSTM's superior temporal pattern recognition capabilities in multi-variate time-series data and the exceptional classification accuracy of the RF model. By integrating the strengths of LSTM and RF models, our method provides not only precise predictions but also effectively discriminates between anomalies and normal occurrences, even in imbalanced datasets. We evaluated our model on two real-world datasets comprising periodic and non-periodic, short-term, and long-term temporal dependencies. Comparative studies indicate that our proposed method outperforms well-established alternatives in anomaly detection, highlighting its potential application in the IIoT environment. [ABSTRACT FROM AUTHOR]

The conventional centralized Industrial Internet of Things (IIoT) framework is plagued by issues like subpar security performance and challenges related to storage expansion. This paper proposes a two-tier distributed secure storage framework based on blockchain for IIoT data. The authors first introduce the two-layer framework, which includes the edge network layer and the blockchain storage layer. The nodes in the edge network layer are classified into administrator nodes and ordinary nodes. It provides a lower latency network environment compared to cloud computing to preprocess raw industrial data. The blockchain storage layer provides storage space to keep data secure and traceable. Secondly, the authors propose a differentiated storage solution. Based on the timestamps of industrial data and the specific media access control (MAC) address, the Universally Unique Identifier (UUID) of the raw data is generated and uploaded to the blockchain for secure storage. Encrypt the corresponding raw data using the elliptic curve cryptography algorithm, and then upload it to InterPlanetary File System (IPFS) to expand the storage capacity of the blockchain. Deploy a smart contract on the blockchain to compare UUIDs for consistency in an automated, lightweight method to determine data integrity. Finally, we analyze the advantages brought by the integration of blockchain and IIoT. Additionally, the authors design comparative tests on different storage methods. The results prove that the security of this paper's scheme is improved, and the storage performance is extended. Noteworthy enhancements include heightened throughput of data uploaded to the blockchain and minimized delay overhead. [ABSTRACT FROM AUTHOR]

The application of blockchain technology in the realm of the Industrial Internet of Things has garnered significant attention in recent research. One of the critical requirements for Industrial Internet of Things is secure real-time data monitoring. While blockchain presents a robust platform for ensuring secure remote monitoring, it also faces challenges when it comes to real-time data transmission, particularly concerning data packet loss. In this study, we propose a conceptual framework utilizing Hyperledger Fabric blockchain for secure real-time remote monitoring within Industrial Internet of Things applications. To validate this concept, we established a Hyperledger Fabric blockchain network comprising several machines and simulated the monitoring of data packets. Through a series of experiments, we assessed the performance of the Hyperledger Fabric blockchain network regarding secure real-time data monitoring, specifically focusing on data packet loss. In 31 experiments, 18 achieved success with no packet loss, demonstrating effective network functionality. For optimal performance, the time between transaction generation must meet or exceed block generation time to reduce packet loss. Additionally, the sizes of transactions and blocks should align with data packet length, ensuring all sensory data is captured in each transaction. The count of transactions per block varies based on network strategy and monitoring time. Lastly, using robust hardware for network nodes is crucial for enhancing processing speed and storage, ultimately improving network performance. The insights gained from this research can facilitate the practical implementation of blockchain-based real-time industrial data monitoring systems in Industrial Internet of Things environments. [ABSTRACT FROM AUTHOR]

In an era where Information and Communication Technologies (ICT) redefine the boundaries of competition and collaboration, the concept of coopetition — simultaneous competition and cooperation — emerges as a strategic imperative for small and medium-sized enterprises (SMEs). This study presents the design and development of an Industrial Internet of Things (IIoT) artefact designed to enable competition among SMEs. Bringing the Service-Dominant Logic (S-D logic) foundations to IIoT, a Design Science Research (DSR) approach was employed. This approach facilitated the integration of design theory with practical problem-solving, creating the Coopetition IIoT-based System. The primary goal of this solution is to augment the dynamics of coopetition networks, with a particular focus on SMEs. The practical evaluation of the Coopetition IIoT-based System is assessed through a prototype evaluation by experts representing twenty-four manufacturing stone SMEs, a crucial sector in the Portuguese economy. The feedback received was highly positive, indicating a positive evaluation rate of 78.9%. This favourable response highlights the Coopetition IIoT-based System's proficiency in fostering simultaneous competition and cooperation throughout the lifecycle of business opportunities in SME networks, thereby underscoring its potential as a facilitator of effective competition. Theoretically, this research enriches the application of S-D logic in coopetition networks and advances state-of-the-art IIoT systems. Practically, the Coopetition IIoT-based System demonstrates significant potential in boosting the competitiveness of SMEs in developed economies. Nonetheless, the ultimate efficacy of such IIoT systems will be best determined through real-world application and evaluation. Future research should concentrate on the real-case deployment and assessment of Coopetition IIoT-based Systems within coopetition networks. [ABSTRACT FROM AUTHOR]

Lean manufacturing focuses on perfection, trying to eliminate all types of Muda (waste), Mura (inconsistency), Muri (overburden), defects, injuries, and accidents through a continuous improvement process. Assembly lines are the final stages of manufacturing before the product is delivered to customers. Kata methodology provides a practical approach to achieving perfection in assembly lines, but its effectiveness is often hindered by delays in data collection, analysis, and diagnostics. In this study, we address these challenges by leveraging industrial internet of things (IIoT) solutions in an industrial setting. The research question of this paper is as follows: "Why was the full potential of traditional Kata to achieve assembly line perfection not realized, and will IIoT-integrated Kata address the limitations of the traditional Kata?" We demonstrate the integration of IIoT and Kata methodology in a factory assembling automobile heating, ventilation, and air conditioning (HVAC) systems to enhance assembly line productivity. We observe that the integration of IIoT with Kata methodology not only addresses existing limitations but drives substantial gains in assembly line performance. We validate improvements in both productivity and efficiency through quantitative and qualitative outcomes. We underscore the pivotal role of real-time data for Kata's effectiveness, discuss the process for digital transformation, and explain the need for data monetization. We recommend the development of an IIoT-savvy workforce, traceability of 4M (men, method, materials, and machine), and present the task scorecards and dashboards for real-time monitoring and decision-making. We highlight the positive impact of IIoT-enabled traceability on overall equipment effectiveness (OEE). The company reduced its workforce from 15 to 13 operators, increased OEE from 75% to 85%, and improved average throughput from 60 to 90 assemblies per hour. The time for traceability of 4M (men, machines, material, and method) was reduced from hours to minutes. The factory eliminated 350 paper documents to achieve a paperless shop floor. This real-world case study serves as a model for companies looking to transition from traditional continuous improvement processes to IIoT-supported lean manufacturing. [ABSTRACT FROM AUTHOR]

In the Industrial Internet of Things (IIoT), leveraging Internet of Things (IoT) technologies such as machines, sensors, and software in industrial applications has been instrumental in enhancing productivity. However, the inherent vulnerability of IIoT systems to cyber-attacks poses significant threats to critical infrastructure and security. This paper explores the improvement of IIoT intrusion detection with ML techniques, using supervised models such as Random Forest and Decision Tree on the NF-UNSW-NB15-v2 dataset. SMOTE is applied to balance the data and improve accuracy, recall, and F1-Score. Two approaches, a multiclass classification and a binary classification followed by a multiclass, are evaluated via performance metrics. This study highlights the potential of machine learning to enhance IIoT security and highlights the importance of data balance in intrusion detection systems. [ABSTRACT FROM AUTHOR]

Due to its outstanding privacy-related characteristics, Federated Learning (FL) has recently become a popular solution for the IIoT's data privacy and scalability issues. However, more research is needed to determine how unique streaming data in IIoT Settings affects FL-enabled IIoT architectures, with unique streaming data affecting accuracy and reducing convergence performance. To achieve this goal, this paper explains the streaming data learning problem in an IIoT framework enabled by FL. Afterward, it outlines two unique issues relevant to this situation: convergence and the catastrophic forgetting that occurs throughout training. This article presents FedStream, a practical FL framework for IIoT streaming data applications, considering these challenges. In particular, we develop a straightforward and effective pairwise similarity-based streaming data replacement training method that systematically replaces original data samples with ones that show high similarity during the iterative training process. This not only improves the accuracy but also reduces the convergence process and catastrophic forgetting problem. Comprehensive case studies support the effectiveness of the proposed method. Finally, the article recommends potential research areas, encouraging academics and industry professionals to explore these emerging topics further. [ABSTRACT FROM AUTHOR]

In recent years, with the application of Internet of Things (IoT) and cloud technology in smart industrialization, Industrial Internet of Things (IIoT) has become an emerging hot topic. The increasing amount of data and device numbers in IIoT poses significant challenges to its security issues, making anomaly detection particularly important. Existing methods for anomaly detection in the IIoT often fall short when dealing with data imbalance, and the huge amount of IIoT data makes feature selection challenging and computationally intensive. In this paper, we propose an optimal deep learning model for anomaly detection in IIoT. Firstly, by setting different thresholds of eXtreme Gradient Boosting (XGBoost) for feature selection, features with importance above the given threshold are retained, while those below are ignored. Different thresholds yield different numbers of features. This approach not only secures effective features but also reduces the feature dimensionality, thereby decreasing the consumption of computational resources. Secondly, an optimized loss function is designed to study its impact on model performance in terms of handling imbalanced data, highly similar categories, and model training. We select the optimal threshold and loss function, which are part of our optimal model, by comparing metrics such as accuracy, precision, recall, False Alarm Rate (FAR), Area Under the Receiver Operating Characteristic Curve (AUC-ROC), and Area Under the Precision–Recall Curve (AUC-PR) values. Finally, combining the optimal threshold and loss function, we propose a model named MIX_LSTM for anomaly detection in IIoT. Experiments are conducted using the UNSW-NB15 and NSL-KDD datasets. The proposed MIX_LSTM model can achieve 0.084 FAR, 0.984 AUC-ROC, and 0.988 AUC-PR values in the binary anomaly detection experiment on the UNSW-NB15 dataset. In the NSL-KDD dataset, it can achieve 0.028 FAR, 0.967 AUC-ROC, and 0.962 AUC-PR values. By comparing the evaluation indicators, the model shows good performance in detecting abnormal attacks in the Industrial Internet of Things compared with traditional deep learning models, machine learning models and existing technologies. [ABSTRACT FROM AUTHOR]

The communication of Industrial Internet of Things (IIoT) devices faces important security and privacy challenges. With the rapid increase in the number of devices, it is difficult for traditional security mechanisms to balance performance and security. Although schemes based on encryption and authentication exist, there are still difficulties in achieving lightweight security. In this paper, an authentication and key exchange scheme combining hardware security features and modern encryption technology is proposed for the MQTT-SN protocol, which is not considered security. The scheme uses Physical Unclonable Functions (PUFs) to generate unpredictable responses, and combines random numbers, time stamps, and shared keys to achieve two-way authentication and secure communication between devices and broker, effectively preventing network threats such as replay and man-in-the-middle attacks. Through verification, the proposed scheme has proved effective in terms of security and robustness, has computational and communication cost advantages compared with recent schemes, and provides higher availability. [ABSTRACT FROM AUTHOR]

In the past few years, latency‐sensitive task computing over the industrial internet of things (IIoT) has played a key role in an increasing number of intelligent applications, such as intelligent self‐driving vehicles and unmanned aircraft systems. The edge computing paradigm provides a basic functional infrastructure for across‐domain business task computing on distributed edge servers. With this observation, a trade‐off between the mobile devices and the fixed edge servers is needed to run moving task computing in a low‐latency way. Given this challenge, an intelligent server selection method, named SeeMe, is proposed in this paper. Technically speaking, this method aims at minimizing the communication capacity and the transferring capacity in a multiobjective optimization way to find a low‐latency edge server. The experiments and comparison analysis verify the availability of our method. [ABSTRACT FROM AUTHOR]

This paper introduces an innovative hybrid wireless power transfer (H-WPT) scheme tailored for IIoT networks employing multiple relay nodes. The scheme allows relay nodes to dynamically select their power source for energy harvesting based on real-time channel conditions. Our analysis evaluates outage probability within decode-and-forward (DF) relaying and adaptive power splitting (APS) frameworks, while also considering the energy used by relay nodes for ACK signaling. A notable feature of the H-WPT scheme is its decentralized operation, enabling relay nodes to independently choose the optimal relay and power source using instantaneous channel gain. This approach conserves significant energy otherwise wasted in centralized control methods, where extensive information exchange is required. This conservation is particularly beneficial for energy-constrained sensor networks, significantly extending their operational lifetime. Numerical results demonstrate that the proposed hybrid approach significantly outperforms the traditional distance-based power source selection approach, without additional energy consumption or increased system complexity. The scheme's efficient power management capabilities underscore its potential for practical applications in IIoT environments, where resource optimization is crucial. [ABSTRACT FROM AUTHOR]