Industrial Internet Of Things Research Articles

Optimized memory allocation in edge-PLCs using Deep Q-Networks and bidirectional LSTM with Quantum Genetic Algorithm

This paper offers a fresh perspective to memory allocation in edge-PLCs within industrial IoT environments, leveraging a hybrid a structure that incorporates Deep Q-Networks (DQN) and Bidirectional Long Short-Term Memory Networks (BiLSTM), complemented by Quantum Genetic Algorithm Optimization. In addressing the dynamic challenges of memory management, our method combines the reinforcement learning capabilities of DQN with the temporal contextualization provided by BiLSTM networks. The DQN component learns to optimize memory allocation policies based on immediate rewards and feedback, while the BiLSTM network captures long-term dependencies in data, enhancing predictive modeling for future data arrival rates. Moreover, we introduce Quantum Genetic Algorithm Optimization, a cutting-edge approach that infuses quantum-inspired principles into the traditional genetic algorithm framework, to further refine the memory allocation process. By leveraging principles of quantum computing, this optimization algorithm explores the solution space more efficiently, allowing for faster convergence and improved performance. Through simulation experiments, we exhibit the potency of our hybrid approach in reducing data loss probability and enhancing system performance in edge-PLCs. Our findings underscore the significance of integrating advanced machine learning techniques with quantum-inspired optimization algorithms to address complex challenges in industrial IoT environments, offering a promising avenue for enhancing memory allocation efficiency in edge computing systems.

Bridging academia and industry in the era of Industry 4.0 by means of the triple helix: The PLANET4 initiative

Practical Learning of Artificial Intelligence on the Edge of Industry 4.0 (PLANET4) is a cross-disciplinary initiative funded by the European Commission under the Erasmus+ program that embodies the triple helix model of collaboration between academia, industry, and administration. It aims to bridge the gap between academic teaching and practical applications in the context of Industry 4.0. PLANET4 focuses on developing hard skills in artificial intelligence, industrial Internet of things, and cloud and edge computing, along with the soft competencies required to manage changes in the industrial ecosystem. It involves three phases: (1) training needs analysis, taxonomy development, and workshop design; (2) collection of best practices and training material design; and (3) implementation of the PLANET4 learning course. This paper presents the materialization of these phases into a blended learning course, highlighting the integration of the triple helix model and the European Commission’s support for academia-industry collaboration with the aim of improving education quality and promoting Industry 4.0 innovation in Europe.

Evaluating Dimensionality Reduction Methods for the Detection of Industrial IoT Attacks in Edge Computing

Edge computing is essential for 6G mobile networks for improving reliability, reducing data rates and latency, and enhancing mobile connectivity. Edge computing is also meant to meet the increasing demands of the Internet of Things (IoT)/ Internet of Everything (IoE). In these approaches, IIoT systems necessitate precision, reliability, and scalability, while vulnerabilities in IIoT systems may lead to financial losses and safety hazards. To tackle this, Edge AI/ML-based IDSs provide adaptability and robustness for IIoT security challenges. These solutions improve security levels, threat detection rates, and response times. However, main issues such as limited resources and the accuracy of attack detection rate are challenged nowadays. In this paper, we present contributions in proposing an intrusion detection system (IDS) for edge devices deploying a lightweight deep neural network to detect IIoT attacks. We present performance analysis of the typical dimensionality reduction methods and balancing data features of the Edge-IIoT dataset to get higher performance metrics than other state-of-the-art studies.

Enhanced Fault Diagnosis in IoT: Uniting Data Fusion with Deep Multi-Scale Fusion Neural Network

One of the biggest challenges is figuring out when industrial IoT devices break. Notwithstanding these difficulties, one of the many advantages of using real-time sensor data from the Industrial Internet of Things (IIoT) is the ability to monitor events and respond promptly. The IIoT's sensor numbers may be analysed, combined with data from other sources, and applied quickly to make decisions. This manuscript proposes Enhanced Fault Diagnosis in IoT, Uniting Data Fusion with Deep Multi-Scale Fusion Neural Network (FD-IoT-DMSFNN). Initially, input sensor data are taken from the CWRU Dataset. Then, sensor data is normalised using Multivariate Fast Iterative Filtering. Then, the normalised sensor data are extensively dispersed and diverse; hence, the data outlier detection is performed using the Deep isolation forest (DIF) approach. Therefore, this manuscript proposes a Mexican Axolotl Optimization (MAO) for tuning the weight parameter of DMSFNN, which exhibits an enhanced fault detection process. Python is used to implement the recommended strategy. The proposed method's performance yields a lower completion time of 6.5%, 1.8%, and 4.13%; higher prediction accuracy of 2.26%, 6.71%, and 8.32% compared with existing approaches such as towards deep domain adaptability training methods for industrial IoT edge device soft real-time fault diagnosis (FD-IoT-LSTM), Intelligent Fault Quantitative Identification for the Industrial Internet of Things (IIoT) utilising a particular deep dual reinforcement learning model with insufficient samples (FD-IoT-DRL) and IIoT- based fault identification model for industrial use (FD-IoT-ML-LSTM) respectively.

An explainable unsupervised anomaly detection framework for Industrial Internet of Things

Industrial Internet of Things (IIoT) systems require effective anomaly detection techniques to ensure optimal operational efficiency. However, constructing a suitable anomaly detection framework for IIoT poses challenges due to the scarcity of labeled data. Additionally, most existing anomaly detection frameworks lack interpretability. To tackle these issues, an innovative unsupervised framework based on time series data analysis is proposed. This framework initially detects anomalous patterns in IIoT sensor data by extracting local features. An improved Time Convolutional Network (TCN) and Kolmogorov–Arnold Network (KAN) based Variational Auto-Encoder (VAE) is then constructed to capture long-term dependencies. The framework is trained in an unsupervised manner and interpreted using Explainable Artificial Intelligence (XAI) techniques. This approach offers insightful explanations regarding the importance of features, thereby facilitating informed decision-making and enhancements. Experimental results demonstrate that the framework is capable of extracting informative features and capturing long-term dependencies. This enables efficient anomaly detection in complex, dynamic industrial systems, surpassing other unsupervised methods.

Optimizing the System Life Cycle in Manufacturing Industry Through Implementation of IoT

This paper aims to explore how the implementation of the Internet of Things (IoT) can optimize the system life cycle in the manufacturing industry, enhancing efficiency, sustainability, and profitability. A qualitative research method with a case study approach was employed. Data collection techniques included observation, documentation, and in-depth interviews with management, supervisors, engineers, and operators. The data were analyzed using an interactive model, consisting of data reduction, data presentation, and conclusion drawing/verification. It was found that the implementation of IoT in the manufacturing industry's production process significantly improves production planning and control, asset and equipment maintenance, production cost reduction, product quality, and work environment safety. IoT-enabled real-time monitoring and data analytics facilitate better decision-making, predictive maintenance, and optimized resource utilization. It was found that. the implementation of IoT in the manufacturing industry's production process significantly improves production planning and control, asset and equipment maintenance, production cost reduction, product quality, and work environment safety. IoT-enabled real-time monitoring and data analytics facilitate better decision-making, predictive maintenance, and optimized resource utilization

Design and Implementation of Long Range Wide Area Networks for Future Industrial IoT Applications

Background: The evolution of Long Range Wide Area Networks (LoRaWAN) is a potential candidate for next generation networks for managing the massive number of devices in the Industrial Internet of Things (IIoT). LoRaWAN is more suitable for transmitting smaller intermittent data but using smaller bandwidth over a long distance. Objective: This research paper proposes to design a Low Power Wide Area Network (LPWAN) to provide long-range data transfer for Industrial IoT applications, especially for industrial sensor data. Methods: This research work deploys the experimental setup of LoRaWAN devices using LoRa gateways and Internet of Things network server to evaluate its performance for IIOT applications. Results: The deployment of this LoRaWAN has demonstrated its long range, low power, stability and low deployment cost through extensive performance evaluation carried out. LoRaWAN has been analyzed for its coverage and throughput performance. Conclusion: Through performance analysis, potential enhancements have been identified to overcome its shortcomings. This paper concludes the feasibility of deploying LoRaWAN technology for the future generation IIOT applications.

Unsourced Multiple Access for Mission-Critical Control Systems in Industrial Internet of Things

Unsourced Multiple Access for Mission-Critical Control Systems in Industrial Internet of Things

EXPRESS: Monitoring Technologies in Industrial Systems

Monitoring technologies, which are at the heart of the industrial Internet of Things (IOT) ecosystems, promise significant transactional efficiencies by making it easier to track product performance and contract compliance. These efficiencies are particularly compelling in industrial multi-vendor, multi-component systems, where complex component interdependencies often cause disputes around liability in the case of product failures. Drawing on transaction cost theory, fieldwork, and a national survey of industrial original equipment manufacturers we estimate how product performance contracts are specified in these contexts, and how these monitoring technologies can impact ex-post exchanges between OEMs and their suppliers. We find that systems architecture associated with the multi-component systems, as well as the presumed efficiencies of monitoring technologies, drive the contract designs through their potential impact on the disputes, monitoring, and contract writing costs faced by the OEM. However, we also find there are clear limits to the benefits offered by these monitoring technologies. The greater monitoring facilitated by these technologies appears to exacerbate disputes. This counterintuitive finding comports with the view that, when unforeseen interdependent failures occur, detailed data from monitoring may trigger a spate disputes over new and unexpected information, as well as over the appropriateness of existing protocols for failure metrics and remedies.

An Efficient RLWE-Based Privacy-Preserving Authentication Scheme Based on Edge Computing in Industrial Internet of Things

An Efficient RLWE-Based Privacy-Preserving Authentication Scheme Based on Edge Computing in Industrial Internet of Things

Smart Wearable Device for Enhancing Safety and Efficiency of Coal Miners

The task of ensuring worker safety in underground coal mines has never been simple. It has always been challenging to ensure worker safety in underground coal mines. Coal miners are seriously injured or killed as a result of numerous fatal and non-fatal accidents all over the world. Accidents occur as a result of lack of monitoring of mining areas and failure to implement proper safety measures. In this review, the coal miner's smart wearable safety device is implemented. A smart wearable safety device that will monitor the miner's health and provides precautionary measures for the miner's safety has been developed with the advent of the Industrial Internet of Things (IIoT). Integrating smart wearable safety devices with various health sensors such as a pulse rate sensor, temperature sensor, blood oxygen sensor, gas sensor, and camera, and then connecting it to Node MCU, and the internet enhances the safety of coal miners. Sensors constantly transmit sensor data to the cloud, and if an unusual situation arises, it notifies the responsible person in the control room as well as the miners. Since deep underground mining is especially susceptible to toxic gases, low levels of oxygen, and hazardous gases, the MQ gas sensor family can detect them. The proposed system is primarily used to improve working conditions inside coal mines and to ensure workers' safety.

Patch-Masked Visual Inspection via Parallel Deep Tensor Factorization in Industrial Internet of Things

Patch-Masked Visual Inspection via Parallel Deep Tensor Factorization in Industrial Internet of Things

Enabling Trustworthy Federated Learning in Industrial IoT: Bridging the Gap Between Interpretability and Robustness

Enabling Trustworthy Federated Learning in Industrial IoT: Bridging the Gap Between Interpretability and Robustness

HALO: HVAC Load Forecasting With Industrial IoT and Local–Global-Scale Transformer

HALO: HVAC Load Forecasting With Industrial IoT and Local–Global-Scale Transformer

Simultaneous Detection of the Orientation and Position of Moving Objects With Simple RFID Array for Industrial IoT Applications

Simultaneous Detection of the Orientation and Position of Moving Objects With Simple RFID Array for Industrial IoT Applications

AoI-Minimal Power Adjustment in RF-EH-Powered Industrial IoT Networks: A Soft Actor-Critic-Based Method

AoI-Minimal Power Adjustment in RF-EH-Powered Industrial IoT Networks: A Soft Actor-Critic-Based Method

Mentor's Musings on Federated Learning Standardization Imperatives in Leveraging It for Industrial IoT

Mentor's Musings on Federated Learning Standardization Imperatives in Leveraging It for Industrial IoT

Edge AI: Revolutionizing Real-Time Intelligence at the Network Periphery

Abstract: Edge AI, which transfers computation from centralized data centers to devices at the edge of the network, is a revolutionary development in artificial intelligence that offers advantages including real-time processing, decreased latency, increased privacy, and increased bandwidth efficiency. This paradigm is especially important for industrial IoT, smart city, and autonomous car applications where quick data processing and decision making are critical. Even with obstacles like scalability and hardware constraints, edge AI capabilities are being significantly expanded by continuing research and technical developments. Its revolutionary influence is demonstrated by current applications in a variety of domains, from improving industrial operations to urban infrastructure. Edge AI promises to revolutionize many industries, changing how we interact with technology and influencing the development of the next wave of AI applications as it develops further thanks to advancements in hardware and AI algorithms. With enormous potential for the future, edge AI represents a major advancement toward ubiquitous AI with broad ramifications for both technology and society

Intrusion detection and prevention systems in industrial IoT network

Intrusion detection and prevention systems in industrial IoT network

Improved Cell Allocation Strategies Using K-Means Clustering in Congested 6TiSCH Environments.

The 6TiSCH protocol (IEEE 802.15.4e) is crucial for the Industrial Internet of Things (IIoT), utilizing a time-slotted channel hopping (TSCH) mode based on node distribution. In this study, we propose an innovative cell allocation strategy based on node position clustering using the K-means algorithm, specifically designed to address congestion and optimize resource distribution in the 6TiSCH network. Our mechanism effectively groups nodes into clusters, allowing for dynamic adjustment of cell capacities in congested areas by analyzing traffic patterns and the spatial distribution of nodes. This clustering approach enhances the efficiency of slot frame utilization and minimizes communication delays by reducing interference and improving routing stability. The proposed strategy leverages the clustering results to improve cell usage efficiency and reduce communication latency between nodes. By tailoring cell allocation to the specific traffic needs of each cluster, we significantly reduce packet loss, manage congestion more effectively, and enhance data transmission reliability. We evaluated the clustering method using the K-means algorithm through experiments with the 6TiSCH simulator. Additionally, we considered using objective functions in Routing Protocol for Low-Power and Lossy Networks (RPL), such as OF0 and MRHOF, to assess clustering results and their impact on throughput and packet delivery. Our method resulted in significantly improved average performance metrics. Under the OF0 routing protocol, we achieved a 30.01% latency reduction, a 15.95% faster joining time, an 8% higher packet delivery ratio, and a 13.82% throughput increase. Similarly, we observed a 12.34% improvement in packet delivery ratio, 21.06% latency reduction, 12.68% faster joining time, and 25.97% higher throughput speed with the MRHOF routing protocol. These findings highlight the effectiveness of the improved cell allocation strategy in congested 6TiSCH environments, offering a better solution for enhancing network performance in IIoT applications.