Industrial Internet Of Things Applications Research Articles

Optimal Resource Management for Hierarchical Federated Learning Over HetNets With Wireless Energy Transfer

Remote monitoring systems analyze the environment dynamics in different smart industrial applications, such as occupational health and safety, and environmental monitoring. Specifically, in industrial Internet of Things (IoT) systems, the huge number of devices and the expected performance put pressure on resources, such as computational, network, and device energy. Distributed training of Machine and Deep Learning (ML/DL) models for intelligent industrial IoT applications is very challenging for resource limited devices over heterogeneous wireless networks (HetNets). Hierarchical Federated Learning (HFL) performs training at multiple layers offloading the tasks to nearby Multi-Access Edge Computing (MEC) units. In this paper, we propose a novel energy-efficient HFL framework enabled by Wireless Energy Transfer (WET) and designed for heterogeneous networks with massive Multiple-Input Multiple-Output (MIMO) wireless backhaul. Our energy-efficiency approach is formulated as a Mixed-Integer Non-Linear Programming (MINLP) problem, where we optimize the HFL device association and manage the wireless transmitted energy. However due to its high complexity, we design a Heuristic Resource Management Algorithm, namely H2RMA, that respects energy, channel quality, and accuracy constraints, while presenting a low computational complexity. We also improve the energy consumption of the network using an efficient device scheduling scheme. Finally, we investigate device mobility and its impact on the HFL performance. Our extensive experiments confirm the high performance of the proposed resource management approach in HFL over HetNets, in terms of training loss and grid energy costs.

Preserving Privacy in Industrial IoT: A Machine Learning Framework Enhanced by Poly1305 Encryption

Abstract: The convergence of Industrial Internet of Things (IoT) systems and machine learning has ushered in new paradigms for predictive maintenance, anomaly detection, and quality control in industrial sectors. Though, the sensitive nature of data generated by IoT devices raises significant privacy and security concerns. To address these challenges, this review paper presents a thorough examination of safeguarding privacy machine learning frameworks in the context of Industrial IoT environments, leveraging the robust Poly1305 encryption algorithm. This paper commences by surveying the landscape of Industrial IoT applications, highlighting the urgency of safeguarding sensitive data without compromising the potential insights gleaned from machine learning models. It then delves into the intricacies of Poly1305 encryption, elucidating its strengths in ensuring data integrity, authenticity, and confidentiality. The integration of Poly1305 encryption within machine learning pipelines is explored, considering encryption at data collection, transmission, storage, and analysis stages. The review systematically analyses a spectrum of data learning models deployed in Industrial IoT scenarios, spanning predictive maintenance to quality enhancement. Each model's compatibility with Poly1305 encryption is assessed, along with performance implications and security guarantees. The paper navigates through key obstacles including key management, computational overhead, and interoperability concerns. In summation, this review paper not only serves as a comprehensive guide for researchers and practitioners in the realm of Industrial IoT and machine learning but also contributes to the ongoing discourse on safeguarding data privacy while harnessing the transformative power of data-driven insights

Privacy preserved data sharing using blockchain and support vector machine for industrial IOT applications

The Industrial Internet of Things (IIoT) paradigm's fast expansion in the amount of information created from linked devices creates new opportunities for improving the service quality and applications through sharing of data. Data security is a significant problem since training and Support Vector Machine (SVM) classifier often involves compiling tagged IoT data from several organizations. Beyond causing the suppliers to lose money, disclosing sensitive information might cause significant problems. To solve these issues, introduced a secure SVM, which is a Privacy-Preserving SVM (PP-SVM) training method using block chain-based encoded IoT data, to fill the void between ideal assumptions and practical restrictions. IoT messages are encrypted before being stored on a decentralized system because Block chain offers safe and dependable data exchange platforms across several data sources. Using a homomorphic cryptographic algorithm, Paillier, reliable modules have been developed, such as protected algebraic multiplying and protected comparison. Furthermore, a protected SVM learning algorithm that only needs two conversations during a single step has been created. According to stringent security assessment, proposed approach guarantees SVM model parameters for data professionals and secrecy of sensitive information for each data source. Extensive testing backs up effectiveness of the suggested plan.

Hierarchical and Multi-Group Data Sharing for Cloud-Assisted Industrial Internet of Things

With the development of Industrial Internet of Things (IIoT) and 5G, massive data are easily collected and transmitted in cloud. Therefore, it is critical to guarantee the security of data sharing. In IIoT applications, the users of a group are in hierarchical structure and they intend to access data by external groups, which requires fine-grained access control, data authenticity and data retrieval. However, existing approaches rarely provide such solutions to satisfy these requirements simultaneously. In this paper, we propose an efficient hierarchical and multi-group data sharing framework (HMGDSF) in cloud-assisted IIoT. Apart from fine-grained data access control for hierarchical users with key leakage resilience, HMGDSF achieves user anonymity with traceability and keyword-based data retrieval. Moreover, the approach supports data authenticity and integrity verification for multi-group data sharing by integrating group signature mechanism. We provide proof for the security of framework and demonstrate its efficiency and practicability by extensive evaluations.

Deep Reinforcement Learning Based Cooperative Partial Task Offloading and Resource Allocation for IIoT Applications

Compared with traditional cloud computing schemes, edge computing provides an effective solution towards meeting real-time, security and reliability demands of compute-intensive and delay-sensitive Industrial Internet of Things (IIoT) applications. However, many existing studies only optimize end-edge-cloud cooperative task offloading, and neglect the optimization of the communication and computation resource allocation. In this paper, the cooperative partial task offloading and resource allocation (CPTORA) framework is designed, which jointly considers cooperation among various IIoT devices, local edge computing servers (ECSs), non-local ECSs, and cloud computing servers. Then, considering the complex dynamics and unpredictability in IIoT environments, the joint optimization problem is modeled as a constrained Markov decision process. Furthermore, we propose an improved soft actor-critic-based CPTORA (ISAC-CPTORA) algorithm, to make task offloading and resource allocation decisions for each IIoT device. This algorithm innovatively introduces the idea of distributional reinforcement learning to the soft actor-critic, which can effectively reduce Q-value overestimations or underestimations. Meanwhile, this algorithm employs the prioritized experience replay to enhance its learning efficiency. Extensive laboratory experiments indicate that our CPTORA framework and ISAC-CPTORA algorithm efficiently decrease the total system costs, in contrast to various baseline frameworks and algorithms.

MapChain-D: A Distributed Blockchain for IIoT Data Storage and Communications

With the rapid growth of the Industrial Internet of Things (IIoT) devices, managing extensive volume of IIoT data becomes a significant challenge. While the conventional cloud storage approaches with centralised data centres suffer from high latency for large-scale IIoT data storage due to the increased communications and latency overheads, distributed storage frameworks such as blockchains have become promising solutions. In this paper, we design and analyse a dual-blockchain framework for secure and scalable distributed data management in large-scale IIoT networks. The proposed framework, named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MapChain-D</i> , consists of a data chain that is mapped to an index chain to provide efficient data storage and lookup. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MapChain-D</i> is designed for practical IIoT applications with storage, latency, and communications constraints. Detailed data exchange protocols are presented for the data insertion and retrieval operations in <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MapChain-D</i> . Based on these, theoretical analyses are provided on the space, time, and communications complexities of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MapChain-D</i> compared with conventional single-chain frameworks with local and distributed data storage. We implement our <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MapChain-D</i> prototype using open-source LoRaWAN communications with multiple RPi and Arduino devices, Kademlia-based distributed hash table (DHT), and Ethereum-based blockchain with proof-of-authority (PoA) consensus. Experimental results from our prototype show that <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MapChain-D</i> is more suitable to be deployed on resource-constrained IIoT devices. We also highlight the scalability and flexibility of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MapChain-D</i> with different numbers of edge nodes in the system.

Anomaly detection with a container-based stream processing framework for Industrial Internet of Things

Online anomaly detection is a key challenge for industrial internet of things (IIoT) applications, as anomalies may occur in data streams from sensors and cause losses or damages. However, most existing methods for online anomaly detection have limitations in efficiency, effectiveness and timeliness, especially with the massive and distributed data streams from IIoT devices. Therefore, developing a data stream processing framework to discover anomalies in time and ensure the proper operation of the system is an urgent issue for IIoT. In this paper, we propose a flexible stream processing framework that enables online anomaly detection for IIoT applications. The framework exploits a distributed computing architecture based on docker containers to improve flexibility, migration capability and customization. The framework also uses a central mediator to coordinate data stream processing tasks running on different docker nodes. Moreover, we develop a prediction-based online anomaly detection model that consists of batch model training and data stream anomaly detection processes. The model uses long short-term memory (LSTM) neural networks to predict data stream values and a dynamic sliding window method to model prediction errors and detect anomalies. We implement a case study to detect abnormal heating temperatures from an industrial heating plant and evaluate the performance of the proposed framework and anomaly detection model. The results show that our framework and model can achieve high accuracy and low latency in detecting anomalies, and they outperform existing methods in terms of scalability, efficiency and adaptability for IIoT applications.

Joint DoA and CFO Estimation Scheme With Received Beam Scanned Leaky Wave Antenna for Industrial Internet of Things (IIoT) Systems

Direction-of-arrival (DoA) estimation is essential in many industrial internet of things (IIoT) applications where IoT users may require a high-resolution estimation algorithm for features limited to positioning and device localization. The conventional DoA estimation is challenging as the number of antenna arrays increases leading to an increase in design complexity and cost in RF circuitry. As a result, the conventional DoA estimation algorithms may not be suited for IIoT applications. In this work, a joint DOA and carrier frequency offset (CFO) schemes is introduced for typical uplink IIoT systems by equipping the receiver with a leaky-wave antenna (LWA). By considering that the LWA can simultaneously steer its beam direction towards the active user. As a result, each user is estimated independently. The joint algorithm is developed based on the high-resolution MUSIC scheme, which utilizes the LWA properties to compute the DoA spectrum. Furthermore, we develop an iterative CFO estimation approach as the desired solution to a multi-dimensional search. Subsequently, we further formulate the Cramer–Rao lower bounds (CRLB) to serve as a performance benchmark for the accuracy of the proposed scheme. The SDR platform is provided to validate the proposed algorithm in real-time. Finally, the simulation results and the SDR experiments justify that the proposed scheme offers more robustness than conventional counterparts with linear array antenna, which achieves a root mean square error (RMSE) approach to the derived CLRB, especially at a medium signal-to-noise ratio (SNR) range which suited for IIoT applications.

From Algorithm to Module: Adaptive and Energy-Efficient Quantization Method for Edge Artificial Intelligence in IoT Society

Next-generation industrial edge artificial intelligence (AI) applications will undoubtedly emerge on energy-efficient, highly-integrated platforms incorporating various sensors, processors, and functional modules. Effectively bridging sensor data captured from a microprocessor or central processing unit with dedicated processing modules is still being studied in academia and industry. Therefore, embedding the data quantization module onto edge AI chips, connecting sensors, processors, and functional modules, is critical to achieving adaptive transformation of diverse data representation formats. This paper proposes a novel adaptive and low-power quantization technique and systematically validates its effectiveness from algorithm to hardware module for industrial IoT applications, covering precise navigation for autonomous vehicles and accurate classification utilizing deep neural networks (DNNs). The proposed quantization method merges an adaptive conversion function from floating-point to fixed-point binaries and an adaptive radix-point determination function, ensuring adequate resolution and minimal error loss of the fixed-point inputs to the edge AI modules. The experimental results demonstrate that the quantization error in the proposed quantization technique contributes negligible errors to the navigation solutions of the strapdown inertial navigation system and the DNNs' top-1 and top-5 classification accuracy (on the order of 10 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{-8}$</tex-math></inline-formula> and 10 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{-7}$</tex-math></inline-formula> ). Moreover, a quantization-on-multiplier (QoM) hardware module is designed, synthesized, and routed in accordance with the proposed quantization technique. The simulation results indicate that the QoM's power consumption and area are 0.1 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$mW$</tex-math></inline-formula> and 649.552 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mu m^{2}$</tex-math></inline-formula> , accounting for 5% and 14.15% of its total energy consumption and area, respectively. With our proposed on-chip quantization technique, the time required to quantize the parameters of DNNs is up to 1142 times shorter than with the existing benchmark off-chip quantization approaches.

Enhanced Fuzzy Logic Zone Stable Election Protocol for Cluster Head Election (E-FLZSEPFCH) and Multipath Routing in wireless sensor networks

A Wireless Sensor Network (WSN) is a system of sensor nodes that communicate with one another and with their surroundings. Wireless sensor nodes are now used as the foundation for the higher-level industrial internet of things applications. Any type of real-time Internet of Things (IoT) application, as long as the data is collected utilizing the device's sensors. WSN are severely limited in terms of energy. Routing is one of the most challenging components of WSNs. Unbalanced energy utilization during data packet routing operations is one of the most serious difficulties with WSNs. This issue must be considered because the energy levels of sensor nodes are limited. We used WSNs multipath routing to save energy, improve scalability, and balance load. Many investigations are being undertaken to increase sensor node energy efficiency and network lifetime. More attention must be devoted to the clustering and routing components of communication in order to conserve energy. Clustering, also known as node clustering is a network organizing approach which helps with energy efficiency, workload distribution, data collection, and a connected hierarchy. The network is made up of numerous sensor nodes that must connect with one another in order for data to reach its goal, and when messages are not sent to intermediary nodes, problems arise. With multipath routing, numerous paths between the source and destination can be created, improving the possibility of data reaching the target and providing additional copies via alternate paths. The proposed routing solution uses less energy and extends the life of the network while compared with well-known approaches i.e., LEACH, ECPF, CHEF, UCR, DFLC, ACAWT, and Gupta. According to the simulation results and overall analysis, the proposed technique is much better than all the previous approaches under different number of nodes and simulation time in terms of end-to-end time reduced by 17.09% to 68.13%, energy consumption reduced by 13.23% to 29.12%, packet loss rate declined by 16.33% to 82.38% and drop rate of alive sensor nodes are much better shows high network resilience.

Industrial Internet of Things enabled technologies, challenges, and future directions

The Industrial Internet of Things (IIoT) is recognized as the fourth industrial revolution as it enhances productivity, dependability, and competitive performance by concentrating on profitability. IIoT-enabled technologies have been reviewed and implemented in several research, but more research into the opportunities and challenges they present is necessary. This paper explores IIoT-enabled technologies and infrastructure, their role in global industrial growth, applications, challenges, and future directions. IIoT applications use the intelligence of things to solve industrial problems like supply chain mismanagement, data privacy risks, a weak cloud strategy, cost containment, and others. For instance, fog computing reduces parking, platform, fuel, and CO2 emissions. A blockchain-based security framework for the cement sector can resolve 51% of security issues and Sybil attacks caused by consensus algorithms like Proof of Work (PoW). Major companies' performance depends on well-designed IIoT infrastructure, despite significant challenges. Industrial technologies will improve as research and experimentation advance IIoT infrastructure.

Workflow Scheduling in Serverless Edge Computing for the Industrial Internet of Things: A Learning Approach

Serverless edge computing is seen as a promising enabler to execute differentiated Industrial Internet of Things (IIoT) applications without managing the underlying servers and clusters. In IIoT serverless edge computing, IIoT workflow scheduling for cloud-edge collaborative processing is closely related to the service quality of users. However, serverless functions decomposed by IIoT applications are limited in their deployment at the edge due to the resource-constrained nature of edge infrastructures. Additionally, the scheduling of complex IIoT applications supported by serverless computing is more challenging. Therefore, considering the limited function deployment and the complex dependencies of serverless workflows, we model the workflow application as Directed Acyclic Graph (DAG) and formulate the scheduling problem as a multi-objective optimization problem. A Dueling Double Deep Q-Network (D3QN)-based solution is proposed to make scheduling decisions under dynamically changing systems. Extensive simulation experiments are conducted to validate the superiority of the proposed scheme.

Edge-Based IIoT Malware Detection for Mobile Devices With Offloading

The advent of 5G brought new opportunities to leapfrog beyond current industrial Internet of Things (IoT). However, the ever growing IoT has also attracted adversaries to develop new malware attacks against various IoT applications. Although deep learning-based methods are expected to combat the sophisticated malwares by exploring the latent attack patterns, such detection can be hardly supported by battery-powered end devices, like Andriod-based smartphones. Edge computing enables near-real-time analysis of IoT data by migrating AI-enabled computation-intensive tasks from resource-constrained IoT devices to nearby edge servers, However, due to varying channel conditions and the demanding latency requirements of malware detection, it is challenging to coordinate the computing task offloading among multiple users. By leveraging the computation capacity and the proximity benefits of edge computing, we propose a hierarchical security framework for IoT malware detection. Considering the complexity of AI-enabled malware detection task, we provide a delay-aware computational offloading strategy with minimum delay. Specifically, we construct a coordinated representation learning model, named by Two Stream Attention-Caps (TSA-Caps) to capture the latent behavioral patterns of evolving malware attacks. Experimental results show that our system consistently outperforms the state-of-the-art systems in detection performance on four benchmark datasets.

METHODOLOGY AND ARCHITECTURE FOR THE IMPLEMENTATION OF TPM 4.0 IN SMALL AND MEDIUM-SIZED COMPANIES

Total Productive Maintenance (TPM) is one of the main maintenance management strategies based on the principles of Lean Manufacturing (LM). The emergence of the Industry 4.0 (I4.0) paradigm has promoted the massive digitization of several functional areas, with predictive maintenance standing out as an ideal field for the application of IIoT (Industrial Internet of Things) sensorization and data analytics. However, TPM encompasses many more techniques and the scientific literature shows that the integration of I4.0 with TPM needs further development to understand how technologies can support continuous improvement. This paper explores the relationship between TPM and I4.0 tools. It proposes a roadmap for its implementation in SMEs to achieve a Cyber-Physical TPM 4.0 system. The proposal is being validated by means of a practical case study in an industrial SME, with no previous experience in TPM, and which is pursuing the digital transformation of its processes. Keywords: SME, TPM, Industry 4.0, Cyber-Physical

Performance Evaluation of an IEEE 802.15.4-Based Thread Network for Efficient Internet of Things Communications in Smart Cities

The increasing demand for Internet of Things (IoT) applications has resulted in vast amounts of data, requiring the utilization of big data analytics. The integration of big data analytics in IoT-based smart cities can greatly benefit from the development of wireless communication protocols, among which the Thread protocol has emerged as a promising option. Thread is IEEE 802.15.4 based and has advanced capabilities like mesh networking, IPv6 support, and multiple gateways providing no single point of failure. This paper presents the design and evaluation of a low-cost mesh network using Raspberry Pi, nRF52840 dongle, and OpenThread 1.2 (i.e., an open-source software implementation of the Thread protocol stack). The research elaborates on the hardware and software solutions used, as well as the network topologies adopted. To evaluate the performance of the developed system, extensive real-time tests are performed, considering parameters, such as jitter, packet loss, and round trip time. These tests effectively demonstrate the effectiveness of the Thread network. Furthermore, the impact of varying payload size and bitrate on the network is analyzed to understand its influence. The behavior of the multi-hop network is also examined under link failure scenarios, providing insights into the network’s robustness. Our findings provide valuable insights for researchers interested in designing low-cost and efficient mesh networks for various IoT applications, including home automation, building/campus monitoring systems, distributed industrial IoT applications, and smart city infrastructure.

A Decomposition-Based Approach for Multitask Scheduling With Execution Uncertainty in Industrial Internet of Things

Industrial Internet of Things (IIoT) is changing the way in which factories operatewith the help of various industrial applications. However, the execution uncertainty of computing tasks has always been ignored in IIoT applications. In this paper, we define a novel conditional task graph to describe the execution uncertainty and present a generation algorithm to obtain all task scenario graphs and corresponding occurrence probabilities. Then, a new IIoT-oriented multi-task scheduling model under executionuncertainty is built. This model is simplified by reformulating the nonlinear constraints and subsequently decomposed into several small-scale models using Lagrange multipliers, from which a decomposition-based algorithm is derived to solve the decomposedsmall-scalemodels and progressively acquire a well-optimized solution of the initial model. Furthermore, a patching algorithm is constructed to improve the obtained solution. Finally, many test cases are generated, and fourselected algorithms are taken for comparison to evaluate the performance of our algorithms. The results demonstrate that our algorithms remarkably outperform the others. Besides, the solutions of the proposed algorithms can completely satisfy the execution deadline constraints of differenttask scenarios.

Cooperative Resource Allocation for Computation-Intensive IIoT Applications in Aerial Computing

Unmanned aerial vehicles (UAVs) will be a vital part of the massive Industrial Internet of Things (IIoT) in the 5G and 6G paradigms. The UAVs are required to collaborate with each other to deal with some computation-intensive IIoT applications in an autonomous UAV system. However, due to the limited processing capacity of UAVs, they are occasionally unable to handle certain tasks adequately (e.g., crowd sensing). Therefore, it is an important issue to realize efficient offloading of these computation-intensive IIoT applications. In this paper, we first partition the computation-intensive IIoT application into a directed acyclic graph with multiple collaborative tasks. Then, we establish a joint optimization problem based on the models of the processor resources and energy consumption for the task offloading scheme. Thirdly, we propose a cooperative resource allocation approach to optimize the joint optimization problem under the constraints of resource and communication latency, and then can migrate more computation-intensive tasks to the edge clouds. Finally, we build an aerial computing simulation system, and make a comparative evaluation and analysis of our proposed cooperative resource allocation approach in terms of effectiveness and performance. The experimental results show that our proposed approach performs better than other related approaches.

Clustered and Multi-Tasked Federated Distillation for Heterogeneous and Resource Constrained Industrial IoT Applications

Service heterogeneity, the diversity of services provided by different devices and systems in the Industrial Internet of Things (IIoT), makes communication and data exchange difficult and affects the IIoT performance. Artificial intelligence, particularly machine learning (ML), can address this challenge by analyzing data, predicting behavior, and developing self-configuring autonomic systems. However, incorporating ML into IIoT faces challenges such as high data complexity and variability, communication costs, lack of data privacy and security, and scalability. Federated multitask learning (FML) is a promising solution to tackle most of these challenges by training ML models locally and exchanging only the updated parameters. However, it still faces challenges in device and system compatibility, data heterogeneity, and scalability, especially for hierarchical heterogeneous IIoT environments. To address all these challenges, this article proposes a novel hybrid framework dubbed Clustered Multitask Federated Distillation (CMFD). In conjunction with the FML, CMFD combines clustered FL to address the data heterogeneity and knowledge distillation to address the system compatibility and scalability. To show the efficiency of CMFD for intelligent IIoT applications, we present a case study of heterogeneous IIoT environments using a realistic dataset. We conclude with useful insights emerging from our work and highlight promising future research directions.

Improved Fault Classification for Predictive Maintenance in Industrial IoT Based on AutoML: A Case Study of Ball-Bearing Faults

The growing complexity of data derived from Industrial Internet of Things (IIoT) systems presents substantial challenges for traditional machine-learning techniques, which struggle to effectively manage the needs of predictive maintenance applications. Automated machine-learning (AutoML) techniques present a promising solution by streamlining the machine-learning process, reducing the necessity for manual hyperparameter tuning and computational resources, thereby positioning themselves as a potentially transformative innovation in the Industry 4.0 era. This research introduces two distinct models: AutoML, employing PyCaret, and Auto Deep Neural Network (AutoDNN), utilizing AutoKeras, both aimed at accurately identifying various types of faults in ball bearings. The proposed models were evaluated using the Case Western Reserve University (CWRU) bearing faults dataset, and the results showed a notable performance in terms of achieving high accuracy, recall, precision, and F1 score on the testing and validation sets. Compared to recent studies, the proposed AutoML models demonstrated superior performance, surpassing alternative approaches even when they utilized a larger number of features, thus highlighting the effectiveness of the proposed methodology. This research offers valuable insights for those interested in harnessing the potential of AutoML techniques in IIoT applications, with implications for industries such as manufacturing and energy. By automating the machine-learning process, AutoML models can help decrease the time and cost related to predictive maintenance, which is crucial for industries where unplanned downtime can lead to substantial financial losses.

AIDA—A holistic AI-driven networking and processing framework for industrial IoT applications

Industry 4.0 is characterized by digitalized production facilities, where a large volume of sensors collect a vast amount of data that is used to increase the sustainability of the production by e.g. optimizing process parameters, reducing machine downtime and material waste, and the like. However, making intelligent data-driven decisions under timeliness constraints requires the integration of time-sensitive networks with reliable data ingestion and processing infrastructure with plug-in support of Machine Learning (ML) pipelines. However, such integration is difficult due to the lack of frameworks that flexibly integrate and program the networking and computing infrastructures, while allowing ML pipelines to ingest the collected data and make trustworthy decisions in real time. In this paper, we present AIDA - a novel holistic AI-driven network and processing framework for reliable data-driven real-time industrial IoT applications. AIDA manages and configures Time-Sensitive networks (TSN) to enable real-time data ingestion into an observable AI-powered edge/cloud continuum. Pluggable and trustworthy ML components that make timely decisions for various industrial IoT applications and the infrastructure itself are an intrinsic part of AIDA. We introduce the AIDA architecture, demonstrate the building blocks of our framework and illustrate it with two use cases.