[go: up one dir, main page]

 
 
applsci-logo

Journal Browser

Journal Browser

Industrial IoT: From Theory to Applications

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: 10 April 2025 | Viewed by 4043

Special Issue Editors


E-Mail Website
Guest Editor
Department of Computer and Electrical Engineering, Mid Sweden University, 851 70 Sundsvall, Sweden
Interests: Internet-of-Things network management of computing; machine learning; industrial 5G; wireless networking

E-Mail Website
Guest Editor
Applied Digitalization, Industrial Systems at RISE Research Institutes of Sweden, Storgatan 73, 852 33 Sundsvall, Sweden
Interests: network security; AI/ML; cyber physical system

Special Issue Information

Dear Colleagues,

The forthcoming evolution of the Industrial Internet of Things (IIoT) will be characterized by advancements in intelligent communication and computational systems. These systems will revolutionize network management to improve operational efficacy and dependability across diverse industrial automation sectors. The forefront of this transformative era is marked by the advent of sophisticated technologies such as network digital twins and self-organizing networks, facilitating a paradigm shift to autonomously managed networks. These innovations are instrumental in diminishing the reliance on manual intervention by enabling networks to self-configure, self-optimize, and self-repair.

At the core of this evolution lies the strategic integration of explainable artificial intelligence (AI) and machine learning (ML) within network frameworks. This integration will pave the way for an era of explainable, trustworthy, and transparent self-sufficient networks capable of self-directed adaptation and optimization. This strategic deployment will ensure immediate and proficient fulfillment of computational and communication needs.

This Special Issue thoroughly explores forward-thinking strategies for network load management and the integration of the edge-to-cloud continuum. It aims to enhance network performance while prioritizing energy efficiency and latency reduction—crucial components for robust IIoT operations. It also addresses the re-engineering of routing protocols to accommodate industrial applications' diverse and fluctuating needs and highlights edge computing's pivotal role in distributing data processing, thus strengthening network autonomy and reducing delays.

Furthermore, predictive network analytics is recognized as crucial in forestalling and addressing network discrepancies and playing a crucial role in sustaining uninterrupted operations. The concept of network slicing is investigated for its ability to furnish customizable and effective network services that align precisely with industrial requirements.

This narrative extends to include the integration of 5G/6G technologies, which are poised to make a profound impact on IIoT. These next-generation wireless networks promise to bring unprecedented levels of flexibility and scalability, driving forward the creation of an extensive, intelligent, and interconnected industrial fabric.

The discourse concludes with an assessment of the potential impact of O-RAN-based architectures on IIoT. These architectures are expected to deliver unparalleled levels of adaptability and scalability, contributing to the cultivation of a more expansive, intelligent, and interconnected industrial ecosystem.

Submissions for this Special Issue are sought to bridge the gap between theoretical innovation and practical application in the field of IIoT, providing insights that will contribute to the collective understanding of IIoT’s evolution. The shared knowledge is intended to advance the industry towards an autonomous and self-regulating industrial future.

Dr. Sarder Fakhrul Abedin
Dr. Nishat I Mowla
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • digital twin
  • self-organizing networks (SONs)
  • cloud–edge continuum
  • predictive maintenance and network analysis
  • zero-touch network management
  • explainable and trustworthy AI/ML in the IIoT
  • intelligent 5G/6G network slicing and resource management
  • O-RAN for IIoT

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (2 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

27 pages, 10538 KiB  
Article
Proposal and Implementation of an Integrated Monitoring Platform for Preventive Maintenance of Industrial Machines
by Nene Kamiya, Shunya Hibino, Konosuke Yoshizato and Takanobu Otsuka
Appl. Sci. 2024, 14(24), 11534; https://doi.org/10.3390/app142411534 - 11 Dec 2024
Viewed by 633
Abstract
In order to realise the efficient maintenance of industrial machines, Small and Medium-sized Enterprises (SMEs) need a system that utilises digital technology to handle everything from data collection to the visualisation of the collected data in an integrated manner. In this paper, an [...] Read more.
In order to realise the efficient maintenance of industrial machines, Small and Medium-sized Enterprises (SMEs) need a system that utilises digital technology to handle everything from data collection to the visualisation of the collected data in an integrated manner. In this paper, an integrated monitoring platform using external sensor devices is proposed and implemented for the purpose of preventive maintenance of industrial machines. The proposed system performs edge processing to calculate features effective for monitoring on the sensor device, collects only the obtained features, and visualises them on a web server. In order to determine the features required by edge processing, a cycle waveform cut-out algorithm was proposed. As an evaluation experiment, the proposed system was used to detect the loosening of bolts on the support side of a ball screw. The results of the analysis showed that the dispersion value immediately after the start of uniform motion from the right end to the left end was valid, so the system was implemented as edge processing in the sensor device. In wireless transmission experiments on a testbed, an average of 20 consecutive cycles were used to achieve a 99.9% correct response rate and high detection accuracy, demonstrating the usefulness of the proposed system. Full article
(This article belongs to the Special Issue Industrial IoT: From Theory to Applications)
Show Figures

Figure 1

Figure 1
<p>Power spectrum of current waveforms [<a href="#B11-applsci-14-11534" class="html-bibr">11</a>].</p>
Full article ">Figure 2
<p>Log likelihood by experimental condition [<a href="#B11-applsci-14-11534" class="html-bibr">11</a>].</p>
Full article ">Figure 3
<p>Schematic diagram of proposed system.</p>
Full article ">Figure 4
<p>Entity Relationship (ER) diagram of the database.</p>
Full article ">Figure 5
<p>Accelerometer devices compatible with Secure Digital (SD) cards.</p>
Full article ">Figure 6
<p>Accelerometer devices for Low Power Wide Area (LPWA) communication.</p>
Full article ">Figure 7
<p>Testbed.</p>
Full article ">Figure 8
<p>x-axis acceleration at 11 N of torque.</p>
Full article ">Figure 9
<p>x-axis acceleration at 1 N of torque.</p>
Full article ">Figure 10
<p>y-axis acceleration at 11 N of torque.</p>
Full article ">Figure 11
<p>y-axis acceleration at 1 N of torque.</p>
Full article ">Figure 12
<p>z-axis acceleration at 11 N of torque.</p>
Full article ">Figure 13
<p>z-axis acceleration at 1 N of torque.</p>
Full article ">Figure 14
<p>Norm at 11 N of torque.</p>
Full article ">Figure 15
<p>Norm at 1 N of torque.</p>
Full article ">Figure 16
<p>Cycle waveform at 11 N of torque.</p>
Full article ">Figure 17
<p>Cycle waveform at 1 N of torque.</p>
Full article ">Figure 18
<p>Operating point of the cycle waveform at 11 N of torque.</p>
Full article ">Figure 19
<p>Dispersion values in uniform motion from the left end to the right end.</p>
Full article ">Figure 20
<p>Dispersion values in uniform motion from the right end to the left end.</p>
Full article ">Figure 21
<p>Dispersion values immediately after the start of uniform motion from the right end to the left end, as displayed in the web application.</p>
Full article ">Figure 22
<p>Variance values immediately after the start of uniform motion from the right end to the left end, as displayed in the web application (20-point average).</p>
Full article ">

Review

Jump to: Research

22 pages, 1690 KiB  
Review
A Comparative Analysis of Anomaly Detection Methods in IoT Networks: An Experimental Study
by Emanuel Krzysztoń, Izabela Rojek and Dariusz Mikołajewski
Appl. Sci. 2024, 14(24), 11545; https://doi.org/10.3390/app142411545 - 11 Dec 2024
Cited by 2 | Viewed by 2590
Abstract
The growth of the Internet of Things (IoT) and its integration with Industry 4.0 and 5.0 are generating new security challenges. One of the key elements of IoT systems is effective anomaly detection, which identifies abnormal behavior in devices or entire systems. This [...] Read more.
The growth of the Internet of Things (IoT) and its integration with Industry 4.0 and 5.0 are generating new security challenges. One of the key elements of IoT systems is effective anomaly detection, which identifies abnormal behavior in devices or entire systems. This paper presents a comprehensive overview of existing methods for anomaly detection in IoT networks using machine learning (ML). A detailed analysis of various ML algorithms, both supervised (e.g., Random Forest, Gradient Boosting, SVM) and unsupervised (e.g., Isolation Forest, Autoencoder), was conducted. The results of tests conducted on popular datasets (IoT-23 and CICIoT-2023) were collected and analyzed in detail. The performance of the selected algorithms was evaluated using commonly used metrics (Accuracy, Precision, Recall, F1-score). The experimental results showed that the Random Forest and Autoencoder methods are highly effective in detecting anomalies. The article highlights the importance of appropriate data preprocessing to improve detection accuracy. Furthermore, the limitations of a centralized machine learning approach in the context of distributed IoT networks are discussed. The article also presents potential directions for future research in the field of anomaly detection in the IoT. Full article
(This article belongs to the Special Issue Industrial IoT: From Theory to Applications)
Show Figures

Figure 1

Figure 1
<p>A simple example of anomaly classification in IoT networks, presented in the form of a diagram (own elaboration).</p>
Full article ">Figure 2
<p>Anomaly detection using RF (own elaboration).</p>
Full article ">Figure 3
<p>Anomaly detection using Isolation Forest (own elaboration).</p>
Full article ">Figure 4
<p>Anomaly detection using Autoencoder (own elaboration).</p>
Full article ">
Back to TopTop