Special Issue(24-05): Trends in Artificial Intelligence for Predictive Maintenance in Industrial IoT Applications

The core of predictive maintenance in the industrial Internet of things is machine learning algorithms driven by AI. These algorithms are able to anticipate possible equipment breakdowns by identifying early warning indicators because they are continuously learning from the data. In order to enhance efficiency, forecast or identify equipment breakdowns, and increase the usable life of asset components, data analysis and machine learning are used. The introduction of AI poses issues that need to be properly addressed, including transparency, reliability, prices, and job displacement. The increasing sophistication of artificial intelligence and machine learning algorithms makes it possible to predict failures with greater accuracy. With edge computing, decision-making can happen faster by analysing sensor data in real-time. IoT predictive maintenance is evaluating machinery, assets, or equipment and better forecasting possible failures or outages using data collected via IoT technology. The PdM systems' brains are AI algorithms, which include machine learning and deep learning methods. 

The algorithms examine the information to determine the key elements associated with potential failures. By analysing past data, they are able to forecast RUL, abnormalities, and equipment failures. Several advantages can be obtained by implementing predictive maintenance in a connected product environment and smart factory use case. These include fewer unplanned breakdowns, increased asset uptime and improved asset reliability, lower operational costs by only performing maintenance or field service when necessary, increased production hours, enhanced safety, more efficient maintenance, lower spare part inventory costs, and more. To assist maintenance personnel in maintaining ideal inventory levels, AI systems can evaluate equipment, inventory, and purchase data in both the past and the present. When it comes to recommending when to refill parts, these systems are able to recognize patterns in the usage and purchasing history associated with the parts. Artificial intelligence (AI), predictive analytics, and the Internet of Things (IoT) are some of the technologies that predictive maintenance depends on. With the help of data analysis, predictive maintenance (PdM) can spot possible equipment flaws and operating irregularities in advance of failures, allowing for prompt repairs. By reducing the frequency of maintenance, it seeks to reduce unplanned outages and needless preventive maintenance expenses. By anticipating when maintenance is necessary, AI-powered predictive maintenance can stop equipment breakdowns. Whereas ML-based systems employ sophisticated modelling to anticipate failure, rule-based systems rely on hard-coded thresholds. 

Generative artificial intelligence (AI) can assist in spotting patterns and abnormalities that might point to imminent equipment failures by learning from enormous volumes of operational data. With the help of sensors, analytics, and machine learning algorithms, IoT-based predictive maintenance may anticipate when a machine or other piece of equipment will need maintenance, saving businesses money by minimising downtime as well as maintenance expenses. The implementation of reliability best practices to maximise equipment uptime in a manufacturing context is known as industrial maintenance, or plant maintenance. Manufacturers can steer clear of obstacles during the supply chain's production phase when their equipment is operating as planned. This technique aids in predicting equipment failures. It also reduces maintenance costs, lengthens the lifespan of machinery, and minimises unplanned downtime. Articles are invited that explore Trends in Artificial Intelligence for Predictive Maintenance in Industrial IoT Applications. Case studies and practitioner perspectives are also welcome.

LIST OF TOPICS    
•    Predictive maintenance: connecting IoT and artificial intelligence.
•    AI-Driven Proactive Maintenance for Industrial Internet of Things Devices.
•    AI for industrial systems predictive maintenance.
•    Industrial Internet of Things predictive maintenance facilitated by deep learning.
•    IoT Device Predictive Maintenance utilising deep learning and time series analysis.
•    Application of artificial intelligence tools to anticipate repair principles.
•    Smart factories with sophisticated sensors and predictive maintenance.
•    Deep learning-based quick predictive maintenance for the industrial internet of things.
•    Predictive maintenance using IoT in the manufacturing industry.
•    Predictive maintenance applications using artificial intelligence.
•    A framework for autonomous monitoring of industrial IoT systems using predictive maintenance.
•    Predictive maintenance using an industrial internet of things platform.
•    Predictive Maintenance using Deep Learning for Industrial Internet of Things Applications.

SUGGESTED TIMELINE    
•    Manuscript submissions due  April 15, 2025
•    First round of reviews completed  June 15, 2025
•    Revised manuscripts due  Aug 15, 2025
•    Second round of reviews completed  Oct 15, 2025
•    Final manuscripts due Dec15, 2025

GUEST EDITORS

•    Dr. Jawad Khan
Assistant Professor
Gachon University, Seongnam, South Korea
Email: [email protected], [email protected]
Google Scholar: 
https://scholar.google.com/citations?user=BWpBBh0AAAAJ&hl=en
Research Gate: 
https://www.researchgate.net/profile/Jawad-Khan-21
ORCID: 
https://orcid.org/0000-0001-8263-7213

•    Dr. Muhammad Hameed Siddiqi
Associate Professor
Jouf University, Sakaka, Aljouf, Saudi Arabia
Email:  [email protected]
Google Scholar: 
https://scholar.google.co.uk/citations?user=PktU0eEAAAAJ&hl=en
Research Gate Link:
https://www.researchgate.net/profile/Muhammad-Siddiqi-7
ORCID: 
https://orcid.org/0000-0002-4370-8012

•    Dr. Tariq Rahim
Lecturer 
Kingston University, Kingston, England
Email: [email protected]
Google Scholar: 
https://scholar.google.com/citations?user=fr4C9ogAAAAJ&hl=en
ResearchGate: 
https://www.researchgate.net/profile/Tariq-Rahim-2
ORCID: 
https://orcid.org/0000-0001-7817-9715

•    Dr. Shah Khalid
Assistant Professor
National University of Sciences & Technology, Islamabad, Pakistan
Email: [email protected]
Google Scholar: 
https://scholar.google.com/citations?user=Sff9RyoAAAAJ&hl=en
ResearchGate: 
https://www.researchgate.net/profile/Shah-Khalid-13
ORCID: 
https://orcid.org/0000-0001-5735-5863