Theme and Scope

With the advent of technology, existing systems are enhanced for performance and better efficiency. Machine health monitoring or machine condition monitoring is an evolving field that helps assess the condition or health of a machine throughout its lifecycle or over a particular period of time. An artificial intelligence (AI) assisted Industrial IoT system that can offer machine health monitoring can significantly reduce the unplanned downtime and the costs associated with it. This can be achieved by proper machine condition monitoring systems that can assess and track the machine health and condition in terms of maintenance, overrunning, and efficiency. In an AI-assisted industrial IoT system, the machine is either embedded or equipped with sensors that collect real-time data on various parameters relating to machine health. This might include recording of temperature, pressure in pipes, vibration frequency, deflection, calibration etc. The data collected by these sensors are transferred to a cloud platform where the data is combined and analysed using various computational tools and analytical methods. The result of such intense calculations and processing is a set of crucial insights about the operational characteristics and condition of the industrial machinery.

The above-said insights are communicated to the users or a self-repairing system in the form of charts, diagrams or signals. AI can even be used to detect a deviation from the actual set values or criteria based on big data sets and Deep Learning (DL) machine models. The machine condition monitoring solution can be implemented for a variety of industrial applications. For instance, the condition of welding and laser equipment, spindles etc. can be tracked in automobile manufacturing industries. Automatic assessment and detection of cracks, sapling, and misalignment can be carried out seamlessly without the need for physical access. Also, sophisticated machine condition monitoring systems can detect extreme conditions like circuit degradation, imbalance in supply current, motor damage, rotor eccentricity, defects in conveyors etc. Cloud-based health monitoring systems are also a common research topic in this area. In spite of its significance in quality control and machine health monitoring, AI-based industrial IoT systems can be further employed for future performance predictions, efficiency, and the probability of producing a defective product. 

List of topic areas include, but are not limited to:

    Knowledge-based machine condition monitoring systems.

    Identification and analysis of floating offshore structures based on AI-assisted machine health monitoring.

    Machine health monitoring of unmanned and long-flight aerial vehicles.

    Support system architectures for AI-based machine health monitoring systems.

    Integration of novel techniques and concepts for automatic detection of structural health in civil infrastructure systems.

    Cloud-based machine health monitoring model using AI and Big Data.

    Innovative methods to assess the vibration in tall towers.

    Data-driven methods for AI-based industrial IoT and machine health monitoring.

    Fault signature analysis for critical machine components using AI and Computer vision.

    Semi-supervised industrial machine health monitoring systems.

Instructions for Manuscripts

Each paper, written in English, the maximum words number in each paper should be below 8,000 words, including references and illustrations. More information can be found at https://jit.ndhu.edu.tw/. Before submission authors should carefully read over the journal’s Author Guidelines, which are located at https://jit.ndhu.edu.tw/about/submissions#authorGuidelines.

Prospective authors should submit an electronic copy of their complete manuscript through the journal Manuscript Tracking System at https://mc04.manuscriptcentral.com/internet-tech. When submitting papers, authors should specify that the manuscript is for Special Issue on “Artificial Intelligence Assisted Industrial IoT for Machine Health Monitoring”. The manuscript template can be found at https://jit.ndhu.edu.tw/about/submissions#authorGuideline.

Important Dates

Manuscript Submission Deadline: October 30, 2022

First Notification: January 02, 2023

Revised Papers Due: March 20, 2023

Final notification: May 15, 2023

Tentative Publication: the 4th Quarter of 2023

Guest Editors:

Dr. Byung-Gyu Kim (Lead Guest Editor)

Sookmyung Women’s University, Seoul, Rep of Korea

E-mail: bg.kim@sookmyung.ac.kr; bg.kim@ieee.org

Dr. Partha Pratim Roy

Indian Institute of Technology Roorkee, India

E-mail: partha@cs.iitr.ac.in

Dr. Leng Lu

Nanchang Hangkong University, China