Advancements in Condition Monitoring of Electric Motors: Integrating Digital Twins, AI, and IoT for Enhanced Operational Efficiency, Fault Diagnosis, and Cybersecurity

Dear Colleagues,

The role of electric motors in powertrains is central, making them essential in a wide range of industrial applications. Yet, their continuous operation and stress in extreme operating conditions poses a significant risk, potentially disrupting the production process. Moreover, aside from the consequences on production, the occurrence of failures can pose significant safety hazards for the workforce. With a view to minimizing the chances of unexpected consequences occurring, it is necessary to focus on the analysis and implementation of monitoring techniques, under any operating condition. In addition, in order to minimize maintenance costs and improve productivity, predictive maintenance is essential to accurately assess the severity of a potential failure in the near future. To this end, the integration of digital twins, Artificial Intelligence (AI), and Internet of Things (IoT) in condition monitoring of electric machines constitutes a cutting-edge approach. By leveraging real-time data from IoT sensors, AI algorithms can analyze the digital twin’s virtual representation of the electrical machine, enabling proactive identification of potential issues and optimizing maintenance strategies for improved operational efficiency and reliability. Furthermore, the security of critical information transmission and data protection from unauthorized users poses a challenge for the development of innovative solutions to enhance security, with a focus on wireless sensor networks (WSNs) and secure data transmission to electric motors.

The aim of this Special Issue is to contact and highlight research developments in key aspects such as i) techniques for continuous monitoring of the operational status of electric machines; ii) the collection and processing of large volumes of data in real and continuous time using IoT technology; iii) the correct placement of sensors in the motor so that data are collected accurately; iv) the detection, diagnosis, and prognosis of faults; v) digital twins-enabled condition monitoring; vi) AI-assisted fault diagnosis; vii) secure data transfer to avoid unforeseen interference; viii) development of advanced security mechanisms for WSNs in industrial applications; ix) ensuring the integrity, confidentiality, and availability of data transmitted between motors; x) minimizing vulnerabilities and weaknesses of digital transformation systems; and xi) improving resilience to fault diagnosis and cyberattacks.

Prof. Dr. Antonios Gasteratos
Prof. Dr. Theoklitos Karakatsanis
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. Machines is an international peer-reviewed open access monthly 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.

• electric motors
• industrial applications
• fault diagnosis
• prognosis
• predictive maintenance
• smart sensors
• condition monitoring
• data collection and security challenges
• digital twins
• artificial intelligence
• secure communication protocols
• critical infrastructure protection
• wireless sensor networks (WSNs)

Title: Predictive Maintenance, Fault Diagnosis and Tolerance of PMSM Drives: Overview and Future Prospects
Authors: Vasileios I. Vlachou; Theoklitos S. Karakatsanis; Dimitrios E. Efstathiou
Affiliation: 1 Laboratory of Electrical Machines and Power Electronics, Department of Electrical and Computer Engineering, National Technical University of Athens, 15780 Athens, Greece. 2 Laboratory of Thermodynamics and Thermal Machines, Department of Production and Management Engineering, Democritus University of Thrace, 67100 Xanthi, Greece, [email protected]. 3 Laboratory of Telecommunications and New Technologies, Department of Computer, Informatics and Telecommunications, International Hellenic University, 62124 Serres, Greece.
Abstract: In recent years we have noticed the effort is focused on introducing electromobility into the everyday life of citizens. Key applications such as electric vehicles, ships, airplanes and elevators focus on energy efficiency and reduction of pollutants. The main source of energy in all these forms relies on the operation of the electric motor and its individual subsystems such as power electronics. In lifting system technologies, the main technology of choice is permanent magnet synchronous motors due to their efficiency and potential for additional energy savings. Elevators are of enormous importance both in the national economy and in everyday life, operating as complex electromechanical systems. Despite their different types and configurations, all elevator systems consist of three fundamental elements: mechanical parts, electrical parts and safety devices. Naturally, each component over time can develop a failure that can affect the overall functionality of the system. Predictive maintenance on PMSMs is of particular research interest as failure of the system can pose a risk to passenger safety. The present research focuses on the bibliographic review of various fault detection methods based either on signal analysis through data transmission from sensors or using modern machine learning techniques. Thus, a new methodology is proposed that includes a combination of parameters and modern methods, drawing useful conclusions on the importance and role of predictive maintenance in elevators.