Using Electrical Torque for Fault Diagnosis of Rotating Machines: AI and Model-Based Approaches

Date: 20/02/2025

Time: 10:00 am

Presenter: Mariela Cerrada Lozada

Abstract: Rotating machines are important devices in manufacturing processes. Particularly, gearboxes offer mechanical power, and their high performance must be preserved. Being that most of the failures in industrial processes appear in mechanical devices, the development of innovative solutions for fault diagnosis is continuously under research. Usually, vibration signals are one the common source of data to this purpose, however the placement of vibration sensors could be not easy to couple in the machines. Given that gearboxes are powered by induction motors, this talk shows the use of the electrical torque as useful signal to get proper data for fault diagnosis in gearboxes. This approach is since mechanical faults of the motor load are transmitted to its electrical variables through the shaft between the motor and the gearbox. In this study, the analysis of the electrical torque is tackled from two points of view: one by using machine learning and the other by the development of a state observer-based model. In the first, we demonstrate that common statistical indicators and alternative signal processing by using Poincaré plots provide useful features for fault classification. In the second, we propose a model-based solution by using state observers to generate proper residual signals which deviate enough their values from zero to warn about the arising of a fault process. Thus, this last approach also serves as a fault severity measure.

Please note: This webinar will be held in Spanish.

Mariela Cerrada Lozada, IEEE Senior member, is a full professor with the Mechatronics career and GIDTEC research group, since 2017 at the Salesian Polytechnic University (Universidad Politécnica Salesiana UPS) in Cuenca, Ecuador. She received the Ph.D. degree in Automatic systems from National Institute of Applied Sciences (INSA) in Toulouse, France. She also was with the Control Systems Department at the University of Los Andes, Venezuela, from 1994 to 2016. Mariela is member of the Technical Committee on Manufacturing Plant Control of the International Federation of Automatic Control (IFAC), member of the executive committee of IEEE Ecuador section, representing the Industrial Engagement Committee for the years 2022 and 2023, as well as the current chair of the joint chapter Industry Applications & Reliability. Her main line of research and development focuses the fault detection and diagnosis of industrial processes. Due to her extensive research trajectory, she has been recently awarded/recognized with Stanford University’s Top 2% Scientists ranking in the 2021 and 2022 editions, Distinguished Researcher of the IEEE Ecuador Section in 2020, Best Industry-University Collaboration by the Corporation for the Development of Research and Academy of Ecuador (CEDIA) in 2021, Industry Solutions Award 2021 from the Industrial Engineering and Operations Management Society, 2022 edition of 50 Women in Robotics you need to know about. Recently in 2024, she received the recognition ATENEA issued by the National Secretary of High Education, Science, Technology and Innovation of Ecuador for her contribution to the engineering and technology.

Using Electrical Torque for Fault Diagnosis of Rotating Machines: AI and Model-Based Approaches

Sign Up To Our Newsletter

We Would Love Your Feedback

Stay connected with IEEE PELS! Follow us on social media or become an IEEE member.