Draft Full Paper Due:
May 1, 2021(extended)

Notification of Draft Paper Acceptance:
May 15, 2021(extended)

Final Manuscript Due:
May 25, 2021(extended)

Author Registration Deadline:
June 1, 2021

Regular Attendee Early Bird Registration Deadline:

June 1, 2021

 

Home > Keynote Speakers
Keynote Speakers

Keynote 1: Deep Learning Applied to Hydro-Generators: Challenges and Further Developments

Professor Ryad Zemouri, Le Cnam, Paris, France; Institut de recherche of Hydro-Québec (IREQ), Varennes, Canada; and the École de Technologie Supérieure, Montréal, Canada

 

 

Abstract of the Keynote Talk:

Thanks to the digitization of industrial assets and the large amount of data coming with it, deep-learning-based fault diagnosis models are nowadays showing promising results for fault diagnosis and prognosis applications.

Many DL architectures have been widely adopted in diagnosis and prognosis in the last years in a so-called End-to-End approach, i.e., from the pre-processed input signal to the end result, such as the identification of the failure and its cause or the prediction of the RUL.

However, when applying these techniques in an industrial practice, a lot of hurdles are faced. These limitations are inherent to the complexity of the systems to monitor. For such systems, the knowledge of the failure or the degradation is very limited. Distinguishing between a normal and an abnormal signature is very difficult in practice, which leads to some difficulties for the supervised learning techniques.

In this talk we will discuss the challenges and applications of deep learning methods in the context of power generation in Hydro-Québec, a public utility that manages the generation, transmission and distribution of electricity in the Canadian province of Quebec, as well as the export of power to portions of the Northeast United States.

 

Keynote Speaker’s Short Bio:

Prof. Ryad Zemouri was born in Algiers, Algeria, in 1974. He received the engineering degree in electronics and control science from the University Mouloud Mammeri of Tizi-Ouzou, Algeria, in 1998, and the post-graduated Diploma, and the Ph.D. degree from the Franche-Comté University of Besançon, France, in 2000 and 2003, respectively. Since 2003, he has been an Associate Professor with the Engineering Department of Automatic Control, Electronics and Computer Science, Conservatoire National des Arts et Métiers, Paris, France. He was a Research Fellow with the Institut de recherche of Hydro-Québec (IREQ), Varennes, Canada, and the École de Technologie Supérieure, Montréal, Canada, from February 2019 to August 2019, and from october 2020 to date. His research interests include machine learning for safety-critical prognosis, diagnosis, and health management. He was awarded with the IEEE International Conference on Prognostics and Health Management (ICPHM) best paper award in 2021.




Keynote 2: Predictive Maintenance in the Industry 4.0 Context

Professor Sharareh Taghipour, Canada Research Chair in Physical Asset Management, Ryerson University, Canada

 

 

Abstract of the Keynote Talk:

The fourth industrial revolution, commonly known as Industry 4.0, offers new challenges to the manufacturing industry. For the full realization of Industry 4.0, autonomous smart decision-making should be present in all aspects of the manufacturing process, including maintenance planning, one of its core components. In manufacturing systems, an automated and interconnected production process might come to a deadlock by a single machine failure, which causes considerable downtime and production outages; if no proper predictive maintenance is employed to forecast malfunctions and prevent them in time. Predictive or condition-based maintenance consists of fault diagnosis and prognostics of mechanical machinery and has been of significant interest to the research community in the last few decades. Predictive maintenance plays a major role in Industry 4.0-based manufacturing systems. It involves real-time monitoring of production line equipment and transferring the related data to the cloud for failure prediction and maintenance process optimization. Moreover, by real-time integration of predictive maintenance data with production data, such as manufacturing schedules, it is possible to adjust the production run dynamically according to unplanned circumstances, such as machine failure.

In this talk, the problem of integrating predictive (or condition-based) maintenance in different Industry 4.0-based manufacturing systems will be addressed. The talk will investigate the performance of different manufacturing systems with the availability of diagnostic and prognostic information about machines as well as the availability of real-time information about machines and other operations.

 

Keynote Speaker’s Short Bio:

Prof. Sharareh Taghipour, PhD, LEL, is an Associate professor at the Department of Mechanical and Industrial Engineering at Ryerson University. She is Canada Research Chair in Physical Asset Management. She obtained her PhD in Industrial Engineering from the University of Toronto and received her BSc in Mathematics and Computer Science and her MASc in Industrial Engineering, both from Sharif University of Technology, Iran. The focus of Dr. Taghipour’s research has been on physical asset management. She has well-established partnerships and research collaborations with numerous industry partners from healthcare to energy, mining, transportation, utilities and manufacturing. She is currently serving as the Regional Editor-North America of the Journal of Quality in Maintenance Engineering, and as the Associate Editor of the Journal of Prognostics and Health Management, and the Proceedings of the Reliability and Maintainability Symposium (RAMS).




Keynote 3: Research on High-Performance Wireless Sensor Networks for Mechanical Vibration Monitoring

Professor Baoping Tang, Vice Dean of College of Mechanical and Vehicle Engineering, Chongqing University

 

 

Abstract of the Keynote Talk:

Wireless sensor network (WSN), a novel information acquisition technology, has the excellent potential in the field of mechanical equipment condition monitoring, especially in sealed and rotating mechanical environment. However, the low sampling frequency and the poor hardware performance of the leading-edge WSN node lead to the issues including high-precision synchronous acquisition of mechanical vibration, high-efficiency and reliable transmission of a large number of vibration data, and high-power energy supply, etc. To solve these problems, first of all, the speech will introduce the design method of high-performance wireless vibration sensor network node with dual-core architecture. Secondly, the method is proposed to improve synchronous acquisition accuracy via network clock synchronization, synchronization trigger and synchronization cumulative error control. And then, in terms of balanced network topology, reliable link, channel bandwidth, data packet loss and retransmission, the approach of efficient and reliable transmission with low power for mass data is proposed. Next, the high-power energy supply method for mechanical vibration wireless sensor network is presented through multi-directional excitation, broadband vibration energy collection and management. Finally, the prospect of wireless, passive, low-power micro nano vibration sensor and mechanical vibration wireless sensor network lightweight edge-to-end collaborative processing methods are discussed.

 

Keynote Speaker’s Short Bio:

Prof. Baoping Tang is currently a professor and Vice dean of College of Mechanical and Vehicle Engineering in Chongqing University. He is an expert enjoying the special allowance of the State Council Government and the Principal Investigator of National Key R&D Projects, has been selected as the national candidates for the "Hundred Thousand Ten Thousand Talents Project". He also serves as the deputy director of the Dynamic Testing Committee of the Chinese Society of Vibration Engineering. His research interests focus on intelligent operation and maintenance of mechanical and electrical equipment, measurement technology, virtual instrument and wireless sensor network. Prof. Tang is the PI over more than 30 research projects including national key R&D projects, National Natural Science Foundation of China, National "863" Program, and has published more than 180 papers. Prof. Tang has received the second prize of National Technology Invention Award in 2004, the second prize of National Science and Technology Progress Award in 2015, the second prize of National Teaching Achievement Awards in 2018.