Mateusz Gizicki has a bachelor's degree in mechanical engineering from the University of Northampton and is currently working towards achieving his doctorate in the area of multi-physics and computational fluid dynamics. He is a member of the Institution of Mechanical Engineers. He has experience in research and development in the industry environment as well as academia. In addition, he has recently completed the Knowledge Transfer Partnership project, which combined management skills with complete product development as an associate.
Dr Stefan Kaczmarczyk is Professor of Applied Mechanics and Postgraduate Programme Leader for Lift Engineering at the University of Northampton, UK. His expertise is in the area of applied dynamics and vibration with particular applications to vertical transportation and material handling systems. He has published over 100 journal and international conference papers in this field. He is a Chartered Engineer, a Fellow of the Institution of Mechanical Engineers and a Fellow of the Higher Education Academy
Dr Rory Smith has over 50 years of experience in all aspects of the lift industry including sales, installation, maintenance, manufacturing, engineering, research & development. He has worked for ThyssenKrupp Elevator for the last 24 years. Prior to becoming involved in ThyssenKrupp's Internet of Things, he was Operations Director, ThyssenKrupp Elevator Middle East. His scientific interests include: operations management, high rise - high speed technology, ride quality, traffic analysis, dispatching. To date he has been awarded numerous patents in these areas and has many pending patents.
In lift installations, suspension ropes pass over rotating components such as traction sheaves and diverter pulleys. These components are subjected to large cycling / dynamic loading conditions due to the rope tension forces. Those conditions, combined with potential loadings due to rotating unbalance, affect roller bearings, which often suffer from fatigue resulting in their damage and failure.
An experimental laboratory rig comprising a rotating disk-shaft assembly with seeded damage (disk unbalance and roller bearing components with damage) has been developed. The rig is instrumented to collect vibration data by using accelerometer sensors. Vibration features are then extracted from the vibration signals and are used in supervised machine learning (ML) to train artificial neural network (ANN) models to recognise patterns and classify the damage.
Classification and recognition of roller bearing damage in Lift Installations using supervised machine learning and vibration analysis.
Mateusz Gizicki, Stefan Kaczmarczyk, Rory Smith.
University of Northampton, UK.