Advanced diagnostics are key to ensuring the quality, reliability and efficiency of the processes being monitored. Research activities are focused on the development of diagnostic systems and techniques for the early identification of emerging problems and the prediction of impending machine failures. The aim is to solve potential problems proactively and in a timely manner, to minimize unplanned machine downtime and to optimize the performance of the diagnosed equipment according to current requirements.

The membership of the research group is multidisciplinary and includes experts from all relevant departments of the Institute of Manufacturing Machines, Systems and Robotics.

Research topics:

• Digital transformation leading to Industry 4.0.

• Development of monitoring systems for the detection of abnormal trends in machine behaviour, which provide early indication of possible malfunctions.

• Use of AI methods in technical diagnostics and maintenance.

• Developing strategies for diagnostic activities, sharing data and coordinating maintenance of machinery and equipment.

• Integration of sensors into production equipment for detailed monitoring of process and plant condition.

• Advanced analysis of big data sets to identify patterns and trends in measured data.

• Using VR and AR technologies to train service technicians and operators, visualise diagnostic data and support of maintenance and repair processes.

• Implementation of automated systems for autonomous monitoring and diagnostics of production equipment.

• Using Edge computing to process diagnostic data directly on the production equipment.

Examples of solved projects:

• Technologies and tools for the digital transformation of engineering

• Application possibilities of the multifunctional grinding machine BUD 100

• The automatic controls of dedicated technological equipment using machine learning

• National Competence Centre of Mechatronics and Smart Technologies for Mechanical Engineering (TN01000071)

• Research and development of a machine tool monitoring unit to support proactive maintenance

Examples of outputs:

• ZUTH, D. Cluster analysis of vibrodiagnostic signal. DIAGO 2023 – Technical diagnostics of machines and production equipment. Ostrava: VSB TU Ostrava, 2023. s. 188-195. ISBN: 978-80-248-4656-9.

• ZUTH, D.; BLECHA, P.; MARADA, T.; HUZLÍK, R.; TŮMA, J.; MARADOVÁ, K.; FRKAL, V. Vibrodiagnostics Faults Classification for the Safety Enhancement of Industrial Machinery. Machines, 2021, roč. 9, č. 10, s. 1-19. ISSN: 2075-1702.

• HOLUB, M.; VETIŠKA, J.; ANDRŠ, O.; KOVÁŘ, J. Effect of position of temperature sensors on the resulting volumetric accuracy of the machine tool. MEASUREMENT, Journal of the International Measurement Confederation (IMEKO), 2019, roč. 2020, č. 150, s. 1-8. ISSN: 0263-2241.

• HOLUB, M.; PAVLÍK, J.; VETIŠKA, J.; ANDRŠ, O.; KOVÁŘ, J.; MAREK, T.; BRADÁČ, F.; KROUPA, J.; ZUTH, D.; ROSENFELD, J.; VELECKÝ, P.; PETŘIVALSKÝ, P.; VAŠEK, L.; VAŠEK, V.; DOLINAY, V.; CHALUPA, P.; CHUDÁ, H.; NOVÁK, J.: Technology to ensure production competence and increase efficiency in the machining of large workpieces. Slovácké strojírny, a.s. (proven technology).

• ANDRŠ, O.; HOLUB, M.; KOVÁŘ, J.; KROUPA, J.; ZUTH, D.; MAREK, J.; BRYCHTA, Z.: TN01000071/02-V13; Multisensor platform for smart machines. Brno University of Technology, Faculty of Mechanical Engineering, Technická 2896/2 616 69 Brno C1/118, MCV 754. (functional sample).

• HOLUB, M.; MARADA, T.; HUZLÍK, R.; KOČIŠ, P.; ZUTH, D.; BRAŽINA, J.; MAREK, J.; BRYCHTA, Z.: TN01000071/02-V17; Sensor database unit. Brno University of Technology, Faculty of Mechanical Engineering, Technická 2896/2 61669 Brno C1/118, MCV 754. (functional sample).

Contact:

Ing. Daniel Zuth, Ph.D.