Implementation of a proper maintenance strategy plays animportant role in increasing the overall efficiency of plants in industries. Naturally,the faults in assets may occur with age-related or random (independent of theasset age) failure rates [1]. It should be noticed that time-based strategies such as preventive maintenance (PM) could not deal with the random nature faults, appropriately. In contrast, the condition-based maintenance (CBM) strategy can manage the addressed faults by analyzing the historical information and monitored data.
Basically, the CBM procedure includes three main steps; conditionmonitoring, diagnostics, and prognostics. The condition monitoring deal withanomaly detection of the machine. In diagnostics, the degradation element orthe source of the fault in the machine is discovered. In prognostics, thecondition monitoring data is utilized to predict the remaining useful life(RUL) of the components. The confidence level (CL) estimation of predictions inthe aforementioned steps is important for decision making and planning themaintenance activities.
The rolling element bearings (REBs) are the most widely usedcomponents in the rotating machinery, which their failure is the cause ofalmost 50% of the machine break down [2]. Therefore, from the reliability point of view, REBs are considered the critical components and their appropriate functionality lead to availability increase in the rotating machinery. On the other hand, REBs are usually degradate gradually and the defects in the elements of the REBs generate specific indicators in the vibration signals. It makes it possible for predicting degradation and RUL of them and many researchers have developed various approaches to this aim. Developing software for analyzing the vibration condition monitoring (VCM) data for diagnostics as well as predicting the RUL of REBs is interesting and applicable for industrial maintenance teams.
The Condition Monitoring and fault diagnostics (CMFD) group at Sharif University of Technology (SUT) has widely researched on different aspects and approaches in the field of REBs diagnostics and prognostics over the last 20 years. A test-rigfor accelerated-life tests on REBs is developed and employed for various run-to-failure experiments in the Lab. The list of thesis and the selected publications of the group are presented in the annex. Due to the complex nature of REBs fault propagation, the artificial intelligent (AI) methods and statistical methods are more focused among the different approaches in the recent researches of the group.
Besides, the group has many industrial experiences along with access to various CM data of industrial rotating machines such as fans, pumps, turbines, compressors, generators, and electromotors in various industries including oil and gas industries, steel manufacturing companies, cement industries, wood and paper industries, food industries, car manufacturing industries, etc. This background is an excellent opportunity that can be used in verifying prognostics algorithms on the industrial machines and actual field VCM data.
Head of the SPbU team professor O.N. Granichin is a member of Russian national Committee on Automatic Control, a member of IFAC Technical Committee 1.1 (Modeling, Identification and Signal Processing), a Senior member of IEEE, IEEE Control System Society, member of Academy of Navigation and Control of Moving, member of the St. Petersburg branch of the Scientific Council of the Russian Academy of Sciences on the methodology of artificial intelligence and cognitive research at the Presidium of the Russian Academy of Sciences. He has been researching control theory since the early 1980s, focusing on control problems under irregular unknown but bounded disturbances. The description of a minimax stabilizing controller for a non-minimum-phase control plant proposed by him in his student course work (1981) was one of the world's first significant theoretical results of the recently popular theory of ℓ1-optimization. Under the guidance of Professor O.N. Granichin at the Department of System Programming, Faculty of Mathematics and Mechanics, St. Petersburg State University a constantly renewing scientific group of young researchers has been formed, engaged in statistical analysis, pattern recognition, and the development of software tools for modeling the behavior of stochastic optimization algorithms in specific applied problems.The high professional level of the project's research team is proved by theavailable scientific results presented at numerous high-ranked internationalconferences and published in peer-reviewed international high-ranked journalsindexed in Scopus and Web of Science.
A distinctive feature of thescientific group can be called the ability to competently combine theoretical fundamental research (in partial, about confidence level (CL) for estimation of predictions) and their practical application for more specific problems.
[1] K.Knutsen, G. Manno, and B. Vartdal, "Beyond Condition Monitoring in theMaritime Industry," DNV GL Strategic Research & Inovation PositionPaper, 2014.
[2] A. Rai and S. Upadhyay,"A Review on Signal Processing Techniques Utilized in the Fault Diagnosisof Rolling Element Bearings," Tribology International, vol. 96, pp.289-306, 2016.