Diagnostic and prognostic platform for automated condition monitoring In the paper we present the Diagnostic and Prognostic Platform (DPP) for automated condition monitoring of a broad spectrum of industrial drives, embedded systems and various other electrochemical processes. Special attention in the paper was dedicated to presenting the innovative procedures foe estimation of the remaining useful life of monitored component. The performance of the novel procedures was demonstrated with two industrial experiments, which showed good agreement between the actual and estimated time of failure.
B.03 Paper at an international scientific conference
COBISS.SI-ID: 24815399The dissertation addresses the problem of parameter estimation of stochastic, discrete-time, state-space models from input and output data. Expectation maximization (EM) algorithm is used for solving this problem. The aim of the dissertation was to explore the performance of the EM algorithm under different approximation schemes, namely the sequential Monte Carlo (SMC) based approximations and unscented transformation (UT). The dissertation proposes a novel implementation of the EM algorithm entirely based on the unscented transformation. The proposed algorithm is applied to a relatively new problem domain dealing with estimation of the remaining useful life of mechanical systems. More particularism the case study dealing with a gear transmission system is addressed.
D.09 Tutoring for postgraduate students
COBISS.SI-ID: 256638720Indirect maintenance costs caused by degraded product quality, reduced production efficiency, loss of customers etc. are at least of the same range of magnitude. A way to reduce the indirect costs is to abandon the current maintenance paradigms (reactive and preventive) and make room for cost-efficient condition-based (predictive) maintenance. This article present a scientific background, problem identification, objective of the future research and state-of-the-art in the proposed field of research. In the article is described the CTD- Integrate intelligent system for monitoring, diagnostics and prognostics machinery conditions and how the step from diagnostics to prognostics can be taken outline a new European e-maintenance concept for information technology based maintenance.
B.04 Guest lecture