COURSES

Goals

Course objectives: - understanding the taxonomy of sensor networks in the area of condition monitoring, - becoming familiar with basic concepts of condition monitoring, - getting acquainted with basic signal processing algorithms in sensor networks, - making students familiar with practical problems. Competences: - ability to perform requirements analysis for condition monitoring systems, - ability to configure a sensor network for system diagnostics and prognostics, - ability to design algorithms for sensor fusion, - ability to make use of MIMOSA database.

Curriculum

- The role of condition monitoring in the maintenance of industrial assets. - The taxonomy of asset condition monitoring and prognostics of the remaining useful life. - Components of the industrial sensor networks, sensors and micro-sensors, smart nodes, systems on chip, gateways and protocol converters. - Feature extraction, Fourier and wavelet transforms, high-order spectra, spectral kurtosis, entropy indices. - Model based approaches: residuals, (non-linear) Kalman filter. - Trend change detection, feature fusion. - Prognostics: statistical approaches based on historical records. - Data acqusition, storage and display in sensor networks, integration with existing information systems, MIMOSA OSA EAI standard. - Industrial case studies. - Individual study of a real case from student’s research work.