Many industrial processes are inherently distributed in space and time and are called spatially distributed dynamical systems\n(SDDSs). Sensor placement affects capturing the spatial distribution and then becomes crucial issue to model or control an SDDS.\nIn this study, a new data-driven based sensor placement method is developed. SVR algorithm is innovatively used to extract the\ncharacteristics of spatial distribution froma spatiotemporal data set.Thesupport vectors learned by SVR represent the crucial spatial\ndata structure in the spatiotemporal data set, which can be employed to determine optimal sensor location and sensor number. A\nsystematic sensor placement design scheme in three steps (data collection, SVR learning, and sensor locating) is developed for an\neasy implementation. Finally, effectiveness of the proposed sensor placement scheme is validated on two spatiotemporal 3D fuzzy\ncontrolled spatially distributed systems.
Loading....