A SVR Learning Based Sensor Placement Approach forNonlinear Spatially Distributed Systems

Many industrial processes are inherently distributed in space and time and are called spatially distributed dynamical systems(SDDSs). Sensor placement affects capturing the spatial distribution and then becomes crucial issue to model or control an SDDS.In this study, a new data-driven based sensor placement method is developed. SVR algorithm is innovatively used to extract thecharacteristics of spatial distribution from a spatiotemporal data set. The support vectors learned by SVR represent the crucial spatialdata structure in the spatiotemporal data set, which can be employed to determine optimal sensor location and sensor number. Asystematic sensor placement design scheme in three steps (data collection, SVR learning, and sensor locating) is developed for aneasy implementation. Finally, effectiveness of the proposed sensor placement scheme is validated on two spatiotemporal 3D fuzzycontrolled spatially distributed systems