Application of multisensor data fusion based on RBF neural networks for fault diagnosis of SAMS

The idea of multisensor integration is to use multiple sensors for measuring the same variables, where each sensor has its own accuracy, reliability and drawbacks. The sensor information is integrated by some data integration algorithms. In this paper, Radial Basis Function (RBF) neural networks and multisensor data fusion technology are combined and used in the fault detection and diagnosis of sensors hardware faults in the Satellite Attitude Measurement System (SAMS). The fusion method of the RBF neural networks is adopted. By using the combination method the outputs of the system are more accurate and reliable than each individual sensor. Research results show that this method for the detection and diagnosis of the sensors hardware faults in the SAMS is feasible and more effective, and for the sensors which measure the same attitude angle, using the method of firstly integration, then faults diagnosis, finally connection with the measurement system, the systematic measurement precision and performance-price-ratio can be improved.