Research on Information Fusion for Sensors Multiple Fault Diagnosis
Hao Yu · Proceedings of the CSEE · 2007
A novel scheme for multiple fault diagnosis of multisensor under different frame of discernment based on evidence theory is proposed. The redundant or complementary information of multisensor in space or time is used to detect and isolate the fault sensors. The evidence of sensor state is obtained through a high modularity of the sensor state recognizer network with modularized RBF,so the advantage of neural net is promoted and the bug of its unusable for change of input parameter is resolved. The evidential combination rule under different frame of discernment is presented,and the operation of refinement and coarsening is adopted,so the maximum of available information is exploited and the uncertainty of the effective state between the potential states of a sensor is decreased. Simulation tests demonstrate that the diagnosis strategy works effectively in multiple fault diagnosis of sensors.