Sensor selected fusion with sensor selection based gating neural network

Manufacturing systems have become more and more complex for adapting to various process conditions. Various and numerous sensors are equipped in the system for measuring various states in process. For efficient manufacturing, a sensor fusion method is needed for inferring state which conventional sensors cannot measure. We (2001) have proposed a sensor fusion method with sensor selection based on the reliability of the sensor value and knowledge database for a response to various environmental conditions. In this paper, we propose a sensor selected fusion system with the sensor selection based gating neural network. The gating neural network is stored, which links the neural network for the inference that should be used. Thus, the gating neural network decides the configuration of the neural network from the sensor selection rule and process conditions. For showing the effectiveness, we apply the proposed method to the inference of the surface roughness in the grinding process