Sensor failure detection and recovery by neural networks

Describes a method of sensor failure detection, isolation, and accommodation using a neural network approach. In a propulsion system such as the Space Shuttle main engine (SSME), the dynamics are complicated and sometimes not well known. However, the number of variables measured is usually much higher than the order of the system. This built-in redundancy of the sensors can be utilized to detect and correct sensor failure problems. The goal is to train a neural network to identify the sensor whose measurement is not consistent with other sensor outputs. Another neural network is trained to recover the value of critical variables when their measurements fail. Techniques for training the network with a limited amount of data are developed. The proposed scheme was tested using simulated data of the SSME in-flight sensor group.<<ETX>>