Sensor validation and fusion using the Nadaraya-Watson statistical estimator

Abstract

The paper describes a novel integrated sensor validation and fusion scheme based on the Nadaraya-Watson statistical estimator. The basis of the sensor validation scheme is that observations used to implement the estimator are obtained from valid sensor readings. Pattern matching techniques are used to relate a measurement vector that is not consistent with the training data to the closest a-priori observation. Defective sensor(s) can be identified and 'masked', and the estimator reconfigured to compute the estimate using data from the remaining sensors. Test results are provided for a range of typical fault conditions using an array of thick film pH sensors. The new algorithm is shown to reliably detect and compensate for bias errors, spike errors, hardover faults, drift faults and erratic operation, affecting up to three of the five sensors in the array. The fused result is more accurate than the single best sensor.