DYNAMIC RECTIFICATION OF DATA VIA RECURRENT NEURAL NETS AND THE EXTENDED KALMAN FILTER

The presence of autocorrelated measurement errors and/or measurement b ias in process measurements poses serious problems in the rectificatio n of data taken from dynamic processes. The proposed procedure to reso lve these problems involves the use of recurrent neural networks (RNN) and the extended Kalman filter (EKF). By interpreting RNNs within a n onlinear state-space context, a state-augmented EKF can be used to opt imally estimate both the states of the RNNs and noise and bias models. RNN models can be identified off-line and utilized for data rectifica tion within the extended Kalman filter in process environments in whic h badly autocorrelated measurement errors exist in the data. The same technique is also used to estimate measurement bias present in both pr ocess input and output variables. This approach has the advantage that models developed from ''first principles'' are not required and that rectification can be performed solely on the basis of the contaminated dynamic data.