Robust parameter estimation with noisy data
Abstract
For process control improvement, coherency of information supplied by instrument lines and sensors must first be ensured; because of the presence of random and possibly gross errors, the model equations of the process are not generally satisfied. Moreover, the parameters of the considered model are not always exactly known. The problem of how to reconcile the measurements so that they satisfy the model constraints is considered in this article. The simultaneous presence of measurement errors in process input and output measurements coupled with the model parameter uncertainty poses serious problem in the rectification of data. In that paper, the problem is solved using a special filter to estimate both the parameters, the input and the output of a process represented by an autoregressive model.