A METHOD TO INCORPORATE BOUNDS IN DATA RECONCILIATION AND GROSS ERROR-DETECTION .1. THE BOUNDED DATA RECONCILIATION PROBLEM

Data reconciliation and gross error detection techniques can be improv ed by exploiting information from bounds on process variables. In this paper a new approach is proposed for incorporating upper and lower bo unds on process variables in data reconciliation and gross error detec tion. Bounds on process variables are directly incorporated as constra ints in data reconciliation and the resulting problem is solved using an efficient quadratic programming algorithm. More importantly, a meth od to obtain the statistical distributions of measurement residuals an d constraint residuals has been developed which is useful for gross er ror detection. Gross error detection methods based on this approach ar e described in Part II of this series (Comput. chem. Engng 17, 1121-11 28).