DATA RECTIFICATION AND GROSS ERROR-DETECTION IN A STEADY-STATE PROCESS VIA ARTIFICIAL NEURAL NETWORKS

One of the many problems engineers face is that of identifying and eli minating gross errors from measured data, and rectifying collected dat a to satisfy process constraints such as the mass and energy balances that describe a process. While it is possible to use statistical metho ds coupled with error reduction techniques to rectify data, the strate gy must be carried out iteratively in many steps. Artificial neural ne tworks (ANN) being composed of basis functions yield excellent models, and can be trained to rectify data. We demonstrate the application of an ANN to rectify the simulated measurements obtained from a steady-s tate heat exchanger. Both random and gross errors added to the simulat ed measurements were successfully rectified. A comparison was made of the application of ANN with rectification by constrained least squares via nonlinear programming, and the ANN treatment proved to be superio r. We conclude that the use of ANN appears to be a promising tool for data rectification.