Abstract: A device and method develop a training record for use in creating an empirical model of a process from data associated with the process. Data from a continuous process in the form of a continuous file or data from a set of batch files associated with different runs of a batch process is used to develop a file having multiple values for each of a plurality of variables associated with the process. A flag or other indicator is placed within the file to indicate the location of a significant event within the process or the location at which the data from different batch files was concatenated together. A record is then developed from the file by selecting a multiplicity of values within the file. Thereafter, it is determined if any two of the selected values within the record are located within the file at positions which are on different sides of the position indicated by the flag or other indicator.

Abstract: A process modeling system and method develop a set of process model inputs for a process model, such as a neural network, from values for a number of process input variables and at least one process output variable. The system and method first determine a correlation measurement between each of the process input variables and the process output variable and select a set of potential model input variables based on the correlation measurements. The system and method then iteratively determine a succession of sets of potential model input variables by performing a regression analysis on the selected set of potential model input variables and the model output variable and by then refining the set of potential model input variables based on the result of the regression analysis and on the correlation measurements. After a number of iterations, the system and method choose a set of potential model input variables as the set of model inputs and develop a process model from the chosen set of model inputs.