Generating process model for manufacture of chipboard or particle board by supplying determined current process parameters to process model to determine expected quality characteristics

摘要

The method is based on patent application 197 18262.3. For the manufacture of board products, in a fourth step, current process parameters are determined and supplied in a fifth step to the process model which determines the expected quality characteristics of the board. These characteristics are then used in an optimization algorithm to determine the process parameters to be set in the manufacturing process. A neural network made of radial base neurons may be used, which combines radial-base functions e.g. of gaussian type.