Abstract: An artificial neural network is used to predict the current state of a process based upon sensor measurements of the process variables at previous times. The output of the neural network provides the process control system with the predicted process state, thereby reducing the time lag of the sensors and providing improved control of the process.

Abstract: A method and apparatus for automatically setting the die height platen on a toggle-operated injection molding machine to achieve a desired mold clamping force. A control is provided and contains information relating a desired clamp tonnage with a toggle crosshead displacement, in order to permit setting the die height platen for a particular set of molds so that the clamp, when operated, will automatically provide the desired clamping force between the mold members. The adjustment is provided by moving the die height platen in response to deviations from a predetermined set of conditions, the die height platen being moved by an hydraulic motor and chain drive to shift the die height platen along guide rods that extend between the die height platen and a stationary mold platen.