This research is focused on developing an on-line control technique that is fast and reliable and can be used to maximize the performance of the tow placement technique. The thermoplastic tow placement is an emerging manufacturing technology that gives more flexibility in the design of parts and in cost reduction through on-line consolidation compared with autoclave processing. A control method is required to take advantage of these features. Therefore, recently developed process models are integrated into a neural-network based optimization package, which is capable of locating optimum setpoints in minimal time. A control algorithm with feedback from an IR thermal camera has been developed and is used to achieve the desired surface temperature. A feedforward neural network with a cascadien architecture is used to simulate the process. Simulation computations are now possible in less than a second, compared to around 20 minutes for the original FORTRAN simulation. This allows running of the process models online for control purposes. An optimization algorithm that suits the rough topology of the network has been written and tested. The algorithm is based on weighting the quality outputs of the neural network and finding the highest process speed for a given minimum quality. The output of the optimization is used as an input to the robot controller and to the temperature controller for the desired process temperature. An infrared camera mounted on the fiber placement head provides real time, on-line surface temperature information to the control module. Utilizing this thermal information, along with process information received from the neural network, the module maintains the desired thermal profile throughout the process by providing control outputs to the heat sources.
Source: Proceedings of the 'NDE applied to Process Control of Composite Fabrication' - Conference, 1-2 Oct 1996 St. Louis, Missouri. Publisher and Organizer: Nondestructive Testing Information Analysis Center (NTIAC) Texas Research Institute Austin, Inc. Austin, Texas [http://www.ntiac.com] [Buying the Proceedings]
|Access to all Abstracts of the Conference |