The objective of the research is to develop, implement and test novel concepts for improved control of composite materials manufacturing process. Advanced composite materials manufacturing is expensive, labor intensive and prone to high part rejection rates. Raw materials costs are only 5 to 15% of the total manufacturing cost. Emerging technologies such as artificial intelligence and model-based control, combined with increased understanding of polymer processing science and technology, provide a synergistic opportunity to advance the state of the art in composite manufacturing. A strategy that combines an on-line process model with experimential processing knowledge will be researched. The system is intended to be adaptive and adjust the processing conditions to compensate for changes in raw materials or product requirements. Due to the difficulty of acquiring the processing knowledge and the volatile nature of this knowledge, a strategy for constant updating and improvement is also required. To achieve this, a methodology for capturing control knowledge from past operational histories of the process is suggested. The result of these innovations is an intelligent processing strategy that will reduce part rejection rate and hence the overall manufacturing cost. The concept will be implemented and tested on a selected process, namely the autoclave curing of composites.
