This content is not included in your SAE MOBILUS subscription, or you are not logged in.
Using Neural Networks to Examine the Sensitivity of Composite Material Mechanical Properties to Processing Parameters
ISSN: 1946-3979, e-ISSN: 1946-3987
Published April 05, 2016 by SAE International in United States
Citation: Zhang, X. and Johrendt, J., "Using Neural Networks to Examine the Sensitivity of Composite Material Mechanical Properties to Processing Parameters," SAE Int. J. Mater. Manf. 9(3):737-745, 2016, https://doi.org/10.4271/2016-01-0499.
Successful manufacture of Carbon Fibre Reinforced Polymers (CFRP) by Long-Fibre Reinforced Thermoplastic (LFT) processes requires knowledge of the effect of numerous processing parameters such as temperature set-points, rotational machinery speeds, and matrix melt flow rates on the resulting material properties after the final compression moulding of the charge is complete. The degree to which the mechanical properties of the resulting material depend on these processing parameters is integral to the design of materials by any process, but the case study presented here highlights the manufacture of CFRP by LFT as a specific example. The material processing trials are part of the research performed by the International Composites Research Centre (ICRC) at the Fraunhofer Project Centre (FPC) located at the University of Western Ontario in London, Ontario, Canada. The experimental processing system is instrumented to record data in three zones of the machine, including temperatures, torques, speeds, forces, and pressures. Material processing trials for six different fibre volume weights were conducted and the mechanical properties of the material were measured in both the zero and ninety degree fibre directions. A neural network model relating the processing parameters (as model inputs) to the mechanical properties of the material (as model outputs) was developed. As a result, the sensitivity of the material’s mechanical properties to the processing parameters could be examined as part of the model optimization process. The results of the sensitivity study are presented here along with a discussion of the further reaching implications on design tool development for composite materials.