Abstract—Material ingredient optimization is favorably and
widely studied by using design of experiment (DOE) and
artificial neural network (ANN). But the nonlinear mapping
relationship model trained by the insufficient DOE samples can
always cause non-negligible errors. This paper suggests a
method adding some artificial samples into the neural network
training data to get a better material ingredient optimization .In
this method, artificial sample generation is combined with
dimensionality reduction and segmentation technique. A
simulation showed at the end of this paper indicates that
compared with the model learning only from real DOE data,
the accuracy can be significantly improved by adding some
artificial training samples.
Index Terms—Material ingredient optimization, DOE,
artificial sample generation, insufficient samples.
The authors are with the School of Information Systems and Management,
National University of Defense Technology, Sanyi Ave, Changsha, China
(e-mail: 18874771120@163.com, sunquan@nudt.edu.cn).
[PDF]
Cite: Juan Chen, Quan Sun, Jing Feng, and Zhengqiang Pan, "Material Ingredient Optimization Based on Design of Experiment and Neural Network with Artificial Sample Generation," International Journal of Materials, Mechanics and Manufacturing vol. 3, no. 3, pp. 218-222, 2015.