Method of Product Innovation Acquisition Based on Dynamic Response Particle Swarm Optimization

Abstract:

In order to accurately locate the changing demands and objects of customers, a novel mining algorithm was presented to predict the Optimum Customer Demand (OCD) in the uncertain front end, which can be formulated as a dynamic nonlinear optimization problem. The improved Particle Swarm Optimization involves accurately detecting the changes all of the search space and reliably updating obsolete particle memories, which has been shown to be effective in locating the changing plentiful innovative thinking. Finally, the algorithm is applied into the prediction of customer demands in car’s appearance feature, which effectively guide the implementation of product innovation and greatly improve the front end performance.

• Periodical: Advanced Materials Research (Volumes 542-543)
• Pages: 3-7
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.542-543.3
• Online since: June 2012
• Authors: Yan Chao Yin, Ya Yu Huang
• Keywords: Dynamic Nonlinear Optimization, Dynamic Response Particle Swarm Optimization (DRPSO), Product Innovation Acquisition, Uncertain Front End

References

[1] P.R. Dean: Int. J. Prod. Res, Vol. 47 (2009), p.1245

[2] B, Zhang, Q.D. Yong, F.C. Xiao: Fuzzy matter–element analysis (Oil Industry Press, China 1997).

[3] Y.W. Zhao, G.X. Zhang: J. Mater. Process. Technol, Vol. 129 (2002), p.612

[4] J. Kennedy, R.C. Eberhart: Particle swarm optimization (IEEE, USA, 1995).

[5] Y.C Yin, C.F Yin, G. Cheng: Optimal Inventory Control Policy in an Uncertain Supply Chain Environment (ASCE, USA, 2008)