Research & Realization on Neural Network for Forecast of AM Automatic Logistics Information-System

Article Preview

Abstract:

This paper gives research on Neural Network for AM Automatic Logistics information System’s Modeling, Simulation and algorithm, contrasted to traditional methods of forecast. In order to raise the design efficiency and get the most excellent design effect, this paper combined Ant Colony Optimization (ACO) algorithm and neural networks, which based on ACO algorithm and the implementing framework of ACO. It gives the basic theory and steps; which proved research on Neural Network for AM Automatic Logistics information-System has good ability of non-linear function’s approach and latent feedback’s dynamic data processing, study online time short, parameter convergence swift, self-adapt ability good, can study and adapt to severity uncertainly dynamic system’s tract, forecast precision is high.

You might also be interested in these eBooks

Info:

Periodical:

Advanced Materials Research (Volumes 97-101)

Pages:

2845-2850

Citation:

Online since:

March 2010

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2010 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] Wang ping, Chen Xingming, Liu fei et al. A Trans-enterprise Logistics Information Collection Technique. Chinese mechanical engineering 2002, 18: 1561-1564.

Google Scholar

[2] Wang Chengliang, Song jun, et al. Application of Intelligent �eural �etwork on Prediction of Time Series Signal. Journal of ChongQi University (Natural Science), 2003, 26(1)34-37.

Google Scholar

[3] Wang Kejun, et al. �� Modeling, forecast and Control. Hartbin: publishing company HarBin Engineering University, (1996).

Google Scholar

[4] Bowersox Donald J, Closs David J . Logistical management: The integrated supply chain process. (1999).

Google Scholar

[5] HuangTiyun. Intelligent Decision-Making System. BeiJing: Publish House of Electronics Industry, (2001).

Google Scholar

[6] Desmond Fletcher. Forecasting with neural networks. Information and Management, 1993, 24(3): 159-167.

Google Scholar

[7] He Yongyong , Chu Fulei , Zhong Binglin. A study of hybrid neural network approaches and the effects of missing data on traffic forecasting. Neural Computing & Applications, 2001, 10(3): 277 - 286.

DOI: 10.1007/s521-001-8054-3

Google Scholar

[8] Thomas Kolarik Gottfried Rudorfer. Time series forecastingusing neural networks. ACM SIGAPL APL Quote Quad, 1994, 86 - 94.

DOI: 10.1145/190468.190290

Google Scholar

[9] Kanad Chakraborty, Kishan Mehrota, Chilukuri Mohan, etc. Forecasting the behaviour of multivariate time series usingneural networks. Neural Networks, 1992, 5 (6): 961 -970.

DOI: 10.1016/s0893-6080(05)80092-9

Google Scholar