Please wait a minute...
Front. Inform. Technol. Electron. Eng.  2010, Vol. 11 Issue (5): 394-400    DOI: 10.1631/jzus.C0910270
    
Model predictive control with an on-line identification model of a supply chain unit
Jian Niu, Zu-hua Xu*, Jun Zhao, Zhi-jiang Shao, Ji-xin Qian
State Key Lab of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China
Download:   PDF(154KB)
Export: BibTeX | EndNote (RIS)      

Abstract  A model predictive controller was designed in this study for a single supply chain unit. A demand model was described using an autoregressive integrated moving average (ARIMA) model, one that is identified on-line to forecast the future demand. Feedback was used to modify the demand prediction, and profit was chosen as the control objective. To imitate reality, the purchase price was assumed to be a piecewise linear form, whereby the control objective became a nonlinear problem. In addition, a genetic algorithm was introduced to solve the problem. Constraints were put on the predictive inventory to control the inventory fluctuation, that is, the bullwhip effect was controllable. The model predictive control (MPC) method was compared with the order-up-to-level (OUL) method in simulations. The results revealed that using the MPC method can result in more profit and make the bullwhip effect controllable.

Key wordsSupply chain      Model predictive control      On-line identification      Optimization with constraint      Piecewise linear price     
Received: 11 May 2009      Published: 28 April 2010
CLC:  TP29  
  C939  
Fund:  Project  supported  by  the  National  Natural  Science  Foundation of China (Nos. 60804023, 60934007, and 60974007), and the National
Basic Research Program (973) of China (No. 2009CB320603) 
Cite this article:

Jian Niu, Zu-hua Xu, Jun Zhao, Zhi-jiang Shao, Ji-xin Qian. Model predictive control with an on-line identification model of a supply chain unit. Front. Inform. Technol. Electron. Eng., 2010, 11(5): 394-400.

URL:

http://www.zjujournals.com/xueshu/fitee/10.1631/jzus.C0910270     OR     http://www.zjujournals.com/xueshu/fitee/Y2010/V11/I5/394


Model predictive control with an on-line identification model of a supply chain unit

A model predictive controller was designed in this study for a single supply chain unit. A demand model was described using an autoregressive integrated moving average (ARIMA) model, one that is identified on-line to forecast the future demand. Feedback was used to modify the demand prediction, and profit was chosen as the control objective. To imitate reality, the purchase price was assumed to be a piecewise linear form, whereby the control objective became a nonlinear problem. In addition, a genetic algorithm was introduced to solve the problem. Constraints were put on the predictive inventory to control the inventory fluctuation, that is, the bullwhip effect was controllable. The model predictive control (MPC) method was compared with the order-up-to-level (OUL) method in simulations. The results revealed that using the MPC method can result in more profit and make the bullwhip effect controllable.

关键词: Supply chain,  Model predictive control,  On-line identification,  Optimization with constraint,  Piecewise linear price 
[1] Yong-gang Peng, Jun Wang, Wei Wei. Model predictive control of servo motor driven constant pump hydraulic system in injection molding process based on neurodynamic optimization[J]. Front. Inform. Technol. Electron. Eng., 2014, 15(2): 139-146.
[2] Mohammad Mohajer Tabrizi, Behrooz Karimi. Supply chain network design under uncertainty with new insights from contracts[J]. Front. Inform. Technol. Electron. Eng., 2014, 15(12): 1106-1122.
[3] Jiao-na Wan, Zhi-jiang Shao, Ke-xin Wang, Xue-yi Fang, Zhi-qiang Wang, Ji-xin Qian. Reduced precision solution criteria for nonlinear model predictive control with the feasibility-perturbed sequential quadratic programming algorithm[J]. Front. Inform. Technol. Electron. Eng., 2011, 12(11): 919-931.
[4] Qing-chao Wang, Jian-zhong Zhang. Wiener model identification and nonlinear model predictive control of a pH neutralization process based on Laguerre filters and least squares support vector machines[J]. Front. Inform. Technol. Electron. Eng., 2011, 12(1): 25-35.