Forecasting Chaotic Series in Manufacturing Systems by Vector Support Machine Regression and Neural Networks

Currently, it is recognized that manufacturing systems are complex in their structure and dynamics. Management, control and forecasting of such systems are very difficult tasks due to complexity. Numerous variables and signals vary in time with different patterns so that decision makers must be able to predict the behavior of the system. This is a necessary capability in order to keep the system under a safe operation. This also helps to prevent  emergencies and the occurrence of critical events that may put in danger human beings and capital resources, such as expensive equipment and valuable production. When dealing with chaotic systems, the management, control, and forecasting are very difficult tasks. In this article an application of neural networks and vector support machines for the forecasting of the time varying average number of parts in a waiting line of a manufacturing system having a chaotic behavior, is presented. The best results were obtained with least square support vector machines and for the neural networks case, the best forecasts, are those with models employing the invariants characterizing the system’s dynamics.

[1]  Hoda A. ElMaraghy,et al.  Manufacturing Systems Configuration Complexity , 2005 .

[2]  J. Scott Armstrong,et al.  Principles of forecasting , 2001 .

[3]  Bernd Scholz-Reiter,et al.  Nonlinear characterization of the performance of production and logistics networks , 2008 .

[4]  Y. Wua,et al.  A study on the cost of operational complexity in customer – supplier systems , 2006 .

[5]  Dimitris Mourtzis,et al.  An Approach for Adaptability Modeling in Manufacturing –Analysis Using Chaotic Dynamics , 2007 .

[6]  Hui Wang,et al.  Manufacturing complexity in assembly systems with hybrid configurations and its impact on throughput , 2010 .

[7]  K. Lee,et al.  A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer , 2011 .

[8]  Vladan Babovic,et al.  Multi-step-ahead model error prediction using time-delay neural networks combined with chaos theory , 2010 .

[9]  L. Vanajakshi,et al.  A comparison of the performance of artificial neural networks and support vector machines for the prediction of traffic speed , 2004, IEEE Intelligent Vehicles Symposium, 2004.

[10]  George Chryssolouris,et al.  Modelling the complexity of manufacturing systems using nonlinear dynamics approaches , 2009 .

[11]  Dimitris A. Karras,et al.  On efficient multistep non-linear time series prediction in chaotic diode resonator circuits by optimizing the combination of non-linear time series analysis and neural networks , 2009, Eng. Appl. Artif. Intell..

[12]  Shian-Chang Huang,et al.  Chaos-based support vector regressions for exchange rate forecasting , 2010, Expert Syst. Appl..

[13]  Kin Keung Lai,et al.  A hybrid slantlet denoising least squares support vector regression model for exchange rate prediction , 2010, ICCS.

[14]  Henry D. I. Abarbanel,et al.  Analysis of Observed Chaotic Data , 1995 .

[15]  Juan M. Sepúlveda,et al.  Chaotic behavior in manufacturing systems , 2006 .

[16]  Vittal Prabhu,et al.  Complexity metrics for manufacturing control architectures based on software and information flow , 2005, Comput. Ind. Eng..

[17]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .