The Application of Multiparadigm Simulation Techniques to Manufacturing Processes

The simulation of manufacturing processes and manufacturing systems using computers has been carried out for several decades. The use of discrete event simulation models for production systems, material planning, machine grouping and various other key problems of resource allocation have been well researched and a number of ready to use commercial products are available. In recent years, the use of artificial intelligence simulation and modelling techniques for certain manufacturing processes have led to significant advantages over conventional techniques. However, the benefits of using AI techniques have not been fully exploited in existing simulation systems. Owing to the different way that some AI techniques process or represent simulation data compared to conventional mathematically based methods, it is not always easy to include AI techniques in existing simulation systems with their inherent structures for representing simulation data. In this paper, a concept which allows the use of AI techniques such as artificial neural networks, genetic algorithms and fuzzy sets as well as traditional mathematical techniques for the simulation and modelling of certain manufacturing processes is presented and discussed. Methods for the exchange of simulation data are demonstrated using the milling process as an example. Furthermore, the notion of distributed simulation and the determination of essential process parameters by remote access to common simulation databases using a client/server model has been reviewed.

[1]  Warren R. DeVries,et al.  A Mechanistic Dynamic Model of End Milling for Process Controller Simulation , 1991 .

[2]  S. Smith,et al.  An Overview of Modeling and Simulation of the Milling Process , 1991 .

[3]  Yusuf Altintas,et al.  Direct adaptive control of end milling process , 1994 .

[4]  Yusuf Altintas,et al.  Prediction of Cutting Forces and Tool Breakage in Milling from Feed Drive Current Measurements , 1992 .

[5]  Robert E. Shannon.  Knowledge based simulation techniques for manufacturing , 1988 .

[6]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[7]  Wei-Hua Chieng,et al.  Adaptive control optimization in end milling using neural networks , 1995 .

[8]  Igor Grabec,et al.  Self-Organizing Neural Network Application to Drill Wear Classification , 1994 .

[9]  Tae Jo Ko,et al.  Cutting state monitoring in milling by a neural network , 1994 .

[10]  S. R. S. Kalpakjian.  Manufacturing Processes for Engineering Materials , 1984 .

[11]  D. J. Myers,et al.  Neural Networks for Vision, Speech, and Natural Language , 1992 .

[12]  Jun Wang,et al.  Multiple-objective optimisation of machining operations based on neural networks , 1993 .

[13]  S. Ros,et al.  Fuzzy model of cutting process on a milling machine , 1994 .

[14]  Tae Jo Ko,et al.  Adaptive modelling of the milling process and application of a neural network for tool wear monitoring , 1996 .

[15]  Yusuf Altintas,et al.  A Solid Modeller Based Milling Process Simulation and Planning System , 1994 .