Simulation And Control Of Tool Steel Quenching Process

Tool steels are widely used materials for making elements of metals, polymers, ceramics and composites. Inflated consumer expectations of contemporary civilization entail the manufacture of better and better tools, accompanied by reduced energy consumption. The application of simulators and controls of technological processes enables the design of optimum processes without the need for time consuming and costly experimental research. The present article is devoted to a tool for simulation and control of tool steel quenching in gases (helium, nitrogen, argon, hydrogen), both at negative as well as at high pressures. The simulator takes as its input the quenching parameters, the individual characteristics of the furnace and the material, dimensions and shape of the treated workpiece, yielding in effect a cooling curve and the forecast post-quench hardness. The monitoring program, which constitutes an integral part of the tool, works on-line with the industrial equipment, thus allowing continuous control of the quenching process with respect to the simulation in progress. In the subsequent sections the article presents the operation of the simulator and the monitor, the field of practical applications thereof, and describes a practical application working with an industrial furnace. Particular attention is drawn to the verification stage of the mathematical model and the results of experimental processes of tool steel quenching.

[1]  Xu Liujie,et al.  Artificial neural network prediction of retained austenite content and impact toughness of high-vanadium high-speed steel (HVHSS) , 2006 .

[2]  Andrzej Bargiela,et al.  Granular prototyping in fuzzy clustering , 2004, IEEE Transactions on Fuzzy Systems.

[3]  M. R. Irving,et al.  Observability Determination in Power System State Estimation Using a Network Flow Technique , 1986, IEEE Transactions on Power Systems.

[4]  L. A. Dobrzański,et al.  The modelling of hardenability using neural networks , 1999 .

[5]  Andrzej Bargiela,et al.  Fuzzy fractal dimensions and fuzzy modeling , 2003, Inf. Sci..

[6]  L. Dobrzański,et al.  Application of neural networks to forecasting the CCT diagrams , 2004 .

[7]  W. Sitek,et al.  Methodology of high-speed steels design using the artificial intelligence tools , 2010 .

[8]  L. A. Dobrzański,et al.  Modelling of properties of the PVD coatings using neural networks , 2007 .

[9]  L. A. Dobrzański,et al.  The prototype of an expert system for the selection of high-speed steels for cutting tools , 1996 .

[10]  Andrzej Bargiela,et al.  A model of granular data: a design problem with the Tchebyschev FCM , 2005, Soft Comput..

[11]  P. Kula,et al.  Modern gas quenching chambers supported by SimVaC Plus Hardness application , 2008 .

[12]  Long Rui,et al.  Artificial neural network prediction of heat-treatment hardness and abrasive wear resistance of High-Vanadium High-Speed Steel (HVHSS) , 2007 .

[13]  L. Dobrzański,et al.  Application of neural networks for the prediction of continuous cooling transformation diagrams , 2004 .