Durability analysis of forging tools after different variants of surface treatment using a decision-support system based on artificial neural networks

Abstract This article concerns a decision-support system based on artificial neural networks (ANN) enabling analysis and forecasting of the durability of forging tools used in the hot forging process of a cover forging – a sealing element of the driveshaft in road freight vehicles. The process of knowledge acquisition, adopted neural network architecture and parameters of the developed network are presented. In addition, 3 variants of a hybrid layer (gas nitrided layer GN + PVD coating) were applied to the selected tools (punches applied in the 2nd top forging operation): GN/AlCrTiN, GN/AlCrTiSiN, and GN/CrN, in order to improve durability, and the resultant tools were also compared to standard tools (with only gas nitriding) and regenerated tools (after repair welding regeneration). The indispensable knowledge about the durability of selected forging tools (after various surface engineering variants), required for the process of learning, testing and validation for various neural network architectures was obtained from comprehensive, multi-year studies. These studies covered, among other things: operational observation of the forging process, macroscopic analysis combined with scanning of tools’ working surfaces, microhardness measurements, microstructural analysis and numerical modeling of the forging process. The developed machine-learning dataset was a collection of approx. 900 knowledge records. The input (independent) variables were: number of forgings manufactures, pressing forces, temperature on selected tool surfaces, friction path and type of protective layer applied to tool. Meanwhile, output (dependent) variables were: geometrical loss of tool material and percentage share of the four main destructive mechanisms. Obtained results indicate the validity of employing ANN-based IT tools to build decision-support systems for the purpose of analyzing and forecasting the durability of forging tools.

[1]  Taylan Altan,et al.  Cold And Hot Forging: Fundamentals And Applications , 2004 .

[2]  Dariusz Mazurkiewicz.  Maintenance of belt conveyors using an expert system based on fuzzy logic , 2015 .

[3]  Kwang Ho Kim,et al.  Estimation of die service life against plastic deformation and wear during hot forging processes , 2005 .

[4]  Dilip Kumar Pratihar,et al.  Fuzzy logic-based expert system to predict the results of finite element analysis , 2007, Knowl. Based Syst..

[5]  Ryszard Tadeusiewicz,et al.  Neural Networks In Mining Sciences – General Overview And Some Representative Examples , 2015 .

[6]  A. Niechajowicz,et al.  The expert system supporting the assessment of the durability of forging tools , 2016 .

[7]  Miaoquan Li,et al.  Prediction of the mechanical properties of forged TC11 titanium alloy by ANN , 2002 .

[8]  Indrajit Basak,et al.  Expert system to predict forging load and axial stress , 2011, Appl. Soft Comput..

[9]  Zbigniew Gronostajski,et al.  Application of a measuring arm with an integrated laser scanner in the analysis of the shape changes of forging instrumentation during production , 2016 .

[10]  Zbigniew Gronostajski,et al.  Analysis of the wear of forging tools surface layer after hybrid surface treatment , 2017 .

[11]  Lukasz Rauch,et al.  Cellular automata model for prediction of crack initiation and propagation in hot forging tools , 2016 .

[12]  Marek Hawryluk,et al.  A durability analysis of forging tools for different operating conditions with application of a decision support system based on artificial neural networks (ANN) , 2017 .

[13]  J. Branco,et al.  Thermal fatigue of hot work tool steel with hard coatings , 1997 .

[14]  F. Meng,et al.  Role of Eta-carbide Precipitations in the Wear Resistance Improvements of Fe-12Cr-Mo-V-1.4C Tool Steel by Cryogenic Treatment , 1994 .

[15]  Zbigniew Gronostajski,et al.  Application of selected surface engineering methods to improve the durability of tools used in precision forging , 2017 .

[16]  Y. Min,et al.  Influence of different surface treatments of H13 hot work die steel on its thermal fatigue behaviors , 2001 .

[17]  J. Smolik,et al.  Badanie wpływu warstw hybrydowych na trwałość matryc do kucia na gorąco , 2010 .

[18]  Marek Hawryluk,et al.  Review of selected methods of increasing the life of forging tools in hot die forging processes , 2016 .

[19]  Hengan Ou,et al.  Die shape optimisation for net-shape accuracy in metal forming using direct search and localised response surface methods , 2011 .

[20]  M. Poursina,et al.  Radial forging force prediction through MR, ANN, and ANFIS models , 2014, Neural Computing and Applications.

[21]  Z. Gronostajski,et al.  A review of the degradation mechanisms of the hot forging tools , 2014 .

[22]  Sture Hogmark,et al.  Thermal fatigue cracking of surface engineered hot work tool steels , 2005 .

[23]  Stanislawa Kluska-Nawarecka,et al.  Practical Aspects of Knowledge Integration Using Attribute Tables Generated from Relational Databases , 2011 .

[24]  Z. Gronostajski,et al.  The main aspects of precision forging , 2008 .

[25]  Taylan Altan,et al.  Estimation of plastic deformation and abrasive wear in warm forging dies , 2012 .

[26]  Guido Berti,et al.  Thermo-mechanical fatigue life assessment of hot forging die steel , 2005 .

[27]  Sture Hogmark,et al.  Simulation and evaluation of thermal fatigue cracking of hot work tool steels , 2004 .

[28]  A. Katunin.  The conception of the fatigue model for layered composites considering thermal effects , 2011 .

[29]  Tsutao Katayama,et al.  Construction of PC-based expert system for cold forging process design , 2004 .

[30]  L. Cser,et al.  Tool Life and Tool Quality in Bulk Metal Forming , 1993 .

[31]  K. Héberger,et al.  Predictive performance of “highly complex” artificial neural networks , 2007 .

[32]  Zbigniew Gronostajski,et al.  The failure mechanisms of hot forging dies , 2016 .

[33]  Y. Sun,et al.  Modelling optimisation of hot processing parameters of Ti–6Al–4V alloy using artificial neural network and genetic algorithm , 2014 .

[34]  Edward Nawarecki,et al.  Multi-aspect Character of the Man-Computer Relationship in a Diagnostic-Advisory System , 2012 .

[35]  S. V. Smirnov,et al.  Damage mechanics for the fracture prediction of metal forming tools , 2000 .