TITLE

Multi-objective optimization of gear forging process based on adaptive surrogate meta-models

AUTHOR(S)
Meng, Fanjuan; Labergere, Carl; Lafon, Pascal; Daniel, Laurent
PUB. DATE
May 2013
SOURCE
AIP Conference Proceedings;May2013, Vol. 1532 Issue 1, p637
SOURCE TYPE
Academic Journal
DOC. TYPE
Article
ABSTRACT
In forging industry, net shape or near net shape forging of gears has been the subject of considerable research effort in the last few decades. So in this paper, a multi-objective optimization methodology of net shape gear forging process design has been discussed. The study is mainly done in four parts: building parametric CAD geometry model, simulating the forging process, fitting surrogate meta-models and optimizing the process by using an advanced algorithm. In order to maximally appropriate meta-models of the real response, an adaptive meta-model based design strategy has been applied. This is a continuous process: first, bui Id a preliminary version of the meta-models after the initial simulated calculations; second, improve the accuracy and update the meta-models by adding some new representative samplings. By using this iterative strategy, the number of the initial sample points for real numerical simulations is greatly decreased and the time for the forged gear design is significantly shortened. Finally, an optimal design for an industrial application of a 27-teeth gear forging process was introduced, which includes three optimization variables and two objective functions. A 3D FE nu merical simulation model is used to realize the process and an advanced thermo-elasto-visco-plastic constitutive equation is considered to represent the material behavior. The meta-model applied for this example is kriging and the optimization algorithm is NSGA-II. At last, a relatively better Pareto optimal front (POF) is gotten with gradually improving the obtained surrogate meta-models.
ACCESSION #
87656141

 

Related Articles

  • Classification Methods with Reject Option Based on Convex Risk Minimization. Ming Yuan; Wegkamp, Marten // Journal of Machine Learning Research;1/1/2010, Vol. 11 Issue 1, p366 

    In this paper, we investigate the problem of binary classification with a reject option in which one can withhold the decision of classifying an observation at a cost lower than that of misclassification. Since the natural loss function is non-convex so that empirical risk minimization easily...

  • On the purpose of Event-B proof obligations. Hallerstede, Stefan // Formal Aspects of Computing;Jan2011, Vol. 23 Issue 1, p133 

    Event-B is a formal modelling method which is claimed to be suitable for diverse modelling domains, such as reactive systems and sequential program development. This claim hinges on the fact that any particular model has an appropriate semantics. In Event-B, this semantics is provided implicitly...

  • Research on Tracked Vehicle Suspension Parameter Optimization Based on Surrogate Model Method. Wang Hongyan; Wang Qinlong; Rui Qiang; Ma Weibiao // Advanced Materials Research;2014, Vol. 936, p2098 

    In this article a surrogate model between suspension system parameters of tracked vehicle and comfort evaluation indices has been built up by using radial basis function method and the dynamic simulation of tracked vehicle. Then the optimization of suspension system parameters has been carried...

  • An experimental evaluation of two approaches to mining context based sequential patterns. Stefanowski, Jerzy; Ziembinski, Radoslaw // Control & Cybernetics;Mar2009, Vol. 38 Issue 1, p27 

    The paper discusses the results of experiments with a new context extension of a sequential pattern mining problem. In this extension, two kinds of context attributes are introduced for describing the source of a sequence and for each element inside this sequence. Such context based sequential...

  • An experimental methodology for response surface optimization methods. Lizotte, Daniel; Greiner, Russell; Schuurmans, Dale // Journal of Global Optimization;Aug2012, Vol. 53 Issue 4, p699 

    Response surface methods, and global optimization techniques in general, are typically evaluated using a small number of standard synthetic test problems, in the hope that these are a good surrogate for real-world problems. We introduce a new, more rigorous methodology for evaluating global...

  • EXTENSION OF THE NEW ITERATIVE APPROACH OF ADOMIAN ALGORITHM TO PARTIAL DIFFERENTIAL EQUATIONS (PDE) STRONGLY NONLINEAR WITH INITIAL AND BOUNDARY CONDITIONS. Abbo, Bakari; Danna, Abba; Youssouf, Pare; Some, Blaise // Far East Journal of Mathematical Sciences;Apr2013, Vol. 75 Issue 2, p245 

    In our previous articles [1-5], we presented a new iterative approach in the algorithm of the Adomian method for solving nonlinear Cauchy ODE and PDE. In this paper, we show the extension of the new technique to nonlinear PDE systems with initial and boundary conditions, thus generalizing a...

  • Independent surrogate variable analysis to deconvolve confounding factors in large-scale microarray profiling studies. Teschendorff, Andrew E.; Zhuang, Joanna; Widschwendter, Martin // Bioinformatics;Jun2011, Vol. 27 Issue 11, p1496 

    Motivation: A common difficulty in large-scale microarray studies is the presence of confounding factors, which may significantly skew estimates of statistical significance, cause unreliable feature selection and high false negative rates. To deal with these difficulties, an algorithmic...

  • Setting targets for surrogate-based optimization. Queipo, Nestor; Pintos, Salvador; Nava, Efrain // Journal of Global Optimization;Apr2013, Vol. 55 Issue 4, p857 

    In the context of surrogate-based optimization (SBO), most designers have still very little guidance on when to stop and how to use infill measures with target requirements (e.g., one-stage approach for goal seeking and optimization); the reason: optimum estimates independent of the surrogate...

  • Composite Binary Losses. Reid, Mark D.; Williamson, Robert C. // Journal of Machine Learning Research;9/1/2010, Vol. 11 Issue 9, p2387 

    No abstract available.

Share

Read the Article

Courtesy of VIRGINIA BEACH PUBLIC LIBRARY AND SYSTEM

Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics