A probabilistic approach for optimising hydroformed structures using local surrogate models to control failures

Abdessalem, Anis Ben; Hami, Abdelkhalak El

doi:10.1016/j.ijmecsci.2015.04.002

Cited by 30 publications

(6 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ben and EI-Hami [40] provided a deep comparison between the quadratic polynomial RSM and SVR as surrogate techniques to construct surrogate models for global sensitivities, multi-objective optimization of the THF process, and they found that the SVR showed its superiority over the quadratic polynomial RSM to deal with nonlinearities proved through analytical test function and practical THF process. Then, they extended the use of SVR to reliability-based design optimization of T-shape THF process [41].…”

Section: Introductionmentioning

confidence: 99%

The multi-objective optimization of the loading paths for T-shape tube hydroforming using adaptive support vector regression

Huang

Song

Liu

2016

Int J Adv Manuf Technol

View full text Add to dashboard Cite

The objective of this study is to introduce adaptive support vector regression, whose accuracy and efficiency are illustrated through a numerical example, to determine the Pareto optimal solution set for T-shape tube hydroforming process. A validated finite element model developed by the explicit finite element code LS-DYNA is used to conduct virtual T-shape tube hydroforming experiments. Multiobjective optimization problem considering contact area between the tube and counter punch, maximum thinning ratio, and protrusion height is formulated. Then, the Latin hypercube design is employed to construct the initial support vector regression model, and some extra sampling points are added to reconstruct the support vector regression model to obtain the Pareto optimal solution set during each iteration. Finally, the ideal point is used to obtain a compromise solution from the Pareto optimal solution set for the engineers.

show abstract

Section: Introductionmentioning

confidence: 99%

The multi-objective optimization of the loading paths for T-shape tube hydroforming using adaptive support vector regression

Huang

Song

Liu

2016

Int J Adv Manuf Technol

View full text Add to dashboard Cite

show abstract

“…Multi objective optimization can be performed in probabilistic or non-probabilistic environments and can take tolerances and variation into account. Having a probability function for the variables in the hydroforming process produces better results in finite element analysis [48] but is not required and other recent examples of using only the bounds of uncertainty have also been successful [49]. Success has been had with simulations that use fuzzy logic, simulated annealing, and traditional modelling techniques and so selection choose comes down to a mix of application, complexity, and experience.…”

Section: Analytical Methods and Numerical Simulationsmentioning

confidence: 99%

“…Several studies cite process variability as a key difficulty in load path optimization and have proposed various means to take this into account. For example, Abdessalem et al use a probabilistic approach to account for variation during load path creation [48], while Huang et al propose a kriging-based non-probability system [49] which only requires the bounds of uncertainty instead of a probabilistic function (presumably because this information is generally easier to acquire). Other studies tried to optimize load paths with fuzzy logic, [50] or by statistical means [51] or with metamodeling techniques to cut down on computational time [52].…”

Section: Process Windows and Loading Pathsmentioning

confidence: 99%

A state of the art review of hydroforming technology

et al. 2019

View full text Add to dashboard Cite

Hydroforming is a relatively new metal forming process with many advantages over traditional cold forming processes including the ability to create more complicated components with fewer operations. For certain geometries, hydroforming technology permits the creation of parts that are lighter weight, have stiffer properties, are cheaper to produce and can be manufactured from fewer blanks which produces less material waste. This paper provides a detailed survey of the hydroforming literature of both established and emerging processes in a single taxonomy. Recently reported innovations in hydroforming processes (which are incorporated in the taxonomy) are also detailed and classified in terms of “technology readiness level”. The paper concludes with a discussion on the future of hydroforming including the current state of the art techniques, the research directions, and the process advantages to make predictions about emerging hydroforming technologies.

show abstract

“…The choice of the suitable metamodelling technique depends mainly on the problem under consideration as the number of parameters to be considered and the complexity of the described phenomenon. In the framework of this work, the Least Square Support Vector Regression (LSSVR) [5] is selected as metamodelling techniques to be adopted due its robustness to deal with nonlinear problems as demonstrated in the following papers [6,7].…”

Section: Surrogate Model Constructionmentioning

confidence: 99%

Improving the reliability of POD curves in NDI methods using a Bayesian inversion approach for uncertainty quantification

Abdessalem¹,

Jenson²,

Calmon³

2016

AIP Conference Proceedings

Self Cite

View full text Add to dashboard Cite

Abstract. This contribution provides an example of the possible advantages of adopting a Bayesian inversion approach to uncertainty quantification in nondestructive inspection methods. In such problem, the uncertainty associated to the random parameters is not always known and needs to be characterised from scattering signal measurements. The uncertainties may then correctly propagated in order to determine a reliable probability of detection curve. To this end, we establish a general Bayesian framework based on a non-parametric maximum likelihood function formulation and some priors from expert knowledge. However, the presented inverse problem is time-consuming and computationally intensive. To cope with this difficulty, we replace the real model by a surrogate one in order to speed-up the model evaluation and to make the problem to be computationally feasible for implementation. The least squares support vector regression is adopted as metamodelling technique due to its robustness to deal with nonlinear problems. We illustrate the usefulness of this methodology through the control of tube with enclosed defect using ultrasonic inspection method.

show abstract

A probabilistic approach for optimising hydroformed structures using local surrogate models to control failures

Cited by 30 publications

References 45 publications

The multi-objective optimization of the loading paths for T-shape tube hydroforming using adaptive support vector regression

The multi-objective optimization of the loading paths for T-shape tube hydroforming using adaptive support vector regression

A state of the art review of hydroforming technology

Improving the reliability of POD curves in NDI methods using a Bayesian inversion approach for uncertainty quantification

Contact Info

Product

Resources

About