Application of abductive network and FEM to predict an acceptable product on T-shape tube hydroforming process

Lin, F. C.; Kwan, Chin Tarn

doi:10.1016/j.compstruc.2004.03.005

Cited by 34 publications

(26 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MatLab toolbox was used like software for the programming (training, generalization…etc) of the neural networks (NN) and the back-propagation like a training algorithm. The back-propagation consists in optimization of the connection weights of the network which were initialized by going up layer by layer, of the output layer towards the input layer in order to minimize the TMSE (Training Means Square Error) given by the Equation [1] calculated in the output S, see Equation [2]. The Training Means Square Error is given as:…”

Section: Training Of Neural Network (Nn)mentioning

confidence: 99%

“…A model based on the network abductive which consists to decompose a complex system in simpler subsystems grouped into several layers using polynomial functional nodes and the FEM is employed by Lin and Kwan [2] to predict an acceptable product on T-shape tube hydroforming process. The contribution of this paper is the application of an original neural network technique to predict the thickness distribution in Tube Hydroforming process (THF) according the loading parameters.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Numerical analyses of tube hydroforming problem using artificial neural networks

Belhadj¹,

Abbassi²,

Mistou

et al. 2010

Int J Mater Form

View full text Add to dashboard Cite

The hydroforming process is characterized in these recent years by the remarkable development to compare with other processes manufacturing such as deep drawing and bending... Hydroforming is a reliable process that improves the resistance and rigidity of parts with the geometrical and dimensional tolerances allowing for lower costs tool and therefore an overall cost of manufacturing reduced. The success of hydroforming process requires the control simultaneously of various parameters such as used material properties, thickness, internal pressure,... In this paper, we introduce our model based in a neural approach (ANN) compared to the numerical simulation and experimental results. This method allows a better thickness distribution during Tee extrusion tube hydroforming process (THF) and the optimization of the final part geometry. A multilayer's neural networks (MNN) program is used to control the tube wall thickness variation, so the loading paths (axial feeding and the internal pressure) are used like inputs for our networks, the thickness is the output.

show abstract

Section: Training Of Neural Network (Nn)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Numerical analyses of tube hydroforming problem using artificial neural networks

Belhadj¹,

Abbassi²,

Mistou

et al. 2010

Int J Mater Form

View full text Add to dashboard Cite

show abstract

“…On the other hand, these variables depend on the process parameters and are called the dependent or response variables in design of experiment. These two response parameters have been considered by many researchers to be the objective functions in the optimization process [3,5,12]. It is worthy to note that usually, the minimum wall thickness and the height of protrusion are considered as the thinning and wrinkling indicators, respectively.…”

Section: Indicators Of Tube Formability In Hydroformingmentioning

confidence: 99%

An investigation of the optimal load paths for the hydroforming of T-shaped tubes

Kadkhodayan

Erfani-Moghadam

2011

Int J Adv Manuf Technol

View full text Add to dashboard Cite

This paper proposes a new method to design the optimal load curves for hydroforming T-shaped tubular parts. In order to assess the mathematical models, a combination of design of experiment and finite element simulation was used. The optimum set of loading variables was obtained by embedding the mathematical models for tube formability indicators into a simulated annealing algorithm. The adequacy of the optimum results was evaluated by genetic algorithm. Using this method, the effect of all loading paths was considered in hydroforming of T-shaped tubes. Eliminating of variables with lower effect could simplify the problem and help designers to study the effect of other parameters such as geometrical conditions and loading parameters. Applying the optimal load paths obtained with the proposed method caused an improvement in the thickness distribution in the part as well as a decrease in maximum pressure.

show abstract

“…It is necessary to perform a lot of numerical simulations obtain a suitable range of the process or material parameters for producing an acceptable product in metal forming process. Lin and Kwan [5] used the finite element method in conjunction with adductive network to predict an acceptable product of which the minimum wall thickness and the protrusion height fulfil the industrial demand on the T-shape tube hydroforming process. Yang and Hsu [6] used a finite element analysis investigate the maximum forging force and [mal face width under different process parameters such as modules, number of teeth, and the ratio of the height to diameter of billet.…”

Section: Finite Element Modelingmentioning

confidence: 99%

The prediction of maximum forging load and effective stress for different material of bevel gear forging

2007

View full text Add to dashboard Cite

The manufacture of gears by applying hot or cold bulk forming processes is a quite widespread production method due to its well-known basic advantages such as material and time cost reduction and the increased strength of the teeth. However, the associated process planning and tool design are more complicated. In the precision forging of gears, the workpiece volume, the die design, the power requirement and careful processing are more critical than traditional forging technology. For complete filling up, predicting the power requirement is an important feature of the near net-shape forging process. In this paper, a finite element analysis is utilized to investigate the material properties such as yielding stress, strength coefficient and strain hardening exponent effects on forming load and maximum effective stress. The adductive network was then applied to synthesize the data set obtained from the numerical simulation. The predicted results of the maximum forging load and maximum equivalent stress of bevel gear forging from the prediction model are consistent with the results obtained from FEM simulation quite well. After employing the prediction model one can provide valuable references in prediction of the maximum forging load and maximum equivalent stress of bevel gear forging under a suitable range of material parameters.

show abstract

Application of abductive network and FEM to predict an acceptable product on T-shape tube hydroforming process

Cited by 34 publications

References 11 publications

Numerical analyses of tube hydroforming problem using artificial neural networks

Numerical analyses of tube hydroforming problem using artificial neural networks

An investigation of the optimal load paths for the hydroforming of T-shaped tubes

The prediction of maximum forging load and effective stress for different material of bevel gear forging

Contact Info

Product

Resources

About