Earing Reduction by Varying Blank Holding Force in Deep Drawing with Deep Neural Network

Tran, Minh Tien; Shan, Zhengtong; Lee, Ho Won; Kim, Dong Kyu

doi:10.3390/met11030395

Cited by 18 publications

(7 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This mapping learns the weight of each neuron from error backpropagation data. 28,29 The goal of the hybrid DNN-SSO procedure is to increase the model's accuracy and reduce the risk of errors. 30 This process is performed until the error values decrease.…”

Section: Hybrid Deep Neural Network (Sso-dnn)mentioning

confidence: 99%

Predicting and improving the novel process parameters involved in deep drawing process of Inconel 718 sheet at room temperature using hybrid DNN-SSO approach

Ganesan

Sambasivam

Ramadass

2023

The Journal of Strain Analysis for Engineering Design

View full text Add to dashboard Cite

The deep drawing technique is an important metal forming processes, and it is rarely used in the Inconel 718 sheet. The main purpose of this study is to perform a deep drawing process using the Inconel 718 alloy. In this research article, the Inconel 718 alloy sheet of 1 mm thickness is drawn into sheet metal cups, and defects such as thinning, and earing are controlled using selected input parameters such as Blank Holding Force (BHF) Blank Diameter (BD), and Punch Nose Radius (Rpn). A Box Behnken design (BBD) is used to evaluate the effects of output parameters. The hybrid Deep Neural Network (DNN) is used to predict the experimental outcomes obtained from the deep drawing process. For deep drawing process blank holding force is favorable for both thinning and earing. The minimum thinning value obtained during experimentation is 0.033 mm. During experimentation less earing value is 2.47 mm. Hybrid Deep Neural Network based Sparrow Search Optimization (DNN-SSO) gives the prediction model, where the values are much closer to the experimented model than RSM and non-Hybrid DNN. The minimum thinning obtained in the prediction model such as RSM, SSO-DNN, and DNN are 0.030, 0.0304, and 0.023 mm. Likewise, the minimum earing obtained from the predictive model is 2.65, 2.49, and 2.51 mm respectively. The minimum error is found in the hybrid DNN and the average RMSE for thinning is 0.002 and earing is 0.0024. The regression coefficient of thinning and earing is 99% which proves the experimental outcomes matches with RSM validation.

show abstract

Section: Hybrid Deep Neural Network (Sso-dnn)mentioning

confidence: 99%

Predicting and improving the novel process parameters involved in deep drawing process of Inconel 718 sheet at room temperature using hybrid DNN-SSO approach

Ganesan

Sambasivam

Ramadass

2023

The Journal of Strain Analysis for Engineering Design

View full text Add to dashboard Cite

show abstract

“…Tran et al 2021 [31] developed a DNN-GA model to predict and optimize segmented blank holder force (BHF) for minimizing earing height variation. By increasing the drawn wall region thickness predicted by the optimized BHF, the deep-drawability could be improved.…”

Section: Literature Reviewmentioning

confidence: 99%

Numerical multi-objective optimization of segmented and variable blank holder force trajectories in deep drawing based on DNN-GA-MCS strategy

Guo¹,

Jeong²,

Park³

et al. 2023

Preprint

View full text Add to dashboard Cite

This research introduces a novel methodology for mitigating defects in sheet metal forming processes. The proposed approach employs a segmented and variable blank holder force (S-VBHF) trajectory, adjusting the blank holder force (BHF) during the forming cycle, enhancing formability, and reducing failure, wrinkling and springback defects. Optimal process parameters, including the S-VBHF, friction coefficient and drawbead restraining force (DBRF), were determined through a systematic methodology integrating deep neural network, genetic algorithm and Monte Carlo simulation (DNN-GA-MCS) techniques. The design constraint, defined as sheet failure during the forming process, was quantitatively evaluated using the forming limit diagram (FLD) to ensure rigorous assessment. The proposed methodology was validated through numerical simulations using a cylindrical cup provided by NUMISHEET 2011 (BM1) as test samples. The simulation results demonstrated a significant improvement in the formed sheet quality, characterized by reductions of 8.33%, 10.81% and 5.88% in failure, wrinkling and springback defects, respectively. These findings underscore the potential of the proposed approach in enhancing the quality of sheet metal forming processes and mitigating defects.

show abstract

“…Their research involved a combination of Analysis of Variance (ANOVA) and process parameters such as punch/die corner radius, blank holder force (BHF), workpiece thickness, and three friction coefficients between the tool and workpiece. Tran et al [18] introduced an innovative method for varying blank holder force, featuring a segmented blank holder, and examined its impact on surface roughness reduction in the circular deep drawing process of aluminum alloy plates. Their study incorporated analytical models and deep neural network (DNN) models, augmented by genetic algorithms (GA), for controlling BHF.…”

Section: Introductionmentioning

confidence: 99%

Optimization and Modelling of Fracture Height in SECC Cylindrical Cup Deep Drawing Processes

Trieu,

Luyen,

Nguyen

2024

Journal of Machine Engineering

View full text Add to dashboard Cite

Deep drawing processes play a pivotal role in the manufacturing of sheet and shell products, making it a widely adopted method. This research employs numerical simulations to investigate the impact of various process parameters on the fracture height of cylindrical cups made from SECC (Steel Electrogalvanized Commercial Cold rolled) material. Specifically, it examines parameters such as blank holder force (BHF), punch corner radius (Rp), die corner radius (Rd), and punch-die clearance (Wc). The study extends to optimizing fracture height, offering a solution to this challenge. Subsequently, the selected parameters are validated through experimental deep drawing of cylindrical cups, resulting in a minimal deviation of 1.55% between simulation and experiment outcomes. A precise mathematical equation is developed to estimate fracture height under diverse machining conditions, with a maximum deviation of 4.52% observed between the mathematical model and simulation. These findings represent a substantial advancement in deep drawing processes technology, particularly in reducing error rates during the production of cylindrical cups.

show abstract

Earing Reduction by Varying Blank Holding Force in Deep Drawing with Deep Neural Network

Cited by 18 publications

References 45 publications

Predicting and improving the novel process parameters involved in deep drawing process of Inconel 718 sheet at room temperature using hybrid DNN-SSO approach

Predicting and improving the novel process parameters involved in deep drawing process of Inconel 718 sheet at room temperature using hybrid DNN-SSO approach

Numerical multi-objective optimization of segmented and variable blank holder force trajectories in deep drawing based on DNN-GA-MCS strategy

Optimization and Modelling of Fracture Height in SECC Cylindrical Cup Deep Drawing Processes

Contact Info

Product

Resources

About