The prediction of part thickness using machine learning in aluminum hot stamping process with partition temperature control

Cai, Hanrong; Xiao, Wenchao; Zheng, Kailun

doi:10.1007/s00170-021-08632-9

Cited by 6 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Stefanos and Georgios [ 23 ] predicted the springback of sheet metal stamping under different input parameters using an artificial neural network (ANN) trained by a Bayesian backpropagation algorithm. Cai et al [ 24 ] compared the four machine learning model of Gaussian process regression (GPR), gradient boosting regression, k-nearest neighbors regression, and multi-layer perception regression on the prediction of maximum thinning and thickening rates, and the gradient boosting regression model had the highest accuracy. This machine learning model provides a fast prediction method for the intelligent optimization of the stamping process.…”

Section: The State Of the Art Of Intelligent Optimization In The Plas...mentioning

confidence: 99%

A Review of the Intelligent Optimization and Decision in Plastic Forming

Tang

Wang²,

Deng³

et al. 2022

Materials

View full text Add to dashboard Cite

The plastic forming process involves many influencing factors and has some inevitable disturbance factors, rendering the multi-objective collaborative optimization difficult. With the rapid development of big data and artificial intelligence (AI) technology, intelligent process optimization has become one of the critical technologies for plastic forming. This paper elaborated on the research progress on the intelligent optimization of plastic forming and the data-driven process planning and decision-making system in plastic forming process optimization. The development trend in intelligent optimization of the plastic forming process was researched. This review showed that the intelligent optimization algorithm has great potential in controlling forming quality, microstructure, and performance in plastic forming. It is a general trend to develop an intelligent optimization model of the plastic forming process with high integration, versatility, and high performance. Future research will take the data-driven expert system and digital twin system as the carrier, integrate the optimization algorithm and model, and realize the multi-scale, high-precision, high-efficiency, and real-time optimization of the plastic forming process.

show abstract

Section: The State Of the Art Of Intelligent Optimization In The Plas...mentioning

confidence: 99%

A Review of the Intelligent Optimization and Decision in Plastic Forming

Tang

Wang²,

Deng³

et al. 2022

Materials

View full text Add to dashboard Cite

show abstract

“…Mold surface compensation is an important technology to improve the level of automotive manufacturing. In the process of compensating for automotive mold surfaces, the main focus is to control some important mechanical process parameters that affect the quality of mold surface forming, such as edge pressure control, mold clearance, mold structure parameters, sheet thickness, friction factors, etc., in order to achieve the effect of compensating for mold surfaces [1,2]. The wrinkling or rupture of certain parts of the sheet metal during the stamping process is the main defect that occurs in the production of aluminum alloy engine hood outer panels.…”

Section: Introductionmentioning

confidence: 99%

Measurement of Aluminum Alloy Automotive Cover Parts Forming Parts Based on ARGUS System

Liu

2024

AJST

View full text Add to dashboard Cite

This article takes the outer panel of an aluminum alloy engine hood as the research object, uses the finite element analysis software Dynaform for finite element analysis simulation, and uses the ARGUS mesh strain measurement system to conduct experimental analysis on the solid formed parts. This article mainly completes the experimental verification of parameters such as thinning rate measurement for a formed aluminum alloy automotive cover using the ARGUS grid strain measurement system. By comparing simulation results with experimental measurement results, check whether the formed part is feasible under this process parameter. To ensure the accuracy of the results, 21 points distributed in different parts of the formed part were taken and measured using the ARGUS grid strain measurement system to check whether the simulation results are close to the experimental results.

show abstract

“…In particular, T. Hart-Rawung et al [ 11 ] applied an Unsupervised Learning model based on artificial neural networks (ANN) to calculate the hot-stamped parts final phase of hot stamping tools design. Supervised Learning has successfully been considered in hot metal forming systems for manufacturing feasibility prediction [ 12 ], anomaly detection [ 13 ], and maximum thinning and thickening rates prediction of hot-stamped parts [ 14 ]. RL represents a set of solutions that do not previously need to know any information about the system dynamics, in contrast with other traditional control and optimization techniques, and give immediate real-time answers to any faced situation.…”

Section: Introductionmentioning

confidence: 99%

A Reinforcement Learning Control in Hot Stamping for Cycle Time Optimization

Nievas

Pagès‐Bernaus

Bonada³

et al. 2022

Materials

View full text Add to dashboard Cite

Hot stamping is a hot metal forming technology increasingly in demand that produces ultra-high strength parts with complex shapes. A major concern in these systems is how to shorten production times to improve production Key Performance Indicators. In this work, we present a Reinforcement Learning approach that can obtain an optimal behavior strategy for dynamically managing the cycle time in hot stamping to optimize manufacturing production while maintaining the quality of the final product. Results are compared with the business-as-usual cycle time control approach and the optimal solution obtained by the execution of a dynamic programming algorithm. Reinforcement Learning control outperforms the business-as-usual behavior by reducing the cycle time and the total batch time in non-stable temperature phases.

show abstract

The prediction of part thickness using machine learning in aluminum hot stamping process with partition temperature control

Cited by 6 publications

References 31 publications

A Review of the Intelligent Optimization and Decision in Plastic Forming

A Review of the Intelligent Optimization and Decision in Plastic Forming

Measurement of Aluminum Alloy Automotive Cover Parts Forming Parts Based on ARGUS System

A Reinforcement Learning Control in Hot Stamping for Cycle Time Optimization

Contact Info

Product

Resources

About