Prediction of maximum forming depth in single point incremental forming of 6061 aluminum alloy based on Adaboost regression

Zhikai LIANG, Zhichao ZHANG, Lan HU, Qiu PANG

PDF(6013 KB)
PDF(6013 KB)
Journal of Materials Engineering ›› 2025, Vol. 53 ›› Issue (4) : 23-34. DOI: 10.11868/j.issn.1001-4381.2024.000847
HIGH-PERFORMANCE FORMING MANUFACTURING TECHNOLOGY FOR TRANSPORTATION EQUIPMENT ALUMN

Prediction of maximum forming depth in single point incremental forming of 6061 aluminum alloy based on Adaboost regression

Author information +
History +

Abstract

Single point incremental forming (SPIF) is a highly flexible manufacturing process widely utilized in the aerospace industry, particularly suited for customized and small-batch production components. However, the appropriate range of process parameters suitable for different models remains undefined, necessitating extensive parameter testing. An orthogonal experiment is conducted to perform a multi-factor analysis of variance, discussing the influence of parameters such as sheet thickness, angle, incremental amount, feed rate, and rotational speed on the maximum forming depth. Based on the experimental results, a regression model using the Adaboost algorithm is developed to predict the forming depth of 6061 aluminum alloy thin sheets at the forming diameter of 100 mm. The results indicate that the influences of single factors on the maximum forming depth in descending order of significance are: thickness, layer increment, angle, feed rate, and rotational speed. Under the optimal forming conditions achieved at the fastest forming speed, the maximum forming angle is 70°, the sheet thickness is 1 mm, the layer increment is 0.2 mm, the feed rate is 2000 mm/min, and the rotational speed is 2000 r/min. Furthermore, the regression model created based on the orthogonal experiment demonstrates high accuracy, correlating well with both the Abaqus simulation results and the actual experimental outcomes. The maximum error between the four groups of tests and simulations is 4.24%, while the maximum error with the actual forming results is -2.45%.

Key words

SPIF / process parameter / 6061 aluminum alloy / Adaboost algorithm / regression model

Cite this article

Download Citations
Zhikai LIANG , Zhichao ZHANG , Lan HU , et al. Prediction of maximum forming depth in single point incremental forming of 6061 aluminum alloy based on Adaboost regression. Journal of Materials Engineering. 2025, 53(4): 23-34 https://doi.org/10.11868/j.issn.1001-4381.2024.000847

References

[1]
徐常志,靳一,李立,等. 面向6G的星地融合无线传输技术[J]. 电子与信息学报202143(1):28-36.
XU C Z JIN Y LI L, et al. Star-ground integrated wireless transmission technology for 6G[J]. Journal of Electronics and Information Technology202143(1):28-36.
[2]
SHANG Z CHEN J ZHOU Y, et al. Research on the rapid 3D measurement of satellite antenna reflectors using stereo tracking technique[J]. Measurement2024232: 114639.
[3]
MOROZOV E V LOPATIN A V. Design, analysis, manufacture and testing of the spacecraft mirror antenna with the composite high precision and size-stable solid surface reflector[J]. Composite Structures2022301: 116185.
[4]
MUSIC O ALLWOOD J M KAWAI K. A review of the mechanics of metal spinning[J]. Journal of Materials Processing Technology2010210(1): 3-23.
[5]
KARBASIAN H TEKKAYA A E. A review on hot stamping[J]. Journal of Materials Processing Technology2010210(15): 2103-2118.
[6]
DEWANG Y SHARMA V. Sheet metal shrink flanging process: a critical review of current scenario and future prospects[J]. Materials and Manufacturing Processes202338(6): 629-658.
[7]
KUBIT A AL-SABUR R GRADZIK A, et al. Investigating residual stresses in metal-plastic composites stiffening ribs formed using the single point incremental forming method[J]. Materials202215(22): 8252.
[8]
李岩,张瑶,庞秋,等. 大径厚比超薄铝合金构件3D增量成形规律[J]. 锻压技术202348(5):193-204.
LI Y ZHANG Y PANG Q, et al. 3D incremental forming laws of ultra-thin aluminum alloy components with large diameter-to-thickness ratios[J]. Forging & Stamping Technology202348(5):193-204.
[9]
ROSA-SAINZ A CENTENO G SILVA M B, et al. Experimental failure analysis in polycarbonate sheet deformed by SPIF[J]. Journal of Manufacturing Processes202164: 1153-1168.
[10]
GOHIL A MODI B. Review of the effect of process parameters on performance measures in the incremental sheet forming process[J]. Proceedings of the Institution of Mechanical Engineers Part B2021235(3): 303-332.
[11]
KIM Y H PARK J J. Effect of process parameters on formability in incremental forming of sheet metal[J]. Journal of Materials Processing Technology2002130(1): 42-46.
[12]
LI Y LIU Z DANIEL W J T, et al. Simulation and experimental observations of effect of different contact interfaces on the incremental sheet forming process[J]. Materials and Manufacturing Processes201429(2): 121-128.
[13]
ZHAN X WANG Z LI M, et al. Investigations on failure-to-fracture mechanism and prediction of forming limit for aluminum alloy incremental forming process[J]. Journal of Materials Processing Technology2020282: 116687.
[14]
NAJM S M PANITI I. Investigation and machine learning-based prediction of parametric effects of single point incremental forming on pillow effect and wall profile of AlMn1Mg1 aluminum alloy sheets[J]. Journal of Intelligent Manufacturing202334(1): 331-367.
[15]
SILVA M B SKJØDT M MARTINS P A F, et al. Revisiting the fundamentals of single point incremental forming by means of membrane analysis[J]. International Journal of Machine Tools and Manufacture200848(1): 73-83.
[16]
XU D LU B CAO T, et al. A comparative study on process potentials for frictional stir-and electric hot-assisted incremental sheet forming[J]. Procedia Engineering201481: 2324-2329.
[17]
张晶. 基于AdaBoost回归树的多目标预测算法的研究[D]. 北京:北京交通大学,2017.
ZHANG J. Research on multi-objective prediction algorithm based on AdaBoost regression tree[D]. Beijing:Beijing Jiaotong University,2017.
[18]
BAI Y XIE J WANG D, et al. A manufacturing quality prediction model based on AdaBoost-LSTM with rough knowledge[J]. Computers & Industrial Engineering2021155: 107227.

Comments

PDF(6013 KB)

Accesses

Citation

Detail

Sections
Recommended

/