锻压技术

基于机器学习的前轴辊锻工艺参数预测

英文标题：Prediction on roll forging process parameters of front axle based on machine learning

作者：董玮陈桂芬

分类号：TG316

出版年,卷(期):页码：2021,46(1):208-214

摘要：

使用基于混合核函数的最小二乘支持向量机算法来进行前轴第1道次辊锻工艺参数的预测，构造混合函数以提高预测模型的预测精度。对工艺参数预测模型进行实验验证，结果表明，与基于单独RBF核的LSSVM算法相比，混合核函数LSSVM算法构建的预测模型具有更高的预测精度，由3组不同核函数参数构成的预测模型对最大成形载荷及展宽的平均预测精度分别为91.8%和92.1%、89.4%和90.1%以及94.5%和93.2%，并且确定了最优的核函数参数：RBF核函数系数γ=4.52、惩罚系数c=276.4、Polynomial核函数核阶数q=1.21以及混合权重系数a=0.28。通过3组工艺参数实验对所研究的前轴辊锻工艺参数预测方法的可行性进行验证，所使用的预测方法预测得到的最大成形载荷和展宽与实际值误差在10%以内。

The roll forging process parameters of the first pass for front axle were predicted by the least square support vector machine algorithm based on the mixed kernel function, and the mixed function was constructed to improve the prediction accuracy of predicted model. Then, the process parameter predicted model was verified by experiment. The results show that compared with LS-SVM algorithm based on the single RBF kernel, the predicted model constructed by the mixed kernel function LS-SVM algorithm has higher prediction accuracy, and the average prediction accuracies of three groups of predicted models with different kernel function parameters for the maximum forming load and widening are 91.8% and 92.1%, 89.4% and 90.1%, 94.5% and 93.2% respectively. Furthermore, the optimal kernel function parameters are determined with RBF kernel function coefficient γ=4.52, penalty coefficient c=276.4, Polynomial kernel function kernel order q=1.21 and mixed weight coefficient a=0.28. Finally, the feasibility of prediction method for the studied front axle roll forging process parameters was verified by three groups of process parameter experiments, and the errors between the predicted maximum forming load and widening by the prediction method and the actual values are less than 10%.

基金项目：

基金项目:吉林省重点科技研发项目(20180201073SF);吉林省科技发展计划资助项目(20190902010TC)

作者简介：董玮（1985-），女，硕士，讲师 E-mail：zishang1999@126.com 通讯作者：陈桂芬(1956-)，女，博士，教授，博士生导师 E-mail：guifchen@163.com

参考文献：

[1]李朝亮, 陈文琳,曹谦,等.基于负公差设计的卡车前轴成形工艺改进[J].塑性工程学报,2019,26(6):30-35.

Li C L, Chen W L, Cao Q, et al. Improvement of forming process of truck front axle based on negative tolerance design [J]. Journal of Plastic Engineering, 2019,26(6): 30-35.

[2]梁聪明, 刘万勇,高展,等.三维扫描和数值模拟在现代锻造企业的结合应用[J].金属加工:热加工,2018,(1):81-84.

Liang C M, Liu W Y, Gao Z, et al. Combined application of 3D scanning and numerical simulation in modern forging enterprises [J]. MW Metal Forming, 2018,(1): 81-84.

[3]周杰, 柳豪,刘旭光,等.某重型卡车前轴成形辊锻工艺设计与优化[J].重庆大学学报,2012,35(3):67-73,91.

Zhou J, Liu H, Liu X G, et al. Desig and optimization of the precision roll forging on a heavy truck front axle[J].Journal of Chongqing University, 2012,35(3):67-73,91.

[4]魏科, 王高潮,李宁,等.基于DEFORM和正交试验法的前轴辊锻工艺优化[J].塑性工程学报,2012,19(1):6-10.

Wei K, Wang G F, Li N, et al. Research on optimization of frontaxle roll forging technique based on DEFORM and orthogonal experimental method[J]. Journal of Plastic Engineering, 2012,19(1): 6-10.

[5]何伟, 董万鹏,孙礼宾,等.基于Deform3D的发动机齿轮轴热锻成形结构优化模拟[J].塑性工程学报,2019,26(6):42-49.

He W, Dong W P, Sun L B, et al. Structural optimization simulation of engine gear shaft hot forging based on Deform3D [J]. Journal of Plastic Engineering, 2019,26(6):42-49.

[6]郑明玉, 喻建军,沙奔,等.前轴精密辊锻成形过程的数值分析[J].热加工工艺,2012,41(13):98-100.

Zheng M Y, Yu J J, Sha B, et al. Numerical analysis for precision roll forging of front axle [J]. Hot Working Technology, 2012,41(13): 98-100.

[7]苏雪冬, 金俊松,王新云,等.厚轮缘盘形件多工步旋压增厚成形工艺[J].塑性工程学报,2018,25(2):113-121.

Su X D, Jin J S, Wang X Y, et al. Multistep spinning thickening process of thick rim disc [J]. Journal of Plastic Engineering, 2018,25(2):113-121.

[8]王晓强, 徐少可,崔凤奎,等.轴承套圈表面超声滚挤压加工硬化模型[J].塑性工程学报,2019,26(3):231-237.

Wang X Q, Xu S K, Cui F K, et al. Ultrasonic rolling extrusion work hardening model of bearing ring surface [J]. Journal of Plastic Engineering, 2019,26(3):231-237.

[9]吕霄. 轻量化汽车前轴成形工艺研究[D]. 武汉:武汉理工大学,2017.

Lyu X. Research on the Forming Process of the Lightweight Automobile Front Axle [D]. Wuhan: Wuhan University of Technology, 2017.

[10]陶善虎. 前轴精密辊锻-整体模锻成形工艺改进[J].精密成形工程,2016,8(3):61-64.

Tao S H. Precision roll forging and die forging process of the vehicle [J]. Journal of Netshap Forming Engineering, 2016,8(3): 61-64.

[11]尚帅. 载重汽车前轴模锻毛坯的辊锻成形工艺研究[D]. 武汉:武汉理工大学,2016.

Shang S. Research on the Roll Forging Process for the Optimal Blank of Truck Front Axle [D]. Wuhan: Wuhan University of Technology, 2016.

[12]刘硕, 李锦棒, 曲建俊,等. 基于最小二乘支持向量机超声电机摩擦材料寿命的预测[J]. 微电机, 2018, 51(1):78-82.

Liu S, Li J B, Qu J J, et al. Prediction of friction material life of ultrasonic motor based on least squares support vector machine [J]. Micromotor, 2018, 51(1):78-82.

[13]郑志成, 徐卫亚,徐飞,等.基于混合核函数PSOLSSVM的边坡变形预测[J].岩土力学,2012, 33(5):1421-1426.

Zheng Z C, Xu W Y, Xu F, et al. Forecasting of slope displacement based on PSOLSSVM with mixed kernel [J]. Rock and Soil Mechanics, 2012,33(5):1421-1426.

服务与反馈：

【文章下载】【加入收藏】