锻压技术

超声滚挤压轴承套圈的表层性能预测模型建立及工艺参数优化

英文标题：Establishment on prediction model of surface performance for ultrasonic roll extrusion bearing ring and optimization on process parameters

作者：刘志飞王晓强朱其萍王排岗

单位：1. 河南科技大学机电工程学院 2. 机械装备先进制造河南省协同创新中心

关键词：超声滚挤压轴承套圈正交试验表层性能径向基神经网络方差分析田口算法

分类号：TG376.1

出版年,卷(期):页码：2021,46(3):118-125

摘要：

采用超声滚挤压技术对轴承套圈进行表面强化，为了提高其表层性能，实现对工艺参数的优化控制,以轴承套圈材料42CrMo钢为研究对象，通过超声滚挤压正交试验，建立了轴承套圈表层性能与加工参数（主轴转速、进给速度、振幅和静压力）之间的径向基（RBF）神经网络预测模型，并采用方差分析法和田口算法分析了工艺参数对表层性能（表面粗糙度、残余应力和硬度）影响的显著性，获取了表层性能的3组最优工艺参数组合，并利用试验和预测模型对最优参数组合进行了验证。结果表明：最优参数组合比正交试验结果中的最大残余压应力和硬度分别增加了0.59%和4.09%，比正交试验结果中的最小表面粗糙度减小了12.9%。

In order to improve the surface performance of bearing ring strengthen by ultrasonic roll extrusion technology and realize the optimal control of process parameters, for bearing ring material of 42CrMo steel, the prediction model of radial basis function (RBF) neural network between surface performance and process parameters (rotation speed, feeding speed, amplitude and static pressure) was established by ultrasonic roll extrusion orthogonal test, and the significant influences of process parameters on the surface performance (surface roughness, residual stress and hardness) were analyzed by variance analysis method and Taguchi algorithm. Then, three sets of optimal combinations for process parameters were obtained, and the optimal combinations of process parameters were verified by experiments and prediction models. The results show that compared the optimal parameter combinations with the orthogonal test results, the maximum residual compressive stress and the hardness increase by 0.59% and 0.79% respectively, and the minimum surface roughness decreases by 12.9%.

基金项目：

国家自然科学基金资助项目(U1804145);国家重点研究专项（2018YFB2000405）

刘志飞(1996-)，男，硕士研究生 E-mail：769240878@qq.com 通讯作者:王晓强（1972-），男，博士，教授 Email：wang_xq2002@163.com

参考文献：

[1]王明海,李世永,郑耀辉.超声铣削钛合金材料表面粗糙度研究[J].农业机械学报,2014,45(6):341-346,340.

Wang M H, Li S Y, Zheng Y H. Surface roughness of titanium alloy under ultrasonic vibration milling[J]. Transactions of the Chinese Society for Agricultural Machinery, 2014,45(6):341-346,340.

[2]张飞,赵运才.超声表面滚压改善45#钢表层特性及疲劳性能的研究[J].表面技术,2017,46(9):185-190.

Zhang F, Zhao Y C. Research on surface characteristics and fatigue properties of 45# steel by ultrasonic surface rolling[J]. Surface Technology, 2017,46(9):185-190.

[3]刘佳佳,姜兴刚,高泽, 等.高速旋转超声椭圆振动侧铣削振幅对钛合金表面完整性影响的研究[J].机械工程学报,2019,55(11):215-223.

Liu J J, Jiang X G, Gao Z，et al. Investigation of the effect of vibration amplitude on the surface integrity in highspeed rotary ultrasonic elliptical machining for side milling of Ti-6Al-4V[J]. Journal of Mechanical Engineering, 2019,55(11):215-223.

[4]Zheng J X, Liu C S, Zhang Y M. Basic research on ultrasonic extrusion for 45 steel shaft[J]. Key Engineering Materials, 2011,1024(910):288-292.

[5]Wang T, Wang D P, Liu G, et al. Investigations on the nanocrystallization of 40Cr using ultrasonic surface rolling processing[J]. Applied Surface Science,2008,255(5):1824-1829.

[6]史学刚,鲁世红,张炜.铝合金超声波喷丸成形制件表面完整性研究[J].中国机械工程,2013,24(22):3100-3104.

Shi X G, Lu S H, Zhang W. Study on surface integrity of aluminum alloy ultrasonic shot peening forming workpieces[J]. China Mechanical Engineering, 2013,24(22):3100-3104.

[7]贾振元,宿友亮,张博宇, 等.基于径向基函数神经网络的CFRP切削力预测[J].复合材料学报,2016,33(3):516-524.

Jia Z Y, Su Y L, Zhang B Y，et al. Prediction of cutting force in CFRP based on radial basis function neural network[J]. Acta Materiae Compositae Sinica, 2016,33(3):516-524.

[8]王晓强,荣莎莎,刘佳, 等.超声滚挤压轴承套圈表面粗糙度响应曲面预测模型[J].塑性工程学报,2018,25(3):54-59.

Wang X Q, Rong S S, Liu J，et al. Surface roughness response prediction model of ultrasonic roll extrusion bearing ring[J]. Journal of Plasticity Engineering, 2018,25(3):54-59.

[9]刘伟,邓朝晖,万林林, 等.基于正交试验-遗传神经网络的陶瓷球面精密磨削参数优化[J].中国机械工程,2014,25(4):451-455.

Liu W, Deng C H, Wan L L, et al. Parameter optimization on precision grinding of ceramic sphere using orthogonal experiment and genetic neural network[J]. China Mechanical Engineering, 2014,25(4): 451-455.

[10]Jing J T, Feng P F, Wei S L, et al. Investigation on surface morphology model of Si3N4 ceramics for rotary ultrasonic grinding machining based on the neural network[J]. Applied Surface Science, 2017,396(1)：85-94.

[11]张厚祖,樊文欣,郭佩剑, 等.QSn7-0.2锡青铜连杆衬套车削加工参数优化[J].特种铸造及有色合金,2019,39(3):346-348.

Zhang H Z, Fan W X, Guo P J，et al. Optimization of machining parameters of tin bronze connecting rod bushing[J]. Special Casting & Nonferrous Alloys, 2019,39(3):346-348.

[12]麻成标.TBM滚刀刀圈模锻成形仿真参数优化[J].锻压技术，2019，44(7)：7-14.

Ma C B. Optimization on simulation parameters for TBM disc cutter ring in die forging[J]. Forging & Stamping Technology, 2019,44(7):7-14.

[13]伍文进,徐中云,滕凯, 等.基于正交实验与BP神经网络的2AL2激光切割工艺参数优化[J].机床与液压,2018,46(10):13-17.

Wu W J, Xu Z Y, Teng K，et al. Process parameters optimization for 2AL2 aluminum alloy laser cutting based on rthogonal experiment and BP neural network[J]. Machine Tool & Hydraulics, 2018,46(10):13-17.

[14]崔凤奎,苏涌翔,王晓强,等.冷滚打花键表层加工硬化双响应曲面-满意度函数的优化分析[J].塑性工程学报,2018,25(3):129-135.

Cui F K, Su Y X, Wang X Q，et al. Analysis on optimization of doubleresponse surfacesatisfaction function of surface workhardening for cold rollbeating spline[J]. Journal of Plasticity Engineering, 2018,25(3):129-135.

[15]郭华锋,李菊丽,孙涛.基于 BP神经网络的光纤激光切割切口粗糙度预测[J].激光技术,2014,38(6):798-803.

Guo H F, Li J L,Sun T. Roughness prediction of kerf cut with fiber laser based on BP artificial neural networks[J]. Laser Technology, 2014,38(6):798-803.

服务与反馈：

【文章下载】【加入收藏】