锻压技术

薄壁细长轴自适应校直技术

英文标题：Self-adaptive straightening technology of thin-walled slender shaft

作者：韩宾王肖笛滕朝斌李颖慧王聚存张琦

分类号：TH69

出版年,卷(期):页码：2022,47(2):100-105

摘要：

为提高现有直线度校直设备的检测精度，提高校直参数计算的准确性，通过对现有轴类零件校直方法的优、缺点进行分析，针对常见细长轴零件的直线度校直加工，设计出校直加工精度为0.1 mm·m-1的薄壁细长轴零件自适应校直设备总体结构。校直过程基于机器学习的BP神经网络算法和数据库积累，基于三点弯曲校直的基本原理，此设备确定了一个适用于此校直工艺的BP神经网络结构，其结构为：输入层为7个节点、输出层为1个节点、单隐含层为6个节点。通过对该神经网络结构的精度验证可得：当数据库包含800组实验数据时，经过1次校直加工，即可满足精度要求，此设备可大幅地减少校直加工次数。

In order to improve the detection accuracy of existing straightness straightening equipment and improve the calculation accuracy of straightening parameters. The advantages and disadvantages of the existing straightening methods for shaft parts were analyzed. Aiming at the straightness straightening processing of common slender shaft parts，the over structure of a self-adaptive straightening equipment for thin-walled slender shaft parts with the straightening accuracy of 0.1 mm·m-1 was designed. The straightening process was established based on machine learning consisting of BP neural network algorithm and database accumulation. Based on the basic principle of three-point bending and straightening，a BP neural network structure suitable for this straightening process of this equipment was determined. Its structure is that the input layer has seven nodes，the output layer has one node, and the single hidden layer has six nodes. By verifying the accuracy of the neural network structure, it can be concluded that when the database containes 800 sets of experimental data, the accuracy requirements can be met after one straightening process. This equipment can greatly reduce the numbers of straightening.

基金项目：

西安交通大学校企合作科研项目（N-20010394）

作者简介：韩宾（1986-），男，博士，副教授,E-mail：hanbinghost@mail.xjtu.edu.cn ;通信作者：张琦（1978-），男，博士，教授,E-mail：henryzhang@mail.xjtu.edu.cn

参考文献：

[1]范永海，郑树清.齿轮轴校直理论及实验研究[J].机械设计与制造，2006，(4)：99-101.

Fan Y H, Zheng S Q. Study on the grear shaft straightening theory [J]. Mechanical Design & Manufacturing, 2006，(4)：99-101.

[2]翟华.台阶轴校直工艺计算方法及实验研究[J].机械强度，2002，24(3)：388-390.

Zhai H. Research on stepped shaft straightening technology theory and experiment[J].Journal of Mechanical Strength，2002，24(3)：388-390.

[3]朱双霞，李骏.压力校直下压量计算方法的比较分析[J].新余学院学报，2010，15(4)：76-78.

Zhu S X, Li J. Comparative analysis of pressure arithmetic under pressure straightening alignment[J].Journal of Xinyu University，2010，15(4)：76-78.

[4]Zhao J, Song X K. Control strategy of multi-point bending one-off straightening process for LSAW pipes[J]. International Journal of Advanced Manufacturing Technology, 2014, 72(9-12):1615-1624.

[5]Ma L F, Ma Z Y, Jia W T, et al. Research and verification on neutral layer offset of bar in two-roll straightening process[J]. International Journal of Advanced Manufacturing Technology, 2015, 79(9-12):1519-1529.

[6]Jin C X, Yu T T. Research on monitoring and early warning of our manufacturing industrial security based on BP neural network[J]. Journal of Beijing University of Technology:Social Science Edition, 2010，(6)：59-62.

[7]Zhan P P, Zhao J, Li P, et al. Three steps control strategy of over-bending setting round for pipe-end of large pipes[J]. Materials Science and Technology, 2014, 22(2):97-103.

[8]翟华，韩春明，柯尊忠.罗拉轴校直工艺理论及实验研究[J].纺织学报， 2002，23(4)：68-69.

Zhai H, Han C M, Ke Z Z. Research on roller shaft straightening technology theory and experiment [J].Journal of Textile Research， 2002，23(4)：68-69.

[9]周里群.轴的校直及校直载荷计算[J].机械设计与制造，2001，(6)：54-55.

Zhou L Q. Shaft straightening and straightening load calculation [J]. Mechanical Design & Manufacturing, 2001，(6)：54-55.

[10]弓海霞，闫通海，王进礼.钻具校直的理论研究[J].哈尔滨工程大学学报，2002，23(3)：116-119.

Gong H X, Yan H T, Wang J L. Straightening of drill pipe[J].Journal of Harbin Engineering University，2002，23(3)：116-119.

[11]韩力群.人工神经网络理论、设计及应用[M].第2版. 北京：化学工业出版社，2007.

Han L Q. Artificial Neural Network Theory, Design and Application[M].The 2nd Edition.Beijing：Chemical Industry Press，2007.

[12]王小川，史峰，郁磊，等.MATLAB神经网络43个案例分析[M].北京：北京航空航天大学出版社，2013.

Wang X C，Shi F，Yu L，et al. Analysis of 43 Cases of MATLAB Neural Network [M].Beijing：Beijing University of Aeronautics and Astronautics Press，2013.

[13]Kennedy J, Eberhart R C. A discrete binary version of the particle swarm algorithm[A]. Proceedings of 1997 IEEE International Conference on Systems,Man,and Cybernetics. Computional Cybernetics and Simulation[C].Orlamdo,FL,USA:IEEE,1997.

[14]Jin J L, Wei Y M, Zou L L, et al. Forewarning of sustainable utilization of regional water resources: A model based on BP neural network and set pair analysis[J]. Natural Hazards, 2012, 62(1):115-127.

服务与反馈：

【文章下载】【加入收藏】