锻压技术

基于KNN算法的中心带孔圆板拉深-翻孔变形方式的研究

英文标题：Study on drawing-flanging deformation mode in circular plate with center-hole based on KNN algorithm

作者：周鑫谢晖付山张清云

单位：湖南大学湖南师大附中

分类号：TG386

出版年,卷(期):页码：2021,46(7):53-59

摘要：

为了准确、快速判别中心带孔圆板拉深-翻孔过程中的变形方式，选取第3代先进超高强钢QP980材料，以预制孔直径、凹凸模圆角半径和板料厚度为特征参量，通过AutoForm成形仿真获取样本数据集，以Python作为编程语言，基于机器学习中的KNN算法构建中心带孔圆板变形方式预测分类器，并利用随机数据集验证其准确度。结果显示，当K=3、p=14且考虑距离权重时，该分类器的预测效果最佳，总体分类准确率达到90.2%，对随机数据集的分类准确率为88.9%。对比传统理论计算和计算机仿真预测，该分类器能以较高的准确度在短时间内同时预测多组样本，能够为实际生产提供参考和借鉴。

In order to discriminate the deformation mode of the circular plate with center-hole in the drawing-flanging process accurately and quickly, for the third-generation advanced high strength steel QP980 material, taking diameter of pre-manufactured hole, fillet radius of punch and die and sheet thickness as characteristic parameters, the sample datasets were obtained by forming simulation software AutoForm, and Python was used as the programming language. Then, based on KNN algorithm in machine learning, a deformation mode predictive classifier of the circular plate with center-hole was built, and its accuracy was verified by a random datasets. The results show that when K=3, p=14 and the distance weight are considered, the classifier has the best prediction effect, the overall classification accuracy reaches 90.2%, and the classification accuracy of the random datasets is still 88.9%. Compared with the traditional method of theoretical calculation and the computer simulation prediction, the classifier is able to simultaneously predict multiple groups of samples in a short time with high accuracy, which can offer experience and reference for actual production.

基金项目：

国家重点研发计划（2017YFB0304400）

作者简介：周鑫（1995-），男，硕士研究生，E-mail：644916184@qq.com；通信作者：谢晖（1971-），男，博士，教授，E-mail：danielxie@163.com

参考文献：

[1]朱亨荣, 王志忠,王镇柱,等.轴对称带孔板坯拉深-翻孔复合成形的仿真与实验[J].塑性工程学报,2013,20(5):50-55.
Zhu H R,Wang Z Z,Wang Z Z,et al.Simulation and experimental study for drawing-flanging compound forming of axisymmetric holed slab[J]. Journal of Plasticity Engineering,2013,20(5):50-55.
[2]余江鸿, 胡成武,占奇锋,等.轴对称带孔板拉深-翻孔复合变形的实验研究[J].塑性工程学报,2010,17(6):14-17.
Yu J H,Hu C W,Zhan Q F,et al.Experimental study on composite deformation of drawing-flanging for axisymmetric holed slab[J]. Journal of Plasticity Engineering, 2010,17(6):14-17.
[3]李建忠. 圆筒件翻孔成形模拟分析及验证[J].模具工业, 2018, 44(2): 23-26.
Li J Z. Simulation analysis and verification of hole flanging for cylinder[J].Die & Mould Industry, 2018,44(2):23-26.
[4]张朝阁, 卢险峰,褚亮.翻孔预孔孔径的计算[J].模具工业,2004,30(1):34-37.
Zhang C G,Lu X F,Zhe L. Calculation of the diameter of the pre manufactured hole for flanging[J]. Die & Mould Industry, 2004,30(1):34-37.
[5]肖卉. 中心带孔圆板拉深-翻孔变形方式的研究[D]. 湘潭：湘潭大学,2012.
Xiao H.Research on Drawing-flanging Deformation Mode of Circular Plate with Center-hole[D]. Xiangtan: Xiangtan University,2012.
[6]郑刚, 彭世揆,戎慧,等.基于KNN方法的森林蓄积量遥感估计和反演概述[J].遥感技术与应用,2010,25(3):430-437.
Zheng G,Peng S K,Rong H,et al. A General introduction to estimation and retrieval of forest volume with remote sensing based on KNN[J].Remote Sensing Technology and Application, 2010,25(3):430-437.
[7]朱彪, 杨俊,吕伟涛,等.基于KNN的地基可见光云图分类方法[J].应用气象学报,2012,23(6):721-728.
Zhu B,Yang J,Lyu W T,et al. Ground-based visible cloud image classification method based on KNN algorithm[J].Journal of Applied Meteorological Science,2012,23(6):721-728.
[8]熊亚军, 廖晓农,李梓铭,等.KNN数据挖掘算法在北京地区霾等级预报中的应用[J].气象,2015,41(1):98-104.
Xiong Y J,Liao X N,Li Z M,et al.Application of KNN data mining algorithm to haze grade forecasting in beijing[J].Meteorological Monthly,2015,41(1):98-104.
[9]胡君萍, 傅科学.基于改进KNN算法的手写数字识别研究[J].武汉理工大学学报: 信息与管理工程版,2019,41(1): 22-26.
Hu J P,Fu K X.An improved knn algorithm for recognition of handwritten numerals[J].Journal of Wuhan University of Technology: Information & Management Engineering,2019, 41(1):22-26.
[10]耿丽娟, 李星毅.用于大数据分类的KNN算法研究[J].计算机应用研究,2014,31(5):1342-1344,1373.
Geng L J,Li X Y.Improvements of KNN algorithm for big data classification[J].Application Research of Computers,2014,31 (5): 1342-1344, 1373.
[11]汤荣志. 数据归一化方法对提升SVM训练效率的研究[D]. 济南：山东师范大学,2017.
Tang R Z.Research on the Method of Data Normalization for Improving SVM Training Efficiency[D]. Jinan: Shandong Normal University,2017.
[12]刘小生, 章治邦.基于改进网格搜索法的SVM参数优化[J].江西理工大学学报,2019,40(1):5-9.
Liu X S,Zhang Z B.Parameter optimization of support vector machine based on improved grid search method[J]. Journal of Jiangxi University of Science and Technology,2019,40(1):5-9.
[13]张盼. 基于混淆矩阵的分类器选择集成方法研究[D].焦作：河南理工大学,2016.
Zhang P.Research on the Method of Classifier Selection Integration Based on Confusion Matrix[D]. Jiaozuo: Henan Polytechnic University,2016.

服务与反馈：

【本网站尚未开通全文下载服务】【加入收藏】