冲压式气动系统的建模与线性化分析

兵工学报 ›› 2010, Vol. 31 ›› Issue (8): 1125-1128.

冲压式气动系统的建模与线性化分析

辛民^1,2，解丽静₁，王西彬₁，石文天₁，杨洪建₁

（1.北京理工大学机械与车辆学院, 北京 100081;2.中国神华铁路货车运输分公司，北京 100011）

收稿日期:2009-01-04 修回日期:2009-01-04 上线日期:2014-05-04
通讯作者: 辛民 E-mail:glorious97@163.com
作者简介:辛民(1979—)男，博士研究生
基金资助:
国防预先研究项目（513181604）

Modeling and Linearity Analysis of Ram-air Servo System

XIN Min^1,2, XIE Li-jing₁, WANG Xi-bin₁, SHI Wen-tian₁, YANG Hong-jian₁

(1.School of Mechanical and Vehicular Engineering, Beijing Institute of Technology, Beijing 100081, China;2.Railway Vehicle Transportation Branch，China Shenhua Group Corporation Limited, Beijing 100011, China）

Received:2009-01-04 Revised:2009-01-04 Online:2014-05-04
Contact: XIN Min E-mail:glorious97@163.com

摘要/Abstract

摘要： 针对零件铣削加工变形难以在线检测的难点，提出了一种基于神经网络的加工变形在线预测方法，通过正交试验方法设计试验方案，进行了不同铣削参数条件下的铣削试验，以试验数据为训练样本建立了基于BP神经网络的铣削加工变形与铣削参数关系的预测模型。通过生产试验验证，此模型在样本参数覆盖范围内的模型精度可达99.56%、在覆盖范围外的模型精度高于95.47%，说明该神经模型能定量的反映出铣削参数与加工变形之间的关系。

关键词: 机械制造工艺与设备, 变形, BP神经网络, 铣削参数, 预测模型

Abstract: In order to settle the troubles in on-line deformation measurement of workpiece, a deformation prediction method based on artificial neutral network was proposed. The cutting experiment scheme was designed by using orthogonal experiment technique. The experiments in different milling parameters were carried out, the workpieces' deformations were measured, and the deformation prediction model was created by using a Back-Propagation neural network and taking the experiment data as its training examples. According to the validation of the additional production experiments, the model's accuracy in the scope of examples is 99.56% and better than 95.47% outside the scope of examples. The results show that the deformation prediction model can accurately reflect the relationship between deformation and milling parameters.

Key words: machinofacture technique and equipment, deformation, BP neural network, milling parameter, prediction model

中图分类号:

TP183
TH161

辛民，解丽静₁，王西彬₁，石文天₁，杨洪建₁. 冲压式气动系统的建模与线性化分析[J]. 兵工学报, 2010, 31(8): 1125-1128.

XIN Min, XIE Li-jing₁, WANG Xi-bin₁, SHI Wen-tian₁, YANG Hong-jian₁. Modeling and Linearity Analysis of Ram-air Servo System[J]. Acta Armamentarii, 2010, 31(8): 1125-1128.

参考文献

［1］金同熹. 机器零件的表面质量和接触［M］. 北京: 机械工业出版社, 1986:136-139.
JIN Tong-xi. the surface quality and contrast of machine part［M］. Beijing: China Machine Press, 1986, 10:136-139. (in Chinese)
［2］郭前建,杨建国,王秀山. 精密磨削加工的神经网络误差补偿技术［J］.中国机械工程, 2006,17(8):55-58.
GUO Qian-jian, YANG Jian-guo, WANG Xiu-shan. Error compensation technology based on neural networks of precision grinding process［J］. China Mechanical Engineer, 2006,17(8):55-58. (in Chinese)
［3］张建立,李钢,俞研. 神经模糊技术在柔性加工工序质量保证系统中的应用研究［J］.兵工学报, 2001,22（4）：566- 569.
ZHANG Jian-li, LI Gang, YU Yan. Application of neutral fuzzy technology in the system of guarantee for working procedure quality in flexible processing［J］. Acta Armamentarii, 2001,22(4): 566-569. (in Chinese)
［4］ ZHAO Xiao-guang, CHEN Bing-zhen, HE Xiao-rong. A novel neural network for the prediction of process variables［J］. Science in China: Series A,1995,38(3):355-367.
［5］ Psichogios D C, Ungar L H. A hybrid neural network first principles approach to process modeling［J］. AIChE Journal, 1992,38(10):1499-1511.
［6］张兵,袁寿其,成立,等.基于L-M优化算法的BP神经网络的作物需水量的预测模型的研究［J］.农业工程学报,2004, 20(6):73-76.
ZHANG Bing, YUAN Shou-qi, CHENG Li, et al. Model for predicting crop water requirements by using L-M optimization algorithm BP neural network［J］. Transactions of the Chinese Society of Agricultural Engineering, 2004, 20(6):73-76.(in Chinese)
［7］ Hornic K, Stinchcombe M,White H. Multiplayer feed-forward networks are universal approximators［J］. Neural Networks,1989,2:25-36.
［8］飞思科技产品研发中心.神经网络理论与MATLAB7实现［M］.北京:电子工业出版社,2005:99-108.
FECIT Technological Product Research Center. Neural networks and its implement MATLAB7［M］. Beijing: Publishing House of Electronics Industry, 2005:99-108. (in Chinese)

[1]	辛大钧，薛琨. 基于人工神经网络的非球形破片阻力系数预测模型[J]. 兵工学报, 2022, 43(5): 1083-1092.
[2]	宁子轩，王琳，程兴旺，程焕武，周哲，张斌斌，王芳，陈东萍. 微观组织对Ti6321钛合金靶板爆炸断裂失效的影响[J]. 兵工学报, 2021, 42(7): 1506-1515.
[3]	顾祖成, 王光华, 卢海涛, 闫文敏. 小口径步枪枪管在连续单发射击下热效应特性[J]. 兵工学报, 2021, 42(4): 734-742.
[4]	陈珂，张勇飞，王杜林，刘子骏，符晓刚. 低温下导弹成像主镜支撑平台微小变形分析[J]. 兵工学报, 2021, 42(12): 2637-2645.
[5]	林锋，姚婉，秦国华，叶海潮，陶江. 飞机整体结构件加工变形的初始残余应力-初始几何误差耦合影响与控制[J]. 兵工学报, 2021, 42(12): 2731-2742.
[6]	徐宝池，石必坤，樊黎霞，杨晨，扶云峰，董雪花. 冷径向锻造身管壁厚方向变形不均匀性研究[J]. 兵工学报, 2020, 41(1): 13-20.
[7]	魏强，黄西成，陈刚，陈鹏万. 高聚物粘结炸药动态损伤破坏的数值刻画[J]. 兵工学报, 2019, 40(7): 1381-1389.
[8]	吕明明，刘荣忠，侯远龙，高强，王力. 一种光电跟踪平台共轴控制的目标运动滤波方法[J]. 兵工学报, 2019, 40(3): 548-554.
[9]	焦立启，侯海量，陈鹏宇，金键. 爆炸冲击载荷下固支单向加筋板的动响应及破损特性研究[J]. 兵工学报, 2019, 40(3): 592-600.
[10]	王阳，李高春，伍鹏，杨明，韩永恒. 基于数字图像相关方法的端羟基聚丁二烯推进剂复合型裂纹J积分测量[J]. 兵工学报, 2019, 40(2): 284-291.
[11]	李龙，李言，杨明顺，陈鑫，李嘉伟. 冷滚打工艺参数对成形力及金属变形影响研究[J]. 兵工学报, 2019, 40(2): 420-429.
[12]	郭亚周，刘小川，何思渊，王计真，杨海. 不同弹形撞击下泡沫铝夹芯结构动力学性能研究[J]. 兵工学报, 2019, 40(10): 2032-2041.
[13]	伍薇, 苏娟. 一种基于双向匹配融合的合成孔径雷达景象匹配算法[J]. 兵工学报, 2019, 40(1): 124-133.
[14]	高华，熊超，殷军辉. 弹丸侵彻多层异质复合靶板中装甲钢变形细观和微观机理研究[J]. 兵工学报, 2018, 39(8): 1565-1575.
[15]	郑成，孔祥韶，周沪，徐维铮，吴卫国. 全封闭舱内爆炸载荷作用下薄板变形研究[J]. 兵工学报, 2018, 39(8): 1582-1589.