磨料水射流切割钢板过程参数优化研究

陈正雄; 武美萍; 强争荣

doi:10.13433/j.cnki.1003-8728.2017.1218

磨料水射流切割钢板过程参数优化研究

doi: 10.13433/j.cnki.1003-8728.2017.1218

陈正雄^1,2,
武美萍^1,2, ,,
强争荣^1,2

1.
江南大学机械工程学院, 江苏无锡 214122;
2.
江南大学江苏省食品先进制造装备技术重点实验室, 江苏无锡 214122

基金项目:

国家自然科学基金项目（51275210）与教育部预研项目（62501036035）资助

详细信息

作者简介:
陈正雄(1992-),硕士研究生,研究方向为先进制造技术及射流技术,czxgasup@163.com

通讯作者:
武美萍(联系人),教授,博士,博士生导师,wmp169@jiangnan.edu.cn

计量
- 文章访问数: 126
- HTML全文浏览量: 15
- PDF下载量: 5
- 被引次数: 0
出版历程
- 收稿日期: 2016-07-03
- 刊出日期: 2017-12-15

Study on Optimization of Processing Parameters in Abrasive Waterjet Cutting Steel Plate

1.
School of Mechanical Engineering, Jiangnan University, Jiangsu Wuxi 214122, China;
2.
Jiangsu Province Key Laboratory of Advanced Food Manufacturing Equipment and Technology, Jiangnan University, Jiangsu Wuxi 214122, China

摘要

摘要: 利用田氏正交试验（L27）进行磨料水射流切割06Cr19Ni10钢板实验，将切割后工件断面表面粗糙度作为评测加工后工件表面质量的标准，选取的过程参数变量为：射流压力、喷嘴横移速度、靶距、磨料粒径和磨料流量。对实验数据进行回归分析，得到表面粗糙度关于5个过程参数变量的回归模型，通过响应面分析法对过程参数进行优化，得到最小表面粗糙度值对应的参数值。再利用人工神经网络对实验样本数据进行训练学习，得到表面粗糙度的最小预测值。分别通过人工智能算法（遗传模式搜索算法和模拟退火法）对过程参数优化，然后通过整合的人工神经网络-遗传模式搜索算法-模拟退火法技术对过程参数进行进一步优化，得到最小表面粗糙度值对应的最佳工艺参数值。通过实验验证了寻优结果的可靠性，通过对比，该整合技术相比单一的遗传模式搜索算法或模拟退火法，大大降低了表面粗糙度值和缩短了寻优时间。
- 磨料水射流 /
- 优化 /
- 响应面分析 /
- 人工神经网络 /
- 智能算法
Abstract: The taguchi's orthogonal array is adopted in cutting steel plate (06Cr19Ni10) experiment by abrasive water jet, then the cross-sectional surface roughness is used to evaluate the standard of surface quality for workpiece. Jet pressure, traverse speed, standoff distance, abrasive grit size and abrasive flow rate were carried as processing parameter variables. A prediction model for surface roughness by using regression analysis is established, and the processing parameters via response surface analysis method to obtain a corresponding parameter value to the minimum surface roughness are optimized. After that, the minimum surface roughness predicted value was obtained, and the experimental learning sample data was trained by using artificial neural network. the optimization of processing parameters was taken respectively via artificial intelligent algorithms (genetic pattern search and simulated annealing), and then the integration of artificial neural network-genetic pattern search-simulated annealing technique to further optimize the processing parameters to obtain the optimum parameter values corresponding minimum surface roughness was accepted. The results show that the integration of technology, compared with single genetic pattern search or simulated annealing method, greatly reduces the surface roughness value and shortens the optimization time.
- abrasive waterjet optimization /
- response surface analysis /
- artificial neural network /
- intelligent algorithms /

HTML全文

参考文献(11)

[1]	Gent M, Menéndez M, Torno S, et al. Experimental evaluation of the physical properties required of abrasives for optimizing waterjet cutting of ductile materials[J]. Wear, 2012,284-285:43-51
[2]	Naresh Babu M, Muthukrishnan N. Investigation of multiple process parameters in abrasive water jet machining of tiles[J]. Journal of the Chinese Institute of Engineers, 2015,38(6):692-700
[3]	张成光,张勇,张飞虎,等.磨料水射流加工去除模型研究[J].机械工程学报,2015,51(7):188-196 Zhang C G, Zhang Y, Zhang F H, et al. Study on removal model of abrasive waterjet machining[J]. Journal of Mechanical Engineering, 2015,51(7):188-196(in Chinese)
[4]	宋圆圆.基于神经网络的前混合磨料水射流切割数据库建立研究[D].江苏徐州:中国矿业大学,2014 Song Y Y. Study on cutting database of ASJ based on neural network[D]. Jiangsu Xuzhou:China University of Mining and Technology, 2014(in Chinese)
[5]	Naresh Babu M, Muthukrishnan N. Investigation on surface roughness in abrasive water-jet machining by the response surface method[J]. Materials and Manufacturing Processes, 2014,29(11-12):1422-1428
[6]	吴有炜.试验设计与数据处理[M].江苏苏州:苏州大学出版社,2002 Wu Y W. Experimental design and data processing[M]. Jiangsu Suzhou:Suzhou University Press, 2002(in Chinese)
[7]	Ebeid J S, Atia A R M, Sayed M M. Prediction of abrasive water jet plain milling process parameters using artificial neural networks[J]. Journal of Machinery Manufacturing and Automation, 2014,3(3):56-73
[8]	Asiltürk I, Çunkaş M. Modeling and prediction of surface roughness in turning operations using artificial neural network and multiple regression method[J]. Expert Systems with Applications, 2011,38(5):5826-5832
[9]	张煜东,吴乐南,王水花.基于遗传算法与模式搜索的混合优化算法[J].南京信息工程大学学报(自然科学版),2012,4(1):34-39 Zhang Y D, Wu L N, Wang S H. A hybrid optimization method based on genetic algorithm and pattern search[J]. Journal of Nanjing University of Information Science and Technology (Natural Science Edition), 2012,4(1):34-39(in Chinese)
[10]	Tamilarasi A, Kumar T A. An enhanced genetic algorithm with simulated annealing for job-shop scheduling[J]. International Journal of Engineering, Science and Technology, 2010,2(1):144-151
[11]	Chen B L, Zeng W H, Lin Y B, et al. An enhanced differential evolution based algorithm with simulated annealing for solving multiobjective optimization problems[J]. Journal of Applied Mathematics, 2014,2014:931630