磨料水射流切割钢板过程参数优化研究
发布时间：2018-08-26 16:54
【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。
[Abstract]:The abrasive water jet cutting 06Cr19Ni10 steel plate was carried out by using the field orthogonal test (L27). The surface roughness of the cut workpiece was taken as the standard for evaluating the surface quality of the machined workpiece. The process parameters were selected as follows: jet pressure, velocity of nozzle transverse shift. Target distance, abrasive particle size and abrasive flow rate. The regression model of surface roughness about five process parameter variables is obtained by regression analysis of experimental data. The process parameters are optimized by response surface analysis, and the corresponding parameters of minimum surface roughness are obtained. Then the artificial neural network is used to train and learn the experimental sample data, and the minimum predicted value of surface roughness is obtained. The process parameters are optimized by artificial intelligence (genetic pattern search algorithm and simulated annealing algorithm), and further optimized by integrated artificial neural network-genetic pattern search algorithm-simulated annealing. The optimum process parameters corresponding to the minimum surface roughness are obtained. The reliability of the optimization results is verified by experiments. Compared with the single genetic pattern search algorithm or simulated annealing method, the integration technique can greatly reduce the value of surface roughness and shorten the searching time.
【作者单位】： 江南大学机械工程学院;江南大学江苏省食品先进制造装备技术重点实验室;
【基金】：国家自然科学基金项目(51275210) 教育部预研项目(62501036035)资助
【分类号】：TG48
[Abstract]:The abrasive water jet cutting 06Cr19Ni10 steel plate was carried out by using the field orthogonal test (L27). The surface roughness of the cut workpiece was taken as the standard for evaluating the surface quality of the machined workpiece. The process parameters were selected as follows: jet pressure, velocity of nozzle transverse shift. Target distance, abrasive particle size and abrasive flow rate. The regression model of surface roughness about five process parameter variables is obtained by regression analysis of experimental data. The process parameters are optimized by response surface analysis, and the corresponding parameters of minimum surface roughness are obtained. Then the artificial neural network is used to train and learn the experimental sample data, and the minimum predicted value of surface roughness is obtained. The process parameters are optimized by artificial intelligence (genetic pattern search algorithm and simulated annealing algorithm), and further optimized by integrated artificial neural network-genetic pattern search algorithm-simulated annealing. The optimum process parameters corresponding to the minimum surface roughness are obtained. The reliability of the optimization results is verified by experiments. Compared with the single genetic pattern search algorithm or simulated annealing method, the integration technique can greatly reduce the value of surface roughness and shorten the searching time.
【作者单位】： 江南大学机械工程学院;江南大学江苏省食品先进制造装备技术重点实验室;
【基金】：国家自然科学基金项目(51275210) 教育部预研项目(62501036035)资助
【分类号】：TG48
【相似文献】
相关期刊论文 前10条
1 蔡祖光;磨料水射流切割技术及其应用[J];液压与气动;2000年02期
2 赵民,赵永赞,刘黎,谢国良,蒲永伟;磨料水射流切割石材的应用研究[J];金刚石与磨料磨具工程;2000年02期
3 赵永赞,吴玉厚,富大伟,赵民,王海波;后混合磨料水射流切割石材的特性[J];河北理工学院学报;2002年02期
4 苏卫民;磨料水射流切割技术[J];大众科技;2004年08期
5 杨丽君;;磨料水射流切割技术[J];淮北职业技术学院学报;2009年05期
6 吴海;刘波;王国涛;何红阳;;磨料水射流切割技术分析及研究[J];机械管理开发;2010年04期
7 董星;王瑞宏;;磨料水射流切割技术[J];机械工程师;1993年05期
8 宫平,王pち，
本文编号：2205555
本文链接：https://www.wllwen.com/kejilunwen/jiagonggongyi/2205555.html
