|
Material Sciences 2022
基于多元非线性回归方法的脉冲电化学光整加工表面质量预测研究
|
Abstract:
本文对脉冲电化学光整加工零件的材料去除率以及表面粗糙度进行预测。首先对实验所得的数据进行分析,找出其中最主要的影响因素,然后从搜集到的数据中取出21组数据建立了数学回归模型。求解模型,对材料的去除率以及表面粗糙度进行了预测,并对模型进行了验证。根据验证结果可以看出,我们所得到的模型可以比较准确的预测出材料去除率以及表面粗糙度。最后我们依据以上结论对模型进行评估和改进,从而得出在其他条件一定时:粗糙度与电解液温度成反比,材料去除率与电解液温度成正比;粗糙度和材料去除率均与电流密度成正比;粗糙度受电解液温度影响更大,材料去除率受电流密度影响更大等结论。
In this paper, the material removal rate and surface roughness of parts processed by pulse electrochemical finishing are predicted. First, we analyze the data obtained from the experiment, find out the most important influencing factors, and then take 21 groups of data from the collected data to establish a mathematical regression model. The mate-rial removal rate and surface roughness were predicted by solving the model, and the model was verified. According to the verification results, the model we obtained can accurately predict the material removal rate and surface roughness. At last, we evaluate and improve the model according to the above conclusions, so that when other conditions are constant, roughness is inversely propor-tional to electrolyte temperature, and material removal rate is proportional to electrolyte temper-ature; roughness and material removal rate are directly proportional to current density; the roughness is more affected by electrolyte temperature, and the material removal rate is more af-fected by current density.
[1] | 魏泽飞, 张斯文, 佘东生, 庞桂兵, 徐文骥. 电化学机械加工对轴/轴承类零件表面质量影响研究[J]. 渤海大学学报(自然科学版), 2021, 42(1): 70-77. https://dx.doi.org/10.13831/j.cnki.issn.1673-0569.2021.01.011 |
[2] | 宋海翔, 殷绍伟, 王晓新, 于元新. 机械零件的表面光整加工常用方法分析[J]. 科技创新与应用, 2017(10): 127. |
[3] | 玛斯库达?阿布力哈孜. 电化学光整加工工艺应用基础研究[D]: [硕士学位论文]. 乌鲁木齐: 新疆大学, 2013. |
[4] | 李海滨, 王辉, 周锦进, 翟小兵, 王志国. 神经网络在脉冲电化学光整加工工艺中的应用[C]//中国机械工程学会. 2005年中国机械工程学会年会: 2005年卷. 2005: 269-272. |
[5] | 黄昕龙, 花海燕, 陈世辉. FDM零件表面粗糙度偏最小二乘回归建模研究[J]. 福建工程学院学报, 2020, 18(6): 524-529. |
[6] | 甘彬霖, 冯旭海, 毕经龙, 姜浩亮. 基于多元非线性回归模型的高强混凝土强度预测研究[J]. 混凝土与水泥制品, 2022(2): 1-7. https://dx.doi.org/10.19761/j.1000-4637.2022.02.001.07 |
[7] | 钟志峰, 周冬平, 张艳, 夏一帆. 基于最小二乘法的混合推荐模型研究[J]. 现代电子技术, 2022, 45(17): 123-128.
https://dx.doi.org/10.16652/j.issn.1004-373x.2022.17.023 |