基于CMA1390型CO_(2)激光切削机的水曲柳切削效果回归模型建立

Regression Modeling of Fraxinus mandshurica Cutting Effect Based on CMA1390 CO_(2) Laser Cutting Machine

【目的】分析激光切削水曲柳的技术参数与切削效果之间的相关性,建立切削效果最优回归模型,为满足切削效果提供合适的技术参数组合。【方法】以激光机镜头高、进给速度和光强为影响因素,以缝深和缝宽为切削效果指标,利用SPSS 27.0对激光切削水曲柳的技术参数与切削效果进行Spearman相关性分析,进一步根据最小二乘法原理采用MATLAB R2020a编程进行多元线性和非线性回归分析。【结果】1)镜头高与缝深和缝宽呈极显著相关,相关系数分别为-0.677和0.962;进给速度与缝深呈极显著相关、与缝宽无显著相关性,相关系数分别为-0.619和-0.090;光强与缝深和缝宽无显著相关性,相关系数分别为0.116和0.057。2)多元线性回归分析结果表明,缝深回归模型的拟合优度(R^(2))为0.77154(P<0.01),缝宽回归模型的R^(2)为0.90458(P<0.01);多元非线性回归分析结果表明,缝深回归模型的R^(2)为0.93669(P<0.01),缝宽回归模型的R^(2)为0.94241(P<0.01);多元线性和非线性回归模型均拟合较好,相对来说多元非线性回归模型的准确度高于多元线性回归模型。3)多元回归模型系数对比和图像变化幅值显示,镜头高对缝深和缝宽的影响大于进给速度和光强。4)在激光切削水曲柳生产实际中,如果只是粗略、快速计算缝深和缝宽,可采用多元线性回归模型估计;如果需精确计算缝深和缝宽,采用多元非线性回归模型估计效果更好。【结论】1)缝深和缝宽随激光机技术参数组合总体上呈周期性变化规律;2)在激光切削水曲柳生产实际中,需要先调整镜头高;3)激光机技术参数组合对缝深与缝宽的影响展现出更为显著的非线性特征。

【Objective】By analysing the technical parameters and cutting effect of laser cutting Fraxinus mandshurica,the optimal regression equation model of cutting effect was established to provide a theoretical basis for estimating the cutting effect.【Method】Taking the technical parameters of the laser machine lens height,cutting speed and light intensity as the influencing factors,and the seam depth and seam width as the cutting effect indicators,the two were analysed by Spearman correlation analysis using SPSS 27.0 software,and further multivariate linear and non-linear regression analyses were carried out by using MATLAB R2020a software programming based on the principle of the least squares method.【Result】1)The lens height was significantly correlated with the seam depth and width,with correlation coefficients of-0.677 and 0.962,indicating that the lens height was negatively correlated with the seam depth and positively correlated with the seam width.The cutting speed was significantly correlated with the seam depth and not with the seam width,with correlation coefficients of-0.619 and-0.090,indicating that the correlation was negatively correlated with the seam depth and seam width.The light intensity was not significantly correlated with the seam depth and seam width,with correlation coefficients of 0.116 and 0.057,indicating a positive correlation with the seam depth and seam width.2)Linear regression analysis showed that the goodness-of-fit R^(2) of the regression model for seam depth was0.77154(P<0.01).The goodness-of-fit R^(2) of the regression model for seam width was 0.90458(P<0.01).Non-linear regression analyses yielded a goodness-of-fit R^(2) of 0.93669(P<0.01)for the regression model of seam depth.The a goodness-of-fit R^(2) of0.94241(P<0.01)for the regression model of seam width.Both multivariate linear and non-linear regression models were well fitted,but the accuracy of the multivariate nonlinear regression model was relatively higher than that of the multivariate linear regression model.3)From the comparison of the coefficients of the multiple regression model equations and the magnitude of the image changes,it can be obtained that the influence of the lens height on the seam depth and width is greater than that of the cutting speed and light intensity.4)In the actual laser cutting Fraxinus mandshurica production,if the values of seam depth and seam width are only roughly and quickly calculated,the multiple linear regression model can be used for estimation;on the contrary,if the values of seam depth and seam width are calculated more accurately,the estimation effect will be better if the multiple nonlinear regression model is used for estimation.【Conclusion】1)Seam depth and seam width generally show a periodic change law with the combination of laser technical parameters.2)In the production of laser cutting Fraxinus mandshurica,it is necessary to adjust the lens height first.3)The influence of the combination of laser parameters on the seam depth and seam width shows more significant non-linear characteristics.