融合磨粒特征和工艺参数的粗糙度智能预测研究

doi:10.3901/JME.2024.07.224

摘要/Abstract

摘要： 针对加工对象受磨削工具表面状态和工艺参数的综合影响而造成表面粗糙度难以有效准确预测问题，提出了融合磨粒特征和工艺参数的表面粗糙度智能预测方法。基于采集的金刚石磨粒图像，利用图像处理技术提取了工具表面的单位面积磨粒数、磨粒分布均匀性和磨粒出刃高度三个关键特征信息，并评价了提取的特征信息的有效性。在此基础上，提出了融合磨粒特征和工艺参数的粗糙度智能预测算法，开展了YG8硬质合金铣磨加工实验，并将加工结果与预测结果进行对比。结果表明：提出的智能算法可以提高粗糙度预测的准确性和稳定性，其预测的准确率可达到95.6%，而基于传统工艺参数回归模型的准确率仅为86.3%，所提出的方法为粗糙度智能预测提供了参考。

关键词: 磨粒加工, 图像处理, 特征信息, 智能算法, 粗糙度

Abstract: Aiming at the problem that it is difficult to predict the surface roughness of the machined object effectively and accurately due to the comprehensive influence of the surface state of grinding tools and process parameters, an intelligent prediction method of surface roughness based on the integration of abrasive characteristics and processing parameters is proposed. Based on the collected diamond abrasive images on the tool surface, three key characteristic information of abrasive number per unit area, abrasive distribution uniformity and abrasive protrusion height on the tool surface are extracted by using image processing technology, and the effectiveness of the extracted characteristic information is verified. On this basis, a surface roughness intelligent prediction algorithm integrating abrasive characteristics and process parameters is proposed, the milling experiment of YG8 cemented carbide is carried out, and the machining results are compared with the predicted results. The results show that the proposed intelligent algorithm can greatly improve the accuracy and stability of surface roughness prediction, and its prediction accuracy can reach 95.6%, while the accuracy of regression model based on traditional process parameters is only 86.3%, which provides a reference for the intelligent prediction of surface roughness in abrasive machining.

Key words: abrasive machining, image processing, characteristic information, intelligent algorithm, surface roughness

中图分类号:

TG176

方从富, 李弘扬, 沈剑云, 吴贤. 融合磨粒特征和工艺参数的粗糙度智能预测研究[J]. 机械工程学报, 2024, 60(7): 224-235.

FANG Congfu, LI Hongyang, SHEN Jianyun, WU Xian. Study on Intelligent Prediction of Surface Roughness Based on Integration of Abrasive Characteristics and Process Parameters[J]. Journal of Mechanical Engineering, 2024, 60(7): 224-235.

参考文献

[1] HONG T T,CUONG N V,KY L H,et al. Effect of process parameters on surface roughness in surface grinding of 90CrSi tool steel[J]. Solid State Phenomena, 2020,305:191-197.
[2] 吴玉厚,王强,王贺,等. 氮化硅套圈内圆磨削及回归分析[J]. 沈阳建筑大学学报,2013,29(1):156-162. WU Yuhou,WANG Qiang,WANG He,et al. Internal grinding of silicon nitride ferrules and regression analysis[J]. Journal of Shenyang Jianzhu University,2013,29(1):156-162.
[3] MANDAL N,DOLOI B,MONDAL B. Surface roughness prediction model using zirconia toughened alumina (ZTA) turning inserts:Taguchi method and regression analysis[J]. Journal of The Institution of Engineers (India):Series C,2016,97:77-84.
[4] 柴桦,黄云,王亚杰,等. 镁合金表面粗糙度预测模型优化的研究[J]. 机械科学与技术,2012,31(6):968-971. CHAI Hua,HUANG Yun,WANG Yajie,et al. Research on the optimization of the prediction model of magnesium alloy surface roughness[J]. Mechanical Science and Technology for Aerospace Engineering,2012,31(6):968-971.
[5] JOSHI K,PATIL B. Prediction of surface roughness by machine vision using principal components based regression analysis[J]. Procedia Computer Science,2020,167(9-12):382-391.
[6] 高超,王生,王会,等. 砂带磨削表面粗糙度理论预测及灵敏度分析[J]. 表面技术,2018,47(11):295-305. GAO Chao,WANG Sheng,WANG Hui,et al. Theoretical prediction and sensitivity analysis of surface roughness in belt grinding[J]. Surface Technology,2018,47(11):295-305.
[7] KHOIRUL EFFENDI M,SOEPANGKAT B O P,NOORCAHYO R,et al. An analysis of frictional coefficient and surface roughness in surface grinding of SKD11 tool steel using minimum quantity lubrication (MQL) and dry techniques[J]. IOP conference series:Materials Science and Engineering,2021,1034(1):012100.
[8] 于铁夫,吕玉山,舒启林. 基于响应曲面法的微磨削钛合金表面粗糙度预测分析[J]. 工具技术,2014,48(4):79-82. YU Tiefu,LV Yushan,SHU Qilin. Prediction and analysis of surface roughness of micro-grinding titanium alloy based on response surface method[J]. Tool Engineering,2014,48(4):79-82.
[9] HONG SON N,DUC TRUNG D,NGUYEN N. Surface roughness prediction in grinding process of the SKD11 steel by using response surface method[J]. IOP Conference Series:Materials Science and Engineering,2020,758(1):012029.
[10] MALKIN S. Grinding technology:Theory and applications of machining with abrasives[D]. Ellis Horwood,New York,1989.
[11] DING W F,DAI C W,YU T Y,et al. Grinding performance of textured monolayer CBN wheels:undeformed chip thickness nouniformity modeling and ground surface topography prediction[J]. International Journal of Machine Tools and Manufacture,2017,122:66-80.
[12] ZHANG Y Z,FANG C F,HUANG G Q,et al. Modeling and simulation of the distribution of undeformed chip thicknesses in surface grinding[J]. International Journal of Machine Tools and Manufacture,2018,127:14-27.
[13] XU X,YE S,YANG Z,et al. Analysis and prediction of surface roughness for robotic belt grinding of complex blade considering coexistence of elastic deformation and varying curvature[J]. Science China Technological Sciences,2021,64(5):957-970.
[14] 宋铁军,周志雄,李伟,等. 硬质合金立铣刀螺旋槽磨削表面粗糙度模型研究[J]. 机械工程学报,2017,53(17):185-192. SONG Tiejun,ZHOU Zhixiong,LI Wei,et al. Research on surface roughness model of carbide end mills grinding spiral groove[J]. Journal of Mechanical Engineering,2017,53(17):185-192.
[15] 田凤杰,司大胜,李伦. 砂带磨削加工表面粗糙度预测与验证[J]. 工具技术,2021,55(4):96-100. TIAN Fengjie,SI Dasheng,LI Lun. Surface roughness prediction and verification of abrasive belt grinding[J]. Tool Engineering,2021,55(4):96-100.
[16] MOHAMMAD R,JOSEPH L Z W. Simulation of workpiece surface roughness after flat grinding by electroplated wheel[J]. Procedia CIRP,2018,7:303-306.
[17] 周合生,王军,吕玉山,等. 磨粒有序排布的电镀CBN砂轮磨削表面粗糙度仿真[J]. 工具技术,2015,49(5):98-100. ZHOU Shenghe,WANG Jun,LV Yushan,et al. Simulation of grinding surface roughness of electroplated CBN grinding wheel with Pattern[J]. Tool Engineering,2015,49(5):98-100.
[18] YU S,YAO P,YE Z,et al. Simulation and experimental research of tool path planning on profile and surface generation of aspherical-cylindrical lens array by ultra-precision envelope grinding[J]. Journal of Materials Processing Technology,2022,307:117690.
[19] WU J,CHENG J,GAO C,et al. Research on predicting model of surface roughness in small-scale grinding of brittle materials considering grinding tool topography[J]. International Journal of Mechanical Sciences,2020,166:105263.
[20] 商维,张沭玥,郭俊,等. 基于虚拟砂轮建模的钢轨打磨材料去除仿真研究[J]. 机械工程学报,2018,54(4):30-36. SHANG Wei,ZHANG Shuyue,GUO Jun,et al. Simulation study on material removal of rail grinding based on virtual grinding wheel modeling[J]. Journal of Mechanical Engineering,2018,54(4):30-36.
[21] 田雪豪,郑鹏,张琳娜. 高速磨削表面粗糙度预测模型研究[J]. 机械设计与制造,2019(10):193-196. TIAN Xuehao,ZHENG Peng,ZHANG Linna. Research on the prediction model of surface roughness for high-speed grinding[J]. Mechanical Design and Manufacture,2019(10):193-196.
[22] KARKALOS N E,KUNDRAK J,MARKOULOS A P. Assessment of the performance of neural networks models for the prediction of surface roughness after grinding of steels[J]. International Journal of Artificial Intelligence,2017,1(15):55-75.
[23] 董浩生,杨赫然,孙兴伟,等. 基于改进神经网络算法的螺杆砂带磨削表面粗糙度预测研究[J]. 表面技术,2022,51(4):275-283. DONG Haosheng,YANG Heran,SUN Xingwei,et al. Research on surface roughness prediction of screw abrasive belt grinding based on improved neural network algorithm[J]. Surface Technology,2022,51(4):275-283.
[24] DU C,HO C L,KAMINSKI J. Prediction of product roughness,profile,and roundness using machine learning techniques for a hard turning process[J]. Advances in Manufacturing,2021,9(2):206-215.
[25] GUO W,WU C,DING Z,et al. Prediction of surface roughness based on a hybrid feature selection method and long short-term memory network in grinding[J]. The International Journal of Advanced Manufacturing Technology,2021,112(9-10):2853-2871.
[26] WU Z,ZHANG L,YANG S. Effect of abrasive grain position patterns on the deformation of 6H-silicon carbide subjected to nano-grinding[J]. International Journal of Mechanical Sciences,2021,211:106779.
[27] QIU Y,HUANG H. Research on the fabrication and grinding performance of 3-dimensional controllable abrasive arrangement wheels[J]. The International Journal of Advanced Manufacturing Technology,2019,104(5-8):1839-1853.
[28] TANAKA H,OKUI K,OKU Y,et al. Corrected power spectral density of the surface roughness of tire rubber sliding on abrasive material[J]. Tribology International,2021,153:106632.
[29] TAHVILIAN A M,LIU Z,CHAMPLIAUD H,et al. Experimental and finite element analysis of temperature and energy partition to the workpiece while grinding with a flexible robot[J]. Journal of Materials Processing Technology,2013,213(12):2292-2303.
[30] TANG J,QIU Z,LI T. A novel measurement method and application for grinding wheel surface topography based on shape from focus[J]. Measurement,2018,133:495-507.
[31] LIN Y F,FANG C F. Study on the segmentation of abrasive grains in diamond tools[J]. International Journal of Abrasive Technology,2018,8(2):203-217.
[32] 苏玲玲,黄辉,徐西鹏. 金刚石磨具表面磨粒分布形态的定量评价[J]. 中国机械工程,2014(10):1290-1294. SU Lingling,HUANG Hui,XU Xipeng. Quantitative evaluation of the distribution of abrasive grains on the surface of diamond abrasive tools[J]. China Mechanical Engineering,2014(10):1290-1294.
[33] 葛恭豪. 机器学习算法原理及效率分析[J]. 电子世界,2018(1):65-66. GE Gonghao. Principles and efficiency analysis of machine learning algorithms[J]. Electronics World,2018(1):65-66.
[34] LI W,WANG W,HUO W. RegBoost:a gradient boosted multivariate regression algorithm[J]. International Journal of Crowd Science,2020,4(1):60-72.