基于PSO算法改进BP神经网络的氟金云母点磨削工艺参数优化

摘要/Abstract

摘要：

通过氟金云母的高速点磨削试验，测试了加工表面硬度和表面粗糙度，分析了表面硬度和表面粗糙度随工艺参数的变化规律。基于单因素试验值和PSO算法改进的BP神经网络，利用最小二乘拟合，建立了氟金云母点磨削表面硬度和表面粗糙度关于各工艺参数的一元模型，以相关系数检验模型，证明模型具有较高可靠性。分析一元模型，提出表面硬度和表面粗糙度分别关于工艺参数的多元模型。基于正交试验值和PSO算法，对模型进行优化求解，并通过试验证明了模型具有较高可靠性。利用PSO算法对两个多元模型进行双目标优化，求解得到一组较为合理的工艺参数值。

关键词: 工艺参数, PSO算法;BP神经网络;点磨削;氟金云母

Abstract:

Through a high speed point grinding experiment,the surface hardness and roughness of the finished surface was tested, and the variations of the surface hardness and roughness with the process parameters were analyzed.Single factor experimental values were predicted with PSO-BP.A series of one-dimensional models of surface hardness and roughness process parameters of fluorophlogopite were built by least-squares fitting. Correlation coefficient test was used to verify the models' high reliability.Multivariate models about surface hardness and roughness process parameters were proposed by analyzing one-dimensional models.The multivariate numerical models were optimized according to the results of orthogonal experiments and PSO and were proved to have high reliability by experiment.A dual objective optimization of two multivariate models was carried out by PSO algorithm, and a set of reasonable process parameters was obtained.

Key words: process , parameter;particle swarm optimization(PSO) algorithm;BP neural , network;point grinding, fluorophlogopite

中图分类号:

TH161

马廉洁, 陈杰, 巩亚东, 王佳. 基于PSO算法改进BP神经网络的氟金云母点磨削工艺参数优化[J]. 中国机械工程, 2016, 27(06): 761-766.

Ma Lianjie, Chen Jie, Gong Yadong, Wang Jia. Process Parameter Optimization Based on PSO-BP Neural Network in Point Grinding Fluorophlogopite[J]. China Mechanical Engineering, 2016, 27(06): 761-766.

参考文献

[1]Ma Lianjie, Yu Aibing. Influencing of Technological Parameter on Tools Wear during Turning Fluorophlogopite Glass-ceramics[J]. Journal of Rare Earths, 2007, 25: 330-333.

[2]Garai M, Sasmal N, Molla A R, et al. Effects of Nucleating Agents on Crystallization and Microstructure of Fluorophlogopite Mica-containing Glass-ceramics[J]. Journal of Materials Science, 2014, 49(4): 1612-1623.

[3]Hche T, Habelitz S, Khodos I I. Origin of Unusual Fluorophlogopite Morphology in Mica Glass-ceramics of the System SiO2-Al2O3-MgO-K2O-Na2O-F2[J]. Journal of Crystal Growth, 1998, 192(1): 185-195.

[4]范世豈. 氟金云母晶体缺陷成因及缺陷与晶体性能的关系[J]. 硅酸盐学报, 1980, 8(1): 1-8.

Fan Shiji. Defects Formation and Relations between Defects and Properties of Fluorophlogopite Crystals[J]. Journal of the Chinese Ceramic Society, 1980, 8(1): 1-8.

[5]Biermann D, Feldhoff M. Influence of Controlled Tool Orientation on Pattern Formation and Waviness in Surface Grinding[J]. Production Engineering, 2011, 5(1): 31-36.

[6]Tnissen S, Klocke F, Feldhaus B, et al. Residual Stress Prediction in Quick Point Grinding[J]. Production Engineering, 2012, 6(3): 243-249.

[7]Ma Lianjie, Gong Yadong, Chen Xiaohui. Study on Surface Roughness Model and Surface Forming Mechanism of Ceramics in Quick Point Grinding[J]. International Journal of Machine Tools and Manufacture, 2014, 77: 82-92.

[8]Yamamoto A, Yamada T,Nakahigashi S, et al. Effects of Surface Grinding on Hardness Distribution and Residual Stress in Low Carbon Austenitic Stainless Steel SUS316L[J]. ISIJ international, 2004, 44(10): 1780-1782.

[9]巩亚东, 曹振轩, 刘月明, 等. 高速点磨削参数对温度场与表面硬度的影响[J]. 东北大学学报 (自然科学版), 2012, 33(3): 414-417.

Gong Yadong, Cao Zhenxuan, Liu Yueming, et al. Effect of High Speed Point Grinding Parameters onTemperature Field and Surface Hardness[J]. Journal of Northeastern University：Natural Science, 2012, 33(3): 414-417.

[10]Fuh K H, Wang S B. Force Modeling and Forecasting in Creep Feed Grinding Using Improved BP Neural Network[J]. International Journal of Machine Tools and Manufacture, 1997, 37(8): 1167-1178.

[11]张臣, 周儒荣, 庄海军, 等. 基于BP神经网络的球头铣刀铣削力建模与仿真[J]. 中国机械工程, 2005, 16(20): 1791-1794.

Zhang Chen, Zhou Rurong, Zhuang Haijun, et al. Simulation and Modeling of Milling Forces for Ball-end Milling Cutter Based on BP Neural Network[J]. China Mechanical Engineering, 2005, 16(20): 1791-1794.

[12]Liu J, Chang H, Hsu T Y, et al. Prediction of the Flow Stress of High-speed Steel during Hot Deformation Using a BP Artificial Neuralnetwork[J]. Journal of Materials Processing Technology, 2000, 103(2): 200-205.

[13]Chauhan P, Pant M, Deep K. Parameter Optimization of Multi-pass Turning Using Chaotic PSO[J]. International Journal of Machine Learning and Cybernetics, 2015, 6(2): 319-337.

[14]Aydｌn M,Karakuzu C, Uar M, et al. Prediction of Surface Roughness and Cutting Zone Temperature in Dry Turning Processes of AISI304 Stainless Steel Using ANFIS with PSO Learning[J]. The International Journal of Advanced Manufacturing Technology, 2013, 67(1/4): 957-967.

[15]陈祯, 黄安贻. 基于PSO-LSSVM的抽油机电动机扭矩软测量建模[J]. 中国机械工程, 2011, 22(11): 1333-1336.

Chen Zhen, Huang Anyi. Modeling of PSO-LSSVM Based Soft Measurement for Electromotor Torque in a Pumping Unit[J]. China Mechanical Engineering, 2011, 22(11): 1333-1336.