Product Operating Performance Prediction Based on Small-sample Data Augmentation Method

doi:10.3901/JME.2024.06.011

Abstract

Abstract: Generally, the production scale of high-precision mechanical products is limited, and there is a complex coupling relationship between assembly characteristic parameters and performances, which is difficult to express by explicit mapping relationship. Building a mapping model that can accurately predict operating performance has practical guiding significance for product assembly and adjustment. To this end, a product operating performance parameter correlation analysis and forecasting method for small-sample data is proposed: The contact stiffness of joint surface is considered to merged into assembly data, and the random forest is adopted to select key characteristics by calculating the importance of assembly feature parameters. The variational autoencoder learning is used to learn prior distribution knowledge of small sample data, then augmented assembly data is generated, and outlier correction is performed on augmented data. The assembly augmented sample is fused with the original assembly data, and the operating performance is predicted by integrated kernel extreme learning machine. Finally, an example of operating performance prediction of a position marker is taken to verify the effectiveness of the proposed method.

Key words: small sample, data augmentation, contact characteristic, operating performance, extreme learning machine

CLC Number:

TH124

LIU Zhenyu, ZHANG Nan, QIU Chan, TAN Jianrong. Product Operating Performance Prediction Based on Small-sample Data Augmentation Method[J]. Journal of Mechanical Engineering, 2024, 60(6): 11-20.

References

[1] SHAO Chao，YE Xin，WANG Lei，et al. An assembly process parameters optimization method for precision assembly performance[J]. Journal of Physics：Conference Series，2019，1303：1-8.
[2] LIU Zhenyu，XU Yunkun，QIU Chan，et al. A novel support vector regression algorithm incorporated with prior knowledge and error compensation for small datasets[J]. Neural Computing and Applications. 2019(31)：4849-4864.
[3] GUO Huan，ZHANG Zhijing，XIAO Muzheng，et al. Measurement and data processing method of machined surface for assembly performance prediction[J]. Journal of Mechanical Science and Technology，2021，35：1689-1698.
[4] WAN Fei，LI Guoxi，RAO Zhihua. Performance prediction of assembly based on dynamic alignment[J]. Applied Mechanics and Materials，2012(271)：657-662.
[5] LI Heng，QIU Leimiao，WANG Zili. et al. A prediction method of mechanical product assembly precision based on the fusion of measured samples and assembly feature fidelity samples[J]. International Journal of Advanced Manufacturing Technology，2020，111：2877-2890.
[6] 贾振元，马建伟，刘巍，等. 多几何要素影响下液压阀件特性的混合神经网络预测模型[J]. 机械工程学报，2010，46(2)：126-131. JIA Zhenyuan，MA Jianwei，LIU Wei，et al. Hybrid neural network prediction model of hydraulic valve characteristics under the affection of multiple geometric factors effected[J]. Journal of Mechanical Engineering，2010，46(2)：126-131.
[7] 刘振宇，周思杭，谭建荣，等. 基于多准则修正的产品性能多参数关联分析与预测方法[J]. 机械工程学报， 2013，49(15)：105-114. LIU Zhenyu，ZHOU Sihang，TAN Jianrong，et al. Multiple parameters correlation analysis and prediction method of product performance based on multi-criteria modification[J]. Journal of Mechanical Engineering，2013，49(15)：105-114.
[8] 王小巧，刘明周，葛茂根，等. 复杂机械产品装配过程质量门监控系统与关键技术[J]. 计算机集成制造系统，2015，21(11)：2869-2884. WANG Xiaoqiao，LIU Mingzhou，GE Maogen，et al. Quality gates monitoring system and key technologies for assembly process of complex mechanical products[J]. Computer Integrated Manufacturing Systems，2015，21(11)：2869-2884.
[9] 寇英信，奚之飞，徐安，等. 基于改进核极限学习机和集成学习理论的目标机动轨迹预测[J]. 国防科技大学学报，2021，43(5)：23-35. KOU Yingxin，XI Zhifei，XU An，et al. Maneuver trajectory prediction of target based on improved KELM and ensemble learning theory[J]. Journal of National University of Defense Technology，2021，43(5)：23-35.
[10] 李玲，王晶晶，裴喜永，等. 机械结合面接触刚度建模新方法[J]. 机械工程学报，2020，56(9)：162-169. LI Ling，WANG Jingjing，PEI Xiyong，et al. A new method for modeling mechanical joint surface contact stiffness[J]. Journal of Mechanical Engineering，2020，56(9)：162-169.
[11] 穆晓凯. 机械结构装配精度及接触性能预测与分析[D]. 大连：大连理工大学，2019. MU Xiaokai. Prediction and analysis of assembly precision and contact performance for mechanical structure[D]. Dalian：Dalian University of Technology，2019.
[12] WANG Yunlong，MU Xiaokai，YUE Cong，et al. A high precision modeling technology of material surface microtopography and its influence on interface mechanical properties[J]. Materials. 2021，14(11)：1-16.
[13] 田爱玲，孙钊，于洵，等. 非高斯随机粗糙表面的数字模拟[J]. 系统仿真学报，2009(10)：2840-2842. TIAN Ailing，SUN Zhao，YU Xun，et al. Numerical simulation of non-gaussian random roughness surface[J]. Journal of System Simulation，2009(10)：2840-2842.
[14] HUANG Guangbin，ZHU Qinyu，SIEW Chee-Kheong. Extreme learning machine：Theory and applications[J]. Neurocomputing. 2006，70(1/3)：489-501.
[15] LI Heng，QIU Lemiao，WANG Zili，et al. An assembly precision prediction method for customized mechanical products based on GAN-FTL[J]. Proceedings of the Institution of Mechanical Engineers，Part B：Journal of Engineering Manufacture，2022，236(3)：160-173.