Nano-machining AFM Tip Wear Monitoring Based on Time Series Data and Support Vector Machine
CHENG Fei1,2,DONG Jing-yan2
1. Management School of Hangzhou Dianzi University, Hangzhou, Zhejiang 310018, China
2. Fitts Department Industrial & System Engineering of NCSU, Raleigh, NC 27606, USA
Abstract：Time-series data analysis and pattern recognition using support vector machine (SVM) are studied to monitor the state changes of the AFM tip-based nanomachining process with respect to the machining performance and tip wear. Time series data (i.e. machining force from the process), which has transient, nonlinear, and non-stationary characteristics, is collected by a data acquisition system. Three status detection features including the maximum force, peak to peak force value, and the variance of the collected lateral machining force, are extracted to classify the state of the nanomachining process. Directed acyclic graph support vector machines with a (Gaussian) radial basis kernel function is constructed to identify the tip wear status. Using this multi-class SVM, the machining process and the tip wear can be classified into three regions, which are effective machining with sharp tip, transition region, and bad/no machining with severe tip wear. The experimental data shows that the accuracy of the SVM is over 94.73% in both binary and ternary classifications.
程菲,董景彦. 基于时间序列数据和支持向量机的纳米加工AFM刀尖损伤监测[J]. 计量学报, 2019, 40(4): 647-654.
CHENG Fei,DONG Jing-yan. Nano-machining AFM Tip Wear Monitoring Based on Time Series Data and Support Vector Machine. Acta Metrologica Sinica, 2019, 40(4): 647-654.
［1］Skrman B, Wallenberg L R, Jacobsen S N, et al. Evaluation of intermittent contact mode AFM probes by HREM and using atomically sharp CeO2 ridges as tip characterizer［J］.Langmuir, 2000, 16(6):6267-6277.
［2］Ho H J. Near-contact mode: a novel AFM operation mode for nondestructive ultrahigh lateral-resolution topography measurement in air［J］. Materials and Device Characterization in Micromachining, 1998, (9):40-53.
［3］Bernal R A, Chen P L, Schall J D, et al. Influence of chemical bonding on the variability of diamondlike carbon nanoscale adhesion［J］.Carbon,2018,128(2):267- 276.
［4］何志坚,周志雄,黄向明. 基于变分模态分解的关联维数及相关向量机的刀具磨损状态监测［J］. 计量学报, 2018, 39(2):182-186.
He Z J, Zhou Z X, Huang X M. Tool wear state monitoring based on variational mode decomposition and correlation dimension and relevance vector machine［J］. Acta Metrologica Sinica, 2018,39(2):182-186.
［5］Malakizadi A, Gruber H , Sadik I, et al. An FEMbased approach for tool wear estimation in machining［J］.Wear, 2016, 368-369(12):10-24.
［6］Yena Y C, Shnerb J , Lillya B, et al. Estimation of tool wear in orthogonal cutting using the finite element analysis［J］.Journal of Materials Processing Technology, 2004, 146(1):82-91.
［7］朱坚民, 赵全龙, 何丹丹. 基于奇异值分解和灰靶决策的车刀磨损状态判别［J］. 计量学报, 2017, 38(2):189-192.
Zhu J M, Zhao Q L, He D D. Wear condition recognition of lathe tool based on singular value decomposition and grey target decision methods［J］. Acta Metrologica Sinica, 2017,38(2):189-192.
［8］Cheng F, Dong J Y. Monitoring tip-based nanomachining process by time series analysis using support vector machine ［J］. Journal of Manufacturing Processes, 2019, 38(1):158-166.
［9］Bukkapatnam S T S, Cheng C. Forecasting the evolution of nonlinear and nonstationary systems using recurrence-based local Gaussian process models［J］. Phys Rev E Stat Nonlin Soft Matter Phys, 2010, 82(5):1-12.
［10］ Wang Z M, Bukkapatnam S T S, Kumara S R T, et al. Change detection in precision manufacturing processes under transient conditions［J］. CIRP AnnalsManufacturing Technology, 2014, 63(1):449-452.
［11］Zhang G L, Dong J Y. High-rate tunable ultrasonic force regulated nanomachining lithography with an atomic force microscope［J］. Nanotechnology, 2013, 23(8):1-8.
［12］Deng J, Zhang L, Dong J Y, et al. AFMbased 3D nanofabrication using ultrasonic vibration assisted nanomachining［J］. Journal of Manufacturing Processes, 2016, 24(10):195-202.
［13］Zhang L, Dong J Y, Cohen P H. Materialinsensitive feature depth control and machining force reduction by ultrasonic vibration in AFMbased nanomachining［J］. IEEE Transactions on Nanotechnology, 2013, 12(5):743-750.
［14］Yamanaka K, Ogiso H, Kolosov O. Ultrasonic force microscopy for nanometer resolution subsurface imaging［J］. Applied Physics Letters, 1994, 64(2):178-180.
［15］Kong X C, Dong J Y, Cohen P H. Modeling of the dynamic machining force of vibration-assisted nanomachining process［J］. Journal of Manufacturing Processes, 2017 , 28(8):101-108.
［16］Deng J, Dong J Y, Cohen P H. Development and characterization of ultrasonic vibration assisted nanomachining process for three-dimensional nanofabrication［J］. IEEE Transactions on Nanotechnology, 2018, 17(3):559-566.
［17］ PlattJ C, Cristianini N, Shawe-Taylor J. Large margin DAGs for multiclass classification［C］//Advances in Neural Information Processing Systems 12(NIPS1999), 547-553, Denver, USA,1999.
［18］ Hsu C W, Lin C J. A Comparison of Methods for Multi-class Support Vector Machines［J］. IEEE Transactions on Neural Networks, 2002, 13(2):415-425.
2019, Vol. 40 
