0
Research Papers

Surface Variation Modeling by Fusing Multiresolution Spatially Nonstationary Data Under a Transfer Learning Framework

[+] Author and Article Information
Jie Ren

Department of Industrial and
Manufacturing Engineering,
Florida A&M University-Florida State
University College of Engineering,
Tallahassee, FL 32310

Hui Wang

Department of Industrial and
Manufacturing Engineering,
Florida A&M University-Florida State
University College of Engineering,
Tallahassee, FL 32310
e-mail: hwang10@fsu.edu

1Corresponding author.

Manuscript received January 15, 2018; final manuscript received September 6, 2018; published online October 10, 2018. Assoc. Editor: Laine Mears.

J. Manuf. Sci. Eng 141(1), 011002 (Oct 10, 2018) (11 pages) Paper No: MANU-18-1031; doi: 10.1115/1.4041425 History: Received January 15, 2018; Revised September 06, 2018

High-definition metrology (HDM) has gained significant attention for surface quality inspection since it can reveal spatial surface variations in detail. Due to its cost and durability, such HDM measurements are occasionally implemented. The limitation creates a new research opportunity to improve surface variation characterization by fusing the insights gained from limited HDM data with widely available low-resolution surface data during quality inspections. A useful insight from state-of-the-art research using HDM is the revealed relationship and positive correlation between surface height and certain measurable covariates, such as material removal rate (MRR). Such a relationship was assumed spatially constant and integrated with surface measurements to improve surface quality modeling. However, this method encounters challenges when the covariates have nonstationary relationships with the surface height over different surface areas, i.e., the covariate-surface height relationship is spatially varying. Additionally, the nonstationary relationship can only be captured by HDM, adding to the challenge of surface modeling when most training data are measured at low resolution. This paper proposes a transfer learning (TL) framework to deal with these challenges by which the common information from a spatial model of an HDM-measured surface is transferred to a new surface where only low-resolution data are available. Under this framework, the paper develops and compares three surface models to characterize the nonstationary relationship including two varying coefficient-based spatial models and an inference rule-based spatial model. Real-world case studies were conducted to demonstrate the proposed methods for improving surface modeling.

FIGURES IN THIS ARTICLE
<>
Copyright © 2019 by ASME
Topics: Modeling , Algorithms
Your Session has timed out. Please sign back in to continue.

References

Nguyen, H. T. , Wang, H. , Tai, B. L. , Ren, J. , Hu, S. J. , and Shih, A. , 2016, “ High-Definition Metrology Enabled Surface Variation Control by Cutting Load Balancing,” ASME J. Manuf. Sci. Eng., 138(2), p. 021010. http://manufacturingscience.asmedigitalcollection.asme.org/article.aspx?articleid=2442384
Ren, J. , Park, C. , and Wang, H. , 2018, “ Stochastic Modeling and Diagnosis of Leak Areas for Surface Assembly,” ASME J. Manuf. Sci. Eng., 140(4), p. 041011. [CrossRef]
Shao, Y. , Yin, Y. , Du, S. , Xia, T. , and Xi, L. , 2018, “ Leakage Monitoring in Static Sealing Interface Based on Three Dimensional Surface Topography Indicator,” ASME J. Manuf. Sci. Eng., 140(10), p. 101003. [CrossRef]
Du, S. , Liu, C. , and Xi, L. , 2015, “ A Selective Multiclass Support Vector Machine Ensemble Classifier for Engineering Surface Classification Using High Definition Metrology,” ASME J. Manuf. Sci. Eng., 137(1), p. 011003. [CrossRef]
Wells, L. J. , Shafae, M. S. , and Camelio, J. A. , 2016, “ Automated Surface Defect Detection Using High-Density Data,” ASME J. Manuf. Sci. Eng., 138(7), p. 071001. [CrossRef]
Zhu, X. , Ding, H. , and Wang, M. Y. , 2004, “ Form Error Evaluation: An Iterative Reweighted Least Squares Algorithm,” ASME J. Manuf. Sci. Eng., 126(3), pp. 535–541. [CrossRef]
Yang, B.-D. , and Menq, C.-H. , 1993, “ Compensation for Form Error of End-Milled Sculptured Surfaces Using Discrete Measurement Data,” Int. J. Mach. Tools Manuf., 33(5), pp. 725–740. [CrossRef]
Grove, D. M. , Woods, D. C. , and Lewis, S. M. , 2004, “ Multifactor b-Spline Mixed Models in Designed Experiments for the Engine Mapping Problem,” J. Qual. Technol., 36(4), pp. 380–391. [CrossRef]
Jung, H. , and Kim, K. , 2000, “ A New Parameterisation Method for Nurbs Surface Interpolation,” Int. J. Adv. Manuf. Technol., 16(11), pp. 784–790. [CrossRef]
Suriano, S. , Wang, H. , and Hu, S. J. , 2012, “ Sequential Monitoring of Surface Spatial Variation in Automotive Machining Processes Based on High Definition Metrology,” J. Manuf. Syst., 31(1), pp. 8–14. [CrossRef]
Yang, T.-H. , and Jackman, J. , 2000, “ Form Error Estimation Using Spatial Statistics,” ASME J. Manuf. Sci. Eng., 122(1), pp. 262–272. [CrossRef]
Xia, H. , Ding, Y. , and Wang, J. , 2008, “ Gaussian Process Method for Form Error Assessment Using Coordinate Measurements,” IIE Trans., 40(10), pp. 931–946. https://www.tandfonline.com/doi/abs/10.1080/07408170801971502
Jin, R. , Chang, C.-J. , and Shi, J. , 2012, “ Sequential Measurement Strategy for Wafer Geometric Profile Estimation,” IIE Trans., 44(1), pp. 1–12. [CrossRef]
Yang, Y. , and Shao, C. , 2018, “ Spatial Interpolation for Periodic Surfaces in Manufacturing Using a Bessel Additive Variogram Model,” ASME J. Manuf. Sci. Eng., 140(6), p. 061001. [CrossRef]
Nguyen, H. T. , Wang, H. , and Hu, S. J. , 2013, “ Characterization of Cutting Force Induced Surface Shape Variation in Face Milling Using High-Definition Metrology,” ASME J. Manuf. Sci. Eng., 135(4), p. 041014. [CrossRef]
Suriano, S. , Wang, H. , Shao, C. , Hu, S. J. , and Sekhar, P. , 2015, “ Progressive Measurement and Monitoring for Multi-Resolution Data in Surface Manufacturing Considering Spatial and Cross Correlations,” IIE Trans., 47(10), pp. 1033–1052. [CrossRef]
Shao, C. , Ren, J. , Wang, H. , Jin, J. J. , and Hu, S. J. , 2017, “ Improving Machined Surface Shape Prediction by Integrating Multi-Task Learning With Cutting Force Variation Modeling,” ASME J. Manuf. Sci. Eng., 139(1), p. 011014. https://manufacturingscience.asmedigitalcollection.asme.org/article.aspx?articleID=2551758
Du, S. , and Fei, L. , 2016, “ Co-Kriging Method for Form Error Estimation Incorporating Condition Variable Measurements,” ASME J. Manuf. Sci. Eng., 138(4), p. 041003. http://manufacturingscience.asmedigitalcollection.asme.org/article.aspx?articleid=2499928
Cheng, C. , Sa-Ngasoongsong, A. , Beyca, O. , Le, T. , Yang, H. , Kong, Z. , and Bukkapatnam, S. T. , 2015, “ Time Series Forecasting for Nonlinear and Non-Stationary Processes: A Review and Comparative Study,” IIE Trans., 47(10), pp. 1053–1071. [CrossRef]
Pan, S. J. , and Yang, Q. , 2010, “ A Survey on Transfer Learning,” IEEE Trans. Knowl. Data Eng., 22(10), pp. 1345–1359. [CrossRef]
Duvenaud, D. K. , Nickisch, H. , and Rasmussen, C. E. , 2011, “ Additive Gaussian Processes,” Advances in Neural Information Processing Systems, pp. 226–234.
Rue, H. , and Held, L. , 2005, Gaussian Markov Random Fields: Theory and Applications, CRC Press, Boca Raton, FL.
Fotheringham, A. S. , Brunsdon, C. , and Charlton, M. , 2002, Geographically Weighted Regression: The Analysis of Spatially Varying Relationships, Wiley, New York.
Hoerl, A. E. , and Kennard, R. W. , 1970, “ Ridge Regression: Biased Estimation for Nonorthogonal Problems,” Technometrics, 12(1), pp. 55–67. [CrossRef]
Zou, H. , and Hastie, T. , 2005, “ Regularization and Variable Selection Via the Elastic Net,” J. R. Stat. Soc.: Ser. B (Stat. Methodol.), 67(2), pp. 301–320. [CrossRef]
Rasmussen, C. E. , 2004, “ Gaussian Processes in Machine Learning,” Advanced Lectures on Machine Learning, Springer, Berlin, pp. 63–71.
Gramacy, R. B. , and Lee, H. K. H. , 2008, “ Bayesian Treed Gaussian Process Models With an Application to Computer Modeling,” J. Am. Stat. Assoc., 103(483), pp. 1119–1130. [CrossRef]
Breiman, L. , 2017, Classification and Regression Trees, Routledge, New York.
Acharya, J. , Diakonikolas, I. , Li, J. , and Schmidt, L. , 2016, “ Fast Algorithms for Segmented Regression,” 33rd International Conference on Machine Learning (ICML), New York, June 19–24, pp. 2878–2886.
Lih, W.-C. , Bukkapatnam, S. T. , Rao, P. , Chandrasekharan, N. , and Komanduri, R. , 2008, “ Adaptive Neuro-Fuzzy Inference System Modeling of MRR and WIWNU in CMP Process With Sparse Experimental Data,” IEEE Trans. Autom. Sci. Eng., 5(1), pp. 71–83. [CrossRef]
Hosseini, M. S. , and Zekri, M. , 2012, “ Review of Medical Image Classification Using the Adaptive Neuro-Fuzzy Inference System,” J. Med. Signals Sens., 2(1), pp. 49–60. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3592505/ [PubMed]
Cabalar, A. F. , Cevik, A. , and Gokceoglu, C. , 2012, “ Some Applications of Adaptive Neuro-Fuzzy Inference System (ANFIS) in Geotechnical Engineering,” Comput. Geotech., 40, pp. 14–33. [CrossRef]
Chang, S. , and Aw, C. , 1996, “ A Neural Fuzzy Control Chart for Detecting and Classifying Process Mean Shifts,” Int. J. Prod. Res., 34(8), pp. 2265–2278. [CrossRef]
Mesina, O. S. , and Langari, R. , 2001, “ A Neuro-Fuzzy System for Tool Condition Monitoring in Metal Cutting,” ASME J. Manuf. Sci. Eng., 123(2), pp. 312–318. [CrossRef]
Ubaid, A. M. , Dweiri, F. T. , Aghdeab, S. H. , and Al-Juboori, L. A. , 2018, “ Optimization of Electro Discharge Machining Process Parameters With Fuzzy Logic for Stainless Steel 304 (ASTM A240),” ASME J. Manuf. Sci. Eng., 140(1), p. 011013. [CrossRef]
Aguilar, L. , Melin, P. , and Castillo, O. , 2003, “ Intelligent Control of a Stepping Motor Drive Using a Hybrid Neuro-Fuzzy ANFIS Approach,” Appl. Soft Comput., 3(3), pp. 209–219. [CrossRef]
Ou, X. , Arinez, J. , Chang, Q. , and Xiao, G. , 2017, “ Cost Analysis and Fuzzy Control for Collapsible Container Usage Based on Closed-Loop Supply Chain Model,” ASME J. Manuf. Sci. Eng., 139(8), p. 081005. [CrossRef]
Wang, L.-X. , and Mendel, J. M. , 1992, “ Back-Propagation Fuzzy System as Nonlinear Dynamic System Identifiers,” IEEE International Conference on Fuzzy Systems, San Diego, CA, Mar. 8–12, pp. 1409–1418.
Yager, R. R. , and Filev, D. P. , 1994, “ Generation of Fuzzy Rules by Mountain Clustering,” J. Intell. Fuzzy Syst.: Appl. Eng. Technol., 2(3), pp. 209–219.
Takagi, T. , and Sugeno, M. , 1985, “ Fuzzy Identification of Systems and Its Applications to Modeling and Control,” IEEE Trans. Syst. Man Cybern., (1), pp. 116–132.
Chiu, S. L. , 1994, “ Fuzzy Model Identification Based on Cluster Estimation,” J. Intell. Fuzzy Syst., 2(3), pp. 267–278.
Jang, J.-S. R. , 1991, “ Fuzzy Modeling Using Generalized Neural Networks and Kalman Filter Algorithm,” AAAI J., 2, pp. 762–767.
Jang, J.-S. R. , 1993, “ ANFIS: Adaptive-Network-Based Fuzzy Inference System,” IEEE Trans. Syst. Man Cybern., 23(3), pp. 665–685. [CrossRef]
Chiu, S. L. , 1996, “ Selecting Input Variables for Fuzzy Models,” J. Intell. Fuzzy Syst., 4(4), pp. 243–256.
Xia, H. , Ding, Y. , and Mallick, B. K. , 2011, “ Bayesian Hierarchical Model for Combining Misaligned Two-Resolution Metrology Data,” IIE Trans., 43(4), pp. 242–258. [CrossRef]

Figures

Grahic Jump Location
Fig. 1

Profilometer measurements on surface roughness and CMM measurements on surface flatness

Grahic Jump Location
Fig. 2

An outline of the research problem formulation for HDM-based surface variation modeling

Grahic Jump Location
Fig. 3

Correlation between process variables and surface height: (a) two directions while cutting; (b) normalized MRR and its relation with surface variation; and (c) cutter insert engagement with surface and its impact on surface height

Grahic Jump Location
Fig. 4

Varying model coefficients of two engine head surfaces: (a) coefficient c1 of surface I and (b) coefficient c1 of surface II

Grahic Jump Location
Fig. 5

Takagi-Sugeno fuzzy rules. Adapted from [44].

Grahic Jump Location
Fig. 6

Architecture of ANFIS and tl-ANFIS

Grahic Jump Location
Fig. 7

Logic of transfer learning (TL)-based spatial modeling for an engine head surface: (a) HDM measurements for surface I (partial enlarged detail shown in the box); (b) normalized MRR for surface I; (c) LDM measurements for surface II; (d) normalized MRR for surface II; and (e) modeling of surface II using TL-based spatial model (partial enlarged detail shown in the box)

Grahic Jump Location
Fig. 8

Modeling results of tail sections on surface II versus true data for the engine head deck face. It can be seen that the proposed methods (b) and (d) achieve an estimation closer to the true data (a) compared with a state-of-the-art method (e) and a commonly used method (f). Method (c) estimates bad at the left tail section.

Grahic Jump Location
Fig. 9

Logic of TL-based spatial modeling for the block surface: (a) HDM measurements for block I; (b) normalized MRR and the number of insert-engagement for block I; (c) LDM measurements for block II; (d) normalized MRR and the number of insert-engagement for block II; and (e) modeling of block II using TL-based spatial model

Grahic Jump Location
Fig. 10

Surface modeling results for block II. The results show that the proposed tl-GWR (b), tl-RR(c), and tl-ANFIS (d) achieve the estimation closer to the true data (a) compared with a state-of-the-art method (e) and a commonly used method (f).

Tables

Errata

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In