Skip to main content
SpringerLink
Log in

A deep transfer learning model based on pockets clustering and feature reconstruction for dimensional accuracy forecast in aerospace skin parts manufacturing

  • ORIGINAL ARTICLE
  • Published:
The International Journal of Advanced Manufacturing Technology Aims and scope Submit manuscript

Abstract

Skin parts are widely used in the modern aerospace industry. The remaining wall thickness of pockets on a skin part must be precisely controlled to reduce overall weight and ensure strength. The in-process dimensional accuracy forecast of remaining wall thickness is urgently required for process efficiency improvement and compensation. In this paper, the spindle power signal of pocket milling is used for the in-process dimensional accuracy forecast. Based on deep learning mothed, the correlation between dimensional accuracy and features extracted from power signal is established. To improve the applicability of the forecast model, a deep transfer learning model based on pockets clustering and feature reconstruction is proposed. The pockets of a skin part are divided into different types through clustering. Then, the trained deep learning network for feature extraction of one type of pocket is transferred to a new type by feature reconstruction. The results indicate that the deep transfer learning model can achieve in-process dimensional accuracy forecast for remaining wall thickness with high precision.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15

Similar content being viewed by others

Data availability

Not applicable.

References

  1. Wang XZ, Bi QZ, Zhu LM, Ding H (2018) Improved forecasting compensatory control to guarantee the remaining wall thickness for pocket milling of a large thin-walled part. Int J Adv Manuf Technol 94:1677–1688. https://doi.org/10.1007/s00170-016-9785-8

    Article  Google Scholar 

  2. Chen ZY, Wang LP, Zhang JB, Guo GQ, Fu SL, Wang C, Li XK (2020) Framework and development of data-driven physics based model with application in dimensional accuracy prediction in pocket milling. Chinese J Aeronaut 34(6):162–177. https://doi.org/10.1016/j.cja.2020.09.011

    Article  Google Scholar 

  3. Kline WA, Devor RE, Shareef IA (1982) The prediction of surface accuracy in end milling. J Eng Ind Trans ASME 104(3):272–278. https://doi.org/10.1115/1.3185830

    Article  Google Scholar 

  4. Sutherland JW, Devor RE (1986) An improved method for cutting force and surface error prediction in flexible end milling systems. J Eng Ind Trans ASME 108(4):269–279. https://doi.org/10.1115/1.3187077

    Article  Google Scholar 

  5. Tsai JS, Liao CL (1999) Finite-element modeling of static surface errors in the peripheral milling of thin-walled workpieces. J Mater Process Tech 94(2–3):235–246. https://doi.org/10.1016/S0924-0136(99)00109-0

    Article  Google Scholar 

  6. Wan M, Zhang WH, Qiu KP, Gao T, Yang YH (2005) Numerical prediction of static form errors in peripheral milling of thin-walled workpieces with irregular meshes. J Manuf Sci E T ASME 127(1):13–22. https://doi.org/10.1115/1.1828055

    Article  Google Scholar 

  7. Kang YG, Wang ZQ (2013) Two efficient iterative algorithms for error prediction in peripheral milling of thin-walled workpieces considering the in-cutting chip. Int J Mach Tool Manu 73(73):55–61. https://doi.org/10.1016/j.ijmachtools.2013.06.001

    Article  Google Scholar 

  8. Ratchev S, Liu SL, Wei H, Becker AA (2007) Machining simulation and system integration combining FE analysis and cutting mechanics modelling. Int J Adv Manuf Tech 35(1–2):55. https://doi.org/10.1007/s00170-006-0700-6

    Article  Google Scholar 

  9. Wan M, Zhang WH (2006) Efficient algorithms for calculations of static form errors in peripheral milling. J Mater Process Tech 171(1):156–165. https://doi.org/10.1016/j.jmatprotec.2005.07.001

    Article  Google Scholar 

  10. Wang L, Si H (2018) Machining deformation prediction of thin-walled workpieces in five-axis flank milling. Int J Adv Manuf Tech 97:4179–4193. https://doi.org/10.1007/s00170-018-2248-7

    Article  Google Scholar 

  11. Li ZL, Tuysuz O, Zhu LM, Altintas Y (2018) Surface form error prediction in five-axis flank milling of thin-walled parts. J Mach Tool Manu 2018:S0890695518300300. https://doi.org/10.1016/j.ijmachtools.2018.01.005

    Article  Google Scholar 

  12. Li WT, Wang LP, Ge SY (2021) Force-induced deformation prediction and flexible error compensation strategy in flank milling of thin-walled parts. J Mater Process Tech 297:117258. https://doi.org/10.1016/j.jmatprotec.2021.117258

    Article  Google Scholar 

  13. Si H, Wang LP (2018) Error compensation in the five-axis flank milling of thin-walled workpieces. P I Mech Eng B-J Eng 233(2):095440541878016. https://doi.org/10.1177/0954405418780163

    Article  MathSciNet  Google Scholar 

  14. Gao YY, Ma JW, Jia ZY, Wang FJ, Si LK, Song DN (2016) Tool path planning and machining deformation compensation in high-speed milling for difficult-to-machine material thin-walled parts with curved surface. Int J Adv Manuf Tech 84(9–12):1757–1767. https://doi.org/10.1007/s00170-015-7825-4

    Article  Google Scholar 

  15. Wang MH, Sun Y (2014) Error prediction and compensation based on interference-free tool paths in blade milling. Int J Adv Manuf Tech 71(5–8):1309–1318. https://doi.org/10.1007/s00170-013-5535-3

    Article  Google Scholar 

  16. Li SM (2020) Research on error compensation method of on-machine measurement system in five axis CNC machine tool. Dissertation, Tsinghua University

  17. Bi QZ, Wang XZ, Wu Q, Zhu LM, Ding H (2018) Fv-SVM-based wall-thickness error decomposition for adaptive machining of large skin parts. IEEE T Ind Inform 15(4):2426–2434. https://doi.org/10.1109/TII.2018.2879500

    Article  Google Scholar 

  18. Wang JJ, Ma YL, Zhang LB, Gao RX, Wu DZ (2018) Deep learning for smart manufacturing: Methods and applications. J Manuf Syst 48(pt.C):144–156. https://doi.org/10.1016/j.jmsy.2018.01.003

  19. Lu C, Wang ZY, Qin WL, Ma J (2017) Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification. Signal Process 130:377–388. https://doi.org/10.1016/j.sigpro.2016.07.028

    Article  Google Scholar 

  20. Sun WJ, Shao SY, Zhao R, Yan RQ, Zhang XW, Chen XF (2016) A sparse auto-encoder-based deep neural network approach for induction motor faults classification. Measurement 89:171–178. https://doi.org/10.1016/j.measurement.2016.04.007

    Article  Google Scholar 

  21. Shao HD, Jiang HK, Wang F, Zhao HW (2017) An enhancement deep feature fusion method for rotating machinery fault diagnosis. Knowl-Based Syst 119:200–220. https://doi.org/10.1016/j.knosys.2016.12.012

    Article  Google Scholar 

  22. Chen YX, Jin Y, Jiri G (2018) Predicting tool wear with multi-sensor data using deep belief networks. Int J Adv Manuf Technol 99:1917–1926. https://doi.org/10.1007/s00170-018-2571-z

    Article  Google Scholar 

  23. Yin JT, Zhao WT (2016) Fault diagnosis network design for vehicle on-board equipments of high-speed railway: a deep learning approach. Eng Appl Artif Intel 56:250–259. https://doi.org/10.1016/j.engappai.2016.10.002

    Article  Google Scholar 

  24. Liang MX, Cao P, Tang J (2021) Rolling bearing fault diagnosis based on feature fusion with parallel convolutional neural network. Int J Adv Manuf Technol 112:819–831. https://doi.org/10.1007/s00170-020-06401-8

    Article  Google Scholar 

  25. Shao SY, Yan RQ, Lu YD, Wang P, Gao RX (2020) DCNN-based multi-signal induction motor fault diagnosis. IEEE T Instrum Meas 69(6):2658–2669. https://doi.org/10.1109/TIM.2019.2925247

    Article  Google Scholar 

  26. Zhao R, Yan RQ, Wang JJ, Mao KZ (2017) Learning to monitor machine health with convolutional bi-directional LSTM networks. Sensors 17(2):273. https://doi.org/10.3390/s17020273

    Article  Google Scholar 

  27. Zhao ZW, Li YG, Liu CQ, Gao J (2020) On-line part deformation prediction based on deep learning. J Intell Manuf 31:561–574. https://doi.org/10.1007/s10845-019-01465-0

    Article  Google Scholar 

  28. Luan XN, Zhang S, Li G (2018) Modified power prediction model based on infinitesimal cutting force during face milling process. Int J Pr Eng Man-GT 5:71–80. https://doi.org/10.1007/s40684-018-0008-7

    Article  Google Scholar 

  29. Pan YN, Kang RK, Dong ZG, Du WH, Yin S, Bao Y (2020) On-line prediction of ultrasonic elliptical vibration cutting surface roughness of tungsten heavy alloy based on deep learning. J Intell Manuf. https://doi.org/10.1007/s10845-020-01669-9

    Article  Google Scholar 

  30. Wen L, Gao L, Li XY (2019) A new deep transfer learning based on sparse auto-encoder for fault diagnosis. IEEE T Syst Man Cy-S 49(1):136–144. https://doi.org/10.1109/TSMC.2017.2754287

    Article  Google Scholar 

  31. Zhao K, Jiang HK, Wu ZH, Lu TF (2020) A novel transfer learning fault diagnosis method based on Manifold Embedded Distribution Alignment with a little labeled data. J Intell Manuf 2:1–15. https://doi.org/10.1007/s10845-020-01657-z

    Article  Google Scholar 

  32. Wang JC, Zou B, Liu MF, Li YS, Ding HJ, Xue K (2021) Milling force prediction model based on transfer learning and neural network. J Intell Manuf 32:947–956. https://doi.org/10.1007/s10845-020-01595-w

    Article  Google Scholar 

  33. Sun C, Ma M, Zhao ZB, Tian SH, Yan RQ, Chen XF (2019) Deep transfer learning based on sparse autoencoder for remaining useful life prediction of tool in manufacturing. IEEE T Ind Inform 15(4):2416–2425. https://doi.org/10.1109/TII.2018.2881543

    Article  Google Scholar 

  34. Luo WC, Hu TL, Ye YX, Zhang CR, Wei YL (2020) A hybrid predictive maintenance approach for CNC machine tool driven by Digital Twin. Robot Cim-Int Manuf 65:101974. https://doi.org/10.1016/j.rcim.2020.101974

    Article  Google Scholar 

Download references

Funding

The research is supported by the State Key Lab of Tribology, Tsinghua University, China (SKLT2021D16), and the National Natural Science Foundation of China (51975319).

Author information

Authors and Affiliations

  1. Department of Mechanical Engineering, Tsinghua University, Beijing, 100084, China

    Liping Wang, Shuailei Fu, Dong Wang, Chao Wang, Zhanying Chen, Yun Zhang & Xuekun Li

  2. State Key Lab of Tribology, Tsinghua University, Beijing, 100084, China

    Liping Wang & Xuekun Li

  3. Beijing Key Lab of Precision/Ultra-precision Manufacturing Equipment and Control, Tsinghua University, 100084, Beijing, China

    Liping Wang, Dong Wang & Xuekun Li

Authors
  1. Liping Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shuailei Fu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Dong Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Chao Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zhanying Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Yun Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Xuekun Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Contributions: Authors 1 and 2 developed the algorithm, performed experiments, and drafted the manuscript. Authors 4 and 5 developed the data acquisition system used in experiments and contributed to the analysis of the results. Authors 3, 6, and 7 contributed to the writing and editing of the manuscript.

Corresponding author

Correspondence to Xuekun Li.

Ethics declarations

Ethics approval

Not applicable.

Consent to participate

Not applicable.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, L., Fu, S., Wang, D. et al. A deep transfer learning model based on pockets clustering and feature reconstruction for dimensional accuracy forecast in aerospace skin parts manufacturing. Int J Adv Manuf Technol 122, 1009–1021 (2022). https://doi.org/10.1007/s00170-022-09909-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00170-022-09909-3

Keywords

Search

Navigation