Multi-feature spatial distribution alignment enhanced domain adaptive method for tool condition monitoring

• Autorzy: Hei Zhendong , Sun Bintao , Wang Gaonghai , Lou Yongjian , Yuqing Zhou

Identyfikatory

DOI

10.17531/ein/171750

• Języki publikacji: EN

Abstrakty

EN

Transfer learning (TL) has been successfully implemented in tool condition monitoring (TCM) to address the lack of labeled data in real industrial scenarios. In current TL models, the domain offset in the joint distribution of input feature and output label still exists after the feature distribution of the two domains is aligned, resulting in performance degradation. A multiple feature spatial distribution alignment (MSDA) method is proposed, Including Correlation alignment for deep domain adaptation (DeepCORAL) and Joint maximum mean difference (JMMD). Deep CORAL is employed to learn nonlinear transformations, align source and target domains at the feature level through the second-order statistical correlations. JMMD is applied to improve domain alignmentby aligning the joint distribution of input features and output labels. ResNet18 combining with bidirectional short-term memory network and attention mechanism is developed to extract the invariant features. TCM experiments with four transfer tasks were conducted and demonstrated the effectiveness of the proposed method.

Słowa kluczowe

EN

condition monitoring; Transfer learning; correlation alignment; joint maximum mean difference; feature extractor

• Wydawca: Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne
• Czasopismo: Eksploatacja i Niezawodność
• Rocznik: 2023
• Tom: Vol. 25, no. 4
• Strony: art. no. 171750
• Opis fizyczny: Bibliogr. 43 poz., rys., tab., wykr.

Twórcy

autor

Hei Zhendong

• College of mechanical and electrical engineering, Wenzhou University, China

• https://orcid.org/0009-0002-4591-4968

autor

Sun Bintao

• College of mechanical and electrical engineering, Wenzhou University, China

• https://orcid.org/0000-0003-2688-6949

autor

Wang Gaonghai

• College of mechanical and electrical engineering, Jiaxing Nanhu University, China

• https://orcid.org/0000-0003-1581-6267

autor

Lou Yongjian

• College of mechanical and electrical engineering, Jiaxing Nanhu University, China

autor

Yuqing Zhou

• College of mechanical and electrical engineering, Wenzhou University, China
• College of mechanical and electrical engineering, Jiaxing Nanhu University, China

• https://orcid.org/0000-0002-8580-5427

Bibliografia

• 1. Ahmad M A F, Nuawi M Z, et al. Tool wear monitoring using macro fibre composite as a vibration sensor via I-kaz statistical signal analysis. ARPN Journal of Engineering and Applied Sciences, 2018, 13(11): p. 3607-3616.
• 2. Ben-David, S., et al., A theory of learning from different domains. Machine learning, 2010. 79: p. 151-175. https://doi.org/10.1007/s10994-009-5152-4
• 3. Chen, K., et al., Short-term load forecasting with deep residual networks. IEEE Transactions on Smart Grid, 2018. 10(4): p. 3943-3952. https://doi.org/10.1109/TSG.2018.2844307
• 4. Chen, W., et al., Diagnosis of wind turbine faults with transfer learning algorithms. Renewable Energy, 2021. 163: p. 2053-2067. https://doi.org/10.1016/j.renene.2020.10.121
• 5. Cheng, M., et al., Intelligent tool wear monitoring and multi-step prediction based on deep learning model. Journal of Manufacturing Systems, 2022. 62: p. 286-300. https://doi.org/10.1016/j.jmsy.2021.12.002
• 6. Dimla Sr, D. and P.M. Lister, On-line metal cutting tool condition monitoring.: I: force and vibration analyses. International Journal of Machine Tools and Manufacture, 2000. 40(5): p. 739-768. , https://doi.org/10.1016/S0890-6955(99)00085-1
• 7. Donoho, D.L., De-noising by soft-thresholding. IEEE transactions on information theory, 1995. 41(3): p. 613-627. https://doi.org/10.1109/18.382009
• 8. G. Vetrichelvan, S. Sundaram, S.S. Kumaran, P. Velmurugan, An investigation of tool wear using acoustic emission and genetic algorithm, J. Vib. Control 2014; 21(15): 3061-3066, https://doi.org/10.1177/1077546314520835 .
• 9. Ganin, Y. and V. Lempitsky. Unsupervised domain adaptation by backpropagation. in International conference on machine learning. 2015. PMLR.
• 10. Gretton, A., et al., Optimal kernel choice for large-scale two-sample tests. Advances in neural information processing systems, 2012. 25.
• 11. Guan, S., W. Song, and H. Pang. Tool Wear Feature Extraction Based on Hilbert Marginal Spectrum. in IOP Conference Series: Materials Science and Engineering. 2017. IOP Publishing. https://doi.org/10.1088/1757-899X/230/1/012049
• 12. Gudelek M U, et al. An industrially viable wavelet long-short term memory-deep multilayer perceptron-based approach to tool condition monitoring considering operational variability. Proceedings of the Institution of Mechanical Engineers. Journal of ProcessMechanical Engineering, 2022. https://doi.org/10.1177/09544089221142161
• 13. Hahn, T.V. and C.K. Mechefske, Self-supervised learning for tool wear monitoring with a disentangled-variational-autoencoder. International Journal of Hydromechatronics, 2021. 4(1): p. 69-98. https://doi.org/10.1504/IJHM.2021.114174
• 14. He, K., et al. Deep residual learning for image recognition. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. https://doi.org/10.1109/CVPR.2016.90
• 15. He, Z., et al., Ensemble transfer CNNs driven by multi-channel signals for fault diagnosis of rotating machinery cross working conditions. Knowledge-Based Systems, 2020. 207: p. 106396. https://doi.org/10.1016/j.knosys.2020.106396
• 16. Huang, J., et al., Geometric deep learning for shape correspondence in mass customization by three-dimensional printing. Journal of Manufacturing Science and Engineering, 2020. 142(6): p. 061003. https://doi.org/10.1115/1.4046746
• 17. Jamshidi M, Chatelain J F, et al. Tool condition monitoring using machine tool spindle electric current and multiscale analysis while milling steel alloy. Journal of Manufacturing and Materials Processing, 2022, 6(5): p. 115. https://doi.org/10.3390/jmmp6050115
• 18. Javed, K., et al., Tool wear monitoring and prognostics challenges: a comparison of connectionist methods toward an adaptive ensemble model. Journal of Intelligent Manufacturing, 2018. 29: p. 1873-1890. https://doi.org/10.1007/s10845-016-1221-2
• 19. Kasim N A, Nuawi M Z, et al. Cutting tool wear progression index via signal element variance. Journal of mechanical engineering and sciences, 2019. 13(1): p. 4596–4612. https://doi.org/10.15282/jmes.13.1.2019.17.0387
• 20. Kasim N A, Nuawi M Z, et al. Enhancing Clustering Algorithm with Initial Centroids in Tool Wear Region Recognition. International Journal of Precision Engineering and Manufacturing, 2021, 22: p. 843-863. https://doi.org/10.1007/s12541-020-00450-5
• 21. Kumar, A., et al., Sparse transfer learning for identifying rotor and gear defects in the mechanical machinery. Measurement, 2021. 179: p. 109494. https://doi.org/10.1016/j.measurement.2021.109494
• 22. 2.Li, C., et al., Novel environmentally friendly manufacturing method for micro-textured cutting tools. International Journal of Precision Engineering and Manufacturing-Green Technology, 2021. 8: p. 193-204, https://doi.org/10.1007/s40684-020-00256-w.
• 23. Li, X. and W. Zhang, Deep learning-based partial domain adaptation method on intelligent machinery fault diagnostics. IEEE Transactions on Industrial Electronics, 2020. 68(5): p. 4351-4361. https://doi.org/10.1109/TIE.2020.2984968
• 24. Li, Y., et al., A novel method for accurately monitoring and predicting tool wear under varying cutting conditions based on meta-learning. CIRP annals 2019; 68(1): 487-490. https://doi.org/10.1016/j.cirp.2019.03.010
• 25. Long, M., et al. Deep transfer learning with joint adaptation networks. in International conference on machine learning. 2017. PMLR.
• 26. Long, M., et al. Learning transferable features with deep adaptation networks. in International conference on machine learning. 2015. PMLR.
• 27. Marei M, El Zaatari, and W. Li. Transfer learning enabled convolutional neural networks for estimating health state of cutting tools. Robotics and Computer-Integrated Manufacturing, 2021, 71: p. 102145. https://doi.org/10.1016/j.rcim.2021.102145
• 28. Nawrocki W, Stryjski R, Kostrzewski M, et al. Application of the vibro-acoustic signal to evaluate wear in the spindle bearings of machining centres. Journal of Manufacturing Processes, 2023. 92: p. 165-178. https://doi.org/10.1016/j.jmapro.2023.02.036.
• 29. Rizal M, Ghani J A, Nuawi M Z, et al. An embedded multi-sensor system on the rotating dynamometer for real-time condition monitoring in milling. The International Journal of Advanced Manufacturing Technology, 2018. 95: p. 811–823. https://doi.org/10.1007/s00170-017-1251-8
• 30. Ross N S, Sheeba P T, et al. A novel approach of tool condition monitoring in sustainable machining of Ni alloy with transferlearning models. Journal of Intelligent Manufacturing, 2023: p. 1-19, https://doi.org/10.1007/s10845-023-02074-8
• 31. Schmidhuber, J., A local learning algorithm for dynamic feedforward and recurrent networks. Connection Science, 1989. 1(4): p. 403-412. https://doi.org/10.1080/09540098908915650
• 32. Sun, B., J. Feng, and K. Saenko. Return of frustratingly easy domain adaptation. in Proceedings of the AAAI conference on artificial intelligence. 2016. https://doi.org/10.1609/aaai.v30i1.10306
• 33. Sun, H., et al., In-process tool condition forecasting based on a deep learning method. Robotics and Computer-Integrated Manufacturing, 2020. 64: p. 101924. https://doi.org/10.1016/j.rcim.2019.101924
• 34. Unver H O, Sener B. A novel transfer learning framework for chatter detection using convolutional neural networks. Journal ofIntelligent Manufacturing, 2021: p. 1-20. https://doi.org/10.1007/s10845-021-01839-3
• 35. Wang HC, Sun W, Sun WF, Ren Y. A novel tool condition monitoring based on Gramian angular field and comparative learning. International Journal of Hydromechatronics 2023: 6(2): 93-107, https://doi.org/10.1504/IJHM.2022.10048957.
• 36. Yan, B., L. Zhu, and Y. Dun, Tool wear monitoring of TC4 titanium alloy milling process based on multi-channel signal and time-dependent properties by using deep learning. Journal of Manufacturing Systems, 2021. 61: p. 495-508. https://doi.org/10.1016/j.jmsy.2021.09.017
• 37. Yosinski, J., et al., How transferable are features in deep neural networks? Advances in neural information processing systems, 2014. 27.
• 38. Zheng G, Sun W, Zhang H, Zhou Y, Gao C. Tool wear condition monitoring in milling process based on data fusion enhanced long shortterm memory network under different cutting conditions. Eksploatacja i Niezawodnosc –Maintenance and Reliability 2021; 23 (4): 612-618, http://doi.org/10.17531/ein.2021.4.3.
• 39. Zhou, Y., B. Sun, and W. Sun, A tool condition monitoring method based on two-layer angle kernel extreme learning machine and binary differential evolution for milling. Measurement, 2020. 166: p. 108186. https://doi.org/10.1016/j.measurement.2020.108186
• 40. Zhou, Y., Kumar, A., Parkash, C., et al. Development of entropy measure for selecting highly sensitive WPT band to identify defective components of an axial piston pump. Applied Acoustics; 2023; 203: 109225, https://doi. org/10.1016/j.apacoust.2023.109225.
• 41. Zhou, Y., Zhi, G., Chen, W., et al., A new tool wear condition monitoring method based on deep learning under small samples. Measurement, 2022. 189: p. 110622. https://doi.org/10.1016/j.measurement.2021.110622
• 42. Zhou YQ, Kumar A, Parkash C, et al. A novel entropy-based sparsity measure for prognosis of bearing defects and development of a sparsogram to select sensitive filtering band of an axial piston pump. Measurement 2022; 203: 111997, https://doi.org/10.1016/j.measurement.2022.111997.
• 43. Zhu, Q., Sun, B., Zhou, Y., et al., Sample augmentation for intelligent milling tool wear condition monitoring using numerical simulation and generative adversarial network. IEEE Transactions on Instrumentation and Measurement, 2021. 70: p. 1-10. https://doi.org/10.1109/TIM.2021.3077995