Abstract
The dimensional accuracy of thin-walled parts is critical to the performance of high-value mechanical systems but remains difficult to guarantee in production because of low structural stiffness, process-dependent deformation, and strongly noisy cutting-force signals. This work proposes a Multi-Scale Spatial Pyramid Pooling Variational Autoencoder (Multi-SPP-VAE) for feature-level dimensional error prediction in thin-walled 6061 aluminum machining. The model performs multiscale convolutional extraction of cutting-force signatures, applies residual shrinkage–based noise suppression with attention-guided latent encoding, and fuses static machining parameters (spindle speed, feed rate, depth of cut) directly into the latent space before supervised regression. Key hyperparameters are automatically tuned using an Enhanced Grey Wolf Optimization (EGWO) strategy to improve repeatability across machining conditions without manual retuning. The framework is evaluated under multiple sliding-window constructions and compared against established sequence modeling baselines. The proposed model consistently outperforms baselines across all datasets, yielding lower MSE, RMSE, and MAE and exhibiting higher stability under varying cutting conditions. It also achieves a high tolerance conformity rate. The improvements are statistically significant across repeated runs, indicating that the approach is suitable for in-process dimensional quality monitoring on standard workstation-class hardware.
Data availability
The datasets generated and analyzed during the current study are not publicly available due to privacy restrictions. However, they can be made available from the corresponding author upon reasonable request, subject to compliance with institutional and ethical guidelines.
References
Kong, D., Zhu, J., Duan, C., Lu, L. & Chen, D. Surface roughness prediction using kernel locality preserving projection and bayesian linear regression. Mech. Syst. Signal Process. 152, 107474 (2021).
Cagan, S. C., Venkatesh, B. & Buldum, B. B. Investigation of surface roughness and chip morphology of aluminum alloy in dry and minimum quantity lubrication machining. Mater. Today Proc. 27, 1122–1126 (2020).
Tercan, H. & Meisen, T. Machine learning and deep learning based predictive quality in manufacturing: a systematic review. J. Intell. Manuf. 33 (7), 1879–1905 (2022).
Zhang, Z. et al. Machining accuracy reliability during the peripheral milling process of thin-walled components. Robot. Comput. Integr. Manuf. 59, 222–234 (2019).
Kaneko, K., Nishida, I., Sato, R. & Shirase, K. Machining state monitoring in end milling based on comparison of monitored and predicted cutting torques. J. Adv. Mech. Des. Syst. Manuf. 13 (3), JAMDSM0052–JAMDSM0052 (2019).
Wang, P., Qu, H., Zhang, Q., Xu, X. & Yang, S. Production quality prediction of multistage manufacturing systems using multi-task joint deep learning. J. Manuf. Syst. 70, 48–68 (2023).
Sun, H., Peng, F., Zhou, L., Yan, R. & Zhao, S. A hybrid driven approach to integrate surrogate model and bayesian framework for the prediction of machining errors of thin-walled parts. Int. J. Mech. Sci. 192, 106111 (2021).
Sun, H. et al. In-situ prediction of machining errors of thin-walled parts: an engineering knowledge based sparse bayesian learning approach. J. Intell. Manuf. 35 (1), 387–411 (2024).
Wang, Y. et al. A new multitask learning method for tool wear condition and part surface quality prediction. IEEE Trans. Industr. Inf. 17 (9), 6023–6033 (2020).
Shang, S., Wang, C., Liang, X., Cheung, C. F. & Zheng, P. Surface Roughness Prediction in Ultra-Precision Milling: An Extreme Learning Machine Method with Data Fusion. Micromachines 14(11), 2016 (2023).
Papananias, M., McLeay, T. E., Mahfouf, M. & Kadirkamanathan, V. An intelligent metrology informatics system based on neural networks for multistage manufacturing processes. Procedia CIRP. 82, 444–449 (2019).
Proteau, A., Zemouri, R., Tahan, A. & Thomas, M. Dimension reduction and 2D-visualization for early change of state detection in a machining process with a variational autoencoder approach. Int. J. Adv. Manuf. Technol. 111, 3597–3611 (2020).
Yingying, S., Lianjuan, H., Jianan, W. & Huimin, W. Quantum-behaved RS‐PSO‐LSSVM method for quality prediction in parts production processes. Concurrency Computation: Pract. Experience 34(7), e5522 (2022).
Nasir, V. & Sassani, F. A review on deep learning in machining and tool monitoring: Methods, opportunities, and challenges. Int. J. Adv. Manuf. Technol. 115 (9–10), 2683–2709 (2021).
Xiao, Guanhua, et al. Surface Roughness Prediction Based on CNN-BiTCN-Attention in End Milling. International Journal of Advanced Computer Science & Applications 15.12 (2024).
Cheng, Feifan, Q. Peter He, and Jinsong Zhao. A novel process monitoring approach based on variational recurrent autoencoder.Computers & Chemical Engineering 129, 106515 (2019).
Doersch, C. Tutorial on variational autoencoders. arXiv preprint arXiv:1606.05908. (2016).
Wang, Chengzhu, et al. VAE4RSS: A VAE-based neural network approach for robust soft sensor with application to zinc roasting process. Engineering Applications of Artificial Intelligence 114, 105180 (2022).
Hemmer, M., Klausen, A., Van Khang, H., Robbersmyr, K. G. & Waag, T. I. Health indicator for low-speed axial bearings using variational autoencoders. IEEE Access. 8, 35842–35852 (2020).
He, Z., Shi, T. & Xuan, J. Milling tool wear prediction using multi-sensor feature fusion based on stacked sparse autoencoders. Measurement 190, 110719 (2022).
Lee, Y. S. & Chen, J. Developing semi-supervised latent dynamic variational autoencoders to enhance prediction performance of product quality. Chem. Eng. Sci. 265, 118192 (2023).
Ma, X., Ma, J. & Jiang, G. Insulator defect detection method based on attention mechanism and multi-scale feature fusion. J. Nanjing Univ. (Natural Sciences). 58 (06), 1020–1029 (2022).
Ioffe, S. & Szegedy, C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning (448–456). pmlr. (2015), June.
Nair, V. & Hinton, G. E. Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th international conference on machine learning (ICML-10) (807–814). (2010).
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I. & Salakhutdinov, R. Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15 (1), 1929–1958 (2014).
Zhao, M., Zhong, S., Fu, X., Tang, B. & Pecht, M. Deep residual shrinkage networks for fault diagnosis. IEEE Trans. Industr. Inf. 16 (7), 4681–4690 (2019).
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., … Polosukhin,I. (2017). Attention is all you need. Advances in neural information processing systems,30.
Devlin, J., Chang, M. W., Lee, K. & Toutanova, K. Bert: Pre-training of deep bidirectional Transformers for Language Understanding. ArXiv Preprint arXiv :181004805. (2018).
Mirjalili, S., Mirjalili, S. M. & Lewis, A. Grey Wolf optimizer. Adv. Eng. Softw. 69, 46–61 (2014).
Sharma, I., Kumar, V. & Sharma, S. A comprehensive survey on grey Wolf optimization. Recent. Adv. Comput. Sci. Commun. (Formerly: Recent. Pat. Comput. Science). 15 (3), 323–333 (2022).
Xiaojuan, L. & Chengji, S. Application of the P-box theory and HGWO-SVM in the fault diagnosis of rolling bearings. J. Vibr Shock. 40, 234–241 (2021).
Rodríguez, L., Castillo, O., Soria, J., Melin, P., Valdez, F., Gonzalez, C. I., …Soto, J. (2017). A fuzzy hierarchical operator in the grey wolf optimizer algorithm.Applied Soft Computing, 57, 315–328.
Bai, L. et al. A hybrid deep learning model for robust prediction of the dimensional accuracy in precision milling of thin-walled structural components. Front. Mech. Eng. 17 (3), 32 (2022).
Wang, Z., Wang, C., Li, Y. Variational autoencoder based on knowledge sharing and correlation weighting for process-quality concurrent fault detection Engineering Applications of Artificial Intelligence 133108051 10.1016/j.engappai.2024.108051. (2024).
Author information
Authors and Affiliations
Contributions
Yichen Liu: Software, Visualization, Writing—Original Draft, Xin Su: Conceptualization, Methodology, Formal Analysis, Investigation, Writing—Original Draft, Writing—Review & Editing,, Ji Li—Writing—Review & Editing. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
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
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Su, X., Liu, Y. & Li, J. Quality prediction using multiscale convolutional VAEs for thin plate parts. Sci Rep (2026). https://doi.org/10.1038/s41598-026-35186-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-35186-1
