Abstract
In most cases, designers must manually specify geometric tolerance types and values when designing mechanical products. For the same nominal geometry, different designers may specify different types and values of geometric tolerances. To reduce the uncertainty and realize the tolerance specification automatically, a tolerance specification method based on machine learning is proposed. The innovation of this paper is to find out the information that affects geometric tolerances selection and use machine learning methods to generate tolerance specifications. The realization of tolerance specifications is changed from rule-driven to data-driven. In this paper, feature engineering is performed on the data for the application scenarios of tolerance specifications, which improves the performance of the machine learning model. This approach firstly considers the past tolerance specification schemes as cases and sets up the cases to the tolerance specification database which contains information such as datum reference frame, positional relationship, spatial relationship, and product cost. Then perform feature engineering on the data and established machine learning algorithm to convert the tolerance specification problem into an optimization problem. Finally, a gear reducer as a case study is given to verify the method. The results are evaluated with three different machine learning evaluation indicators and made a comparison with the tolerance specification method in the industry. The final results show that the machine learning algorithm can automatically generate tolerance specifications, and after feature engineering, the accuracy of the tolerance specification results is improved.
Similar content being viewed by others
Abbreviations
- DRF:
-
Datum reference frame
- CAT:
-
Computer-aided tolerancing
- GPS:
-
Geometrical product specification and verification
- TTRS:
-
Technologically and topologically related surfaces
- MGDE:
-
Minimum geometric datum elements
- L:
-
Feature vector for geometric tolerance selection
- l:
-
Characteristic parameter in the feature vector
- n:
-
Number of characteristic parameters
- d:
-
Normalized size of the feature
- V:
-
Volume of the feature
- S:
-
Surface area of the feature
- c:
-
Detection cost
- p:
-
Machining accuracy
- m:
-
Instrument uncertainty
- u:
-
Manufacturer’s expectation of product cost
- Q:
-
Training set
- yn :
-
Class label
- yxn :
-
Model output result
- P:
-
Parts to be specified
- r:
-
Shape tolerance tendency parameter
- SR:
-
Spatial relationship between the feature to be specified and the main datum
References
Anselmetti, B., Chavanne, R., Yang, J.-X., & Anwer, N. (2010). Quick GPS: A new CAT system for single-part tolerancing. Computer-Aided Design, 42(9), 768–780.
Archana, P., & Dharmpal, D. (2017). An outlook in some aspects of hybrid decision tree classification approach: A survey. In S. C. Satapathy, V. Bhateja, & A. Joshi (Eds.), Proceedings of the international conference on data engineering and communication technology, Singapore, 2017 (pp. 85–95). Singapore: Springer.
Armillotta, A. (2013). A method for computer-aided specification of geometric tolerances. Computer-Aided Design, 45(12), 1604–1616.
Armillotta, A. (2019). Tolerance analysis of gear trains by static analogy. Mechanism and Machine Theory, 135, 65–80.
Bjorke, O. (1978). Computer-aided tolerancing. New York: Tapir Publishers.
Bustillo, A., Pimenov, D. Y., Mia, M., & Kapłonek, W. (2020a). Machine-learning for automatic prediction of flatness deviation considering the wear of the face mill teeth. Journal of Intelligent Manufacturing. https://doi.org/10.1007/s10845-020-01645-3.
Bustillo, A., Reis, R., Machado, A. R., & Pimenov, D. Y. (2020b). Improving the accuracy of machine-learning models with data from machine test repetitions. Journal of Intelligent Manufacturing. https://doi.org/10.1007/s10845-020-01661-3.
Cao, Y., Zhang, H., Li, B., Wu, Z., & Yang, J. (2013). Study on functional specification scheme on interface based on positioning features. Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, 227(5), 745–753.
Cao, Y., Zhao, Q., Liu, T., Ren, L., & Yang, J. (2018). The strategy of datum reference frame selection based on statistical learning. Journal of Computing and Information Science in Engineering, 18(2), 021002-1–021002-9.
Chen, S., Webb, G. I., Liu, L., & Ma, X. (2020). A novel selective naïve Bayes algorithm. Knowledge-Based Systems, 192, 105361.
Chih-Wei, H., & Chih-Jen, L. (2002). A comparison of methods for multiclass support vector machines. IEEE Transactions on Neural Networks, 13(2), 415–425.
Clément, A., Rivière, A., Serré, P., & Valade, C. (1998). The TTRSs: 13 Constraints for dimensioning and tolerancing. In H. A. ElMaraghy (Ed.), Geometric design tolerancing: Theories, standards and applications (pp. 122–131). Boston: Springer.
Cohen, J. (1960). A coefficient of agreement for nominal scales. Educational and Psychological Measurement, 20(1), 37–46.
González Rodríguez, G., Gonzalez-Cava, J. M., & Méndez Pérez, J. A. (2020). An intelligent decision support system for production planning based on machine learning. Journal of Intelligent Manufacturing, 31(5), 1257–1273. https://doi.org/10.1007/s10845-019-01510-y.
Grigorios, T., & Ioannis, K. (2007). Multi-label classification: An overview. International Journal of Data Warehousing and Mining (IJDWM), 3(3), 1–13.
Haghighi, P., Mohan, P., Kalish, N., Vemulapalli, P., Shah, J. J., & Davidson, J. K. (2015). Toward automatic tolerancing of mechanical assemblies: First-order GD&T schema development and tolerance allocation. Journal of Computing and Information Science in Engineering, 15(4), 041003-1–041003-9.
Hao, S., & Yang, M. (2020). Support point of locally optimal designs for multinomial logistic regression models. Journal of Statistical Planning and Inference, 209, 144–159. https://doi.org/10.1016/j.jspi.2020.03.006.
Huang, K.-Z., & Ren, H.-W. (2008). A growth design approach for tolerancing. In Asme International Design Engineering Technical Conferences & Computers & Information in Engineering Conference.
Hung, T.-C., & Chan, K.-Y. (2013). Multi-objective design and tolerance allocation for single- and multi-level systems. Journal of Intelligent Manufacturing, 24(3), 559–573. https://doi.org/10.1007/s10845-011-0608-3.
Imran, M., & Young, B. (2015). The application of common logic based formal ontologies to assembly knowledge sharing. Journal of Intelligent Manufacturing, 26(1), 139–158. https://doi.org/10.1007/s10845-013-0768-4.
Jiang, W., Lin, J., Wang, H., & Zou, S. (2020). Hybrid semantic service matchmaking method based on a random forest. Tsinghua Science and Technology, 25(6), 798–812. https://doi.org/10.26599/TST.2020.9010003.
Mathew, A. (2010). A CAD system for extraction of mating features in an assembly. Assembly Automation, 30(2), 142–146.
Mathew, A. T., & Rao, C. S. P. (2010). A novel method of using API to generate liaison relationships from an assembly. Journal of Software Engineering and Applications, 2(3), 167–175.
Mishra, A., & Deb, S. (2019). Assembly sequence optimization using a flower pollination algorithm-based approach. Journal of Intelligent Manufacturing, 30(2), 461–482. https://doi.org/10.1007/s10845-016-1261-7.
Qin, Y., Lu, W., Qi, Q., Liu, X., Huang, M., Scott, P. J., et al. (2018). Towards an ontology-supported case-based reasoning approach for computer-aided tolerance specification. Knowledge-Based Systems, 141, 129–147.
Qin, Y., Zhong, Y., Huang, M., & Liu, F. (2013). An assembly tolerance representation model based on spatial relations for generating assembly tolerance types. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 228(6), 1005–1020.
Rao, S. J. D. F. P., Technical Report No. TR-SR–49. (2013). Reconciling GDT rules: RECON versus ASU rule set.
Shi, X., Tian, X., & Wang, G. (2020). Screening product tolerances considering semantic variation propagation and fusion for assembly precision analysis. International Journal of Precision Engineering and Manufacturing, 21, 1259–1278.
Wang, T., Qiao, M., Zhang, M., Yang, Y., & Snoussi, H. (2020). Data-driven prognostic method based on self-supervised learning approaches for fault detection. Journal of Intelligent Manufacturing, 31(7), 1611–1619. https://doi.org/10.1007/s10845-018-1431-x.
Wu, Y., & Gu, Q. (2016). The composition principle of the datum reference frame. Procedia CIRP, 43, 226–231.
Yan, Z., Wu, Q., Ren, M., Liu, J., Liu, S., Qiu, S. J. C., et al. (2019). Locally private Jaccard similarity estimation. Concurrency and Computation: Practice and Experience, 31(24), e4889.
Zhang, Y., Li, Z., Gao, J., & Hong, J. (2011). New reasoning algorithm for assembly tolerance specifications and corresponding tolerance zone types. Computer-Aided Design, 43(12), 1606–1628.
Zhang, Y., Li, L., Song, M., & Yi, R. (2019). Optimal tolerance design of hierarchical products based on quality loss function. Journal of Intelligent Manufacturing, 30(1), 185–192. https://doi.org/10.1007/s10845-016-1238-6.
Zhang, S., Li, X., Zong, M., Zhu, X., & Wang, R. (2018). Efficient kNN classification with different numbers of nearest neighbors. IEEE Transactions on Neural Networks and Learning Systems, 29(5), 1774–1785. https://doi.org/10.1109/TNNLS.2017.2673241.
Zhao, Q., Li, T., Cao, Y., Yang, J., & Jiang, X. (2019). A rule-based exclusion method for tolerance specification of revolving components. Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, 234(3), 527–537.
Zhong, Y., Qin, Y., Huang, M., Lu, W., Gao, W., & Du, Y. (2013). Automatically generating assembly tolerance types with an ontology-based approach. Computer-Aided Design, 45(11), 1253–1275.
Acknowledgements
This project was supported by National Natural Science Foundation of China (51505506); Henan universities key scientific research projects (19A460035, 20A460031, 20A460033); The Science and Technology Key Project of the Department of Education of Henan Province (Grant No. 202102210068). Applied Research Project of Independent Innovation in Zhongyuan Universtiy of Technology (K2018YY001).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Cui, Lj., Sun, My., Cao, Yl. et al. A novel tolerance geometric method based on machine learning. J Intell Manuf 32, 799–821 (2021). https://doi.org/10.1007/s10845-020-01706-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10845-020-01706-7