Abstract
This work presents an interpretability study with XAI tools to explain an XGBoost model for hardness prediction in the simultaneous double-frequency induction hardening. Experiments were carried out on C45 steel spur-gear. In order to explain the model, firstly, the built-in tool of the XGBoost library was used to interpret the feature importance. Then, a more advanced approach with the SHAP library was employed to highlight local and global explanations. Finally, the implementation of an interpretable surrogate model allowed to illustrate rules for prediction, making the explanation, although approximate, clear. This study proposes a relevant approach of AI to explain the results obtained by black box models which is currently a major element for the industry allowing to justify the quality of the results in a clear way. It is concluded that the model is consistent with physical principles.
Similar content being viewed by others
References
Rokicki P (2017) Induction hardening of tool steel for heavily loaded aircraft engine components. Arch Metall Mate 62:315–320
Candeo A, Ducassy C, Bocher P, Dughiero F (2011) modeling of induction hardening of ring gears for the aerospace industry. IEEE Trans Magn 47(5):918–921
Rudnev, V, Loveless, D and Cook, R (2017) Handbook of Induction Heating. CRC Press, 2nd ed
Qiu G, Zhan D, Li C, Yang Qi, M, Jiang, Z and Zhang, H, (2020) Effects of yttrium and heat treatment on the microstructure and mechanical properties of clam steel. J of Materi Eng and Perform 29(1):42–52
Celada-Casero C, Huang B, Yang J-R, San-Martin D (2019) Microstructural mechanisms controlling the mechanical behaviour of ultrafine grained martensite/austenite microstructures in a metastable stainless steel. Materials & Design 181:107922
Hömberg D, Liu Q, Montalvo-Urquizo J, Nadolski D, Petzold T, Schmidt A, Schulz A (2016) Simulation of multi-frequency-induction-hardening including phase transitions and mechanical effects. Finite Elem Anal Des 121:86–100
Maresca F, Kouznetsova V, Geers M, Curtin W (2018) Contribution of austenite-martensite transformation to deformability of advanced high strength steels: from atomistic mechanisms to microstructural response. Acta Mater 156:463–478
Xu S, Li J, Cui Y, Zhang Y, Sun L, Li J, Luan J, Jiao Z, Wang X-L, Liu C et al (2020) Mechanical properties and deformation mechanisms of a novel austenite-martensite dual phase steel. International Journal of Plasticity 128:102677
Wuppermann, C and Míček, E (2018) Importance of heat treatment for the variety of applications of modern materials. Prozesswarme, pp 95–101
Hömberg D (2004) A mathematical model for induction hardening including mechanical effects. NONLINEAR ANAL-REAL WORLD APP 5:55–90
Spezzapria M, Dughiero F, Forzan M, Candeo A (2012) Multiphysics fem simulation of contour induction hardening process on aeronautical gears. J Iron Steel Res 19:95–98
Wang K, Chandrasekar S, Yang H (1992) Finite-element simulation of induction heat treatment. J of Materi Eng and Perform 1:97–112
Samiuddin M, Muzamil M (2016) Experimental investigation and optimization of process parameters for through induction hardening using factorial design of experiments. Journal of Engineering Research 5:174–185
Langer M, Oster D, Speith T, Hermanns H, Kästner L, Schmidt E, Sesing A, Baum K (2021) What do we want from explainable artificial intelligence (xai)?-a stakeholder perspective on xai and a conceptual model guiding interdisciplinary xai research. Artif Intell 296:103473
Das, A and Rad, P (2020) Opportunities and challenges in explainable artificial intelligence (xai): A survey. arXiv preprint arXiv:2006.11371
Tjoa, E and Guan, C (2019) A survey on explainable artificial intelligence (XAI): towards Medical XAI, pp 21
Loyola-Gonzalez O (2019) Black-box vs. white-box: Understanding their advantages and weaknesses from a practical point of view. IEEE Access 7:154096–154113
Adadi A, Berrada M (2018) Peeking inside the black-box: a survey on explainable artificial intelligence (xai). IEEE Access 6:52138–52160
Guidotti R, Monreale A, Ruggieri S, Turini F, Giannotti F, Pedreschi D (2019) A survey of methods for explaining black box models. ACM Comput Surv 51:1–42
García MV, Aznarte JL (2020) Shapley additive explanations for no2 forecasting. Ecological Informatics 56:101039
Abdollahi A, Pradhan B (2021) Urban vegetation mapping from aerial imagery using explainable ai (xai). Sensors 21(14):4738
Dikshit A, Pradhan B (2021) Interpretable and explainable ai (xai) model for spatial drought prediction. Sci Total Environ 801:149797
Yoo S, Kang N (2021) Explainable artificial intelligence for manufacturing cost estimation and machining feature visualization. Expert Syst Appl 183:115430
Jeon, J, Seo, N, Jung, J-G, Son, SB and Lee, S-J (2022) Prediction and mechanism explain of austenite-grain growth during reheating of alloy steel using xai. Journal of Materials Research and Technology
Garois S, Daoud M, Traidi K, et al (2023) Artificial intelligence modeling of induction contour hardening of 300M steel bar and C45 steel spur-gear. Int J Mater Form 16:26. https://doi.org/10.1007/s12289-023-01748-1
Chen, T, He, T, Benesty, M, Khotilovich, V, Tang, Y, Cho, H, Chen, K et al (2015) Xgboost: extreme gradient boosting. R package version 0.4-2, 1(4):1–4
ISO, E, (2018) 6507–1: 2018-metallic materials-vickers hardness test-part 1: Test method. Geneva, Switzerland, ISO
Zheng, H, Yuan, J and Chen, L (2017) Short-term load forecasting using emd-lstm neural networks with a xgboost algorithm for feature importance evaluation. Energies, 10(8)1168
Goutte, C and Gaussier, E (2005) A probabilistic interpretation of precision, recall and f-score, with implication for evaluation. In: European conference on information retrieval, pp 345–359. Springer
Ribeiro, MT, Singh, S and Guestrin, C (2016) Why Should I Trust You?: Explaining thepredictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, (San Francisco California USA), pp 1135–1144, ACM
Guidotti, R, Monreale, A, Ruggieri, S, Pedreschi, D, Turini, F and Giannotti, F (2018) Local rule-based explanations of black box decision systems. arXiv:1805.10820
Lundberg, SM and Lee, S-I (2017) A Unified Approach to Interpreting Model Predictions. In: Advances in neural information processing systems, 30, Curran Associates, Inc
Lundberg, SM, Erion, GG and Lee, S-I (2019) Consistent Individualized Feature Attribution for Tree Ensembles. arXiv:1802.03888
Azodi CB, Tang J, Shiu S-H (2020) Opening the black box: interpretable machine learning for geneticists. Trends Genet 36(6):442–455
Quinlan JR (1996) Learning decision tree classifiers. ACM Computing Surveys (CSUR) 28(1):71–72
Li J, Cao Z, Liu L, Liu X, Peng J (2021) Effect of Microstructure on Hardness and Wear Properties of 45 Steel after Induction Hardening. Steel Research International 92:2000540
Derouiche K, Garois S, Champaney V, Daoud M, Traidi K, Chinesta F (2021) Data-driven modeling for multiphysics parametrized problems-application to induction hardening process. Metals 11(5):738
Acknowledgements
This work was conducted with the help of the French Technological Research Institute for Materials, Metallurgy and Processes (IRT-M2P). The authors would like to acknowledge IRTM2P and the partners of the project TRANSFUGE led by IRT-M2P.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Compliance with ethical standards
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix A: Example : SHAP value calculation
Appendix A: Example : SHAP value calculation
This appendix present a short example of SHAP values calculation. The case presented in Eq. 1 shows a space of variables X which is too large for explanation. Indeed,
The number of elements of X is denoted by card(X) i.e. \(card(X) = 6\). F being the powerset of X i.e. the space of all possible combinations of the elements in X, \(card(F) = 2^6 = 64\) which is too many elements to graphicly present the concepts. Hence, a subset will be used for this example as the space of variables is now defined as:
As mentioned, the powerset F is the space containing all the different combinations of variable. Here it can be illustrated like in Fig. 21.
It is then possible to defined F as:
Hence, it comes \(card(F) = 2^3 = 8\). Each node of the powerset represents a model trained with the set of variables of the node. Hence each node has its own predicted value of hardness H. For a single value \(x_0\) to predict, every hardness predictions \(\hat{y_0}\) in each node are recorded in Fig. 22.
Each edge is the impact of a variable added on a previous model to the new one. Therefore, each edge represents the marginal contribution of a variable, it is calculated with the difference of the predicted values \(\hat{y_0}\) between 2 nodes, the first one should have not the evaluated variable it, while the second one should. In this example, the marginal contribution of the temperature T between the first two nodes is defined as:
Moreover, this marginal contribution is weighted. The weighted are defined as follow:
-
the sum of the weights of a row must be equal to the sum of a any other row.
-
all weights involved in the marginal contribution must be equal to 1.
-
all weights of the same row are equal to each other.
The edges concerned with the marginal contribution calculation of the temperature T are illustrated in Fig. 23.
Therefore, in this example, \(w_1 = w_2 + w_3 = w_4\) with \(w_2 = w_3\). It comes \(w_1 = w_4 = \frac{1}{3}\) and \(w_2 = w_3 = \frac{1}{6}\).
Moreover, with the Eq. 4 presented in the SHAP value section, the weights are defined as:
The weight values can be verified, here the calculation of \(w_2\) as an example:
Now it is possible to have the SHAP value of T for the whole powerset, it is defined as :
The shap value is calculated and can be used for several plotting functions to better understand how the model actually predict.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) 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.
About this article
Cite this article
Garois, S., Daoud, M. & Chinesta, F. Explaining hardness modeling with XAI of C45 steel spur-gear induction hardening. Int J Mater Form 16, 57 (2023). https://doi.org/10.1007/s12289-023-01780-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12289-023-01780-1