Data-driven and physics-based modelling of process behaviour and deposit geometry for friction surfacing. (English) Zbl 1539.74254
Summary: In the last decades, there has been an increase in the number of successful machine learning models that have served as a key to identifying and using linkages within the process-structure-property-performance chain for vastly different problems in the domains of materials mechanics. The consideration of physical laws in data-driven modelling has recently been shown to enable enhanced prediction performance and generalization while requiring less data than either physics-based or data-driven modelling approaches independently. In this contribution, we introduce a simulation-assisted machine learning framework applied to the solid-state layer deposition technique friction surfacing, suitable for solid-state additive manufacturing as well as repair or coating applications. The objective of the present study is to use machine learning algorithms to predict and analyse the influence of process parameters and environmental variables, i.e. substrate and backing material properties, on process behaviour and deposit geometry. The effects of maximum process temperatures supplied by a numerical heat transfer model on the predictions of the targets are given special attention. Numerous different machine learning algorithms are implemented, optimized and evaluated to take advantage of their varied capabilities and to choose the optimal one for each target and the provided data. Furthermore, the input feature dependence for each prediction target is evaluated using game-theory related Shapley Additive Explanation values. The experimental data set consists of two separate experimental design spaces, one for varying process parameters and the other for varying substrate and backing material properties, which allowed to keep the experimental effort to a minimum. The aim was to also represent the cross parameter space between the two independent spaces in the predictive model, which was accomplished and resulted in an approximately 44 % reduction in the number of experiments when compared to carrying out an experimental design that included both spaces.
MSC:
| 74M15 | Contact in solid mechanics |
| 68T05 | Learning and adaptive systems in artificial intelligence |
Keywords:
machine learning; feature selection; numerical modelling; heat transfer; design of experiments; explainable AIReferences:
| [1] | Gandra, J.; Krohn, H.; Miranda, R. M.; Vilaça, P.; Quintino, L.; Dos Santos, J. F., Friction surfacing—A review. J. Mater Process. Technol., 5, 1062-1093 (2014) |
| [2] | Klopstock, H.; Neelands, A. R., An improved method of joining or welding metals (1941) |
| [3] | Damodaram, R.; Rai, P.; Cyril Joseph Daniel, S.; Bauri, R.; Yadav, D., Friction surfacing: A tool for surface crack repair. Surf. Coat. Technol. (2021) |
| [4] | Dilip, J. J.S.; Babu, S.; Rajan, S. V.; Rafi, K. H.; Janaki Ram, G. D.; Stucker, B. E., Use of friction surfacing for additive manufacturing. Mater. Manuf. Process., 2, 189-194 (2013) |
| [5] | Suhuddin, U.; Mironov, S.; Krohn, H.; Beyer, M.; Dos Santos, J. F., Microstructural evolution during friction surfacing of dissimilar aluminum alloys. Metall. Mater. Trans. A, 13, 5224-5231 (2012) |
| [6] | Hanke, S.; Dos Santos, J. F., Comparative study of severe plastic deformation at elevated temperatures of two aluminium alloys during friction surfacing. J. Mater Process. Technol., 257-267 (2017) |
| [7] | Isupov, F. Y.; Panchenko, O.; Zhabrev, L.; Mushnikov, I.; Rylkov, E.; Popovich, A. A., Finite element simulation of temperature field during friction surfacing of Al-5Mg consumable rod. Key Eng. Mater., 737-744 (2019) |
| [8] | Kallien, Z.; Rath, L.; Roos, A.; Klusemann, B., Experimentally established correlation of friction surfacing process temperature and deposit geometry. Surf. Coat. Technol., 6 (2020) |
| [9] | Krohn, H.; Hanke, S.; Beyer, M.; Dos Santos, J. F., Influence of external cooling configuration on friction surfacing of AA6082 T6 over AA2024 T351. Manuf. Lett., 17-20 (2015) |
| [10] | Liu, X.; Yao, J.; Wang, X.; Zou, Z.; Qu, S., Finite difference modeling on the temperature field of consumable-rod in friction surfacing. J. Mater Process. Technol., 3, 1392-1399 (2009) |
| [11] | Vitanov, V. I.; Javaid, N., Investigation of the thermal field in micro friction surfacing. Surf. Coat. Technol., 16-17, 2624-2631 (2010) |
| [12] | Kallien, Z.; Klusemann, B., Combined experimental-numerical analysis of the temperature evolution and distribution during friction surfacing. Surf. Coat. Technol., 8 (2022) |
| [13] | Pirhayati, P.; Jamshidi Aval, H., An investigation on thermo-mechanical and microstructural issues in friction surfacing of Al-Cu aluminum alloys. Mater. Res. Expr., 5 (2019) |
| [14] | Rahmati, Z.; Jamshidi Aval, H.; Nourouzi, S.; Jamaati, R., Modeling and experimental study of friction surfacing of AA2024 alloy over AA1050 plates. Mater. Res. Expr., 8 (2019) |
| [15] | Chollet, F., Deep Learning with Python (2017), Manning |
| [16] | Bock, F. E.; Aydin, R. C.; Cyron, C. J.; Huber, N.; Kalidindi, S. R.; Klusemann, B., A review of the application of machine learning and data mining approaches in continuum materials mechanics. Front. Mater., 443 (2019) |
| [17] | Meng, L.; McWilliams, B.; Jarosinski, W.; Park, H.-Y.; Jung, Y.-G.; Lee, J.; Zhang, J., Machine learning in additive manufacturing: A review. JOM, 6, 2363-2377 (2020) |
| [18] | Xiong, J.; Zhang, G.; Hu, J.; Wu, L., Bead geometry prediction for robotic GMAW-based rapid manufacturing through a neural network and a second-order regression analysis. J. Intell. Manuf., 1, 157-163 (2014) |
| [19] | Wacker, C.; Köhler, M.; David, M.; Aschersleben, F.; Gabriel, F.; Hensel, J.; Dilger, K.; Dröder, K., Geometry and distortion prediction of multiple layers for wire arc additive manufacturing with artificial neural networks. Appl. Sci., 10, 4694 (2021) |
| [20] | Deng, J.; Xu, Y.; Zuo, Z.; Hou, Z.; Chen, S., Bead geometry prediction for multi-layer and multi-bead wire and arc additive manufacturing based on XGBoost, 125-135 |
| [21] | Oh, W.-J.; Lee, C.-M.; Kim, D.-H., Prediction of deposition bead geometry in wire arc additive manufacturing using machine learning. J. Mater. Res. Technol., 4283-4296 (2022) |
| [22] | Barrionuevo, G. O.; Sequeira-Almeida, P. M.; Ríos, S.; Ramos-Grez, J. A.; Williams, S. W., A machine learning approach for the prediction of melting efficiency in wire arc additive manufacturing. Int. J. Adv. Manuf. Technol., 5-6, 3123-3133 (2022) |
| [23] | Paulo Davim, J.; Oliveira, C.; Cardoso, A., Predicting the geometric form of clad in laser cladding by powder using multiple regression analysis (MRA). Mater. Des., 2, 554-557 (2008) |
| [24] | Milhomme, S.; Lartigau, J.; Brugger, C.; Froustey, C., Bead geometry prediction using multiple linear regression analysis. Int. J. Adv. Manuf. Technol., 1-2, 607-620 (2021) |
| [25] | Biyikli, M.; Karagoz, T.; Calli, M.; Muslim, T.; Ozalp, A. A.; Bayram, A., Single track geometry prediction of laser metal deposited 316L-Si via multi-physics modelling and regression analysis with experimental validation. Metals Mater. Int., 10, 292s (2022) |
| [26] | Lee, E. M.; Shin, G. Y.; Yoon, H. S.; Shim, D. S., Study of the effects of process parameters on deposited single track of M4 powder based direct energy deposition. J. Mech. Sci. Technol., 7, 3411-3418 (2017) |
| [27] | Caiazzo, F.; Caggiano, A., Laser direct metal deposition of 2024 Al alloy: Trace geometry prediction via machine learning. Mater. (Basel, Switzerland), 3 (2018) |
| [28] | Liu, H.; Qin, X.; Huang, S.; Jin, L.; Wang, Y.; Lei, K., Geometry characteristics prediction of single track cladding deposited by high power diode laser based on genetic algorithm and neural network. Int. J. Precis. Eng. Manuf., 7, 1061-1070 (2018) |
| [29] | Feenstra, D. R.; Molotnikov, A.; Birbilis, N., Utilisatioan of artificial neural networks to rationalise processing windows in directed energy deposition applications. Mater. Des. (2021) |
| [30] | Vitanov, V.; Voutchkov, I.; Bedford, G., Decision support system to optimise the Frictec (friction surfacing) process. J. Mater Process. Technol., 1-3, 236-242 (2000) |
| [31] | Vitanov, V.; Voutchkov, I.; Bedford, G., Neurofuzzy approach to process parameter selection for friction surfacing applications. Surf. Coat. Technol., 3, 256-262 (2001) |
| [32] | Vitanov, V. I.; Voutchkov, I. I., Process parameters selection for friction surfacing applications using intelligent decision support. J. Mater Process. Technol., 1, 27-32 (2005) |
| [33] | Sugandhi, V.; Ravishankar, V., Optimization of friction surfacing process parameters for aa1100 aluminum alloy coating with mild steel substrate using response surface methodology (RSM) technique. Mod. Appl. Sci., 2, 69 (2012) |
| [34] | Ikeuchi, D.; Vargas-Uscategui, A.; Wu, X.; King, P. C., Neural network modelling of track profile in cold spray additive manufacturing. Mater. (Basel, Switzerland), 17 (2019) |
| [35] | Kadaganchi, R.; Gankidi, M. R.; Gokhale, H., Optimization of process parameters of aluminum alloy AA 2014-T6 friction stir welds by response surface methodology. Def. Technol., 3, 209-219 (2015) |
| [36] | Srinivasa Rao, M.; Ramanaiah, N., Optimization of process parameters for FSW of Al-Mg-Mn-Sc-Zr alloy using CCD and RSM. Strojnícky Cas. - J. Mech. Eng., 3, 195-224 (2018) |
| [37] | Lakshminarayanan, A. K.; Balasubramanian, V., Comparison of RSM with ANN in predicting tensile strength of friction stir welded AA7039 aluminium alloy joints. Trans. Nonferr. Met. Soc. China, 1, 9-18 (2009) |
| [38] | Manvatkar, V. D.; Arora, A.; De, A.; DebRoy, T., Neural network models of peak temperature, torque, traverse force, bending stress and maximum shear stress during friction stir welding. Sci. Technol. Weld. Join., 6, 460-466 (2012) |
| [39] | Shojaeefard, M. H.; Akbari, M.; Asadi, P., Multi objective optimization of friction stir welding parameters using FEM and neural network. Int. J. Precis. Eng. Manuf., 11, 2351-2356 (2014) |
| [40] | Bock, F. E.; Blaga, L. A.; Klusemann, B., Mechanical performance prediction for friction riveting joints of dissimilar materials via machine learning. Procedia Manuf., 615-622 (2020) |
| [41] | Ikeuchi, D.; Vargas-Uscategui, A.; Wu, X.; King, P., Data-efficient neural network for track profile modelling in cold spray additive manufacturing. Appl. Sci., 4, 1654 (2021) |
| [42] | Chinesta, F.; Cueto, E.; Abisset-Chavanne, E.; Duval, J. L.; Khaldi, F. E., Virtual, digital and hybrid twins: A new paradigm in data-based engineering and engineered data. Arch. Comput. Methods Eng., 1, 1 (2018) |
| [43] | Bock, F. E.; Keller, S.; Huber, N.; Klusemann, B., Hybrid modelling by machine learning corrections of analytical model predictions towards high-fidelity simulation solutions. Mater. (Basel, Switzerland), 8, 1883 (2021) |
| [44] | Ibáñez, R.; Abisset-Chavanne, E.; González, D.; Duval, J.-L.; Cueto, E.; Chinesta, F., Hybrid constitutive modeling: Data-driven learning of corrections to plasticity models. Int. J. Mater. Form., 1567, 565 (2018) |
| [45] | González, D.; Chinesta, F.; Cueto, E., Learning corrections for hyperelastic models from data. Front. Mater., 752 (2019) |
| [46] | Lundberg, S. M.; Lee, S.-I., A unified approach to interpreting model predictions, 4765-4774 |
| [47] | Chen, S.; Kaufmann, T., Development of data-driven machine learning models for the prediction of casting surface defects. Metals, 1, 1 (2022) |
| [48] | Baturynska, I.; Martinsen, K., Prediction of geometry deviations in additive manufactured parts: comparison of linear regression with machine learning algorithms. J. Intell. Manuf., 1, 179-200 (2021) |
| [49] | Fitseva, V.; Hanke, S.; Dos Santos, J. F., Influence of rotational speed on process characteristics, material flow and microstructure evolution in friction surfacing of Ti-6Al-4V. Mater. Manuf. Process., 5, 557-563 (2016) |
| [50] | Jin, R.; Chen, W.; Sudjianto, A., An efficient algorithm for constructing optimal design of computer experiments. J. Statist. Plann. Inference, 1, 268-287 (2005) · Zbl 1066.62075 |
| [51] | Bouhlel, M. A.; Hwang, J. T.; Bartoli, N.; Lafage, R.; Morlier, J.; Martins, J. R.R. A., A Python surrogate modeling framework with derivatives. Adv. Eng. Softw. (2019) |
| [52] | Constellium, M. A., Airware 2050-T84 plate (2017) |
| [53] | MatWeb - Material Property Data, M. A., Aluminum 5083-H112 (2022), http://www.matweb.com/search/DataSheet.aspx?MatGUID=bd6317b19dd94faf8bff851e4f339e88, Accessed 28.05.2021 |
| [54] | MatWeb - Material Property Data, M. A., Aluminum 7050-T7451 (7050-t73651) (2022), http://www.matweb.com/search/DataSheet.aspx?MATGUID=142262cf7fbc4c83917ca5c3d17df1ed, Accessed 08.03.2021 |
| [55] | MatWeb - Material Property Data, M. A., Overview of materials for Low Carbon Steel (2022), https://www.matweb.com/search/DataSheet.aspx?MatGUID=034970339dd14349a8297d2c83134649. Accessed 15.09.2022 |
| [56] | MatWeb - Material Property Data, M. A., Titanium Ti-6Al-4V (Grade 5), STA (2022), http://www.matweb.com/search/DataSheet.aspx?MatGUID=b350a789eda946c6b86a3e4d3c577b39. Accessed 08.03.2021 |
| [57] | Witten, I. H.; Frank, E.; Hall, M. A. |
| [58] | Pedregosa, F.; Varoquaux, G.; Gramfort, A.; Michel, V.; Thirion, B.; Grisel, O.; Blondel, M.; Prettenhofer, P.; Weiss, R.; Dubourg, V.; Vanderplas, J.; Passos, A.; Cournapeau, D.; Brucher, M.; Perrot, M.; Duchesnay, E., Scikit-learn: Machine learning in python. J. Mach. Learn. Res., 2825-2830 (2011), URL http://arxiv.org/pdf/1201.0490v4 · Zbl 1280.68189 |
| [59] | Chen, T.; Guestrin, C., XGBoost: A scalable tree boosting system, 785-794, URL http://doi.acm.org/10.1145/2939672.2939785 |
| [60] | Chollet, F., Keras (2015), URL https://github.com/fchollet/keras |
| [61] | Abadi, M.; Agarwal, A.; Barham, P.; Brevdo, E.; Chen, Z.; Citro, C.; Corrado, G. S.; Davis, A.; Dean, J.; Devin, M.; Ghemawat, S.; Goodfellow, I.; Harp, A.; Irving, G.; Isard, M.; Jia, Y.; Jozefowicz, R.; Kaiser, L.; Kudlur, M.; Levenberg, J.; Mané, D.; Monga, R.; Moore, S.; Murray, D.; Olah, C.; Schuster, M.; Shlens, J.; Steiner, B.; Sutskever, I.; Talwar, K.; Tucker, P.; Vanhoucke, V.; Vasudevan, V.; Viégas, F.; Vinyals, O.; Warden, P.; Wattenberg, M.; Wicke, M.; Yu, Y.; Zheng, X., TensorFlow: Large-scale machine learning on heterogeneous systems (2015), URL https://www.tensorflow.org/. Software available from tensorflow.org |
| [62] | Murphy, K. |
| [63] | Wade, C., Hands-on Gradient Boosting with XGBoost and Scikit-Learn: Perform Accessible Machine Learning and Extreme Gradient Boosting with Python (2020), Packt Publishing |
| [64] | Bergstra, J.; Yamins, D.; Cox, D., Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures, 115-123 |
| [65] | Vapnik, V. N., The Nature of Statistical Learning Theory (1995), Springer New York: Springer New York New York, NY · Zbl 0833.62008 |
| [66] | Vapnik, V.; Golowich, S. E.; Smola, A., Support vector method for function approximation, regression estimation and signal processing, 281-287 |
| [67] | Drucker, H.; Burges, C. J.C.; Kaufman, L.; Smola, A.; Vapnik, V., Support vector regression machines |
| [68] | Haykin, S. S., Neural Networks: A Comprehensive Foundation (1998), Prentice Hall: Prentice Hall Upper Saddle River, NJ |
| [69] | Rosenblatt, F., The perceptron: A probabilistic model for information storage and organization in the brain. Psychol. Rev., 6, 386-408 (1958) |
| [70] | Kingma, D.; Ba, J., Adam: A method for stochastic optimization |
| [71] | O’Malley, T.; Bursztein, E.; Long, J.; Chollet, F.; Jin, H.; Invernizzi, L., Keras Tuner (2019), https://github.com/keras-team/keras-tuner |
| [72] | Shapley, L. S., 17. A value for n-person games, 307-318 |
| [73] | Lundberg, S. M.; Erion, G.; Chen, H.; DeGrave, A.; Prutkin, J. M.; Nair, B.; Katz, R.; Himmelfarb, J.; Bansal, N.; Lee, S.-I., From local explanations to global understanding with explainable AI for trees. Nat. Mach. Intell., 1, 2522-5839 (2020) |
| [74] | Li, H.; Xu, Z.; Zhou, Z., Numerical simulation of the plunge stage of friction surfacing of AA5083 aluminum alloy. IOP Conf. Ser.: Mater. Sci. Eng., 1 (2020) |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
