Ensemble Methods for APS In-Flight Particle Temperature and Velocity Prediction Considering Torch Electrodes Ageing
Source abstract
Abstract
Abstract The nonlinear relationship between the input process parameters and in-flight particle characteristics of the atmospheric plasma spray (APS) is of paramount importance for coating properties design and quality. It is also known that the ageing of torch electrodes affects this relationship. In recent years, machine learning algorithms have proven to be able to take into account such complex nonlinear interactions. This work illustrates the application of ensemble methods to predict the in-flight particle temperature and velocity during an APS process considering torch electrodes ageing. Experiments were performed to record simultaneously the input process parameters, the in-flight powder particle characteristics and the electrodes usage time. Random Forest (RF) and Gradient Boosting (GB) were used to rank and select the features for the APS process data recorded as the electrodes aged and the corresponding predictive models were compared. The time series aspect of the multivariate APS in-flight particle characteristics data is explored. Two strategies of time series embedding are considered. The first one simply embeds the attributes and the targets from the previous $$n$$ time segments considered without any modification; whereas the second strategy first performs differencing to make the time series stationary before embedding. For the present application, RF is found to be more suitable than GB since RF can predict both the in-flight particle velocity and temperature simultaneously, properly considering the interactions between the two targets. On the other hand, GB can only predict these two targets one at a time. The superior performance of both embedded predictive models and the feature rankings of them suggest that it is better to consider the APS data as time series for the in-flight particle characteristic prediction. In particular, it is demonstrated that it is advantageous to first make the time series stationary using the traditional differencing technique, even when modeling using RF.
Source: crossref · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Radiative Heat Transfer Studies · Laser-induced spectroscopy and plasma · Gas Dynamics and Kinetic Theory
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (39)
Show source-provided references
1. S. Guessasma, G. Montavon, P. Gougeon, and C. Coddet, Designing Expert System Using Neural Computation in View of the Control of Plasma Spray Processes, Mater. Des., 2003, 24(7), p 497-502. https://doi.org/10.1016/S0261-3069(03)00109-210.1016/S0261-3069(03)00109-2 ↗
2. S. Guessasma, G. Montavon, and C. Coddet, Modeling of the APS Plasma Spray Process Using Artificial Neural Networks: Basis, Requirements and an Example, Comput. Mater. Sci., 2004, 29(3), p 315-333. https://doi.org/10.1016/j.commatsci.2003.10.00710.1016/j.commatsci.2003.10.007 ↗
3. A.-F. Kanta, M.-P. Planche, G. Montavon, and C. Coddet, In-Flight and Upon Impact Particle Characteristics Modelling in Plasma Spray Process, Surf. Coat. Technol., 2010, 204(9-10), p 1542-1548. https://doi.org/10.1016/j.surfcoat.2009.09.07610.1016/j.surfcoat.2009.09.076 ↗
4. W. Sha, Comment on Modelling of the APS Plasma Spray Process Using Artificial Neural Networks: Basis, Requirements and an Example’ by Guessasma et al. [Comput. Mater. Sci. 29 (2004) 315], Comput. Mater. Sci., 2010, 50, p 805-809. https://doi.org/10.1016/j.commatsci.2010.09.01310.1016/j.commatsci.2010.09.013 ↗
5. T.A. Choudhury, N. Hosseinzadeh, and C.C. Berndt, Artificial Neural Network application for predicting in-flight particle characteristics of an atmospheric plasma spray process, Surf. Coat. Technol., 2011, 205(21-22), p 4886-4895. https://doi.org/10.1016/j.surfcoat.2011.04.09910.1016/j.surfcoat.2011.04.099 ↗
6. T.A. Choudhury, C.C. Berndt, and Z. Man, An Extreme Learning Machine Algorithm to Predict the In-flight Particle Characteristics of an Atmospheric Plasma Spray Process, Plasma Chem. Plasma Process., 2013, 33(5), p 993-1023. https://doi.org/10.1007/s11090-013-9466-410.1007/s11090-013-9466-4 ↗
7. T.A. Choudhury, C.C. Berndt, and Z. Man, Modular Implementation of Artificial Neural Network in Predicting In-Flight Particle Characteristics of an Atmospheric Plasma Spray Process, Eng. Appl. Artif. Intell., 2015, 45, p 57-70. https://doi.org/10.1016/j.engappai.2015.06.01510.1016/j.engappai.2015.06.015 ↗
8. T. Liu, S. Deng, M.-P. Planche, and G. Montavon, Estimating the Behavior of Particles Sprayed by a Single-Cathode Plasma Torch Based on a Nonlinear Autoregressive Exogenous Model, Surf. Coat. Technol., 2015, 268, p 284-292. https://doi.org/10.1016/j.surfcoat.2014.10.04010.1016/j.surfcoat.2014.10.040 ↗
9. J. Zhu, X. Wang, L. Kou, L. Zheng, and H. Zhang, Prediction of Control Parameters Corresponding to In-Flight Particles in Atmospheric Plasma Spray Employing Convolutional Neural Networks, Surf. Coat. Technol., 2020, 394, 125862. https://doi.org/10.1016/j.surfcoat.2020.12586210.1016/j.surfcoat.2020.125862 ↗
10. A.-F. Kanta, G. Montavon, C.C. Berndt, M.-P. Planche, and C. Coddet, Intelligent System for Prediction and Control: Application in Plasma Spray Process, Expert Syst. Appl., 2011, 38(1), p 260-271. https://doi.org/10.1016/j.eswa.2010.06.05610.1016/j.eswa.2010.06.056 ↗
11. T. Liu et al., Plasma Spray Process Operating Parameters Optimization Based on Artificial Intelligence, Plasma Chem. Plasma Process., 2013, 33(5), p 1025-1041. https://doi.org/10.1007/s11090-013-9475-310.1007/s11090-013-9475-3 ↗
12. J. Zhu, X. Wang, L. Kou, L. Zheng, and H. Zhang, Application of Combined Transfer Learning and Convolutional Neural Networks to Optimize Plasma Spraying, Appl. Surf. Sci., 2021, 563, 150098. https://doi.org/10.1016/j.apsusc.2021.15009810.1016/j.apsusc.2021.150098 ↗
13. S. Guessasma, G. Montavon, and C. Coddet, Analysis of the Influence of Atmospheric Plasma Spray (APS) Parameters on Adhesion Properties of Alumina-Titania Coatings, J. Adhes. Sci. Technol., 2004, 18(4), p 495-505. https://doi.org/10.1163/15685610432301638810.1163/156856104323016388 ↗
14. L. Wang, J.C. Fang, Z.Y. Zhao, and H.P. Zeng, Application of Backward Propagation Network for Forecasting Hardness and Porosity of Coatings by Plasma Spraying, Surf. Coat. Technol., 2007, 201(9-11), p 5085-5089. https://doi.org/10.1016/j.surfcoat.2006.07.08810.1016/j.surfcoat.2006.07.088 ↗
15. A.-F. Kanta, G. Montavon, M.-P. Planche, and C. Coddet, Artificial Intelligence Computation to Establish Relationships Between APS Process Parameters and Alumina-Titania Coating Properties, Plasma Chem. Plasma Process., 2008, 28(2), p 249-262. https://doi.org/10.1007/s11090-007-9116-910.1007/s11090-007-9116-9 ↗
16. Z. Wu, Empirical Modeling for Processing Parameters’ Effects on Coating Properties in Plasma Spraying Process, J. Manuf. Process., 2015, 19, p 1-13. https://doi.org/10.1016/j.jmapro.2015.03.00710.1016/j.jmapro.2015.03.007 ↗
17. C.-M. Lin, S.-H. Yen, and C.-Y. Su, Measurement and Optimization of Atmospheric Plasma Sprayed CoMoCrSi Coatings Parameters on Ti-6Al-4V Substrates Affecting Microstructural and Properties Using Hybrid Abductor Induction Mechanism, Measurement, 2016, 94, p 157-167. https://doi.org/10.1016/j.measurement.2016.07.07710.1016/j.measurement.2016.07.077 ↗
18. M. Kuhn and K. Johnson, Applied Predictive Modeling, Springer, New York, 2013.10.1007/978-1-4614-6849-3 ↗
19. R. Caruana and A. Niculescu-Mizil, An empirical comparison of supervised learning algorithms, In: Proceedings of the 23rd international conference on Machine learning - ICML ’06, Pittsburgh, Pennsylvania, 2006, pp. 161-168. doi: https://doi.org/10.1145/1143844.1143865.10.1145/1143844.1143865 ↗
20. M. Fernández-Delgado, E. Cernadas, S. Barro, and D. Amorim, Do we Need Hundreds of Classifiers to Solve Real World Classification Problems?, J. Mach. Learn. Res., 2014, 15(90), p 3133-3181.
21. L. Breiman, Random Forests, Mach. Learn., 2001, 45(1), p 5-32. https://doi.org/10.1023/A:101093340432410.1023/A:1010933404324 ↗
22. J.H. Friedman, Greedy Function Approximation: A Gradient Boosting Machine, Ann. Stat., 2001, 29(5), p 1189-1232. https://doi.org/10.1214/aos/101320345110.1214/aos/1013203451 ↗
23. J.H. Friedman, Stochastic Gradient Boosting, Comput. Stat. Data Anal., 2002, 38(4), p 367-378. https://doi.org/10.1016/S0167-9473(01)00065-210.1016/S0167-9473(01)00065-2 ↗
24. B. Boehmke and B.M. Greenwell, Hands-on Machine Learning with R, CRC Press, Boca Raton, 2019.10.1201/9780367816377 ↗
25. D.H. Wolpert, The Lack of A Priori Distinctions Between Learning Algorithms, Neural Comput., 1996, 8(7), p 1341-1390. https://doi.org/10.1162/neco.1996.8.7.134110.1162/neco.1996.8.7.1341 ↗
26. M. Hostetter, A. Ahmadzadeh, B. Aydin, M. K. Georgoulis, D. J. Kempton, and R. A. Angryk, Understanding the Impact of Statistical Time Series Features for Flare Prediction Analysis, In: 2019 IEEE International Conference on Big Data (Big Data), Los Angeles, CA, USA, 2019, pp. 4960-4966. doi: https://doi.org/10.1109/BigData47090.2019.9006116.10.1109/BigData47090.2019.9006116 ↗
27. E. Mussumeci and F. Codeço Coelho, Large-Scale Multivariate Forecasting Models for Dengue LSTM Versus Random Forest Regression, Spatio-Temporal Epidemiol Spat, 2020 https://doi.org/10.1016/j.sste.2020.10037210.1016/j.sste.2020.100372 ↗
28. G. Dudek, Short-Term Load Forecasting Using Random Forests, In: Intelligent Systems’2014, vol. 323, D. Filev, J. Jabłkowski, J. Kacprzyk, M. Krawczak, I. Popchev, L. Rutkowski, V. Sgurev, E. Sotirova, P. Szynkarczyk, and S. Zadrozny, Eds. Cham: Springer International Publishing, 2015, pp. 821-828. doi: https://doi.org/10.1007/978-3-319-11310-4_71.10.1007/978-3-319-11310-4_71 ↗
29. C. Paoli, C. Voyant, M. Muselli, and M.-L. Nivet, Forecasting of Preprocessed Daily Solar Radiation Time Series Using Neural Networks, Sol. Energy, 2010, 84(12), p 2146-2160. https://doi.org/10.1016/j.solener.2010.08.01110.1016/j.solener.2010.08.011 ↗
30. P.-H. Chiang, S. P. V. Chiluvuri, S. Dey, and T. Q. Nguyen, Forecasting of Solar Photovoltaic System Power Generation Using Wavelet Decomposition and Bias-Compensated Random Forest, In: 2017 Ninth Annual IEEE Green Technologies Conference (GreenTech), Denver, CO, USA, 2017, pp. 260-266. doi: https://doi.org/10.1109/GreenTech.2017.4410.1109/GreenTech.2017.44 ↗
31. M. Segal and Y. Xiao, Multivariate Random Forests, WIREs Data Min. Knowl. Discov., 2011, 1(1), p 80-87. https://doi.org/10.1002/widm.1210.1002/widm.12 ↗
32. Comparing random forests and the multi-output meta estimator — scikit-learn 0.24.1 documentation. https://scikit-learn.org/stable/auto_examples/ensemble/plot_random_forest_regression_multioutput.html (accessed 19, 2021).
33. H. Ishwaran and U. B. Kogalur, randomForestSRC: Fast Unified Random Forests for Survival, Regression, and Classification (RF-SRC). 2020. Accessed: 19, 2021. [Online]. Available: https://CRAN.R-project.org/package=randomForestSRC
34. R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice (3rd ed). Accessed: 10, 2021. [Online]. Available: https://Otexts.com/fpp3/
35. T. Hastie, R. Tibshirani, and J.H. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd ed. Springer, New York, NY, 2009.10.1007/978-0-387-84858-7 ↗
36. sklearn.ensemble.RandomForestRegressor, scikit-learn. https://scikit-learn/stable/modules/generated/sklearn.ensemble.RandomForestRegressor.html (accessed 08, 2022).
37. J. Brownlee, A Gentle Introduction to the Challenge of Training Deep Learning Neural Network Models,” Machine Learning Mastery, 14, 2019. https://machinelearningmastery.com/a-gentle-introduction-to-the-challenge-of-training-deep-learning-neural-network-models/ (accessed 08, 2022).
38. A Recipe for Training Neural Networks. http://karpathy.github.io/2019/04/25/recipe/ (Accessed 08, 2022).
39. K.S. Kim, Control-Oriented Dynamic Model of an Inductively Coupled Plasma Torch by Artificial Intelligence Methodology, Plasma Phys. Control. Fusion, 2019, 61(4), 044002. https://doi.org/10.1088/1361-6587/aaffb410.1088/1361-6587/aaffb4 ↗