Predicting Maximum Process Temperature in Cortical Bone Milling: An XGBoost Approach with Sensitivity Insights

Document Type : Research Paper

Authors

Department of Mechanical Engineering, Arak University of Technology, Arak, Iran

Abstract

Bone milling, a crucial biomechanical process in medical engineering, finds applications in dentistry, orthopedic surgery, and bone-related treatments. The utilization of computer numerical control (CNC) surgical mills has significantly enhanced this process, but it comes with challenges such as elevated temperatures that induce thermal necrosis in bone tissue. This study examines key inputs, including tool diameter, feed rate, rotational speed, and cutting depth, conducting a detailed experiment to predict maximum process temperature using the XGBoost machine learning algorithm. The XGBoost model consistently demonstrated exceptional predictive accuracy, yielding high determination coefficients of 0.99 in training and 0.94 in testing. Accurate predictions were evident through close alignment between model-predicted and actual values, with mean absolute percentage error (MAPE) values of 0.33% and 3.38% for training and testing, respectively. Rotational speed emerged as a critical factor, indicating a key point where temperature trends shift. Higher speeds are correlated with lower temperatures due to enhanced chip removal and reduced bone heat conductivity. Elevated feed rates were associated with increased bone temperature, emphasizing the intricate interplay between frictional forces and heat production. Additionally, often-overlooked factors like cutting depth and tool diameter substantially influenced process temperature, impacting surgery recovery times. Sobol sensitivity analysis identified cutting depth, rotational speed, tool diameter, and feed rate as primary factors influencing maximum process temperature fluctuations, with effectiveness percentages of 46.7%, 36%, 13.2%, and 4.1%, respectively. This comprehensive analysis sheds light on optimizing bone milling processes and mitigating thermal risks in medical applications.

Keywords

References

[1] Dahotre, N. B., & Joshi, S. (2016). Machining of bone and hard tissues. Springer. https://doi.org/10.1007/978-3-319-39158-8
[2] Schröter, L., Kaiser, F., Küppers, O., Stein, S., Krüger, B., Wohlfahrt, P., Geroneit, I., Stahlhut, P., Gbureck, U., & Ignatius, A. (2024). Improving bone defect healing using magnesium phosphate granules with tailored degradation characteristics. Dental Materials, 40(3), 508–519. https://doi.org/10.1016/j.dental.2023.12.019
[3] Guenther, D., Schmidl, S., Klatte, T. O., Widhalm, H. K., Omar, M., Krettek, C., Gehrke, T., Kendoff, D., & Haasper, C. (2015). Overweight and obesity in hip and knee arthroplasty: Evaluation of 6,078 cases. World Journal of Orthopedics, 6(1), 137–144. https://doi.org/10.5312/wjo.v6.i1.137
[4] Aliyu, A. A. A., Abdul Rani, A. M., Ginta, T. L., Prakash, C., Axinte, E., Razak, M. A., & Ali, S. (2017). A review of additive mixed electric discharge machining: Current status and future perspectives for surface modification of biomedical implants. Advances in Materials Science and Engineering, 8723239. https://doi.org/10.1155/2017/8723239
[5] Pezzotti, G., & Yamamoto, K. (2014). Artificial hip joints: The biomaterials challenge. Journal of the Mechanical Behavior of Biomedical Materials, 31, 3–20. https://doi.org/10.1016/j.jmbbm.2013.06.001
[6] Plaskos, C. (2002). Bone sawing and milling in computer-assisted total knee arthroplasty [Master’s thesis, University of British Columbia]. https://doi.org/10.14288/1.0080992
[7] Rosen, J., Hannaford, B., & Satava, R. M. (2011). Surgical robotics: Systems applications and visions. Springer Science & Business Media.
[8] Hernandez Montero, E., Caballero, E., & García Ibanez, L. (2020). Surgical management of middle cranial fossa bone defects: Meningoencephalic herniation and cerebrospinal fluid leaks. American Journal of Otolaryngology, 41, 102560. https://doi.org/10.1016/j.amjoto.2020.102560
[9] Dahibhate, R. V., & Jaju, S. B. (2019). Bone drilling parameters and necrosis: An in vitro study. In Smart Technologies for Energy, Environment and Sustainable Development: Select Proceedings of ICSTEESD 2018 (pp. 599–606). Singapore: Springer Singapore.
[10] Gallo, J., Goodman, S. B., Konttinen, Y. T., Wimmer, M. A., & Holinka, M. (2013). Osteolysis around total knee arthroplasty: A review of pathogenetic mechanisms. Acta Biomaterialia, 9, 8046–8058. https://doi.org/10.1016/j.actbio.2013.06.032
[11] Zhang, Y., Robles Linares, J. A., Chen, L., Liao, Z., Shih, A. J., & Wang, C. (2022). Advances in machining of hard tissues – from material removal mechanisms to tooling solutions. International Journal of Machine Tools and Manufacture, 172, 103838. https://doi.org/10.1016/j.ijmachtools.2021.103838
[12] Eriksson, A., & Albrektsson, T. (1983). Temperature threshold levels for heat induced bone tissue injury: A vital microscopic study in the rabbit. The Journal of Prosthetic Dentistry, 50(1), 101–107. https://doi.org/10.1016/0022-3913(83)90174-9
[13] Berman, A. T., Spence, R. J., Yanicko, D. R., Sih, G. C., & Zimmerman, M. (1984). Thermally induced bone necrosis in rabbits: Relation to implant failure in humans. Clinical Orthopaedics and Related Research, 186, 284–292. https://doi.org/10.3109/02844318409052849
[14] Lundskog, J. (1972). An experimental investigation of the thermal properties of bone tissue and threshold levels for thermal injury. Scandinavian Journal of Plastic and Reconstructive Surgery, 9, 1–80.
[15] Bonfield, W., & Li, C. (1968). The temperature dependence of the deformation of bone. Journal of Biomechanics, 1, 323–329. https://doi.org/10.1016/0021-9290(68)90026-2
[16] Eriksson, R., Albrektsson, T., & Magnusson, B. (1984). Assessment of bone viability after heat trauma: A histological, histochemical and vital microscopic study in the rabbit. Scandinavian Journal of Plastic and Reconstructive Surgery, 18(3), 261–268. https://doi.org/10.3109/02844318409052849
[17] Eriksson, R., & Albrektsson, T. (1984). The effect of heat on bone regeneration: An experimental study in the rabbit using the bone growth chamber. Journal of Oral and Maxillofacial Surgery, 42, 705–711. https://doi.org/10.1016/0278-2391(84)90417-8
[18] Eriksson, R. A., & Adell, R. (1986). Temperatures during drilling for the placement of implants using the osseointegration technique. Journal of Oral and Maxillofacial Surgery, 44, 4–7. https://doi.org/10.1001/joms.1986.00860030056014
[19] Al Abdullah, K. I. A. L., Abdi, H., Lim, C. P., & Yassin, W. A. (2018). Force and temperature modelling of bone milling using artificial neural networks. Measurement, 116, 25–37. https://doi.org/10.1016/j.measurement.2017.10.051
[20] Liao, Z., Axinte, D., & Gao, D. (2019). On modelling of cutting force and temperature in bone milling. Journal of Materials Processing Technology, 266, 627–638. https://doi.org/10.1016/j.jmatprotec.2018.11.039
[21] Tahmasbi, V., Ghoreishi, M., & Zolfaghari, M. (2017). Investigation, sensitivity analysis, and multi-objective optimization of effective parameters on temperature and force in robotic drilling cortical bone. Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine, 231(11), 1012–1024. https://doi.org/10.1177/0954411917726098
[22] Hassanalideh, H. H., & Gholampour, S. (2020). Finding the optimal drill bit material and proper drilling condition for utilization in the programming of robot-assisted drilling of bone. CIRP Journal of Manufacturing Science and Technology, 31, 34–47. https://doi.org/10.1016/j.cirpj.2020.09.011
[23] Shin, H., & Yoon, Y.-S. (2006). Bone temperature estimation during orthopaedic round bur milling operations. Journal of Biomechanics, 39, 33–39.
[24] Sugita, N., Osa, T., & Mitsuishi, M. (2009). Analysis and estimation of cutting-temperature distribution during end milling in relation to orthopedic surgery. Medical Engineering & Physics, 31, 101–107. https://doi.org/10.1016/j.medengphy.2008.05.005
[25] Malvisi, A., Vendruscolo, P., Morici, F., Martelli, S., & Marcacci, M. (2000). Milling versus sawing: Comparison of temperature elevation and clinical performance during bone cutting. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 1238–1244). Berlin, Heidelberg: Springer Berlin Heidelberg.
[26] Talebi Ghadikolaee, H., Moslemi Naeini, H., Rabiee, A. H., Zeinolabedin Beygi, A., & Alexandrov, S. (2023). Experimental numerical analysis of ductile damage modeling of aluminum alloy using a hybrid approach: Ductile fracture criteria and adaptive neural fuzzy system (ANFIS). International Journal of Modelling and Simulation, 43(4), 736–751. https://doi.org/10.1080/02286203.2023.11866137
[27] Rabiee, A. H., Sherkatghanad, E., Zeinolabedin Beygi, A., Moslemi Naeini, H., & Lang, L. (2023). Experimental investigation and modeling of fiber metal laminates hydroforming process by GWO optimized neuro fuzzy network. Journal of Computational & Applied Research in Mechanical Engineering (JCARME), 12, 193–209. https://doi.org/10.22059/jcarme.2023.342589.623
[28] Safari, M., Rabiee, A., & Tahmasbi, V. (2022). Resistance spot welding process of AISI 304 steel: Application of sensitivity analysis and ANFIS GWO methods. Journal of Stress Analysis, 6, 21–29. https://doi.org/10.22059/jsa.2022.337368.1060
[29] Liu, C., He, Y., Li, Y., Wang, Y., Wang, L., Wang, S., & Wang, Y. (2021). Predicting residual properties of ball screw raceway in whirling milling based on machine learning. Measurement, 173, 108605. https://doi.org/10.1016/j.measurement.2020.108605
[30] Du, C., Ho, C. L., & Kaminski, J. (2021). Prediction of product roughness, profile, and roundness using machine learning techniques for a hard turning process. Advances in Manufacturing, 9, 206–215. https://doi.org/10.1007/s40436-021-00385-y
[31] He, Z., Shi, T., Xuan, J., & Li, T. (2021). Research on tool wear prediction based on temperature signals and deep learning. Wear, 478–479, 203902. https://doi.org/10.1016/j.wear.2021.203902
[32] Varghese, A., Kulkarni, V., & Joshi, S. S. (2021). Tool life stage prediction in micro milling from force signal analysis using machine learning methods. Journal of Manufacturing Science and Engineering, 143(5), 054501. https://doi.org/10.1115/1.4048636
[33] Tahmasbi, V., & Rabiee, A. H. (2022). Intelligent temperature modeling in robotic cortical bone milling process based on teaching learning-based optimization algorithm. Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine, 236(8), 1118–1128. https://doi.org/10.1177/09544119221106822
[34] Safari, M., Tahmasbi, V., & Rabiee, A. H. (2021). Investigation into the automatic drilling of cortical bones using ANFIS-PSO and sensitivity analysis. Neural Computing and Applications, 33(23), 16499–16517. https://doi.org/10.1007/s00521-021-06248-4
[35] Banda, T., Liu, Y.-C., Farid, A. A., & Lim, C. S. (2023). A machine learning model for flank wear prediction in face milling of Inconel 718. The International Journal of Advanced Manufacturing Technology, 126(7–8), 935–945. https://doi.org/10.1007/s00170-023-11152-3
[36] Rabiee, A. H., Tahmasbi, V., & Qasemi, M. (2023). Experimental evaluation, modeling and sensitivity analysis of temperature and cutting force in bone micro milling using support vector regression and EFAST methods. Engineering Applications of Artificial Intelligence, 120, 105874. https://doi.org/10.1016/j.engappai.2023.105874
[37] Zeng, S., & Pi, D. (2023). Milling surface roughness prediction based on physics informed machine learning. Sensors, 23, 4969. https://doi.org/10.3390/s23094969
[38] Araghizad, A. E., Pashmforoush, F., Tehranizadeh, F., Kilic, K., & Budak, E. (2024). Improving milling force predictions: A hybrid approach integrating physics based simulation and machine learning for remarkable accuracy across diverse unseen materials and tool types. Journal of Manufacturing Processes, 114, 92–107. https://doi.org/10.1016/j.jmapro.2024.02.015
[39] Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). https://doi.org/10.1145/2939672.2939785
[40] Asselman, A., Khaldi, M., & Aammou, S. (2023). Enhancing the prediction of student performance based on the machine learning XGBoost algorithm. Interactive Learning Environments, 31(6), 3360–3379. https://doi.org/10.1080/10494820.2021.1928235
[41] Wang, C.-C., Kuo, P.-H., & Chen, G.-Y. (2022). Machine learning prediction of turning precision using optimized XGBoost model. Applied Sciences, 12(15), 7739. https://doi.org/10.3390/app12157739
[42] Zhang, X. Y., Trame, M. N., Lesko, L. J., & Schmidt, S. (2015). Sobol sensitivity analysis: A tool to guide the development and evaluation of systems pharmacology models. CPT: Pharmacometrics & Systems Pharmacology, 4(2), 69–79. https://doi.org/10.1002/psp4.6
[43] Nossent, J., Elsen, P., & Bauwens, W. (2011). Sobol’s sensitivity analysis of a complex environmental model. Environmental Modelling & Software, 26, 1515–1525. https://doi.org/10.1016/j.envsoft.2011.06.019
[44] Kumar, D., Singh, A., Kumar, P., Jha, R. K., Sahoo, S. K., & Jha, V. (2020). Sobol sensitivity analysis for risk assessment of uranium in groundwater. Environmental Geochemistry and Health, 42, 1789–1801. https://doi.org/10.1007/s10653-020-00522-5
Iranian Journal of Materials Forming
Volume 12, Issue 3
2025
Pages 4-19

Files

Share

How to cite

Statistics