APPLICATION OF NEURAL NETWORK IN MONITORING THE THERMAL STATE OF BIOLOGICAL TISSUE IN THE WELDING ZONE
DOI:
https://doi.org/10.11603/mie.1996-1960.2023.3-4.14469Keywords:
artificial intelligence, neuron network, welding of biological tissues, thermal state controlAbstract
Background. The article discusses modern methods of regulating the welding process of soft biological tissues, based on the measurement of electrical parameters of high-frequency current and control of welding time. However, these methods do not consider input parameters such as the degree of compression of SBT and the temperature of SBT in the welding zone, which are constantly changing and can lead to problems during actual surgical welding. The use of thermocouples has its difficulties.
Materials and methods. In this study, a neural network (NN) was proposed and investigated, developed using the Neural Network Toolbox program in MatLab. For training this neural network, data obtained as a result of modelling the welding process of biological tissue of a pig's heart in the COMSOL environment were used. The modelling took into account thermal processes and the compression force of the biological tissue.
Results. It is crucial to have information about the thermal level of microbiological thermo compensation at given points to optimize the biological tissue welding process. This task can be effectively solved using artificial neural networks, which offer higher speed and accuracy compared to traditional methods. In this case, the neural network should be trained on an adequate model obtained by the finite element method or based on data from a physical experiment. The application of such a trained neural network allows taking into account the temperature and degree of compression of microbiological tissue by electrodes in the welding zone. In addition, the neural network can be used in a feedback system to control the technological process in order to ensure the necessary quality of welding.
Conclusions. The article describes examples of approaches to creating a «virtual temperature sensor» between the electrodes in the biological tissue welding zone.
References
Lebedev, O. V., Dubko, A. G., Chvertko, N. A. (2023). Fundamentals of computer multiphysics modelling of resistance welding of live tissues. Avtomatychne Zvaryuvannya, 5, 44-47. doi: 10.37434/as2023.05.05. [In Ukrainian]. DOI: https://doi.org/10.37434/as2023.05.05
Lankin, Yu. N., Sushy, L. F., Bajshtruk, E. N. (2014). System for measurement of temperature of biological tissues in bipolar high-frequency welding. The Paton Welding Journal, 11, 32-35. doi: 10.15407/tpwg2014.11.06. [In Russian]. DOI: https://doi.org/10.15407/tpwj2014.11.06
Paton, B. E., Krivtsun, I. V., Lankin, Yu. N. et al. (2013). Contact welding of soft biological tissues as an object of automatic control. Welding and heat treatment of living tissues. Theory. Practice. Perspectives: Proceedings of the Eighth Intern. scientific-practical. conf., Ed. by G. S. Marinskiy, K.: E.O. Paton Electric Welding Institute of the NAS of Ukraine, 32. [In Russian].
Ledesma, S., Ibarra-Manzano, M. A., Garcia-Hernandez, M. G., Almanza-Ojeda, D. L. (2017). Neural lab a simulator for artificial neural networks. Computing Conference, 18-20 July 2017, London: UK. doi: 10.1109/SAI.2017.8252175. DOI: https://doi.org/10.1109/SAI.2017.8252175
Wang, H., Yang, X., Madeniyeti, N. et al. (2022). Temperature distribution of vessel tissue by high frequency electric welding with combination optical measure and simulation. Biosensors, 12(4), 209. doi: 10.3390/bios12040209. DOI: https://doi.org/10.3390/bios12040209
Tran, N.-H., Bui, V.-H., Hoang, V.-T. (2023). Development of an artificial intelligence-based system for predicting weld bead geometry. Appl. Sci., 13(7). doi: 10.3390/app13074232. DOI: https://doi.org/10.3390/app13074232
Sacks, M. S., Motiwale, S., Goodbrake, C., Zhang, W. (2022). Neural network approaches for soft biological tissue and organ simulations. Journal of biomechanical engineering, 144(12). doi: 10.1115/1.4055835. DOI: https://doi.org/10.1115/1.4055835
Lankin, Yu. N., Soloviev, V. G., Romanova., I. Yu. (2021). Modeling of the anisotropy of the specific electrical conductivity of biological tissue arising at local compression by bipolar welding electrodes. Tekhnichna Elektrodynamika, 2, 13-19. doi: 10.15407/techned2021.02.013. [In Ukrainian]. DOI: https://doi.org/10.15407/techned2021.02.013
Lankin, Yu. M., Solovyov, V. G., Romanovа, I. Yu. (2021). Study of change in specific electrical conductivity of biological tissues as a result of local compression by electrodes in bipolar welding. The Paton Welding Journal, 1, 35-39. doi: 10.37434/tpwg2021.01.07. DOI: https://doi.org/10.37434/tpwj2021.01.07
Gukhman, A. A. (1973). Introduction to the theory of similarity. 2nd ed. M.: Higher school, 296 p. [In Russian].
Beale, M. H., Hagan, M. T., Demuth, H. B. (2010). Neural network toolbox user's guide. Version 7. The Math Works, Inc.: USA. Retrieved from: http://www.mathworks.com/help/pdf_doc/nnet/nnet.pdf.
Downloads
Published
How to Cite
Issue
Section
License
Journal Medical Informatics and Engineering allows the author(s) to hold the copyright without registration
The majority of Medical Informatics and Engineering Open Access journals publish open access articles under the terms of the Creative Commons Attribution (CC BY) License which permits use, distribution and reproduction in any medium, provided the original work is properly cited. The remaining journals offer a choice of licenses.
This journal is available through Creative Commons (CC) License CC-BY 4.0
