Development of a personalized decompression control system based on an integral safety criterion

Improving the quality of decision-making in dive decompression planning is a relevant task in the modern development of decompression planning and management systems. The article describes the structural organization and operating principles of a comprehensive adaptive decompression control system. The system integrates classical gradient factor models with modules for monitoring and assessing key external factors and the physiological state of the diver. The paper details the system architecture, which includes planning, data processing, forecasting and decision-making blocks designed to identify optimal safe ascent strategies. To achieve this, an integral safety criterion was developed that aggregates five key indicators: current diver body temperature estimation, blood viscosity parameters, microbubble load assessment, total decompression stop time, and a historical dive type classifier. Solving the minimization problem of this criterion under specified constraints allows for the generation of an adaptive, personalized decompression profile. An algorithm for microbubble-based correction of stop times is described, built upon a baseline gradient factor plan and adaptively adjusting stop durations when threshold values of the microbubble criterion are exceeded. The proposed approach demonstrates its effectiveness in enhancing decision-making quality for decompression planning and management. Furthermore, the adequacy of the developed mathematical and algorithmic framework has been verified through the simulation of various ascent strategies.

1. Blaginin A.A., Zhiltsova I.I., Emelyanov Yu.A. Issues on decompression safety of flight crew. Military Medical Journal. 2017;338(7):42–45. (In Russ.).

2. Skovpin N.S., Parinov M.V. Model for planning and forecasting decompression dives using the correction method. Control Systems and Information Technology. 2021;(2):85–89. (In Russ.). https://doi.org/10.36622/VSTU.2021.84.2.018

3. Aguilella-Arzo М., Alcaraz А., Aguilella V. Heat loss and hypothermia in free diving: Estimation of survival time under water. American Journal of Physics. 2003;71(4):333–337. https://doi.org/10.1119/1.1531581

4. Mikheev M.A., Mikheeva I.M. Fundamentals of heat transfer. Moscow: Energiya; 1973. 320 p. (In Russ.).

5. Moraga C. Introduction to fuzzy logic. Facta universitatis – series: Electronics and Energetics. 2005;18(2):319–328. https://doi.org/10.2298/FUEE0502319M

6. Schreiner H.R. Mathematical approaches to decompression. International Journal of Biometeorology. 1967;11(3):301–310. https://doi.org/10.1007/BF01426653

7. Skovpin N., Parinov M. Simulation modeling of gas exchange processes based on physical factors and effects with the implementation that uses big data analysis methods. Journal of Physics: Conference Series. 2022;2373. https://doi.org/10.1088/1742-6596/2373/6/062018

8. Nikolaev V.P. Assessment of decompression safety by the number and size of gas bubbles formed in the body. Proceedings of the USSR Academy of Sciences. Biological Series. 1983;(6):822–834. (In Russ.).

9. Anuradha, Gupta G. A self explanatory review of decision tree classifiers. In: International Conference on Recent Advances and Innovations in Engineering (ICRAIE-2014), 09–11 May 2014, Jaipur, India. IEEE; 2014. https://doi.org/10.1109/ICRAIE.2014.6909245

10. Bühlmann A.A. Decompression – Decompression Sickness. Berlin, Heidelberg: Springer; 1984. 90 p. https://doi.org/10.1007/978-3-662-02409-6

11. Yount D.E., Hoffman D.C. On the use of a bubble formation model to calculate diving tables. Aviation, Space, and Environmental Medicine. 1986;57(2):149–156.