Prevention of emergency situations in complex technical systems using a neuromorphic approach

Prevention of emergency situations in complex technical systems using a neuromorphic approach

Alexandra A. Demcheva
Russian State Scientific Center for Robotics and Technical Cybernetics (RTC), Software Engineer, 21, Tikhoretsky pr., Saint Petersburg, 194064, Russia, This email address is being protected from spambots. You need JavaScript enabled to view it., ORCID: 0000 0002 1208 6353

Anton M. Korsakov
RTC, Senior Research Scientist, 21 Tikhoretsky pr., Saint-Petersburg, 194064, Russia, This email address is being protected from spambots. You need JavaScript enabled to view it., ORCID: 0000-0002-6132-7504

Ivan S. Fomin
RTC, Junior Research Scientist, 21 Tikhoretsky pr., Saint-Petersburg, 194064, Russia, This email address is being protected from spambots. You need JavaScript enabled to view it., ORCID: 0000-0001-9066-4836

Aleksandr V. Bakhshiev
PhD in Technical Sciences, Peter the Great Saint Petersburg Polytechnical University (SPbPU), Associate Professor, 29, Politekhnicheskaya ul., Saint Petersburg, 195251, Russia, This email address is being protected from spambots. You need JavaScript enabled to view it., ORCID: 0000 0002 1284-0088

Ekaterina Yu. Smirnova
RTC, Deputy Head of Scientific and Research Center, 21, Tikhoretsky pr., Saint Petersburg, 194064, Russia, This email address is being protected from spambots. You need JavaScript enabled to view it.

Received June 6, 2023

Abstract
The paper proposes a scheme of emergency prevention system based on neuromorphic approach. The system includes a prediction unit that implements a mathematical model of the cerebellum predictive functions, and an alarm unit that implements the pain sensation model, proposed by the authors earlier. As a basic element of the proposed system the Compartmental Spiking Neuron Model (CSNM) was used, capable of learning from a small number of examples. The use of neuromorphic approach allows to overcome the limitations associated with the formalizing complexity of the systems being diagnosed and the low availability of data for modeling the processes occurring in them. The overcoming these limitations is possible due to the possibility of learning from a small number of examples and the absence of the need to model the system being diagnosed itself. The paper also presents the results of testing of the proposed scheme, which was carried out on a computer model using synthetic data. The results of the testing showed the fundamental applicability of the proposed scheme in neuromorphic control systems.

Key words
Compartmental spiking neuron model; neuromorphic system; predictor; cerebellum model; model of pain; state control.

Acknowledgements
This work was done as the part of the Ministry of Education and Science of Russia state task No. 075-01623-22-00 «The Research and development of a biosimilar system based on energy-efficient software and hardware neuromorphic tools for controlling the behavior of mobile robots» (FNRG-2022-0016 1021060307690-3-1.2.1;2.2.2).

DOI
10.31776/RTCJ.11405

Bibliographic description
Demcheva, A.A. et al. (2023). "Prevention of emergency situations in complex technical systems using a neuromorphic approach". Robotics and Technical Cybernetics, vol. 11, no. 4, pp. 281-291, DOI: 10.31776/RTCJ.11405. (in Russian).

UDC identifier
004.896

References

  1. Tsvetkov, V.Ya. (2017), “Complex technical systems”, Educational resources and technologies, 3(20), pp. 86-92, DOI: 10.21777/2500-2112-2017-3-86-92. (in Russian).
  2. Korsakov, A., Bakhshiev, A., Astapova, L. and Stankevich, L. (2021), “Behavioral functions implementation on spiking neural networks”, Informatics and Automation, 20, no. 3, pp.591-622, DOI: 10.15622/ia.2021.3.4/
  3. Demcheva, A., Korsakov, A. and Bakhshiev, A. (2022), “Simulating of pain perceptions for solving binary classification problems, In: XXIV International Scientific and Technical Conference “Neuroinformatics-2022": Collection of scientific papers, MIPT, Moscow, Russia, pp. 355–361.
  4. Popa, L.S. and Ebner, T.J. (2019), “Cerebellum, Predictions and Errors”, Frontiers in Cellular Neuroscience, vol. 12, DOI: 10.3389/fncel.2018.00524.
  5. Bastian, A.J. and Thach, W.T. (2001), Structure and function of the cerebellum, in Manto, M.-U. and Pandolfo, M. (ed.), The Cerebellum and Its Disorders. Cambridge University Press, pp. 49–66. DOI: 10.1017/CBO9780511666469.007.
  6. Molinari, M., and Masciullo, M. (2019), “The Implementation of Predictions During Sequencing”, Frontiers in Cellular Neuroscience, vol. 13.
  7. Romanov, S.P., Pavlov Institute of Physiology, Russian Academy of Sciences (1974), Exstrapolyator [Extrapolator], USSR, Pat. SU 415672 A1. (in Russian).
  8. Bakhshiev, A. and Gundelakh, F. (2015). “Mathematical Model of the Impulses Transformation Processes in Natural Neurons for Biologically Inspired Control Systems Development”, In: AIST-SUP 2015 Proceedings, Yekaterinburg, Russia.
  9. Bakhshiev, A., Demcheva, A., and Stankevich, L. (2022), “CSNM: The Compartmental Spiking Neuron Model for Developing Neuromorphic Information Processing Systems”, in Kryzhanovsky, B., Dunin-Barkowski, W., Redko, V., Tiumentsev, Y. and Klimov, V.V. (ed.), Advances in Neural Computation, Machine Learning, and Cognitive Research V, Studies in Computational Intelligence. Springer International Publishing, Cham, pp. 327–333, DOI: 10.1007/978-3-030-91581-0_43.
  10. Melzack, R. and Wall, P.D. (1967), “Pain mechanisms: a new theory”, Survey of Anesthesiology,11, pp. 89–90, DOI: 10.1097/00132586-196704000-00002.
  11. Bakhshiev, A.V., Korsakov, A.M., Astapova, L.A. and Stankevich, L.A. (2021), “Structural adaptation of the Compartment spiking neuron model”, In: Proceedings of the VII All-Russian Conference, pp. 30–33. (in Russian).
  12. Bakhshiev, A. et al. (2020), “The architecture of a software platform for growing spiking neural networks simulator developing”, Journal of Physics: Conference Series, 1679, 042001, DOI: 10.1088/1742-6596/1679/4/042001.