STUDY OF THE APPLICATION OF THE SPIKING NEURAL NETWORK AND FINITE ELEMENT METHOD FOR DIAGNOSTICS OF ROBOT ASSEMBLIES
Abstract
One of the key parameters of any modern mechanical system is its vibration and acoustic characteristics, which have a direct impact on the environment and humans during operation. In this connection, the task of diagnosing the vibration characteristics of various complex mechanical objects, to which industrial robotic complexes can be referred, remains relevant. Due to the difficulty in carrying out diagnostics and experimental debugging of newly developed mechanisms, it is interesting to apply modern approaches to solving the problem of diagnostics, in particular, with the use of neural networks and numerical methods. The purpose of this work was to investigate the possibility of joint application of spike neural network and finite element method for estimation of vibration characteristics on the example of wave gearbox bearing. The paper describes in detail the algorithm of diagnostics, which includes the stages of development of both the finite element model of the investigated mechanical system and the development of the neural network architecture. At the same time, the generation of training and control datasets for the neural network is carried out on a simplified finite element model having characteristics similar to the detailed one, which is ensured by the coincidence of the first ten eigenforms of the assembly. The data sets were generated on the basis of numerical calculations using an explicit scheme of integration in time of a simplified model of a gearbox with several types of artificially introduced defects similar to those appearing during operation of a real bearing. To analyze the frequency characteristics, a spike neural network architecture was developed and further improved on a training set of single defects. As a result of the study it was determined that the developed spike neural network provides classification of data on the control dataset with 85% accuracy, which allows us to conclude about the applicability of the proposed method of determining the vibration state of mechanical systems with the joint use of neural networks and finite element method.
References
1. Пархоменко П.П. О технической диагностике. – М.: Знание, 1969. – 90 с.
2. Челомей В.Н. и др. Вибрации в технике. Т. 5. – М.: Машиностроение, 1981. – 496 с.
3. ГОСТ Р ИСО 7919-1-99. Контроль состояния машин по результатам измерений вибрации на
вращающихся валах. Общие требования. – М.: Госстандарт.
4. Masoumi M., Alimohammadi H. An investigation into the vibration of harmonic drive systems // Frontiers
of Mechanical Engineering. – 2013. – Vol. 8. – P. 409-419.
5. Gerike B., Mokrushev A. The Detection of Defects in Rolling Bearings Based on the Analysis of
Vibroacoustic Signal // Proceedings of the 9th China- u ssia Symposium: “Coal in the 21 Century:
Mining, Intelligent Equipment and Environment Protection”. – 2018.
6. Huang D., Zong P., Jingjun G. Defect elimination in torsional harmonic reducer based on harmonic
resonance // Vibroengineering PROCEDIA. – 2019. – Vol. 28. – P. 6.
7. Raviola A., De Martin A., Guida R., Jacazio G., Mauro S., & Sorli M. Harmonic Drive Gear Failures in
Industrial Robots Applications: An Overview // PHM Society European Conference. – 2021. – Vol. 6.
8. Abdeljaber O., Avci O., Kiranyaz S., Gabbouj M., Inman D. Real-Time Vibration-Based Structural
Damage Detection Using One-Dimensional Convolutional Neural Networks // Journal of Sound and
Vibration. – 2016. – Vol. 388. – P. 154-170. – DOI: 10.1016/j.jsv.2016.10.043.
9. Abdeljaber O., Sassi S., Avci O., Kiranyaz S., Ibrahim A., Gabbouj M. Fault Detection and Severity
Identification of Ball Bearings by Online Condition Monitoring // IEEE Transactions on Industrial
Electronics. – 2018. –DOI: 10.1109/TIE.2018.2886789
10. Avci O., Abdeljaber O., Kiranyaz S., Hussein M., Gabbouj M., Inman D. A review of vibration-based
damage detection in civil structures: From traditional methods to Machine Learning and Deep Learning
applications // Mechanical Systems and Signal Processing. – 2021. – Vol. 147.
11. Yang G., Zhong Y., Yang L., Du R. Fault Detection of Harmonic Drive Using Multiscale Convolutional
Neural Network // IEEE Transactions on Instrumentation and Measurement. – 2020.
12. Wang H., Fang K., Li, Jie, Xi, Chaofei. Analysis and experimental study on vibration characteristics of
the RV reducer // Advances in Mechanical Engineering. – 2023.
13. Костюков В.Н., Науменко А.П. Основы виброакустической диагностики и мониторинга машин.
– Омск: ОмГТУ, 2011. – 414 с.
14. Shrestha A., Mahmood A. Review of Deep Learning Algorithms and Architectures // IEEE Access.
– 2019.
15. Calude C.S., Heidari S., Sifakis J. What perceptron neural networks are (not) good for? // Information
Sciences. – 2023. – Vol. 621.
16. Yamazaki K., Vo-Ho V.-K., Bulsara D., Le N. Spiking Neural Networks and Their Applications:
A Review // Brain Sci. – 2022. – Vol. 12.
17. Бахшиев А.В., Демчева А.А. Сегментная спайковая модель нейрона // Известия вузов. ПНД.
– 2022. – Т. 30, № 3. – С. 299-310.
18. Кузьмин М.И., Тамм А.Ю., Прохоренкова И.Г. Разработка методики моделирования зубчатого
зацепления волнового редуктора с применением МКЭ // Экстремальная робототехника. – 2024.
– № 1 (34). – С. 376-386.
19. Корсаков А.М., Астапова Л.А., Бахшиев А.В. Применение сегментной спайковой модели нейро-
на со структурной адаптацией для решения задач классификации // Информатика и автоматиза-
ция. – 2022. – Т. 21, № 3. – P. 493-520.
20. Бахшиев А.В., Корсаков А.М., Астапова Л.А., Станкевич Л.А. Структурная адаптация сегментной
спайковой модели нейрона. – Институт прикладной физики Российской академии наук, 2021.
21. Kingma D.P., Ba J. Adam: A Method for Stochastic Optimization // arXiv:1412.6980 [cs]. – arXiv, 2017
