INFORMATIZATION AND MANAGEMENT

Construction of a neural network classifier of defects in pumping equipment of bakery industries based on simulated vibration spectra

Authors

EDN: ETYLIO

How to cite

GOST Poletaev A. A., Yablokov A. E. Construction of a neural network classifier of defects in pumping equipment of bakery industries based on simulated vibration spectra // Bakery of Russia. 2025. Vol. 69. No. 3-4. P. 45-56.
APA Poletaev, A. A. & Yablokov, A. E. (2025). Construction of a neural network classifier of defects in pumping equipment of bakery industries based on simulated vibration spectra. Bakery of Russia, 69(3-4), 45-56.

Abstract

The article discusses a method for constructing a neural network classifier of the technical conditions of pumping equipment used in the technological processes of bakery industries. The initial data for the analysis were obtained from real bearing assemblies, after which a simulation of typical defects was carried out, including cracks in the cage, roller wear, separator damage and rotor imbalance. As a result of the simulation, a set of averaged vibration acceleration and vibration velocity spectra was formed, reflecting the characteristics of both serviceable and defective states. Based on the data obtained, an artificial neural network was trained in the MATLAB environment using the nnstart toolkit. The network architecture includes one hidden layer with 20 neurons and an output with five classes of state. A scaled conjugate gradient algorithm and a cross-entropy loss function are used for training. The classification accuracy was assessed, error matrices and training schedules were analyzed. The results obtained confirm the effectiveness of the neural network approach to the diagnosis of pumping units, and also demonstrate the potential of using simulated spectra as training data. The technique can be applied in the development of intelligent predictive maintenance systems.

Keywords

vibration diagnostics pumping equipment neural network classification bakery production bearing units simulation modeling spectral analysis

References

Bryakin I.V., Bochkarev I.V. Measuring device for systems of technical vibration diagnostics of power equipment // News of higher educational institutions. Energy problems. 2023. Vol. 25. № 2. pp. 137-152.

Bukirev A.S., Savchenko A.Yu., Yatsechko M.I., Malyshev V.A. A system for diagnosing the technical condition of an aircraft's on-board equipment complex based on intelligent information technologies // Modeling, optimization and information technologies. 2020. Vol. 8. № 1(28).

Gerike P.B., Gerike B.L. Development of a system of unified diagnostic criteria for assessing the technical condition of mining machinery and equipment according to the parameters of mechanical vibrations // Innovations in the fuel and energy complex and mechanical engineering (TEK-2022): mat. of the III Inter. scien. and prac. conf. (April 19-21, 2022, Kemerovo). Kemerovo: T.F. Gorbachev Kuzbass State Technical University, 2022. pp. 206-213.

GOST 30576-98. Vibration. Centrifugal feed pumps of thermal power plants. Vibration standards and general requirements for measurements. M.: Publishing House of Standards, 2000.

GOST 31350-2007. Vibration. Industrial fans. Requirements for vibration and balancing quality. M.: Standartinform, 2008.

GOST R ISO 13374-3-2015. Condition monitoring and diagnostics of machines. Processing, transmission and provision of data. Part 3. Data transmission. M.: Standartinform, 2018. 12 p.

GOST IEC 60034-14-2014. Electric rotating machines. Part 14. Mechanical vibration of certain types of machines with shaft heights of 56 mm or more. Measurements, assessment and limits of vibration stiffness. M.: Standartinform, 2015. 16 p.

Zakirnichnaya M.M., Palladina Ya.A. Identification of the main malfunctions of centrifugal pumping units using a colorimetric amplitude indicator based on modeling of wavelet patterns // Electrotechnical and information complexes and systems. 2024. Vol. 20. № 3. pp. 98-106.

Ishmetyev E.N., Chistyakov D.V., Panov A.N. Vibration protection systems, vibration monitoring and vibration diagnostics of industrial equipment // Electrical engineering systems and complexes. 2019. № 1(42). pp. 67-73.

Kolobov A.B. Vibration diagnostics: theory and practice: a textbook. 2nd ed. M.: Vologda: Infra-Engineering, 2024. 252 p.

Levin V.M., Khalyasmaa A.I., Akhieev D.S., Manusov V.Z. Application of artificial intelligence methods in the tasks of technical diagnostics of electrical equipment of electrical systems. Novosibirsk: Novosibirsk State Technical University, 2020. 446 p.

Nikitin Yu.R., Trefilov S.A., Lekomtsev P.V. Intelligent mechatronic systems. Predicting the remaining resource: a textbook. M.: AI Art Media, 2023. 99 p.

Panina O.V., Zavalko N.A., Eremin S.G. Development of neural networks for analyzing vibration signals of mining equipment and emergency prevention // Mining Industry. 2025. № 2. pp. 97-104.

Piven V.V., Syzrantsev V.N., Chelombitko S.I. Vibration diagnostics of rotary equipment: a textbook. Tyumen: Tyumen Industrial University, 2021. 80 p.

Poletaev A.A., Yablokov A.E. Neural network method of technical diagnostics of equipment based on vibration velocity and vibration acceleration spectra // Proceedings of Tula State University. Technical sciences. 2024. № 5. pp. 476-481.

Safiullin R.A., Yangirov I.F. Investigation of vibration of an asynchronous electric motor // Electrotechnical and information complexes and systems. 2021. Vol. 17. № 2. pp. 41-54.

Semenov P.V., Sevostyanov A.Yu. Features of vibration diagnostics in monitoring the technical condition of an aircraft piston engine (review) // Ufa State Aviation Technical University bulletin. 2021. Vol. 25. № 3(93). pp. 72-79.

Shcherbatov I.A., Salov I.V. Forecasting the technical condition of equipment using machine learning methods on the example of a steam turbine bearing // Kazan State Power Engineering University bulletin. 2024. Vol. 16. № 4(64). pp. 25-37.

Yablokov A.E. Scientific and practical bases of creation of automated systems of technical monitoring and diagnostics of equipment of grain processing enterprises on the basis of neural network methods of data analysis: dis. … D-r of tech. scien. M., 2022. 377 p.

Yablokov A.E., Latyshev M.A., Blagoveshchenskiy I.G. Development of an intelligent system for technical monitoring of equipment using a universal sensor based on the STM32 microcontroller // Scientific and Technical Bulletin of the Volga region. 2024. № 10. pp. 143-146.

Yablokov A.E., Latyshev M.A., Shilina V.D., Poletaev A.A. ANN technologies in the problem of spectral vibration diagnostics of bakery equipment. 2024. Vol. 68. № 3. pp. 16-25.

Yablokov A.E. Vibration diagnostics of the main technological equipment of the grinding department of the mill: dis. … сand. of tech. scien. M., 2001. 183 p.

Czech P. Vibration diagnosis of car motor engines // Acta technica corviniensis – Bulletin of engineering. 2010. Fascicule 1. Vol. III. pp. 37-42.

Kelly S. Graham. Advanced Vibration Analysis (Dekker Mechanical Engineering). 2013. 637 p.

Xue X., Dong Y., Wu X. Motion Induced Eddy Current Sensor for Non-Intrusive Vibration Measurement // IEEE Sensors Journal, 2020, vol. 20, no. 2, pp. 735-744.

Yang Z., Wang S., Hong J., Li J. Analysis of electromagnetic exciting force and vibration of rotating armature permanent magnet synchronous motor // Journal of engineering. 2018, no. 17, pp. 1903-1908.

Issue

Vol. 69 No. 3-4 (2025): Bakery of Russia

Section

INFORMATIZATION AND MANAGEMENT

Metrics

16 views
0 downloads
JATS XML
Want to publish with us?
Submit an article

Machine-readable metadata

JATS XML

Similar Articles

1 2 3 4 5 6 > >> 

You may also start an advanced similarity search for this article.

Most read articles by the same author(s)