Журнал Российского общества по неразрушающему контролю и технической диагностике
The journal of the Russian society for non-destructive testing and technical diagnostic
 
| Русский Русский | English English |
 
Главная Current Issue
18 | 11 | 2024
2021, 03 March

DOI: 10.14489/td.2021.03.pp.004-015

Kozelskaya S. O., Akimov D. A., Andreev A. S., Budadin O. N., Kotelnikov V. V.
APPLICATION OF DEEP NEURAL NETWORKS BASED ON PALLIATIVE ANALYSIS UNDER CONDITIONS OF INCOMPLETE INFORMATION OF OPTICAL THERMAL AND ELECTRIC NONDESTRUCTIVE TESTING FOR PREDICTION OF THE LIMIT RESOURCE OF OPERATION OF CONSTRUCTION
(pp. 4-15)

Abstract. The problem of assessing operational stability and, accordingly, assessing the storage and safe operation periods of objects (for example, load-bearing structural structures made of polymer composite materials (PCM)) has always been one of the most important. At present, this prediction problem is mainly solved on the basis of product testing, as well as a detailed study of the regularities of the physicochemical aging processes occurring in PCM and changes in the physical and mechanical characteristics of products, and the creation on this basis of appropriate test methods and mathematical prediction models. The paper considers the problem of increasing the reliability of assessing the maximum service life of multicomponent structures by constructing predictive models using the results of optical-thermal and electrical non-destructive testing of the state of objects by temperature fields and the value of internal deformation of the material under force on the structure as input information. It is shown that in the case of using logical approaches as a software tool for predicting the ultimate resource of structures made of polymer composite materials, part of the knowledge should be used for reasoning that provides an explanation of the conclusions drawn, since formal logic is of limited applicability, especially in conditions of incomplete or uncertain information. In this case, the solution to the problem becomes the identification and establishment of cause-and-effect relationships. For the tasks of technical assessment of the quality of structures and their service life, the use of such logical conclusions as inductive, deductive and analogous conclusions is impossible, since for their work, they require all information about the diagnosed structure. The use of the proposed method for assessing the service life will allow timely stopping the loading of products with loads and, thus, preventing structural destruction. It should be borne in mind that in order to reliably predict the ultimate service life of complex structures made of composite materials using the proposed method, a set of various input instrumental and subjective information about the structural and operational characteristics of the product is required, including information on intermediate tests, non-destructive testing data. at various stages of manufacturing, design features, stability of parameters during the development process, subjective opinions of specialists, changes in the properties of materials from time to time and loads, etc. Implementation of the proposed approach will allow creating a new generation of test methods and predicting operational stability with an assessment of the limiting service life of elements and structures, which, ultimately, will provide an additional opportunity for developing practical recommendations for confirming or extending the warranty periods of operation and increasing the reliability and safety of operation of structures.

Keywords: safety of structures, deep forecasting, artificial intelligence, forecasting the resource of structures, deep neural network, polymer composite materials, flaw detection, incomplete information, non-destructive testing, data processing.

S. O. Kozelskaya (JSC “CRISM”, Khotkovo, Moscow region, Russia) E-mail: Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра.
D. A. Akimov (Russian Technological University (MIREA) (RTU MIREA), Moscow, Russia) E-mail: Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра.
A. S. Andreev (Yaroslavl Higher Military School of Air Defense, Yaroslavl, Russia) E-mail: Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра.
O. N. Budadin (JSC “CRISM”, Khotkovo, Moscow region, Russia) E-mail: Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра.
V. V. Kotelnikov (Additional Professional Education “Training Center” Safety in Industry, Moscow, Russia) E-mail: Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра.

 

1. Budadin O. N., Kul'kov A. A., Rykov A. N. et al. (2015). Forecasting ultimate service life of complex engineering systems based on prediction simulation and artificial intelligence elements. Kontrol'. Diagnostika, 210(12), pp. 28 – 33. [in Russian language] DOI: 10.14489/ td.2015.12.pp.028-033
2. Kozelskaya S. (2020). Integrated thermal flaw detection technology of complex spatial composite structures in operation. Journal of Physics: Conference Series, Vol. 1636. The XXII Russian National Conference on Non-Destructive Testing and Technical Diagnostics “Transformation of Non-Destructive Testing and Technical Diagnostics in the Era of Digitalization. Society Security in a Changing World.” Moscow. DOI: 10.1088/1742-6596/1636/1/012023.
3. Kozel'skaya S. O. (2020). Method for electric power thermo-optical control of spatial objects and device for its implementation. [in Russian language]
4. Liu W., Wang Z., Liu X. et al. (2017). A survey of deep neural network architectures and their applications. Neurocomputing, Vol. 234, pp. 11 – 26.
5. Sozykin A. B. (2017). Overview of methods for training deep neural networks. Vestnik YuUrGU. Seriya Vychislitel'naya matematika i informatika, Vol. 6, (3), pp. 28 – 59. [in Russian language]
6. Morozova T. Yu., Bekarevich A. A., Budadin O. N. (2014). The new approach to identification of product defects. Kontrol'. Diagnostika, 194(8), pp. 42 – 48. [in Russian language] DOI: 10.14489/td.2014.08.pp.042-048
7. Cox P. T., Pietrzykowski T. (1987). General diagnosis by abductive inference. Proceedings of the IEEE Symposium on Logic Programming, pp. 183 – 189. San Francisco.
8. Golyandina N., Zhigljavsky A. (2013). Singular Spectrum Analysis for Time Series. Cardiff: Springer.
9. Klyuev V. V., Budadin O. N., Abramova E. V. et al. (2017). Thermal control of composite structures under conditions of force and shock loading. Moscow: ID «Spektr». [in Russian language]
10. Kaledin Val. O., Vyachkina E. A., Galdin D. A. et al. (2019). Electric power thermography constructions made of composite materials. Kontrol'. Diagnostika, (8), pp. 22 – 27. [in Russian language] DOI: 10.14489/td.2019.08.pp.022-027
11. Kulikov G. V., Do Ch. (2020). Efficiency of an adaptive filter with an envelope tracking algorithm when receiving signals from a multi-position PM against a background of non-fluctuation noise. Rossiyskiy tekhnologicheskiy zhurnal, 5(8), pp. 34 – 43. Available at: https://doi.org/10.32362/2500-316X-2020-8-5-34-43 [in Russian language]

This article  is available in electronic format (PDF).

The cost of a single article is 450 rubles. (including VAT 18%). After you place an order within a few days, you will receive following documents to your specified e-mail: account on payment and receipt to pay in the bank.

After depositing your payment on our bank account we send you file of the article by e-mail.

To order articles please copy the article doi:

10.14489/td.2021.03.pp.004-015

and fill out the  form  

 

 

 
Search
Rambler's Top100 Яндекс цитирования