Kohonen’s algorithm in problems of classification of defects in printed circuit assemblies

The article presents a new method for diagnosing the technical condition of radio-electronic components, combining the methods of thermal diagnostics with the technologies of artificial neural networks. The structure of the method is shown, and the composition of the functional blocks is determined. The implementation of the method is a symbiosis of technologies for mathematical and simulation modeling of the technical state of a radio-electronic device with its physical tests and research of characteristics. When developing the method, specialized software tools for design and circuit design were actively used, such as Altium Designer CAD, SolidWorks, NI Multisim, the FloTHERM PCB thermal analysis module, as well as the MATLAB mathematical modeling and calculation package. With the help of these tools, a number of studies were carried out, including sets of numerical values of the power of circuit elements and temperature indicators of the printing unit, both for the correct state of the device and in states with artificially introduced defects. They, in turn, became the basis of the database of electronic node failures. To implement diagnostic procedures and identify the technical condition, an artificial neural network based on selforganizing Kohonen maps was created, its structure, parameters and algorithms of functioning were determined. The diagnostic procedure is based on the analysis of information from the fault database and its comparison with experimental data obtained as a result of a physical experiment. The results of the study showed that the network automatically classifies the characteristic defects of electronic components using the algorithms embedded in it. The list of characteristic defects in the proposed diagnostic method is limited to a discrete set of the most common faults, because, as their number increases, the use of the self-organizing Kohonen network for automatic classification becomes much more complicated and ineffective in terms of performance and reliability of identification. Among the advantages of this technology, it should be noted that the Kohonen network has the ability to convert largedimensional input data into a two-dimensional array. So, the results are easy to visualize and convenient to use when generating reports and recommendations for subsequent decision-making about the possibility of using an electronic device.

1. Lyshov S.M., Uvaysov S.U., Chernoverskaya V.V., Le Quok Han Pham. Engineering technique for vibrodiagnostics of structures on-board radio electronic means. Naukoemkie tekhnologii = Science Intensive Technologies. 2020;21(2−3):17−29 (in Russ.). https://doi.org/10.18127/j19998465-202002-3-03

2. Uvaysov S.U., Chernoverskaya V.V., Lyshov S.M., Le Quok Han Pham, Uvaysova A.S. Artificial neural network in the problem of diagnostics of defects in the construction of printed circuit components of electronic devices. Naukoemkie tekhnologii = Science Intensive Technologies. 2020;21(10):29−39 (in Russ.). https://doi.org/10.18127/j19998465-202010-04

3. Lyshov S.M., Uvaysov S.U., Chernoverskaya V.V., Han P.Q. Method of vibration diagnostics of the technical condition of electronic means structures. Rossiiskii tekhnologicheskii zhurnal = Russian Technological Journal. 2021;9(2):44−56 (in Russ.). https://doi.org/10.32362/2500-316X-2021-9-2-44-56

4. Merkukhin E.N. A priori criteria of evaluation effictiveness optimization of thermal mode the rational placement of electronic elements. Sovremennye naukoemkie tekhnologii = Modern High Technologies. 2018;10:77–81 (in Russ.). Available from URL: http://top-technologies.ru/ru/article/view?id=37198

5. Sergeeva V.A., Tarasov R.G. Method for measuring thermal parameters of semiconductor products as part of an electronic module. Trudy Mezhdunarodnogo simpoziuma “Nadezhnost’ i kachestvo” = Proceedings of the International Symposium “Reliability and Quality”. 2020;2:183−185 (in Russ.).

6. Suleimanov S.P., Dolmatov A.V., Uvaisov S.U. Warm diagnostics of radio-electronic devices. In: Konferentsiya “Radiovysotometriya – 2004” (Radio Altimetry – 2004: Proceedings of First All-Russian scientific conf.). Ekaterinburg: Izd-vo AMB; 2004, p. 55−59. (in Russ.).

7. Isaev S.S., Yurkov N.K. Technique of thermal imaging control of faults in printed circuit assemblies of electronic equipment at the production stage. Trudy Mezhdunarodnogo simpoziuma “Nadezhnost’ i kachestvo” = Proceedings of the International Symposium “Reliability and Quality”. 2013;2:92−95 (in Russ.). Available from URL: https://cyberleninka.ru/article/n/metodika-teplovizionnogo-kontrolya-neispravnosteypechatnyh-uzlov-rea-na-etape-proizvodstva

8. Valyaev E.A. Neural network cascade based on selforganizing Kohonen maps. In: Sbornik izbrannykh statei po materialam nauchnykh konferentsii GNII “NATSRAZVITIE” (Themed collection of papers from international conferences by HNRI “National Development”). St. Petersburg: GNII “Natsrazvitie”; 2019. Part 2, p. 192−204. (in Russ.).

9. Kohonen T. Self-organizing maps. Verlag, Heidelberg: Springer; 2001. 502 p. [Kohonen T. Samoorganizuyushchiesya karty (Self-organizing maps). Moscow: BINOM. Laboratoriya znanii; 2008. 655 p. (in Russ.).]

10. Tian J., Azarian M.H., Pecht M. Anomaly detection using self-organizing maps based k-nearest neighbor algorithm. In: Proceedings of the European Conf. of the PHM Society. 2014;2(1).

11. Gorbachenko V.I., Akhmetov B.S., Kuznetsova O.Yu. Intellektual’nye sistemy: nechetkie sistemy i seti: uchebnoe posobie dlya vuzov (Intelligent systems: fuzzy systems and networks: a textbook for universities). Moscow: Yurait; 2019. 105 p. (in Russ.). ISBN 978-5-534-08359-0

12. Andreichikov A.V., Andreichikova O.N. Intellektual’nye informatsionnye sistemy i metody iskusstvennogo intellekta: uchebnik (Intelligent information systems and artificial intelligence methods: textbook). Moscow: INFRA-M; 2021. 530 p. ISBN 978-5-16-014883-0

13. Andreichikov A.V., Andreichikova O.N. Intellektual’nye tsifrovye tekhnologii kontseptual’nogo proektirovaniya inzhenernykh reshenii: uchebnik (Intelligent digital technologies for conceptual design of engineering solutions: textbook). Moscow: INFRA-M; 2019. 511 p. ISBN 978-5-16-014884-7

14. Haykin S. Neural networks. Prentice Hall, NJ: Upper Saddle River; 1999. 938 p. [Haykin S. Neironnye seti: polnyi kurs (Neural networks: a complete course). Moscow: Vil’yams; 2008. 1103 p. (in Russ.). ISBN 978-5-8459-0890-2]

15. Beale M.H., Hagan M.T., Demuth H.B. Neural Network Toolbox. User’s Guide. Natick: Math Works, Inc.; 2015. 406 p.