Email this article Enhancing Noise Immunity in a Voice Control System
- Authors: Palkov A.S.1,2, Kozlov V.V.3, Bodin A.Y.3, Kramm M.N.3, Bodin O.N.4
-
Affiliations:
- JSC “Research Institute of Physical Measurements”
- Penza State University
- National Research University “Moscow Power Engineering Institute”
- Penza State Technological University
- Issue: No 1 (2024)
- Pages: 47-59
- Section: Computer engineering and informatics
- URL: https://ogarev-online.ru/2306-2819/article/view/275997
- DOI: https://doi.org/10.25686/2306-2819.2024.1.47
- EDN: https://elibrary.ru/NPRUDL
- ID: 275997
Cite item
Full Text
Abstract
Introduction. In modern digital control systems, ensuring the reliability of ADCs is topical. Self-diagnosis algorithms are commonly employed to detect and address failures, thereby enhancing reliability. This research aims at developing a novel approach by harnessing the capabilities of a local fragmented control device (LFCD) to identify failures in the main measuring neuron (MMN) system, followed by the exclusion of the failed MMN from the neural network.
Materials and Methods. The study applied self-diagnosis algorithms to identify failed MMNs for two neural network structures: the "Internal Feedback Structure" and the "Redundant Link Structure." Graphical interpretations of the operation sequence are provided for cases of complete uncertainty, where the state of all neurons from the base group is unknown, and for cases of the unknown state of one neuron. The concept of the base group is introduced as the minimum number of neurons required for self-diagnosis.
Results and Conclusion. In the MatLab Simulink environment, we developed a model to compare neural network structures and self-diagnosis algorithms. We utilized this model to investigate the algorithm complexity and total time required for neural network analysis based on the number of tested neurons. Our findings demonstrated that for the "Internal Feedback Structure," the base group consists of 2m MMNs, where m represents the ADC resolution during self-diagnosis, while for the "Redundant Link Structure," it is 2m+1. The analysis highlighted that the "Redundant Link Structure" and selecting parameter m=3 represent the most optimal solution, offering shorter verification time and requiring less hardware resources while maintaining other characteristics.
Practical Significance. Research findings will enable subsequent self-diagnosis of control system elements and developing a diagnostic algorithm that ensures parallel checking in different areas of neural networks and the process of analog-to-digital conversion on the free part.
Full Text
About the authors
Alexander S. Palkov
JSC “Research Institute of Physical Measurements”; Penza State University
Author for correspondence.
Email: alekspalkov@gmail.com
SPIN-code: 3501-8949
Engineer, Master's student
Russian Federation, 8/10, Volodarskogo str., Penza,440026; 40, Krasnaja str., Penza,440026Valeriy V. Kozlov
National Research University “Moscow Power Engineering Institute”
Email: alekspalkov@gmail.com
SPIN-code: 3605-4537
Candidate of Technical Sciences, Associate Professor, Associate Professor at the Department of Information and Measuring Technology and Metrology
Russian Federation, 14, Krasnokazarmennaja str., Moscow,111250Andrey Y. Bodin
National Research University “Moscow Power Engineering Institute”
Email: alekspalkov@gmail.com
SPIN-code: 3307-4732
PhD student
Russian Federation, 14, Krasnokazarmennaja str., Moscow,111250Mikhail N. Kramm
National Research University “Moscow Power Engineering Institute”
Email: alekspalkov@gmail.com
ORCID iD: 0000-0002-8360-9879
SPIN-code: 3184-9707
Doctor of Engineering Sciences, Associate Professor, Professor at the Department of Radio Engineering Fundamentals
Russian Federation, 14, Krasnokazarmennaja str., Moscow,111250Oleg N. Bodin
Penza State Technological University
Email: alekspalkov@gmail.com
Russian Federation, 1a/11, Baidukova proezd/Gagarina str., Penza,440039
References
- Dyrmovsky DV, Matveev YuN, Balykina LA. Modern market of speech technologies. Control Engineering Russia. 2015;(1);18-24. (In Russ.).
- Sagatsyan MV, Kulikov AV, Tupitsin GS. Development and research into neuronet algorithm of speaker-independent speech recognition. Vestnik of Volga State University of Technology. Series “Radio Engineering and Infocommunication Systems”. 2014;(1);68-75. (In Russ.).
- Bodin ON, Bezborodova OE, Spirkin AN. Bionic control systems for mobile robotic complexes. Penza: Penza State University; 2022. 236 p. (In Russ.).
- Kozlov VV, Fokina EA, Trofimov AA. Pre-processing of signal in recognition of voice commands by method of improved complete multiple decomposition to empirical modes. Measurements. Monitoring. Management. Control. 2022;(3);56-61. (In Russ.). doi: 10.21685/2307-5538-2022-3-6
- Kamenskaya EN. Noise protection. Rostov-on-Don: Southern Federal University; 2023. 145 p. (In Russ.).
- Ivanova-Lukyanova GN. Culture of oral speech: intonation, pausing, logical stress, tempo, rhythm. Moscow: Flinta; 2022. 200 p. (In Russ.).
- Grishina SYu, Kurtsev GM, Putechev AD. The use of the software for calculation of the expected noise. Noise Theory and Practice. 2016;(2);35-41. (In Russ.).
- Kibrik AA, Podleskaya VI. The problem of segmentation of oral discourse and the cognitive system of the speaker. Kognitivnye issledovanija. Moscow: Institute of Psychology RAS,2006;(1):138–158. (In Russ.).
- Dyakonov VP. MATLAB 6/6.1/6.5+SIMULINK 4/5 in mathematics and modeling: Complete user guide. Moscow: SOLON-Press; 2003. 576 p. (In Russ.).
- Sklyar B. Digital communication. Theoretical foundations and practical application. Moscow: Williams Publishing House; 2017. 1100 p. (In Russ.).
Supplementary files
