The System Simulating the State of the Objects and the Process of Their Monitoring with the Help of the Convolutional Neural Network

Daniil A. Loktev; Alexey A. Loktev; Alexander Andreevich Makarov; Dmitry Shepelev

doi:10.15866/iremos.v15i1.19567

The System Simulating the State of the Objects and the Process of Their Monitoring with the Help of the Convolutional Neural Network

Daniil A. Loktev⁽¹⁾, Alexey A. Loktev⁽²⁾, Alexander Andreevich Makarov^(3*), Dmitry Shepelev⁽⁴⁾

^(*) Corresponding author

Authors' affiliations

DOI: https://doi.org/10.15866/iremos.v15i1.19567

Abstract

In this paper, the implementation of the system simulating the states of the objects and the process of their monitoring is considered. The tasks for this system include detection and diagnosis of defective states of the studied objects. In order to configure flexibly the system and to reduce the human factor, the use of neural networks is proposed. The model of the complex for the object monitoring simulation is presented. It is introduced in the form of a software application and is tested as a part of a diagnostic system fitted in the railroad track measuring car. This system makes it possible to determine the dimensions of artificial structures on the railway and, most importantly, to find the sites where the standard overall dimensions are reduced due to the deviation of separate structural elements from their designed position. The algorithmic and mathematical support employed in this paper allows determining the geometric (dimensions and position in space), the kinematic (speed and direction of movement) and the dynamic (motion acceleration, unredeemed car acceleration) characteristics of both moving and stationary objects. During its implementation, such system takes the form of a software and hardware complex equipped with movable and fixed photodetectors, depending on the set of tasks to be solved. A characteristic feature of this study is that the methods and the algorithms it proposes for image processing can be adapted and used in building digital twins of transport infrastructure objects including not only the railway tracks but also various technological and service facilities. Due to this approach, the input of the nodal points of infrastructure objects and their elements can be automated into the project design scheme, exponentially reducing the laboriousness of creating primary models. The aggregation of the proposed methods with the capabilities of modern neural networks improves the primary image processing speed on the side of the client application, without fully occupying the data transfer channel between different modules of the information-measuring complex.
Copyright © 2022 Praise Worthy Prize - All rights reserved.

Keywords

Measurement and Monitoring System; Image Analysis; Convolutional Neural Network; Object Parameters; Characteristic Points; Type I and II Errors; Simulation

Full Text:

PDF

References

H. Borstell, J. Nonnen, Simulation of Image Data to Support the Training of Convolutional Neural Networks for Objects Recognition, Advanced Logistic Systems - Theory and Practice, Vol. 13 (Issue 1): 37-45, July 2019.
https://doi.org/10.32971/als.2019.010

D.J. Murray-Smith, Methods of System Identification, Parameter Estimation and Optimisation Applied to Problems of Modelling and Control in Engineering and Physiology, D.Sc. dissertation, Dept. Electron. Elect. Eng., Univ. Glasgow, Glasgow, 2019.
http://theses.gla.ac.uk/1170/

N.V. Ruzanov, M.A. Bolotov, V.A. Pechenin, The Model for Estimating the Measurement Error in Geometric Parameters of Complex Surfaces, Journal of Physics: Conference Series, Vol. 1096 (Issue 1): 1-6, December 2018.
https://doi.org/10.1088/1742-6596/1096/1/012163

Sokolov, S., Plotnikov, D., Grachev, A., Lebedev, V., Evaluation of Loads Applied on Engineering Structures Based on Structural Health Monitoring Data, (2020) International Review of Mechanical Engineering (IREME), 14 (2), pp. 146-150.
https://doi.org/10.15866/ireme.v14i2.18269

D. A. Loktev, A. A. Loktev, Determination of Object Location by Analyzing the Image Blur, Contemporary Engineering Sciences, Vol. 8 (Issue 9): 467-475, April 2015.
https://doi.org/10.12988/ces.2015.52198

D. A. Loktev, Y. A. Bykov, N. I. Kovalenko, Use of the Analysis Technique of Image Blurring for Detection of External Defects of a Railway Track (in Russian), Science and Technology of Transport, (Issue 1): 69-75, April 2016.
http://ntt.rgotups.ru/english/2016_1.html

D.A. Loktev, A.A. Loktev, Diagnostics of External Defects of Railway Infrastructure by Analysis of Its Images, 2018 Global Smart Industry Conference, pp. 1-7, Chelyabinsk, Russia, November 2018.
https://doi.org/10.1109/GloSIC.2018.8570083

Sánchez Ocaña, W., Delgado, E., Jácome, E., Moreano, L., Designing and Implementing a Didactic Module of Artificial Vision for the Selection of Objects According to Colors and Morphological Characteristics, (2020) International Review of Automatic Control (IREACO), 13 (5), pp. 244-254.
https://doi.org/10.15866/ireaco.v13i5.19089

Alhasanat, M., Alsafasfeh, M., Alhasanat, A., Althunibat, S., RetinaNet-Based Approach for Object Detection and Distance Estimation in an Image, (2021) International Journal on Communications Antenna and Propagation (IRECAP), 11 (1), pp. 19-25.
https://doi.org/10.15866/irecap.v11i1.19341

Gorshkova, K., Zueva, V., Kuznetsova, M., Tugashova, L., Optimizing Deep Learning Methods in Neural Network Architectures, (2021) International Review of Automatic Control (IREACO), 14 (2), pp. 93-101.
https://doi.org/10.15866/ireaco.v14i2.20591

Habib, T., Nonlinear Spacecraft Attitude Control via Cascade-Forward Neural Networks, (2020) International Review of Automatic Control (IREACO), 13 (3), pp. 146-152.
https://doi.org/10.15866/ireaco.v13i3.19149

Belkhiri, D., Alaoui, M., Improved Tracking of Optimal Torque by Artificial Neural Network for Wind Energy Systems, (2021) International Review on Modelling and Simulations (IREMOS), 14 (2), pp. 110-117.
https://doi.org/10.15866/iremos.v14i2.19157

G. Chandan, A. Jain, H. Jain, M. Mohana, Real Time Object Detection and Tracking Using Deep Learning and OpenCV, International Conference on Inventive Research in Computing Applications, pp. 1305-1308, Coimbatore, India, July 2018.
https://doi.org/10.1109/ICIRCA.2018.8597266

D.A. Loktev, A.A. Loktev, Development of a User Interface for an Integrated System of Video Monitoring Based on Ontologies, Contemporary Engineering Sciences, Vol. 8 (Issue 20): 789-797, September 2015.
https://doi.org/10.12988/ces.2015.57196

O.V. Chernoyarov, M. Breznan, M., A.V. Terekhov, Restoration of Deterministic and Interference Distorted Signals and Images with Use of the Generalized Spectra in Bases of Orthogonal Polynomials and Functions, Communications - Scientific Letters of the University of Zilina, Vol. 15 (Issue 2A): 71-77, July 2013.
https://doi.org/10.26552/com.C.2013.2A.71-77

A.A. Voevoda, D.O. Romannikov, Formation of the Structure of a Neuron Network through Decomposition of the Initial Task on a Particular Example of the Robot-Manipulator Managing Problem (in Russian), Proceedings of Saint Petersburg Electrotechnical University Journal, (Issue 9): 27-32, October 2018.
https://izv.etu.ru/en/archive/2018/9/27-32

I.S. Drokin, About an Algorithm for Consistent Weights Initialization of Deep Neural Networks and Neural Networks Ensemble Learning, Vestnik of Saint Petersburg University. Series 10. Applied Mathematics. Computer Science. Control Processes, (Issue 4): 66-74, December 2016.
https://doi.org/10.21638/11701/spbu10.2016.406

V.I. Koshelev, D.T. Nguyen, Training of Multilayer Neural Networks Based on the Algorithm of Back Propagation of Errors in Recognition of Airborne Objects (in Russian), Vestnik of Ryazan State Radioengineering University, (Issue 20): 81-85, April 2017.
http://vestnik.rsreu.ru/en/archive/2007/1-issue-20

A. D'Acremont, R. Fablet, A. Baussard, G. Quin, CNN-based Target Recognition and Identification for Infrared Imaging in Defence Systems, Sensors, Vol. 19 (Issue 9): 1-16, April 2019.
https://doi.org/10.3390/s19092040

V.G. Manzhula, D.S. Fedyashov, Kohonen Neural Networks and Fuzzy Neural Networks in Data Mining (in Russian), Fundamental Research, (Issue 4): 108-114, April 2011.
https://www.fundamental-research.ru/en/article/view?id=21239

V.D. Semeikin, A.V. Skupchenko, Management Network Data Based on Neural Networks (in Russian), Infokommunikacionnye Tecnologii, Vol. 9 (Issue 2): 27-31, March 2011.

P. Langley, User Modeling in Adaptive Interfaces. Seventh International Conference on User Modeling, Vol. 407, pp. 357-370, Banff, Canada, June 1999.
https://doi.org/10.1007/978-3-7091-2490-1_48

A.R. Puerta, Issues in Automatic Generation of User Interfaces in Model-Based Systems. Second International Workshop on Computer-Aided Design of User Interfaces, pp. 323-325, Namur, Belgium, June 1996.

A.A. Loktev, D.A. Loktev, Assessment of Measurements of the Distance to the Object in the Study of Its Graphic Image (in Russian), Vestnik MGSU (Monthly Journal on Construction and Architecture), Vol. 10 (Issue 10): 54-65, October 2015.
https://doi.org/10.22227/1997-0935.2015.10.54-65

A. Loktev, V. Sychev, B. Gluzberg, E. Gridasova, Modeling the Dynamic Behavior of Railway Track Taking into Account the Occurrence of Defects in the System Wheel-Rail, XXVI R-S-P Seminar 2017 Theoretical Foundation of Civil Engineering, Vol. 117, pp. 1-6, Warsaw, Poland, August 2017.
https://doi.org/10.1051/matecconf/201711700108

D.A. Loktev, A.A. Loktev, A.V. Salnikova, A.A. Shaforostova, Determination of the Dynamic Vehicle Model Parameters by Means of Computer Vision, Communications - Scientific Letters of the University of Zilina, Vol. 21 (Issue 3): 28-34, August 2019.
https://doi.org/10.26552/com.C.2019.3.28-34

D.A. Loktev, A.A. Loktev, Estimation of Measurement of Distance to the Object by Analyzing the Blur of Its Image Series, 2016 International Siberian Conference on Control and Communications, pp. 1-6, Moscow, Russia, May 2016.
https://doi.org/10.1109/SIBCON.2016.7491683

D. Loktev, A. Loktev, R. Stepanov, V. Pevzner, K. Alenov, An Aggregated Method for Determining Railway Defects and Obstacle Parameters, IOP Conference Series: Materials Science and Engineering, Vol. 317 (Issue 1): 012-021, March 2018.
https://doi.org/10.1088/1757-899X/317/1/012021

Chernoyarov, O., Dobrucky, B., Salnikova, A., Makarov, A., Detection and Measurement of the Unknown Moment and Magnitude of the Gaussian Random Process Energy Parameter Abrupt Change, (2019) International Review on Modelling and Simulations (IREMOS), 12 (5), pp. 264-280.
https://doi.org/10.15866/iremos.v12i5.17839

Refbacks

There are currently no refbacks.

Username
Password
Remember me