Photographic images sets collecting system and approaches to training neural networks for digital management practical problems solving for a high-performance aquafarm based on the principles of closed water circulation

A.A. Agarkov, K.A. Samsonov, V.N. Malyshev, G.V. Sverdlik

Abstract


The purpose of this work was to develop basic technologies for creating a full-fledged industrial robot in the field of aquabiotechnology for high-intensity fish farms with closed water circulation systems. A controlled robot movement system has been designed, manufactured and tested, as well as a system for collecting sets of video datasets for training neural networks in order to make technological decisions. The integrated control complex of the robotic platform is based on the microcomputer-microcontroller-driver architecture. The system provides positioning of the platform with an accuracy of 5 centimeters and the transmission of a 4K video image with a delay of 150 milliseconds. The mechanical scheme of the robot movement system requires refinement based on the test results to ensure stable movement on curved sections of the trajectory. The layout of the datasets will be carried out by qualified personnel. Based on accumulated cognitive experience. The first version of the neural network has been selected and tested, which successfully solves the problem of determining the size of objects in images in conditions of high concentration and significant mutual overlap. The YOLOv8 convolutional neural network model was used to solve the problem. On the simplest sets of objects, the accuracy of determining the size varies between 97.8 – 99.2%. A set of real video images from an industrial site was obtained for testing the method on real data.

Full Text:

PDF (Russian)

References


Fish to 2030. Prospects for Fisheries and Aquaculture [Электронный ресурс]. – URL: fao.org›3/a-i3640e.pdf (дата обращения: 02.04.2022).

FAO. 2018. The State of World Fisheries and Aquaculture– URL: http://www.fao.org/3/i9540EN/i9540en.pdf (29.03.2022).

Federal Agency for Fisheries. 09.07.2021 – URL: https://fish.gov.ru/news/2021/07/09/mirovoepotreblenie-rybyuvelichilos-do-212-kg-na-cheloveka-k2030-godu-fao/ (02.04.2022).

Federal Agency for Fisheries. 11.04.2022 – URL: https://fish.gov.ru/news/2022/04/11/proizvodstvorybnojprodukczii-v-strane-vyroslo-na-2-i-dostiglo-628- tys-tonn-v-tom-chisle-za-schyotvy

Fore, M., Frank, K., Norton, T., Svendsen, E., Alfredsen, J.A., Demp-ster, T., Eguiraun, H., Watson, W., Stahl, A., Sunde, L.M., Schellewald, C., Skoien, K.R., Alver, M.O., Berckmans, D. (2018) Precision fish farming: A new framework to improve production in aquaculture Biosystems Engineering, 173, pp. 176- 193

Sabanchieva A A 2019 Situation and prospects of biotechnology development in the digital economy Modern world economy: Prob-lems and prospects in the era of digital technologies and biotechnolo-gy development 104 655

Migunov R A 2019 Digital technologies in Russian agriculture. Rural territories in the spatial development of the country: potential, prob-lems, prospects. Nikon Readings-2019: Proceedings of the XIV International Scientific Journal 362-363

Digital Farming: what does it really mean? Retrieved from: https://www.cemaagri.org/images/publications/position-papers/CEMA_Digital_Farming_- Agriculture 4.0 13.02.2017

Zhabitskii M.G., Andryenko Y.A., Malyshev V.N., Chuykova S.V., Zhosanov A.A., Digital transformation model based on the digital twin concept for intensive aquaculture production using closed water circulation technology, IOP Conf. Series: Earth and Environmental Science 723 (2021) 032064 doi:10.1088/1755-1315/723/3/032064

Mikhail Zhabitskii, Yuriy Andrienko, Vladimir Malyshev, Svetlana Chuykova, Aleksey Zhosanov, A Digital Twin of Intensive Aquabi-otechnological Production Based on a Closed Ecosystem Modeling & Simulation, 33rd European Modeling & Simulation Symposium, 18th International Multidisciplinary Modeling & Simulation Multiconfer-ence, ISSN 2724-0029 ISBN 978-88-85741-57-7 doi: 10.46354/i3m.2021.emss.034, 2021

Dmitry Grigorev, Daria Bolgova., Conceptual project of partial auto-mation of recirculation aquaculture farm, International Journal of Open Information Technologies ISSN: 2307-8162 vol. 9, no. 8, 2021, стр. 52-57

T.V. Khurtina, M.G. Zhabitsky, Yu.A. Andrienko, Development of a prototype of a digital platform for the control and monitoring of tech-nological processes of a biotechnical system, International Journal of Open Information Technologies. 2022. Т. 10. № 8. С. 62-67

K.U. Mokshin, M.G. Zhabitskii, U.A. Andrienko, A digital model of the fish population Clarias gariepinus species development for crea-tion industrial fish farm digital twin based on IIoT technology with the possibility of predictive analytics, International Journal of Open Information Technologies ISSN: 2307-8162 vol. 10, no. 8, 2022, стр. 68-76

Implementing a System Architecture for Data and Multimedia Transmission in a Multi-UAV System [сайт]. URL: https://link.springer.com/chapter/10.1007/978-3-030-02931-9_20 (дата обращения 10.05.2023).

IoT Based Automated Fish Farm Aquaculture Monitoring System // Researchgate. — URL: https://www.researchgate.net/publication/334091423_IoT_Based_Automate d_Fish _Farm_Aquaculture_Monitoring_System (25.05.2023).

Cyber Aqua Culture Monitoring System Using Ardunio And Raspber-ry Pi [сайт] // International Journal of Advanced Research in Electri-cal, Electronics and Instrumentation Engineering. — URL: http://ijareeie.com/upload/2015/may/97_CYBER.pdf (дата обращения 25.04.2023).

Andrea Zanella, senior member, IEEE, Nicola Bui, Angelo Castellani, Lorenzo Vangelista and Michele Zorzi, “Internet of things for smart cities”, “IEEE internet of things journal, vol.1, no.1, February 2014.”

BodepudiSrinivasaRao, U JyothiKameswari, Department of ECM, K.L University. “Design an monitoring system for aquaculture with multienvironmental factors using ARM-7.” International Journal of computer science and information technology vol.3, 2012. 87

Daudi S. Simbeye and Shi Feng Yang, College of electronic infor-mation and automation, “Water quality monitoring and control for aquaculture based on wireless sensor networks.” Journal of networks, vol.9, no.4, April 2014.

Orange Pi Zero2 http://www.orangepi.org/html/hardWare/computerAndMicrocontrollers/details/Orange-Pi-Zero-2.html

Arduino Uno Rev3 Internet: https://store.arduino.cc/usa/arduinouno-rev3 , [March 14, 2018] (PDF)

Browse Electronic Parts By Brands https://crossic.com/product/jyqd-yl02d/

ANNOYBIKE Official https://annoybike-official-store.axyl.ru/

Shenzhen Besder Technology Co.,Ltd https://besder.tech/

Chuan Luo, Wei Yang, Panling Huang, Jun Zhou. Overview of Image Matching Based on ORB Algorithm. Journal of Physics: Conference Series, 2019, Department of Mechanical Engineering, Shandong Uni-versity, Jinan 250061, China. Available at: https://iopscience.iop.org/article/10.1088/1742- 6596/1237/3/032020/pdf (дата обращения: 08.04.2023).

Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik. Rich feature hierarchies for accurate object detection and semantic segmentation, Tech report (v5), 2014, UC Berkeley. Available at: https://arxiv.org/abs/1311.2524 (дата обращения: 18.04.2023).

Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks, 2016. Available at: https://arxiv.org/abs/1506.01497 (дата об-ращения: 25.04.2023).

Wei Liu1, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, Alexander C. Berg. SSD: Single Shot MultiBox 84 Detector, 2016. Available at: https://arxiv.org/abs/1512.02325 (дата обращения 28.04.2023).

Computer vision lessons in Python + OpenCV from the very basics. Part 3– URL: https://habr.com/ru/post/654663/ (12.05.2023).

Perspective Transformation [Электронный ресурс]. – URL: https://theailearner.com/tag/cv2-getperspectivetransform/ (дата об-ращения: 25.05.2023).


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность MoNeTec 2024

ISSN: 2307-8162