Design and implementation of software modules for automated control and monitoring of the state of agrophytocenoses in conditions of virus-free seed production, as well as the ability to study plant growth and development using a neural network

The article presents a description of the developed software modules that make it possible to implement combinations of climatic parameters within a closed ecosystem, to carry out operational monitoring and assessment of the state of nutrient media and individual plant parts for the presence of deviations during digital phenotyping. An intelligent technology for monitoring the state of agrophytocenoses is proposed, taking into account the phases of the growing season in conditions of virus-free seed production with the ability to study plant growth and development using a neural network.

Introduction. The article is devoted to the problems of design and computer implementation of an ensemble of software modules, the basic functionality of which is automated monitoring of the growth dynamics of agrobiocenoses under conditions of their controlled cultivation with the possibility of further research of development by vegetation phases using a deep learning neural network with convolutional layers. The main stages of the development of digital device circuits, algorithms for their operation and computer implementation of combinations of climatic parameters within closed ecosystems, operational monitoring of the state of nutrient media and individual plant parts for deviations during digital phenotyping are considered.

Object. The object of the study is the growth and development of agro-bioceons under controlled cultivation conditions.

Materials and methods. Design and computer implementation were carried out in a simulation environment with the selection of basic components of an intelligent control system with subsequent integration with microcontroller components. Computer implementation of program modules was carried out in an integrated application development environment in the C++ programming language.

Results and conclusions. An automated system for implementing combinations of climatic parameters within closed ecosystems, operational monitoring of the state of nutrient media and individual plant parts for deviations in digital phenotyping were modeled, and its performance was tested in a simulation environment that proved its effectiveness. A set of special software is presented for implementing the algorithms for the operation of the proposed intelligent algorithms. A concept is proposed for managing and monitoring the state of agrophytocenoses in conditions of virus-free seed production with the ability to study plant growth and development using a neural network with convolutional layers. The diagram includes a three-level automation system: at the lower level, sensors and relays of actuators; application of computer vision algorithms for operational monitoring of the state of the growing medium, growth and development of plants, displaying images on the screen of a computerized supervisory control and data acquisition system (CSDUiSD), exporting images to cloud data storage services for multi-class classification according to pre-prepared data deep learning neural network classes with convolutional layers (CNN); connection between computer vision components, microcontrollers for operational monitoring and notification when deviations are detected (the presence of contamination of the nutrient medium / explants, diseases) when growing agrobiocenoses in virus-free seed production.

1. General meeting of the section of mechanization, electrification and automation of the department of agricultural sciences of the Russian Academy of Sciences. Agricultural machinery and technology. 2016. № 2. Pp. 4.

2. Berezhnoy V. A., Ivashchuk O. A., Maslakov Y. N. Approaches for Automated Monitoring and Evaluation of In Vitro Plant’s Morphometric Parameters. Journal of Computational and Theoretical Nanoscience. 2020. V. 17. № 9-10. Pp. 4725-4732.

3. Berezhnoy V. V., Ivaschuk O. A., Semenov D. S. Overview of methods and algorithms of automated plant phenotyping systems. Modern science-intensive technologies. 2021. № 4. Pp. 111-116.

4. Berezhnoy V. A., Ivashchuk O. A., Maslakov Yu. N. Development of a method for segmentation of 3d models of the vegetative part of the shoot. Scientific and technical bulletin of the Volga region. 2021. № 5. Pp. 30-34.

5. Lebed N. I., Tokarev K. E. Increasing the productivity of agrophytocenoses in precision farming using deep learning neural network algorithms: justification for application and aspects of computer implementation. International Agricultural Journal. 2022. № 6 (390). Pp. 662-664.

6. Tokarev K. E., Lebed N. I. Neural network system for recognition and visualization of problem areas of crops in precision farming: justification of application and aspects of implementation. IOP Conference Series: Earth and Environmental Sciencethis link is disabled. 2023. № 1138 (1). 012017.

7. Zykov A. V., Yunin V. A., Zakharov A. M. The use of robotics in the agro-industrial complex. International Research Journal. 2019. № 3 (81). Pp. 8-11.

8. Runov B. A. Application of robotics in the agro-industrial complex. Agricultural machinery and technology. 2016. № 2. Pp. 44-47.

9. Lebed N. I., Tokarev K. E., Nekhoroshev D. D., Aksenov M. P. Research and modeling of the operating modes of the firmware complex of the microclimate system based on the ATMEGA2560 microcontroller. Bulletin of Tambov State Technical University. 2022. № 4. V. 28. Pp. 595-605.

10. Tokarev K. E., Rudenko A. Yu., Kuzmin V. A., Chernyavsky A. N. Theory and digital technologies of intelligent decision support for increasing the bio-productivity of agroecosystems based on neural network models. Izvestia of the Nizhnevolzhsky Agricultural University Complex: Science and Higher Professional Education. 2021. № 4 (64). Pp. 421-440.

11. Khvostenko T. M., Aleksanov I. A. Introduction and problems of robotic means in the agro-industrial complex. Bulletin of the educational consortium Central Russian University. Information technology. 2022. № 2 (20). Pp. 4-9.

12. Tyurin S. F., Kovylyaev D. A., Danilova E. Yu., Gorodilov A. Yu. Study of microcontroller programming in Proteus CAD. Bulletin of Perm University. Maths. Mechanics. Informatics. 2021. № 2 (53). Pp. 69-74.

13. Lepeshko L. S. Overview of software products for automation in the agro-industrial complex. Science news in the agro-industrial complex. 2019. № 3 (12). Pp. 318-324.

14. Lebed N. I., Gapich D. S., Khanin Yu. I., Veselova N. M., Fomin S. D. Development and justification of the automated control system and software of the SCADA system by the process of cutting fruit and vegetable materials with a slice grinder. News of the Lower Volga Agricultural University Complex: Science and Higher Professional Education. VolGAU. 2022. № 2 (66). Pp. 364-372.