Application of artificial neural network in modeling illumination distribution in three-dimensional space

The paper deals with modeling three-dimensional illumination distribution from light sourсes using artificial neural network (ANN). This problem is especially relevant in greenhouse irradiation systems due to the design features, namely large dimensions of the phytoirradiators relative to the small suspension height, which makes it impossible to represent them as point sources. The aim of the research is to develop a methodology for modeling illumination distribution in threedimensional space, which includes obtaining experimental data and processing them using an artificial neural network. A dataset comprising 2,100 records was obtained experimentally for the developed phytoirradiator. The illumination values E were measured at the nodes of the coordinate grid with a step of 10 cm within the range from 0 to 120 cm (along the x coordinate) and from 0 to 100 cm (along the y coordinate) in all four quadrants, at different suspension height of the phytoirradiator h at levels of 30, 50, 70 and 90 cm. The TensorFlow and Keras libraries of the Python programming language were used to build the model. The results showed that the created neural network effectively describes the flux distribution on the irradiated surface, taking into account the real geometry of the light source. The key advantage of the method is the ability to calculate illumination for any combination of suspension height and point coordinates on the plane, which overcomes the limitations of conventional lighting calculations based on the inverse square law. The mean absolute error of the neural network model is 0.04 klx, the value of the determination coefficient R² = 0.9967 with a 95 % confidence interval of [0.09953, 0.9977], which is a good result. Mean absolute prediction error is 7.5 %, this value can be improved by regularization and data augmentation. It has been established that ANN-based method is applicable to the design of energy-efficient lighting systems, adaptable to the spectral characteristics and reflected light. After retraining, the model can be used for phytoirradiators of arbitrary design, which expands its practical significance in plant lighting.

1. Panarin V. M., Grishakov K. V., Maslova A. A., Grishakova O. V., Arkhipov A. V. Application of artificial neural networks in engineering and environmental developments. Izvestiya Tulskogo gosudarstvennogo universiteta. Tekhnicheskiye nauki. 2022;(4):278–284. (In Russ.). DOI: https://doi.org/10.24412/2071-6168-2022-4-278-284

2. Kutyrev A. I., Filippov R. A. Application of convolutional neural network for monitoring the condition of strawberries. Agrarnaya nauka Еvro-Severo-Vostoka = Agricultural Science Euro-North-East. 2023;24(4):685–696. (In Russ.). DOI: https://doi.org/10.30766/2072-9081.2023.24.4.685-696

3. Cherepenin V. A., Katsupeyev A. A. Analysis of approaches to creating a "Smart greenhouse" system based on a neural network. Programmniye sistemi i vichislitelniye metodi = Software Systems and Computational Methods. 2024;(1):68–78. (In Russ.). DOI: https://doi.org/10.7256/2454-0714.2024.1.69794

4. Smirnov A. V., Tishchenko I. P. Application of siamese neural networks to classify plant biomass by visual state. Programmniye sistemi: teoriya i prilozheniya = Program Systems: Theory and Applications. 2024;15(3(62)):53–74. (In Russ.). DOI: https://doi.org/10.25209/2079-3316-2024-15-3-53-74

5. Vorobyov N. I., Lysov A. K., Kornilov T. V., Hyutti A. V. Computational neural network for processing light-reflective spectra of plants and remote phytosanitary monitoring of potatoes. Agrarnaya nauka Еvro-SeveroVostoka = Agricultural Science Euro-North-East. 2024;25(2):283-292. (In Russ.). DOI: https://doi.org/10.30766/2072-9081.2024.25.2.283–292

6. Sorokin M. I. Using convolutional neural networks to classify types of artificial lighting. Alleya nauki. 2018;3(6(22)):1008–1011. (In Russ.). URL: https://elibrary.ru/item.asp?id=35326748

7. Lork C., Cubillas M., Kiat Ng B. K., Yuen C., Tan M. Minimizing Electricity Cost through Smart Lighting Control for Indoor Plant Factories. IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society. 2020. DOI: https://doi.org/10.1109/iecon43393.2020.9255061

8. Yersoy Yilmaz A., Rozovsky E. I. Neural network modeling of the dependence of the color temperature of lighting on the light source and the optical system of the lamp. Svetotekhnika = Light & Engineering. 2017;(1):49–54. (In Russ.). URL: https://elibrary.ru/item.asp?id=28777660

9. Kazanasmaz T., Günaydin M., Binol S. Artificial neural networks to predict daylight illuminance in office buildings. Building and Environment. 2009;44(8):1751–1757. DOI: https://doi.org/10.1016/j.buildenv.2008.11.012

10. Dudzik M., Dechnik M., Furtak M. Application of neural networks to lighting systems. MATEC Web of Conferences. 2019;282(2):02069. DOI: https://doi.org/10.1051/matecconf/201928

11. Borodulin D. M., Shafray A. V., Maksimenko A. A. Neural network and home hydroponics. Tekhnika i tekhnologiya pishchevikh proizvodstv = Food Processing: Techniques and Technology. 2023;53(2):384–395. (In Russ.). DOI: https://doi.org/10.21603/2074-9414-2023-2-2440

12. Zhang Y., Li S. Study on Illumination Measurement Method of Lighting Environment Based on RBF Neural Network. Journal of Physics: Conference Series. 2022;2196(1):012004. DOI: https://doi.org/10.1088/1742-6596/2196/1/012004

13. Semenova N. G., Valiullin K. R. Intelligent energy-efficient street lighting control system based on neural network technology. Vestnik Orenburgskogo gosudarstvennogo universiteta = Vestnik of the Orenburg State University. 2015;(4(179)):183–188. (In Russ.). URL: https://elibrary.ru/item.asp?id=24097618

14. Egorov A. D., Pavlyuchenko D. A. Design of electric lighting using artificial neural networks. Energetik. 2020;(11):21–25. (In Russ.). URL: https://elibrary.ru/item.asp?id=44236455

15. Rakutko S. A., Rakutko E. N. Assessment of lighting uniformity as a factor of energy efficiency in greenhouse horticulture. Inzhenerniye tekhnologii i sistemi = Engineering Technologies and Systems. 2021;31(3):470–486. (In Russ.). DOI: https://doi.org/10.15507/2658-4123.031.202103.470-486

16. Rakutko S. A., Rakutko E. N., Vaskin A. V. Effect of lighting fixtures spatial arrangement on energy and ecological performance of greenhouse horticulture. AgroEkoInzheneriya = AgroEcoEngineering. 2021;(3(108)):33–51. (In Russ.). DOI: https://doi.org/10.24412/2713-2641-2021-3108-33-50

17. Galkin V. A., Gavrilenko T. V., Smorodinov A. D. Some aspects of approximation and interpolation of functions artificial neural networks. Vestnik KRAUNTs. Fiziko-matematicheskiye nauki = Bulletin KRASEC. Physical and Mathematical Sciences. 2022;38(1):54–73. (In Russ.). DOI: https://doi.org/10.26117/2079-6641-2022-38-1-54-73