Neural Network and Home Hydroponics
Hydroponics is a method of soilless cultivation of plants. It shortens the vegetation period, reduces the risk of disease and insect infestation, and provides a year-round growing cycle. Hydroponics depends on efficient water management. It is associated with a complex design, operation, and mainten...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Kemerovo State University
2023-06-01
|
| Series: | Техника и технология пищевых производств |
| Subjects: | |
| Online Access: | https://fptt.ru/en/issues/21711/21760/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841564853279391744 |
|---|---|
| author | Dmitry M. Borodulin Anton V. Shafrai Alexander A. Maximenko |
| author_facet | Dmitry M. Borodulin Anton V. Shafrai Alexander A. Maximenko |
| author_sort | Dmitry M. Borodulin |
| collection | DOAJ |
| description | Hydroponics is a method of soilless cultivation of plants. It shortens the vegetation period, reduces the risk of disease and insect infestation, and provides a year-round growing cycle. Hydroponics depends on efficient water management. It is associated with a complex design, operation, and maintenance. Neural networks can control complex technological processes in agriculture. The research objective was to use a neural network to increase the efficiency of a home hydroponics system.
The study involved a nutrient bed hydroponics setup with ten Lactuca sativa plants. Sensors collected information about the temperature and humidity of air, illumination, and the temperature of the leaf surface. Data processing, neural network training, and microcontroller programming relied on Python 3, PyTorch, and MicroPython.
The four-layer perceptron, which is a popular control mechanism, turned out to be the most effective neural network architecture. Fewer layers resulted in a high error rate (≥ 5%). When the number of layers was > 4, the error level remained at that of the four-layer experiment (0.2%). Further practical tests showed an increase in energy efficiency by 32.3%, compared to the classical control algorithm at close values of plant transpiration.
Neural net technology could be integrated into energy-saving residential premises and smart home systems in order to increase the self-sufficiency of hydroponics installations. |
| format | Article |
| id | doaj-art-0f7a1b540d8f4c0b97de78fcd1a0c212 |
| institution | Kabale University |
| issn | 2074-9414 2313-1748 |
| language | English |
| publishDate | 2023-06-01 |
| publisher | Kemerovo State University |
| record_format | Article |
| series | Техника и технология пищевых производств |
| spelling | doaj-art-0f7a1b540d8f4c0b97de78fcd1a0c2122025-01-02T22:02:19ZengKemerovo State UniversityТехника и технология пищевых производств2074-94142313-17482023-06-0153238439510.21603/2074-9414-2023-2-2440Neural Network and Home HydroponicsDmitry M. Borodulin0https://orcid.org/0000-0003-3035-0354Anton V. Shafrai1https://orcid.org/0000-0003-4512-1933Alexander A. Maximenko2https://orcid.org/0000-0002-6408-9839Kemerovo State University, Kemerovo, RussiaKemerovo State University, Kemerovo, RussiaKemerovo State University, Kemerovo, RussiaHydroponics is a method of soilless cultivation of plants. It shortens the vegetation period, reduces the risk of disease and insect infestation, and provides a year-round growing cycle. Hydroponics depends on efficient water management. It is associated with a complex design, operation, and maintenance. Neural networks can control complex technological processes in agriculture. The research objective was to use a neural network to increase the efficiency of a home hydroponics system. The study involved a nutrient bed hydroponics setup with ten Lactuca sativa plants. Sensors collected information about the temperature and humidity of air, illumination, and the temperature of the leaf surface. Data processing, neural network training, and microcontroller programming relied on Python 3, PyTorch, and MicroPython. The four-layer perceptron, which is a popular control mechanism, turned out to be the most effective neural network architecture. Fewer layers resulted in a high error rate (≥ 5%). When the number of layers was > 4, the error level remained at that of the four-layer experiment (0.2%). Further practical tests showed an increase in energy efficiency by 32.3%, compared to the classical control algorithm at close values of plant transpiration. Neural net technology could be integrated into energy-saving residential premises and smart home systems in order to increase the self-sufficiency of hydroponics installations.https://fptt.ru/en/issues/21711/21760/hydroponicsplant growing technologiesmodern plant growingprocess automation |
| spellingShingle | Dmitry M. Borodulin Anton V. Shafrai Alexander A. Maximenko Neural Network and Home Hydroponics Техника и технология пищевых производств hydroponics plant growing technologies modern plant growing process automation |
| title | Neural Network and Home Hydroponics |
| title_full | Neural Network and Home Hydroponics |
| title_fullStr | Neural Network and Home Hydroponics |
| title_full_unstemmed | Neural Network and Home Hydroponics |
| title_short | Neural Network and Home Hydroponics |
| title_sort | neural network and home hydroponics |
| topic | hydroponics plant growing technologies modern plant growing process automation |
| url | https://fptt.ru/en/issues/21711/21760/ |
| work_keys_str_mv | AT dmitrymborodulin neuralnetworkandhomehydroponics AT antonvshafrai neuralnetworkandhomehydroponics AT alexanderamaximenko neuralnetworkandhomehydroponics |