• Journal of Practical Agriculture & Fisheries Research
• /
• v.17 no.1
• /
• pp.57-71
• /
• 2015

This study was conducted to develop the fertigation system with a peristaltic hose pump and brushless DC motor. The fertigation system was consisted of sensor, main controller, motor control unit, peristaltic pump, water supply pump, control panel, and filter. The peristaltic pump discharges liquid by squeezing the tube with rollers. Rollers attached to the external circumference of the rotor compresses the flexible tube. The fluid is contained within a flexible tube fitted inside a circular pump casing. The developed fertigation system has no mixing tank but instead injects directly a concentrated nutrient solution into a water supply pipe. The revolution speed of the peristaltic pump is controlled by PWM (Pulse width modulation) method. When the revolution speed of the peristaltic pump was 300rpm, the flow rate of the 3.2, 4.8, 6.3mm diameter tube was 202, 530, 857mL/min, respectively. As increasing revolution speed, the flow rate of the peristaltic pump linearly increased. As the inner diameter of a tube larger, a slope of graph is more steep. Flow rate of three roller was more than that of four roller. Flow rate of a norprene tube with good restoring force was more than that of a pharmed tube. As EC sensor probe was installed in direct piping in comparison with bypass piping showed good performance. After starting the system, it took 16~17 seconds to stabilize EC. The maximum value of EC was 1.44~1.7dS/m at a setting value of 1.4dS/m. The developed fertigation system showed ±0.06dS/m deviation from the setting value of EC. In field test, Cucumber plants generally showed good growth. From these findings, this fertigation system can be appropriately suitable for fertigation culture for crops.

• Journal of Bio-Environment Control
• /
• v.32 no.3
• /
• pp.249-255
• /
• 2023

Korean melon (Cucumis melo L.) is grown mostly in Northeast Asia area, and as a fruit mainly produced in Korea, the yield per unit area continues to improve, but the cultivation method is limited to soil cultivation, so it is necessary to develop hydroponic cultivation technology for scale and labor-saving is needed. As the ratio of NO₃^- increased, the plant height, the leaf length, the leaf width, and the internode length became longer and larger. On the other hand, the SPAD value decreased. The lower the ratio of NO₃^-, the faster the female flower bloom, and there was no difference in fruit maturity between treatments. There was no difference in the shape of fruit according to the ratio of NO₃^-, and the hardness was higher as the ratio of NO₃^- was lower. The total yield from March to July was KM3 5,650 kg/10a and KM1 4,439 kg/10a, 27% higher in KM3 and, in particular, 36% higher in quantity from March to May, when Korean melon prices were high season. Therefore, it was judged that it would be appropriate to supply NO₃^- suitable for hydroponic cultivation of Korean melon, which was formalized in December and produced from spring, at the level of 6.5 to 10 me·L^-1.

• Journal of Bio-Environment Control
• /
• v.32 no.4
• /
• pp.434-441
• /
• 2023

Determining the size or area of a plant's leaves is an important factor in predicting plant growth and improving the productivity of indoor farms. In this study, we developed a convolutional neural network (CNN)-based model to accurately predict the length and width of lettuce leaves using photographs of the leaves. A callback function was applied to overcome data limitations and overfitting problems, and K-fold cross-validation was used to improve the generalization ability of the model. In addition, ImageDataGenerator function was used to increase the diversity of training data through data augmentation. To compare model performance, we evaluated pre-trained models such as VGG16, Resnet152, and NASNetMobile. As a result, NASNetMobile showed the highest performance, especially in width prediction, with an R_squared value of 0.9436, and RMSE of 0.5659. In length prediction, the R_squared value was 0.9537, and RMSE of 0.8713. The optimized model adopted the NASNetMobile architecture, the RMSprop optimization tool, the MSE loss functions, and the ELU activation functions. The training time of the model averaged 73 minutes per Epoch, and it took the model an average of 0.29 seconds to process a single lettuce leaf photo. In this study, we developed a CNN-based model to predict the leaf length and leaf width of plants in indoor farms, which is expected to enable rapid and accurate assessment of plant growth status by simply taking images. It is also expected to contribute to increasing the productivity and resource efficiency of farms by taking appropriate agricultural measures such as adjusting nutrient solution in real time.