• Journal of Platform Technology
• /
• v.8 no.3
• /
• pp.10-21
• /
• 2020

Partial discharge occurs a lot in high-voltage power equipment such as switchgear, transformers, and switch gears. Partial discharge shortens the life of the insulator and causes insulation breakdown, resulting in large-scale damage such as a power outage. There are several types of partial discharge that occur inside the product and the surface. In this paper, we design a predictive model that can predict the pattern and probability of occurrence of partial discharge. In order to analyze the designed model, learning data for each type of partial discharge was collected through the UHF sensor by using a simulator that generates partial discharge. The predictive model designed in this paper was designed based on CNN during deep learning, and the model was verified through learning. To learn about the designed model, 5000 training data were created, and the form of training data was used as input data for the model by pre-processing the 3D raw data input from the UHF sensor as 2D data. As a result of the experiment, it was found that the accuracy of the model designed through learning has an accuracy of 0.9972. It was found that the accuracy of the proposed model was higher in the case of learning by making the data into a two-dimensional image and learning it in the form of a grayscale image.

• Korean Journal of Soil Science and Fertilizer
• /
• v.45 no.6
• /
• pp.1230-1236
• /
• 2012

To verify that the electrokinetic remediation is effective for decreasing salinity of fields of the plastic-film house, field tests for physical property, chemical property, and crop productivity of soils have been conducted. The abridged result of those tests is as follows. In the EK treatment, the electrokinetic remediation has been treated at the constant voltage (about 0.8 V $cm^{-1}$) for fields of the farm household. At this time, an alternating current (AC) 220 V of the farm household was transformed a direct current. The HSCI (High Silicon Cast Iron) that the length of the stick for a cation is 20cm, and the Fe Plate for an anion have been spread out on the ground. As the PVC pipe that is 10 cm in diameter was laid in the bottom of soils, cations descend on the cathode were discharged together. For soil physical properties according to the EK treatment, the destruction effect of soil aggregate was large, and the infiltration rate of water was increased. However, variations of bulk density and porosity were not considerable. Meanwhile, in chemical properties of soils, principal ions of such as EC, $NO_3{^-}$-N, $K^+$, and $Na^+$ were better rapidly reduced in the EK treated control plot than in the untreated control plot. And properties such as pH, $P_2O_5$ and $Ca^{2+}$ had a small impact on the EK. For cropping season of crop cultivation according to the EK treatment, decreasing rates of chemical properties of soils were as follows; $NO_3{^-}$-N 78.3% > $K^+$ 72.3% > EC 71.6% $$\geq_-$$ $Na^+$ 71.5% > $Mg^{2+}$ 36.8%. As results of comparing the experimental plot that EK was treated before crop cultivation with it that EK was treated during crop cultivation, the decreasing effect of chemical properties was higher in the case that EK was treated during crop cultivation. After the EK treatment, treatment effects were distinct for $NO_3{^-}$-N and EC that a decrease of nutrients is clear. However, because the lasting effect of decreasing salinity were not distinct for the single EK treatment, fertilization for soil testing was desirable carrying on testing for chemical properties of soils after EK treatments more than two times. In the growth of cabbages according to the EK treatment, the rate of yield increase was 225.5% for the primary treatment, 181.0% for the secondary treatment, and 124.2% for third treatment compared with the untreated control plot. The yield was increased by a factor of 130.0% for the hot pepper at the primary treatment (Apr. 2011), 248.1% for the lettuce at the secondary treatment (Nov.2011), and 125.4% for the young radish at the third treatment (Jul. 2012). In conclusion, the effect of yield increase was accepted officially for all announced crops.