KR-20260064290-A - Charger cooling environment monitoring system using autoencoder

Abstract

The present invention relates to a charger cooling environment monitoring system comprising: a solar irradiance sensor for measuring solar irradiance irradiated to a charger; an output monitoring unit for acquiring output data regarding output power by monitoring the output terminal of an inverter equipped in the charger; and a control unit for determining whether there is a failure or defect in the inverter through an analysis of the relationship between the solar irradiance measured by the solar irradiance sensor and the output data of the inverter.

Inventors

• 강태승

Assignees

• 주식회사 에스씨에스

Dates

Publication Date

20260507

Application Date

20241031

Claims (5)

1. In a charger cooling environment monitoring system configured to monitor the cooling environment of a charger that charges a battery, A solar radiation sensor that measures the amount of solar radiation irradiated by the above charger; An output monitoring unit that monitors the output terminal of an inverter provided in the charger to acquire output data regarding output power; and A charger cooling environment monitoring system characterized by comprising a control unit that determines whether the inverter is faulty or defective through an analysis of the relationship between the solar radiation measured by the solar radiation sensor and the output data of the inverter.
2. In paragraph 1, A charger cooling environment monitoring system characterized in that the above output data is the amount of charge or power generated by the inverter charging the battery.
3. In paragraph 2, A charger cooling environment monitoring system characterized by the above-described control unit obtaining a trend line through linear regression analysis of the charging amount or power generation amount and solar irradiance, and setting upper and lower threshold values centered on the trend line.
4. In paragraph 2, A charger cooling environment monitoring system characterized by the above-described control unit calculating inverter efficiency using the charging amount or power generation amount and the input power of the inverter, obtaining a trend line between the inverter efficiency and solar irradiance using the reconstruction error of the autoencoder, and setting upper and lower threshold values centered on the trend line.
5. In paragraph 3 or 4, A charger cooling environment monitoring system characterized by the above-described control unit determining data that deviates from the upper and lower threshold values as anomalies and determining that a failure or defect has occurred in the corresponding inverter.

Description

Charger cooling environment monitoring system using autoencoder The present invention relates to a charger cooling environment monitoring system using an autoencoder, and more specifically, to a charger cooling environment monitoring system using an autoencoder capable of detecting a defective charger inverter at an early stage through the analysis of the relationship between solar irradiance inside and outside the charger and output data of the charger. Generally, a battery charger, particularly a charger for an electric vehicle, is configured to include a power conversion means (e.g., an inverter) that converts input power into AC or DC output power and supplies it to the electric vehicle's battery. At this time, the input power can be supplied from a commercial AC power source or provided from a DC power source generated from a solar panel. Since inverters are devices that convert large amounts of power, they are prone to failure and vulnerable to manufacturing defects; however, conventional electric vehicle chargers have a problem in that they lack technology to effectively monitor inverter failures or defects. In particular, technology is required to detect defective inverters by monitoring the characteristics of the inverter that vary according to the external environment, such as solar irradiance. FIG. 1 is a block diagram illustrating a charger cooling environment monitoring system according to the present invention. Figure 2 is a heatmap showing the correlation between solar radiation and the charging amount of an electric vehicle charger. Figure 3 is a diagram showing the results of a linear regression analysis between solar radiation and the charging amount of an electric vehicle charger. Figure 4 is a diagram showing the relationship between solar irradiance and the efficiency of an inverter using an autoencoder. A preferred embodiment of the present invention will be described in detail below with reference to the accompanying drawings. The following detailed description is merely illustrative and illustrates a preferred embodiment of the present invention. FIG. 1 is a block diagram illustrating a charger cooling environment monitoring system according to the present invention. Referring to FIG. 1, the charger cooling environment monitoring system according to the present invention may be configured to include a solar irradiance sensor that measures solar irradiance irradiated to the charger, an output monitoring unit that monitors the output terminal of an inverter to acquire output data regarding output power, and a control unit that determines whether there is a failure or defect in the inverter through the analysis of the relationship between the solar irradiance measured by the solar irradiance sensor and the output data of the inverter. Output data regarding the output power of the inverter may be the amount of charge for charging the battery of an electric vehicle, or, in the case where the input power is direct current power input from a solar panel, the amount of solar power generated. Here, the charger may be an electric vehicle charger, but is not limited thereto, and may also be a charger for an energy storage system (ESS). The charger cooling environment monitoring system according to the present invention may be provided inside the charger or configured separately from the charger. Figure 2 is a heatmap showing the correlation between solar radiation and the charging amount of an electric vehicle charger. Solar irradiance and output data have a linear correlation. In other words, as solar irradiance values increase, the charge amount corresponding to output power tends to decrease; therefore, if the charge amount is too large or too small under the same solar irradiance conditions, it can be identified as anomalies. Figure 2 is a heatmap showing the linear regression analysis of irradiation and the active power of the output power. According to Figure 2, the magnitude of the correlation coefficient between solar radiation and the amount of charge or power generation is 0.95, which indicates a high correlation, so it can be seen that solar radiation directly affects the amount of charge or power generation. The meaning of the terms indicated in the heatmap presented in Figure 2 is as shown in Table 1 below. [Table 1] Figure 3 is a diagram showing the results of a linear regression analysis between solar radiation and the charging amount of an electric vehicle charger. The charger cooling environment monitoring system according to the present invention can be configured to determine outliers by using linear regression analysis of the relationship between solar radiation and the amount of charge or power generation. In Figure 3, the central black line is a trend line obtained through linear regression analysis, and the two red lines above and below the trend line may represent threshold values that are separated from the trend line by a predetermined deviation, for example, +3 × stan