Automatic detection method for electrical performance of water cooling system

Abstract

The invention relates to the technical field of data processing, in particular to an automatic detection method for electrical performance of a water cooling system. Obtaining a voltage suspected abnormal moment according to a voltage difference characteristic between any moment and an adjacent historical time period in the voltage time sequence; obtaining a temperature interval and a voltage characterization value according to the temperature distribution characteristics and the voltage distribution characteristics in the temperature and voltage association diagram; and according to the humidity difference characteristics of the voltage suspected abnormal moment and the historical time period in the humidity time sequence and the voltage distribution characteristics of the temperature interval where the temperature of the voltage suspected abnormal moment is located, obtaining the temperature and voltage correlation credibility. According to the voltage characterization value of the temperature interval where the temperature at the suspected voltage abnormal moment is located, the difference characteristic of the voltage at the suspected voltage abnormal moment and the temperature and voltage correlation credibility, the voltage abnormal degree is obtained, the electrical performance of the water cooling system is detected, and the detection accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to an automated detection method for the electrical performance of a water-cooling system. Background Art

[0002] A water-cooling system is a device system that uses cold water as a medium for cooling. In order to avoid poor cooling effects caused by water-cooling system failures, it is necessary to detect the working state of the water-cooling system to achieve the purpose of timely warning and regulating the equipment state. The water-cooling system realizes water circulation through a water pump unit. Therefore, the cooling effect of the water-cooling system is closely related to the working state of the electrical equipment in the system. Therefore, detecting the voltage of the electrical equipment can reflect whether the electrical equipment and the water-cooling system are normal. Existing anomaly detection methods usually set voltage thresholds for judgment, but this method does not consider the influence relationship between temperature and humidity in the water-cooling system on voltage, resulting in the identification of voltage deviation situations as anomalies under the influence of partial temperature and humidity, affecting the detection accuracy of the electrical performance in the water-cooling system. Summary of the Invention

[0003] In order to solve the above technical problem of low accuracy in detecting electrical performance only based on set voltage thresholds, the purpose of the present invention is to provide an automated detection method for the electrical performance of a water-cooling system, and the specific technical solution adopted is as follows: Obtain the temperature time series, humidity time series, and voltage time series during the operation of the water-cooling system; Obtain the voltage deviation degree according to the voltage difference characteristics between any moment and the adjacent historical period in the voltage time series; obtain the suspected voltage abnormal moment according to the voltage deviation degree at any moment; obtain the temperature-voltage correlation diagram according to the temperature time series and the voltage time series; obtain the temperature range and voltage characterization value according to the temperature distribution characteristics and voltage distribution characteristics in the temperature-voltage correlation diagram; Obtain the humidity normal index according to the humidity difference characteristics between the suspected voltage abnormal moment and the historical period in the humidity time series; obtain the data distribution characteristic value according to the voltage distribution characteristics in the temperature range where the temperature of the suspected voltage abnormal moment is located; obtain the temperature-voltage correlation credibility according to the humidity normal index and the data distribution characteristic value; Obtain the voltage abnormal degree according to the difference characteristics between the voltage characterization value in the temperature range where the temperature of the suspected voltage abnormal moment is located and the voltage of the suspected voltage abnormal moment, and the temperature-voltage correlation credibility; detect the electrical performance of the water-cooling system according to the voltage abnormal degree.

[0004] Further, the step of obtaining the voltage deviation degree according to the voltage difference characteristics between any moment and the adjacent historical period in the voltage time series includes: Calculate the cumulative sum of the absolute values of the voltage differences between any given moment and each historical moment in the adjacent historical period to obtain a cumulative voltage difference value; positively map the cumulative voltage difference value to obtain the voltage deviation degree at any given moment.

[0005] Further, the step of obtaining the voltage suspected abnormal moment according to the voltage deviation degree at any given moment includes: Take any moment when the voltage deviation degree exceeds a preset deviation threshold as the voltage suspected abnormal moment.

[0006] Further, the step of obtaining the temperature-voltage correlation diagram according to the temperature time series and the voltage time series includes: Normalize the temperature time series to obtain temperature mapping values at different moments; normalize the voltage time series to obtain voltage mapping values at different moments; construct a coordinate diagram with the temperature mapping values on the horizontal axis and the voltage mapping values on the vertical axis, and construct a temperature-voltage correlation diagram according to the positions of the temperature mapping values and voltage mapping values at the same moment in the coordinate diagram.

[0007] Further, the step of obtaining the temperature range and voltage characterization value according to the temperature distribution characteristics and voltage distribution characteristics in the temperature-voltage correlation diagram includes: Divide the temperature mapping values of the temperature-voltage correlation diagram according to a preset segmentation interval to obtain different temperature ranges; calculate the average value of the voltage mapping values corresponding to the temperature ranges to obtain the voltage characterization value.

[0008] Further, the step of obtaining the humidity normal index according to the humidity difference characteristics between the voltage suspected abnormal moment and the historical period in the humidity time series includes: Calculate the average humidity value of the historical period before the voltage suspected abnormal moment to obtain the historical humidity value; calculate the absolute value of the difference between the humidity at the voltage suspected abnormal moment and the historical humidity value and negatively map it to obtain the humidity normal index at the voltage suspected abnormal moment.

[0009] Further, the step of obtaining the data distribution characteristic value according to the voltage distribution characteristics of the temperature range where the temperature at the voltage suspected abnormal moment is located includes: Calculate the ratio of the number of voltage mapping values in the temperature range where the temperature at the voltage suspected abnormal moment is located to the voltage mapping values in the temperature-voltage correlation diagram to obtain the data proportion characteristic value; calculate the variance of the voltage mapping values in the temperature range where the temperature at the voltage suspected abnormal moment is located and negatively map it to obtain the voltage concentration; calculate the product of the data proportion characteristic value and the voltage concentration to obtain the data distribution characteristic value at the voltage suspected abnormal moment.

[0010] Further, the step of obtaining the temperature-voltage correlation confidence based on the humidity normal index and the data distribution characteristic value includes: Calculate the product of the humidity normal index and the data distribution characteristic value and perform a positive correlation mapping to obtain the temperature-voltage correlation credibility at the moment of suspected voltage anomaly.

[0011] Further, the step of obtaining the voltage anomaly degree based on the difference characteristic between the voltage characterization value of the temperature range where the temperature is located at the moment of suspected voltage anomaly and the voltage at the moment of suspected voltage anomaly, and the temperature-voltage correlation credibility includes: Calculate the absolute value of the difference between the voltage characterization value of the temperature range where the temperature is located at the moment of suspected voltage anomaly and the voltage mapping value corresponding to the moment of suspected voltage anomaly to obtain a voltage difference index; calculate the product of the voltage difference index and the temperature-voltage correlation credibility to obtain the voltage anomaly degree at the moment of suspected voltage anomaly.

[0012] Further, the step of detecting the electrical performance of the water-cooling system based on the voltage anomaly degree includes: When the voltage anomaly degree at the moment of suspected voltage anomaly exceeds a preset anomaly threshold, the electrical performance of the water-cooling system is abnormal at the moment of suspected voltage anomaly.

[0013] The present invention has the following beneficial effects: In the present invention, obtaining the voltage deviation degree can initially determine the moment when electrical equipment anomalies may occur according to the operating conditions of electrical equipment in the water-cooling system, so as to obtain the moment of suspected voltage anomaly. Obtaining the temperature-voltage correlation diagram can reflect the voltage characteristics of electrical equipment at different temperatures, and obtaining the temperature range can distinguish the temperature characteristics, so as to determine the voltage characteristics under different temperature range conditions; obtaining the voltage characterization value can characterize the comprehensive voltage level in the same temperature range, and further judge the difference degree between the voltage at the moment of suspected voltage anomaly and the voltage characterization value under the same temperature condition, reducing the influence of temperature on voltage in the water-cooling system and further improving the accuracy of electrical equipment detection. Obtaining the humidity normal index can determine the influence degree of humidity on voltage at the moment of suspected voltage anomaly, making voltage detection more accurate; obtaining the data distribution characteristic value can characterize the reliability of the voltage characterization value in the temperature range, further improving the accuracy of electrical equipment detection. Obtaining the temperature-voltage correlation credibility characterizes the influence degree of external factors during voltage anomaly detection, thereby reducing the probability of false detection; obtaining the voltage anomaly degree can perform anomaly judgment on electrical equipment based on the analysis of voltage differences under the same temperature condition and combining the temperature-voltage correlation credibility, improving the accuracy of electrical equipment detection in the water-cooling system. Description of the Drawings

[0014] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0015] Figure 1 Flowchart of an automatic detection method for the electrical performance of a water-cooling system provided by an embodiment of the present invention. Detailed implementation manners

[0016] To further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in conjunction with the drawings and preferred embodiments, details the specific implementation manners, structures, features, and effects of an automatic detection method for the electrical performance of a water-cooling system proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0017] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0018] The following specifically describes the specific solution of an automatic detection method for the electrical performance of a water-cooling system provided by the present invention with reference to the drawings.

[0019] Please refer to Figure 1 , which shows a flowchart of an automatic detection method for the electrical performance of a water-cooling system provided by an embodiment of the present invention. The method includes the following steps: Step S1, obtain the temperature time series, humidity time series, and voltage time series during the operation of the water-cooling system.

[0020] In the embodiment of the present invention, the implementation scenario is to detect the electrical performance of the water-cooling system to improve the detection accuracy. First, obtain the voltage time series during the operation of the water-cooling system. In the embodiment of the present invention, the voltage time series during the operation of the water pump unit is collected as the voltage time series. Since the temperature of the circulating water and the humidity inside the water pump unit will both cause changes in the voltage, the temperature of the circulating water and the humidity of the water pump at the same time period are collected. In the embodiment of the present invention, the data collection frequency is once per second, and the implementer can determine it according to the implementation scenario.

[0021] Step S2: Obtain the voltage deviation degree according to the voltage difference characteristics between any moment in the voltage time series and the adjacent historical period; obtain the suspected abnormal voltage moments according to the voltage deviation degree at any moment; obtain the temperature-voltage correlation diagram according to the temperature time series and the voltage time series; obtain the temperature range and voltage characterization value according to the temperature distribution characteristics and voltage distribution characteristics in the temperature-voltage correlation diagram.

[0022] During the normal operation of the water cooling system, the voltage of the water pump unit is relatively stable; when there is a voltage change, it may be caused by an abnormal situation of electrical equipment. Therefore, it is necessary to initially determine the moment when electrical equipment may be abnormal according to the voltage fluctuation situation. Thus, obtain the voltage deviation degree according to the voltage difference characteristics between any moment in the voltage time series and the adjacent historical period; preferably, in the embodiment of the present invention, the steps of obtaining the voltage deviation degree include: calculating the cumulative sum of the absolute values of the voltage differences between any moment and each historical moment in the adjacent historical period to obtain the voltage difference cumulative value; in the embodiment of the present invention, the adjacent historical period is the range of the nearest 20 historical moments before this arbitrary moment; if the voltage at this arbitrary moment is abnormal, there is a difference from the voltage at the historical moment. Therefore, the larger the voltage difference cumulative value, the more abnormal the voltage at this arbitrary moment. Map the voltage difference cumulative value positively to obtain the voltage deviation degree at this arbitrary moment; when the voltage deviation degree is larger, it means that the electrical equipment in the water cooling system is more likely to be abnormal at this arbitrary moment. Furthermore, the suspected abnormal voltage moments can be obtained according to the voltage deviation degree at any moment, specifically including: taking any moment with a voltage deviation degree exceeding the preset deviation threshold as the suspected abnormal voltage moment. In the embodiment of the present invention, the preset deviation threshold is 0.7, and the implementer can determine it according to the implementation scenario.

[0023] Furthermore, at the suspected abnormal voltage moment, it means that there may be an abnormal situation of electrical equipment. And both the temperature and humidity in the water cooling system have a certain possibility of causing the voltage of electrical equipment to be abnormal. Therefore, it is necessary to analyze the influence of temperature and humidity on the voltage to improve the accuracy of electrical performance detection. Since the temperature of the circulating water in the water cooling system will affect the resistance of electrical equipment, for example, when the power of the target to be cooled suddenly rises and the cooling system does not meet the cooling requirements of this target, there will be a sudden change in the temperature of the circulating water. As the temperature rises, the resistance of the metal conductor inside the electrical equipment will increase linearly, thereby affecting the voltage of the electrical equipment; when the temperature drops, the resistance of the metal conductor will also decrease linearly. Therefore, there is a certain influence correlation between the temperature of the circulating water and the voltage of the electrical equipment. Therefore, it is necessary to obtain the correlation between temperature and voltage, so obtain the temperature-voltage correlation diagram according to the temperature time series and the voltage time series.

[0024] Preferably, in the embodiments of the present invention, the steps of obtaining the temperature-voltage correlation diagram include: normalizing the maximum and minimum values of the temperature time series to obtain the temperature mapping values at different times; normalizing the maximum and minimum values of the voltage time series to obtain the voltage mapping values at different times. It should be noted that the maximum-minimum normalization belongs to the prior art, and the specific steps will not be elaborated here. Construct a coordinate graph with the temperature mapping values on the horizontal axis and the voltage mapping values on the vertical axis, and construct the temperature-voltage correlation diagram according to the positions of the temperature mapping values and voltage mapping values at the same time in the coordinate graph. The temperature-voltage correlation diagram characterizes the voltage distribution corresponding to different temperatures. Since multiple voltage values correspond to different temperature values, it is necessary to use representative voltage values to characterize the voltage characteristics of a certain temperature range for subsequent voltage anomaly analysis. Therefore, obtain the temperature range and voltage characterization value according to the temperature distribution characteristics and voltage distribution characteristics in the temperature-voltage correlation diagram; preferably, in the embodiments of the present invention, the steps of obtaining the temperature range and voltage characterization value include: dividing the temperature mapping values of the temperature-voltage correlation diagram according to a preset segmentation interval to obtain different temperature ranges; in the embodiments of the present invention, the preset segmentation interval is 0.05, and a temperature range is divided every 0.05 on the horizontal axis of the temperature mapping value. The implementer can determine it according to the implementation scenario. Calculate the average value of the voltage mapping values corresponding to the temperature range to obtain the voltage characterization value; the voltage characterization value reflects the voltage characteristics of the electrical equipment at the corresponding temperature range.

[0025] Step S3, obtain the humidity normal index according to the humidity difference characteristics between the voltage suspected abnormal moment and the historical period in the humidity time series; obtain the data distribution characteristic value according to the voltage distribution characteristics of the temperature range where the temperature of the voltage suspected abnormal moment is located; obtain the temperature-voltage correlation credibility according to the humidity normal index and the data distribution characteristic value.

[0026] Humidity in electrical equipment can have a certain impact on voltage. When humidity increases, insulating materials in electrical equipment, such as plastics, rubbers, enameled wires, etc., may absorb moisture, resulting in a decline in insulation performance; under high humidity, water vapor is likely to form a thin water film on the surface of high-voltage components, thereby reducing the insulation resistance and triggering surface discharge phenomena, further reducing the voltage stability of electrical equipment and resulting in suspected abnormal voltage moments. Therefore, when analyzing the abnormalities of electrical equipment, the influence of humidity inside the equipment needs to be considered. Thus, a humidity normal index is obtained based on the humidity difference characteristics between the suspected abnormal voltage moments and the humidity in the historical period in the humidity time series; preferably, in the embodiments of the present invention, the steps of obtaining the humidity normal index include: calculating the average humidity in the historical period before the suspected abnormal voltage moment to obtain the historical humidity value; under normal circumstances, electrical equipment in the water-cooling system has good sealing performance to prevent moisture in the external environment from infiltrating into the equipment and causing damage. Therefore, the historical humidity value represents the relatively low humidity level inside the equipment under normal circumstances. Calculating the absolute value of the difference between the humidity at the suspected abnormal voltage moment and the historical humidity value and performing a negative correlation mapping to obtain the humidity normal index at the suspected abnormal voltage moment; the larger the absolute value of the difference between the humidity at the suspected abnormal voltage moment and the historical humidity value, the higher the humidity at this suspected abnormal voltage moment, and the more likely it is to affect the voltage of the electrical equipment, and the smaller the humidity normal index; the larger the humidity normal index, the more normal the humidity at this moment, and the smaller the possibility of causing voltage abnormalities.

[0027] Further, when there are more voltage mapping values within the temperature range in the temperature-voltage correlation graph and the values are closer, it means that the confidence level of the voltage characterization value obtained in this temperature range is higher and more representative. At this time, if the difference between the voltage at this temperature range and the voltage characterization value is greater, it can better indicate that the voltage is abnormal. When the voltage mapping values within the temperature range are fewer and more discrete, it means that the confidence level of the voltage characterization value obtained in this temperature range is lower and less representative. Even if the difference between the voltage at this temperature range and the voltage characterization value is relatively large, it cannot accurately characterize that the voltage is abnormal. Therefore, the data distribution characteristic value is obtained according to the voltage distribution characteristic of the temperature range where the temperature is located at the moment of suspected voltage abnormality. Preferably, in the embodiment of the present invention, the steps of obtaining the data distribution characteristic value include: calculating the ratio of the number of voltage mapping values in the temperature range where the temperature is located at the moment of suspected voltage abnormality to the voltage mapping values in the temperature-voltage correlation graph to obtain the data proportion characteristic value. When the data proportion characteristic value is larger, it means that there is more voltage data in this temperature range. Calculate the variance of the voltage mapping values in the temperature range where the temperature is located at the moment of suspected voltage abnormality and map it negatively to obtain the voltage concentration degree. When the variance of the voltage mapping values is smaller, it means that the voltage data in this temperature range is more concentrated, the data is more reliable, and the voltage concentration degree is larger. Calculate the product of the data proportion characteristic value and the voltage concentration degree to obtain the data distribution characteristic value at the moment of suspected voltage abnormality. When the data distribution characteristic value is larger, it means that the reliability of the voltage characterization value in the temperature range corresponding to this moment of suspected voltage abnormality is stronger and the persuasive power during voltage detection is higher.

[0028] After obtaining the influence situation of humidity and the data distribution characteristic value, the temperature-voltage correlation credibility can be obtained according to the humidity normal index and the data distribution characteristic value. Preferably, in the embodiment of the present invention, the steps of obtaining the temperature-voltage correlation credibility include: calculating the product of the humidity normal index and the data distribution characteristic value and mapping it positively to obtain the temperature-voltage correlation credibility at the moment of suspected voltage abnormality. When the temperature-voltage correlation credibility is larger, it means that the influence of humidity at this moment of suspected voltage abnormality is smaller, and the reliability of the voltage characterization value in the temperature range corresponding to this moment is stronger. When the temperature-voltage correlation credibility is smaller, it means that the influence of humidity at this moment of suspected voltage abnormality is larger, and the reliability of the voltage characterization value in the temperature range corresponding to this moment is weaker, thereby reducing the probability of voltage abnormality detection error. The formula for obtaining the temperature-voltage correlation credibility includes:

[0029] In the formula, W represents the temperature-voltage correlation credibility at the moment of suspected voltage abnormality, represents the exponential function with the natural constant as the base, S represents the humidity normal index, N represents the data proportion characteristic value, R represents the voltage concentration degree, represents the data distribution characteristic value.

[0030] Step S4: Obtain the voltage anomaly degree based on the difference characteristics between the voltage characterization value in the temperature range where the temperature is at the suspected voltage anomaly moment and the voltage at the suspected voltage anomaly moment, and the temperature-voltage correlation credibility; detect the electrical performance of the water-cooling system according to the voltage anomaly degree.

[0031] After obtaining the temperature-grid correlation credibility at the suspected voltage anomaly moment, the voltage anomaly degree can be obtained based on the difference characteristics between the voltage characterization value in the temperature range where the temperature is at the suspected voltage anomaly moment and the voltage at the suspected voltage anomaly moment, and the temperature-voltage correlation credibility; preferably, in the embodiment of the present invention, the steps of obtaining the voltage anomaly degree include: calculating the absolute value of the difference between the voltage characterization value in the temperature range where the temperature is at the suspected voltage anomaly moment and the voltage mapping value corresponding to the suspected voltage anomaly moment to obtain a voltage difference index; the larger the voltage difference index, the greater the difference between the voltage mapping value and the voltage characterization value corresponding to the suspected voltage anomaly moment in the same temperature range, and the more likely the suspected voltage anomaly moment is caused by an abnormality of the electrical equipment. Calculate the product of the voltage difference index and the temperature-voltage correlation credibility to obtain the voltage anomaly degree at the suspected voltage anomaly moment; since the voltage difference index only analyzes the voltage difference under the same temperature condition and does not consider the influence of humidity and the reliability of the voltage characterization value in this temperature range, the voltage difference index is weighted by the temperature-voltage correlation credibility. If the voltage difference index is larger and the temperature-voltage correlation credibility is also larger at the same time, it indicates that an abnormality of the electrical equipment is more likely to occur at the suspected voltage anomaly moment; on the contrary, when the temperature-voltage correlation credibility is smaller, it indicates that the voltage difference index cannot represent the occurrence of an abnormality of the electrical equipment at the suspected voltage anomaly moment, thereby improving the detection accuracy of the abnormality of the electrical equipment.

[0032] Furthermore, the electrical performance of the water-cooling system can be detected according to the voltage anomaly degree. When the voltage anomaly degree at the suspected voltage anomaly moment exceeds the preset anomaly threshold, the electrical performance of the water-cooling system is abnormal at the suspected voltage anomaly moment; in the embodiment of the present invention, the preset anomaly threshold is 0.6, and the implementer can determine it according to the implementation scenario. Subsequently, early warning and maintenance of the electrical equipment of the water-cooling system can be carried out according to the frequency of the abnormal moment, which is not limited here.

[0033] In summary, the embodiment of the present invention provides an automated detection method for the electrical performance of a water cooling system; obtaining suspected abnormal voltage moments according to the voltage difference characteristics between any moment in the voltage time series and the adjacent historical period; obtaining a temperature range and a voltage characterization value according to the temperature distribution characteristics and voltage distribution characteristics in the temperature-voltage correlation diagram; obtaining the temperature-voltage correlation credibility according to the humidity difference characteristics between the suspected abnormal voltage moment and the historical period in the humidity time series and the voltage distribution characteristics of the temperature range where the temperature of the suspected abnormal voltage moment is located. The voltage abnormality degree is obtained according to the difference characteristics between the voltage characterization value of the temperature range where the temperature of the suspected abnormal voltage moment is located and the voltage of the suspected abnormal voltage moment, and the temperature-voltage correlation credibility, and the electrical performance of the water cooling system is detected, improving the detection accuracy.

[0034] It should be noted that the above sequence of embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0035] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A method for automatic detection of electrical performance of a water cooling system, characterized in that: The method comprises the following steps: Obtain the temperature, humidity and voltage timings during the operation of the water cooling system; The voltage deviation is obtained according to the voltage difference characteristics between any moment in the voltage time series and the adjacent historical period; the voltage suspected abnormal moment is obtained according to the voltage deviation at any moment; the temperature-voltage correlation diagram is obtained according to the temperature time series and the voltage time series; the temperature range and voltage characterization value are obtained according to the temperature distribution characteristics and the voltage distribution characteristics in the temperature-voltage correlation diagram; Obtain a normal humidity index according to the humidity difference characteristics between the voltage suspected abnormal moment and the historical period in the humidity time series; obtain a data distribution characteristic value according to the voltage distribution characteristics of the temperature interval where the temperature at the voltage suspected abnormal moment is located; obtain a temperature-voltage correlation credibility according to the normal humidity index and the data distribution characteristic value; The voltage abnormality degree is obtained based on the difference characteristics between the voltage characterization value in the temperature range where the temperature is located at the moment when the voltage is suspected to be abnormal and the voltage at the moment when the voltage is suspected to be abnormal, and the temperature-voltage correlation credibility; and the electrical performance of the water cooling system is detected based on the voltage abnormality degree.

2. The method for automatic detection of electrical performance of a water cooling system according to claim 1, characterized in that: The step of obtaining the voltage deviation according to the voltage difference characteristics between any moment in the voltage time series and the adjacent historical time period comprises: The voltage difference absolute value between the arbitrary moment and each historical moment in the adjacent historical period is calculated to obtain the voltage difference cumulative value; the voltage difference cumulative value is positively correlated mapped to obtain the voltage deviation at the arbitrary moment.

3. The method for automatic detection of electrical performance of a water cooling system according to claim 1, characterized in that: The step of obtaining the moment of suspected voltage abnormality according to the voltage deviation at any moment comprises: Any time when the voltage deviation exceeds a preset deviation threshold is regarded as the voltage suspected abnormality time.

4. The method for automatic detection of electrical performance of a water cooling system according to claim 1, characterized in that: The step of obtaining a temperature-voltage correlation diagram according to the temperature time series and the voltage time series comprises: The temperature time series is normalized to the maximum and minimum values ​​to obtain the temperature mapping values ​​at different times; the voltage time series is normalized to the maximum and minimum values ​​to obtain the voltage mapping values ​​at different times; a coordinate graph is constructed with the horizontal axis being the temperature mapping value and the vertical axis being the voltage mapping value, and a temperature-voltage correlation graph is constructed according to the positions of the temperature mapping values ​​and the voltage mapping values ​​at the same time in the coordinate graph.

5. The method for automatic detection of electrical performance of a water cooling system according to claim 4, characterized in that: The step of obtaining the temperature interval and the voltage characterization value according to the temperature distribution characteristics and the voltage distribution characteristics in the temperature-voltage association diagram comprises: The temperature mapping values ​​of the temperature-voltage association diagram are divided according to a preset segmentation interval to obtain different temperature intervals; and the average values ​​of the voltage mapping values ​​corresponding to the temperature intervals are calculated to obtain the voltage characterization value.

6. The method for automatic detection of electrical performance of a water cooling system according to claim 1, characterized in that: The step of obtaining a humidity normal index according to the humidity difference characteristics between the voltage suspected abnormal moment and the historical period in the humidity time series comprises: The humidity average value of the historical period before the voltage is suspected to be abnormal is calculated to obtain the historical humidity value; the absolute value of the difference between the humidity at the time when the voltage is suspected to be abnormal and the historical humidity value is calculated and negatively correlated to obtain the humidity normal index at the time when the voltage is suspected to be abnormal.

7. The method for automatic detection of electrical performance of a water cooling system according to claim 4, characterized in that: The step of obtaining a data distribution characteristic value according to the voltage distribution characteristic of the temperature interval in which the temperature at the time when the voltage is suspected to be abnormal is located comprises: Calculate the ratio of the voltage mapping value of the temperature interval where the temperature at the moment the voltage is suspected to be abnormal to the voltage mapping value in the temperature-voltage association diagram to obtain the data proportion characteristic value; calculate the variance of the voltage mapping value of the temperature interval where the temperature at the moment the voltage is suspected to be abnormal and negatively map it to obtain the voltage concentration; calculate the product of the data proportion characteristic value and the voltage concentration to obtain the data distribution characteristic value at the moment the voltage is suspected to be abnormal.

8. The method for automatic detection of electrical performance of a water cooling system according to claim 1, characterized in that: The step of obtaining the temperature-voltage correlation confidence according to the humidity normal index and the data distribution characteristic value comprises: The product of the humidity normal index and the data distribution characteristic value is calculated and positively correlated to obtain the temperature-voltage correlation credibility at the moment when the voltage is suspected to be abnormal.

9. The method for automatic detection of electrical performance of a water cooling system according to claim 4, characterized in that: The step of obtaining the voltage abnormality degree according to the difference characteristics between the voltage characterization value in the temperature interval where the temperature at the time when the voltage is suspected to be abnormal and the voltage at the time when the voltage is suspected to be abnormal and the temperature-voltage association credibility comprises: Calculate the absolute value of the difference between the voltage characterization value in the temperature interval where the temperature is located at the moment when the voltage is suspected to be abnormal and the voltage mapping value corresponding to the moment when the voltage is suspected to be abnormal, and obtain the voltage difference index; calculate the product of the voltage difference index and the temperature-voltage association credibility to obtain the voltage abnormality degree at the moment when the voltage is suspected to be abnormal.

10. The method for automatic detection of electrical performance of a water cooling system according to claim 1, characterized in that: The step of detecting the electrical performance of the water cooling system according to the voltage abnormality degree comprises: When the voltage abnormality degree at the time when the voltage is suspected to be abnormal exceeds a preset abnormality threshold, the electrical performance of the water cooling system is abnormal at the time when the voltage is suspected to be abnormal.

Images