High-voltage power distribution cabinet heat dissipation system based on big data

Abstract

The invention discloses a high-voltage power distribution cabinet heat dissipation system based on big data, which relates to the technical field of heat dissipation of electrical equipment and comprises a data acquisition module, a processing analysis module, a man-machine interaction module and a data storage module. An existing heat dissipation mode usually depends on a static fan or air conditioning equipment, dynamic adjustment cannot be carried out according to environment changes and load conditions, and the problems of high energy consumption and slow response exist. The system processes data, eliminates abnormal values, fills missing data, calculates correlation among temperature, humidity, current and fan rotating speed, predicts change trends of the temperature, the humidity and the current through a time sequence model, and displays key data through a graphical interface by a man-machine interaction module, so that the equipment management efficiency is improved; and precious historical data is provided for subsequent fault analysis and tracking, so that optimization of a maintenance strategy of the system and reduction of potential operation risks are facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of heat dissipation of electrical equipment, and in particular to a heat dissipation system for a high-voltage power distribution cabinet based on big data. Background Art

[0002] With the continuous development of power systems and the acceleration of industrialization, high-voltage distribution cabinets are increasingly used in power transmission and distribution. High-voltage distribution cabinets have dense internal equipment and generate a lot of heat, especially during peak load periods. If the heat dissipation is poor, the internal temperature will rise, increasing the risk of equipment failure, and in serious cases, it may cause safety accidents such as fire. Therefore, how to efficiently manage the heat dissipation problem of distribution cabinets is an important issue in the safe operation of power systems;

[0003] Traditional heat dissipation methods usually rely on static fans or air-conditioning equipment, which cannot be dynamically adjusted according to environmental changes and load conditions, and have problems such as high energy consumption and slow response. Summary of the invention

[0004] In order to solve the above-mentioned defects, the present invention provides a technical solution, which provides an intelligent heat dissipation system for high-voltage distribution cabinets based on big data analysis. It utilizes real-time data monitoring and big data analysis to realize accurate monitoring of the temperature in the distribution cabinet and intelligent heat dissipation control, thereby improving the operating efficiency and safety of the equipment.

[0005] The core idea of ​​the present invention is to collect temperature, humidity, current, voltage and other data inside and outside the power distribution cabinet through multiple sensors, and upload these data to the cloud or local server for big data analysis. By analyzing historical data and current operating status, the system can predict the temperature change trend and intelligently adjust the working status of the heat dissipation device (such as fan speed, cooling system start time, etc.) to achieve precise heat dissipation and energy-saving control.

[0006] The object of the present invention can be achieved by the following technical solutions: A high-voltage power distribution cabinet heat dissipation system based on big data, including a data processing and analysis module and an intelligent control module;

[0007] The data processing and analysis module processes the various data obtained from the data acquisition module specifically as follows:

[0008] Step 1: Identify the collected data and process the outliers in the data;

[0009] Step 2: By performing multi-dimensional correlation analysis on the data of different sensors, the linear relationship between two variables is measured according to the Pearson correlation coefficient, and the correlation coefficient between temperature and humidity, the correlation coefficient between temperature and load current, and the correlation coefficient between temperature and cooling fan speed n are calculated;

[0010] Step 3: Obtain the historical data of temperature, humidity and current within a certain time range through the data storage module and substitute them into the prediction model to output the corresponding prediction results of the three variables, including predicted temperature, predicted humidity and predicted current;

[0011] Step 4: Detect the working condition of the sensor through the value and correlation coefficient of the sensor to determine whether there is an abnormality; if the correlation coefficient exceeds the normal range, it is marked as abnormal, and a fault information record is generated and sent to the human-computer interaction module;

[0012] The intelligent control module performs analysis based on the sensor data, correlation coefficient and predicted value provided by the data processing and analysis module, specifically:

[0013] Control the fan: perform data fusion analysis on the real-time temperature, predicted temperature, predicted temperature and the correlation coefficient between temperature and load current to obtain the heat dissipation temperature and generate a heat dissipation enhancement signal;

[0014] Control the air conditioner: When the heat dissipation enhancement signal is received, the cooling and heat dissipation are started. The cooling power of the air conditioner is dynamically adjusted according to the heat dissipation demand. The cooling intensity of the air conditioner is obtained based on the temperature deviation and demand analysis. The correlation coefficient r between temperature and humidity is used to determine the cooling intensity of the air conditioner. TH ,When the correlation coefficient between temperature and humidity is positive, the minimum threshold Hmin of humidity H is set through the ,human-computer interaction module. If the humidity does not exist within the ,safe range, a signal to reduce the humidity is generated.

[0015] As a preferred embodiment of the present invention, the specific process of measuring the linear relationship between two variables according to the Pearson correlation coefficient and calculating the correlation coefficient between temperature and humidity, the correlation coefficient between temperature and load current, and the correlation coefficient between temperature and cooling fan speed n is as follows:

[0016] Perform multi-dimensional correlation analysis on the data of different sensors to identify the working mode and rules of the cooling system under different environmental conditions and workloads; measure the linear relationship between two variables based on the Pearson correlation coefficient, and use the formula of the Pearson correlation coefficient: Calculate the correlation coefficient r between temperature and humidity TH , whose value range is between -1 and 1: 1 indicates a perfect positive correlation, that is, when one variable increases, the other variable also increases, -1 indicates a perfect negative correlation, that is, when one variable increases, the other variable decreases, and 0 indicates no linear correlation; where: Ti and Hi are the data points of the i-th temperature and humidity, respectively. are the means of temperature and humidity data respectively; similarly, the correlation coefficient r between temperature and humidity is obtained according to the Pearson correlation coefficient TH The correlation coefficient r between temperature and cooling fan speed n Tn .

[0017] As a preferred embodiment of the present invention, the working condition of the sensor is detected by the value and correlation coefficient of the sensor to determine whether an abnormality occurs; if the correlation coefficient exceeds the normal range, it is marked as abnormal, a fault information record is generated, and the specific process of sending it to the human-computer interaction module is as follows:

[0018] According to the normal range of the set ambient humidity H, the real-time data of the temperature sensor is monitored; if the real-time data of the temperature sensor is continuously significantly higher or lower than the normal fluctuation range of the historical data, or the temperature data remains unchanged for a long time, it is judged that the temperature sensor has a fault or drift; if the ambient humidity H is within a certain range, if it is detected that the real-time data of the temperature sensor is continuously greater than or continuously less than the historical data, or the real-time data remains unchanged, it means that the sensor is faulty and the sensor is marked as a faulty sensor; according to the correlation coefficient analysis, under normal operating conditions, the correlation coefficients between the temperature and humidity, temperature and load current, and temperature and cooling fan speed variables should be maintained within a preset range, and a threshold value for each correlation coefficient is set, and the calculated correlation coefficient is compared with the set threshold value. If the correlation coefficient exceeds the normal range, it is marked as abnormal; if under normal circumstances, the correlation coefficient between temperature and humidity is between 0.5 and 1.0; if the real-time calculated correlation coefficient is 0.4, there is an abnormality; when an abnormal situation or sensor failure is found, the system generates a fault information record and sends it to the human-computer interaction module.

[0019] As a preferred embodiment of the present invention, the specific process of obtaining the heat dissipation temperature and generating the heat dissipation enhancement signal by performing data fusion analysis on the real-time temperature, the predicted temperature, and the correlation coefficient between the predicted temperature and the temperature and the load current is as follows:

[0020] By calculating the real-time temperature T, predicted temperature YCT, predicted temperature YCI and the correlation coefficient r between temperature and load current TI Data fusion is performed according to the formula: The heat dissipation temperature SRT is obtained; where α, β, and γ are all weight coefficients; when the heat dissipation temperature is higher than the set threshold, according to the incremental PID algorithm: Δn = K p ·(e t -e t-1 )+K i ·e t +K d ·(e t -2e t-1 -e t-2 ), nnew=n+Δn to calculate the fan speed n new , where Δn is the incremental adjustment value of the fan speed; Kp is the proportional gain, Ki is the integral gain, and Kd is the differential gain, which is set through the human-computer interaction module; e tis the current temperature error, defined as: e t =SRT-T target , where T target is the set temperature target value; e t-1 and e t-2 are the temperature errors at the previous and previous two time points respectively; n new is the adjusted fan speed; the intelligent control module increases the fan speed n to enhance the heat dissipation effect; on the contrary, when the heat dissipation temperature is lower than the set threshold, the fan speed is reduced to save energy;

[0021] Then calculate the correlation coefficient r between temperature and fan speed Tn , when there is a positive correlation between temperature T and fan speed n, the fan speed increases with the temperature, and the cooling system operates well in responding to temperature changes; when there is no correlation between temperature T and fan speed n, that is, r Tn =0, the fan speed n reaches the maximum and cannot increase with the temperature. The fan heat dissipation cannot meet the heat dissipation requirements of the high-voltage distribution cabinet, and the system generates a heat dissipation enhancement signal.

[0022] As a preferred embodiment of the present invention, when a heat dissipation enhancement signal is received, refrigeration and heat dissipation are started, and the refrigeration power of the air conditioner is dynamically adjusted according to the heat dissipation demand. The specific process of deriving the refrigeration strength of the air conditioner according to the temperature deviation and demand analysis is as follows:

[0023] When the heat dissipation enhancement signal is received, the cooling and heat dissipation is started, and the cooling power of the air conditioner is dynamically adjusted according to the heat dissipation demand. According to the temperature deviation and demand, the formula: P AC =Kac·(SRT-Ttarget) to calculate the cooling intensity of the air conditioner; where Kac is the proportional coefficient of the air conditioner cooling power.

[0024] As a preferred embodiment of the present invention, it also includes a data acquisition module, a human-computer interaction module and a data storage module;

[0025] The data acquisition module collects the temperature T, humidity H, current I data and the speed n of the heat dissipation device inside the power distribution cabinet in real time through high-precision sensors installed at key positions inside the power distribution cabinet, and transmits the collected data to the data processing and analysis module;

[0026] The data storage module is used to store and acquire data;

[0027] The human-computer interaction module realizes communication and control between the system and the operator, and displays key data inside the power distribution cabinet in real time through the graphical user interface; the operator adjusts the control parameters of the system through the human-computer interaction module.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] 1. The present invention improves the reliability and stability of the system by effectively monitoring the working status of the sensor and timely discovering anomalies and faults. When the data of the temperature sensor is continuously abnormal or the correlation coefficient exceeds the set range, the system can automatically mark the faulty sensor and generate a fault record to ensure that maintenance personnel receive warnings in time and take corresponding measures. The active monitoring mechanism not only improves the efficiency of equipment management, but also provides valuable historical data for subsequent fault analysis and tracking, which helps to optimize the system's maintenance strategy and reduce potential operational risks.

[0030] 2. The present invention uses an intelligent control module to monitor and dynamically adjust the operating status of the heat dissipation equipment in real time, ensuring that the temperature and humidity inside the high-voltage distribution cabinet remain within a safe range, thereby improving the stability and reliability of the equipment. Through precise control of fans and air conditioners, it can not only effectively meet the heat dissipation needs and prevent equipment from overheating, but also reduce humidity through the dehumidification function to avoid the risks caused by moisture in the insulating material; in addition, the system can automatically identify abnormal situations and generate alarms to remind maintenance personnel to deal with problems in a timely manner. Intelligent management significantly reduces the need for manual intervention, optimizes operation and maintenance efficiency, and improves the safety and service life of the equipment.

[0031] 3. The present invention uses the intuitive graphical user interface (GUI) of the human-computer interaction module to display the key data of the power distribution cabinet in real time, so that operators can easily monitor the system operation status and perform data analysis. The historical trend chart helps to predict faults and optimize equipment management. When an abnormal situation is detected, the system will immediately issue an alarm to ensure timely response; in addition, the operator can flexibly adjust the control parameters through this module to affect the operation of the heat dissipation equipment in real time, thereby improving the system's resilience and operating efficiency, enhancing the convenience of equipment management, and ensuring the safety and stable operation of the power distribution cabinet. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The present invention will be further described below in conjunction with the accompanying drawings.

[0033] Figure 1 This is the overall system block diagram of the present invention. DETAILED DESCRIPTION

[0034] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] It should be understood that the terms "include" and "comprising" used in the specification and claims of the present disclosure indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0036] It should also be understood that the terms used in this disclosure are only for the purpose of describing specific embodiments and are not intended to limit the disclosure. As used in this disclosure and claims, the singular forms of "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" used in this disclosure and claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations.

[0037] See also Figure 1 As shown, a high-voltage power distribution cabinet heat dissipation system based on big data, the high-voltage power distribution cabinet heat dissipation system is connected to the heat dissipation equipment for communication to collect the working information of the heat dissipation equipment, and is controlled in real time by the intelligent control module; the high-voltage power distribution cabinet heat dissipation system also includes a data acquisition module, a data processing and analysis module, a human-computer interaction module and a data storage module;

[0038] The data acquisition module collects the temperature T, humidity H, current I data and the speed n of the heat dissipation device inside the power distribution cabinet in real time through high-precision sensors installed at key locations inside the power distribution cabinet (such as high-heat areas, heat dissipation channels, and near electrical components), and transmits the collected data to the data processing and analysis module;

[0039] The data processing and analysis module is responsible for processing various data obtained from the data acquisition module, and then analyzing and processing the uploaded data based on big data technology, including statistical analysis of historical data, monitoring of real-time data, prediction of temperature change trends, etc.; specifically, it includes the following steps:

[0040] Step 1: According to the types and functions of different sensors, the collected data is identified and processed for abnormal values, mutations or unreasonable values, and noise in the data is removed through filters or signal processing technology; missing data that occurs during the collection process is supplemented by interpolation or filling methods to ensure the continuity, completeness and accuracy of the data; the results of data processing need to be stored for subsequent access and analysis;

[0041] Step 2: By deeply analyzing the stored data, calculate the basic statistics of each sensor data, such as the mean, and understand the basic characteristics of the data; by performing multi-dimensional correlation analysis on the data of different sensors, the working mode and law of the cooling system under different environmental conditions and workloads can be identified; the linear relationship between two variables can be measured according to the Pearson correlation coefficient, and the formula of the Pearson correlation coefficient is: Calculate the correlation coefficient r between temperature and humidity TH , whose value range is between -1 and 1: 1 indicates a perfect positive correlation, that is, when one variable increases, the other variable also increases; -1 indicates a perfect negative correlation, that is, when one variable increases, the other variable decreases; 0 indicates no linear correlation; where: Ti and Hi are the data points of the i-th temperature and humidity, respectively, and are specifically the values ​​at a certain moment, are the means of temperature and humidity data respectively; similarly, according to the formula of Pearson correlation coefficient: Calculate the correlation coefficient r between temperature and load current TI , where Ti and Ii are the data points of the i-th temperature and load current, respectively. are the means of temperature and load current data respectively; according to the formula of Pearson correlation coefficient: Calculate the correlation coefficient r between temperature and cooling fan speed n Tn , where Ti and Ni are the data points of the ith temperature and the cooling fan speed n, respectively. are the mean values ​​of temperature and load current data respectively; finally, r TH 、r TH and r Tn , and sent to the intelligent control module;

[0042] Step 3: Obtain the historical data of temperature, humidity and current within a certain time range through the data storage module as the training data of the prediction model; at the same time, the real-time uploaded temperature, humidity and load data are used as the input of the prediction model, and the time series model ARIMA model is selected to predict the change trend of temperature T, humidity H and current I, and the prediction results are reflected through three variables, namely, the predicted temperature YCT, the predicted humidity YCH and the predicted current YCI;

[0043] Step 4: Check the working condition of the sensor through the sensor value and correlation coefficient to see if there is any abnormality; monitor the real-time data of the temperature sensor according to the normal range of the set ambient humidity H. If it is found that the real-time data of the temperature sensor is continuously significantly higher or lower than the normal fluctuation range of the historical data, or the temperature data remains unchanged for a long time, this may mean that the temperature sensor is faulty or drifting. For example, when the ambient humidity H is within a certain range, if the real-time data of the temperature sensor is detected to be continuously greater than or continuously less than the historical data, or the real-time data remains unchanged, it means that the sensor is faulty and the sensor is marked as a faulty sensor. According to the correlation coefficient analysis, under normal operating conditions, the correlation coefficients between variables such as temperature and humidity, temperature and load current, temperature and cooling fan speed should be maintained within a certain reasonable range. A threshold value for each correlation coefficient is set, and the calculated correlation coefficient is compared with the set threshold value. If the correlation coefficient exceeds the normal range, it is marked as abnormal. Assuming that the correlation coefficient between temperature and humidity should be between 0.5 and 1.0 under normal circumstances, if the real-time calculated correlation coefficient is 0.4, there is an abnormality. When an abnormal situation or sensor failure is found, the system will generate a fault information record and send it to the human-computer interaction module. After receiving the fault information, the human-computer interaction module will immediately issue a warning on the user interface to prompt the maintenance personnel to check the relevant equipment. At the same time, the system will automatically record the detailed information of the abnormal event, including the time when the abnormality occurred, the sensor type, the correlation coefficient, and the type of fault, etc., for subsequent analysis and tracking.

[0044] The main function of the intelligent control module is to dynamically adjust the operating status of the heat dissipation equipment (such as fans, air conditioners, etc.) according to the sensor data, correlation coefficients and predicted values ​​provided by the data processing and analysis module to ensure that the internal temperature and humidity of the high-voltage distribution cabinet remain within a reasonable range, thereby ensuring the normal operation of the equipment; specifically:

[0045] According to the real-time data, correlation coefficient and predicted value of the sensor, the intelligent control module controls the heat dissipation equipment to achieve heat dissipation inside the power distribution cabinet; including fan control and air conditioning control:

[0046] Fan control: Fan control is the first level of heat dissipation control. It is based on the real-time temperature T, predicted temperature YCT, predicted temperature YCI and the correlation coefficient r between temperature and load current. TI Data fusion is performed according to the formula: The heat dissipation temperature SRT is obtained; where α, β, and γ are weight coefficients used to adjust the influence of each factor; when the SRT is higher than the set threshold, according to the incremental PID algorithm (proportional-integral-differential):

[0047] Δn=Kp·(et-et-1)+Ki·et+Kd·(et-2et-1-et-2), nnew=n+Δn to calculate the fan speed n new , where Δn is the incremental adjustment value of the fan speed; Kp is the proportional gain, Ki is the integral gain, and Kd is the differential gain, which needs to be set through the human-computer interaction module; e t is the current temperature error, defined as: e t =SRT-T target , where T target is the set temperature target value; e t-1 and e t-2 are the temperature errors at the previous and previous two time points respectively; n new is the adjusted fan speed. The intelligent control module will increase the fan speed n to enhance the cooling effect; conversely, when the SRT is lower than the set threshold, the fan speed will be reduced to save energy;

[0048] By calculating the correlation coefficient between temperature and fan speed When there is a positive correlation between temperature T and fan speed n This indicates that the fan speed increases with increasing temperature, which indicates that the cooling system operates well in responding to temperature changes; when there is no correlation between temperature T and fan speed n, that is, This indicates that the fan speed n has reached the maximum and cannot increase with the temperature. The fan heat dissipation cannot meet the heat dissipation requirements of the high-voltage power distribution cabinet, and the system generates a heat dissipation enhancement signal.

[0049] Air conditioning control: Air conditioning is used for two functions: cooling and dehumidification;

[0050] Cooling: Air conditioning cooling is the second cooling level of cooling control. It is mainly started when fan control cannot meet the cooling demand to provide additional cooling and cooling capacity. When the cooling enhancement signal is received, cooling and cooling are started. The cooling power of the air conditioner is dynamically adjusted according to the cooling demand. The system will adjust the cooling power according to the temperature deviation and demand through the formula: P AC = Kac·(SRT-Ttarget) to calculate the cooling intensity P of the air conditioner AC ; Where Kac is the proportional coefficient of air conditioning cooling power, which is set according to the specific equipment and environment;

[0051] Dehumidification: through the correlation coefficient r between temperature and humidity TH , directly reflects the effect of humidity on temperature. When the correlation coefficient between temperature and humidity is positive (r TH>0), indicating that the temperature increases with increasing humidity and decreases with decreasing humidity; for example, in a high humidity environment, the temperature will increase with increasing humidity due to the increase in thermal conductivity of the air; at the same time, insulating materials (such as cable insulation, switchgear insulation, etc.) easily absorb moisture, resulting in a decrease in insulation performance. Moisture absorption by insulating materials will cause a decrease in insulation resistance, increasing the risk of electric shock. At this time, the humidity needs to be reduced, and the system generates a humidity reduction signal; it should be added that the humidity cannot be reduced too low. In a low humidity environment, the conductivity of the air decreases, and static electricity is easily generated and accumulated. Static electricity discharge will cause instantaneous high-voltage shock to electronic components and control systems, which may damage the equipment or cause malfunctions. Therefore, the minimum threshold Hmin of the humidity H needs to be set through the human-computer interaction module to keep the humidity within a safe range (usually between 40% and 60%) to ensure the normal operation of the equipment in the distribution cabinet.

[0052] When receiving a signal to reduce humidity, the air conditioner turns on the dehumidification mode; after switching to the dehumidification mode, the air conditioner first reduces the humidity in the distribution cabinet by reducing the moisture content in the air. The dehumidification mode cools the air to reach the dew point temperature, causing the water vapor in the air to condense into water droplets, thereby reducing the air humidity; the system will continuously monitor the humidity level inside the distribution cabinet. According to the difference between the actual humidity and Hmin, the system dynamically adjusts the intensity of the dehumidification function to ensure that the humidity is maintained within a safe range of 40% to 60%; when the humidity reaches the set safety range, the air conditioner will automatically exit the dehumidification mode and return to the normal temperature control mode; if the ambient humidity rises again, the system will re-trigger the dehumidification mode; if an abnormal situation is detected (such as the dehumidification effect is not obvious or the humidity cannot be reduced), the system will generate a fault alarm and display the air conditioner fault through the human-computer interaction module;

[0053] The human-computer interaction module is responsible for realizing the communication and control between the system and the operator. Its main functions include:

[0054] The computer interaction module displays key data inside the power distribution cabinet in real time through a graphical user interface (GUI), such as temperature, humidity, load current, fan speed, etc. The operator can intuitively understand the current operating status of the system through this interface; it provides historical trend charts of data, showing the changing trends of parameters such as temperature and humidity, and helps operators perform data analysis and fault prediction;

[0055] When the system detects sensor failure, excessive temperature, abnormal humidity, etc., the human-computer interaction module will immediately send out an alarm signal to remind the operator to take corresponding measures. The system will record the time of each alarm, fault type, related sensor data and other information in detail to facilitate future analysis and maintenance;

[0056] Operators can adjust the system's control parameters through the human-computer interaction module, such as temperature setting value, humidity threshold, fan speed, air conditioning cooling intensity, etc. The adjusted parameters will take effect in real time and directly affect the operation of the cooling system. Operators can manually switch the system's working mode through the interface, such as switching from automatic mode to manual mode, to cope with special operating requirements or equipment maintenance;

[0057] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A high-voltage power distribution cabinet heat dissipation system based on big data, including a data processing and analysis module and an intelligent control module, characterized in that: The data processing and analysis module processes the various data obtained from the data acquisition module specifically as follows: Step 1: Identify the collected data and process the outliers in the data; Step 2: By performing multi-dimensional correlation analysis on the data of different sensors, the linear relationship between two variables is measured according to the Pearson correlation coefficient, and the correlation coefficient between temperature and humidity, the correlation coefficient between temperature and load current, and the correlation coefficient between temperature and cooling fan speed n are calculated; Step 3: Obtain the historical data of temperature, humidity and current within a certain time range through the data storage module and substitute them into the prediction model to output the corresponding prediction results of the three variables, including predicted temperature, predicted humidity and predicted current; Step 4: Detect the working condition of the sensor through the value and correlation coefficient of the sensor to determine whether there is an abnormality; if the correlation coefficient exceeds the normal range, it is marked as abnormal, and a fault information record is generated and sent to the human-computer interaction module; The intelligent control module performs analysis based on the sensor data, correlation coefficient and predicted value provided by the data processing and analysis module, specifically: Control the fan: perform data fusion analysis on the real-time temperature, predicted temperature, predicted temperature and the correlation coefficient between temperature and load current to obtain the heat dissipation temperature and generate a heat dissipation enhancement signal; Control the air conditioner: When the heat dissipation enhancement signal is received, the cooling and heat dissipation are started. The cooling power of the air conditioner is dynamically adjusted according to the heat dissipation demand. The cooling intensity of the air conditioner is obtained based on the temperature deviation and demand analysis. The correlation coefficient r between temperature and humidity is used to determine the cooling intensity of the air conditioner. TH ,When the correlation coefficient between temperature and humidity is positive, the minimum threshold Hmin of humidity H is set through the ,human-computer interaction module. If the humidity does not exist within the ,safe range, a signal to reduce the humidity is generated.

2. According to a high-voltage power distribution cabinet heat dissipation system based on big data according to claim 1, it is characterized in that: The specific process of measuring the linear relationship between two variables according to the Pearson correlation coefficient and calculating the correlation coefficient between temperature and humidity, the correlation coefficient between temperature and load current, and the correlation coefficient between temperature and cooling fan speed n is as follows: Perform multi-dimensional correlation analysis on the data of different sensors to identify the working mode and rules of the cooling system under different environmental conditions and workloads; measure the linear relationship between two variables based on the Pearson correlation coefficient, and use the formula of the Pearson correlation coefficient: Calculate the correlation coefficient r between temperature and humidity TH , whose value range is between -1 and 1: 1 indicates a perfect positive correlation, that is, when one variable increases, the other variable also increases, -1 indicates a perfect negative correlation, that is, when one variable increases, the other variable decreases, and 0 indicates no linear correlation; where: Ti and Hi are the data points of the i-th temperature and humidity, respectively. and are the means of temperature and humidity data respectively; similarly, the correlation coefficient r between temperature and humidity is obtained according to the Pearson correlation coefficient TH The correlation coefficient r between temperature and cooling fan speed n Tn .

3. According to a high-voltage power distribution cabinet heat dissipation system based on big data according to claim 2, it is characterized in that: The specific process of detecting the working condition of the sensor through the value and correlation coefficient of the sensor to determine whether an abnormality occurs; if the correlation coefficient exceeds the normal range, it is marked as abnormal, generating a fault information record, and sending it to the human-computer interaction module is as follows: According to the normal range of the set ambient humidity H, the real-time data of the temperature sensor is monitored; if the real-time data of the temperature sensor is continuously significantly higher or lower than the normal fluctuation range of the historical data, or the temperature data remains unchanged for a long time, it is judged that the temperature sensor is faulty or drifting; if the ambient humidity H is within a certain range, if it is detected that the real-time data of the temperature sensor is continuously greater than or continuously lower than the historical data, or the real-time data remains unchanged, it means that the sensor is faulty and the sensor is marked as a faulty sensor; according to the correlation coefficient analysis, under normal operating conditions, the correlation coefficients between the temperature and humidity, temperature and load current, temperature and cooling fan speed variables should be maintained within the preset range, and the threshold of each correlation coefficient is set, and the calculated correlation coefficient is compared with the set threshold. If the correlation coefficient exceeds the normal range, it is marked as abnormal; If the correlation coefficient between temperature and humidity is between 0.5 and 1.0 under normal circumstances, if the correlation coefficient calculated in real time is 0.4, there is an abnormality; When an abnormal situation or sensor failure is detected, the system generates a fault information record and sends it to the human-computer interaction module.

4. According to a high-voltage power distribution cabinet heat dissipation system based on big data according to claim 3, it is characterized in that: The specific process of obtaining the heat dissipation temperature and generating the heat dissipation enhancement signal by performing data fusion analysis on the real-time temperature, the predicted temperature, and the correlation coefficient between the predicted temperature and the temperature and the load current is as follows: By calculating the real-time temperature T, predicted temperature YCT, predicted temperature YCI and the correlation coefficient r between temperature and load current TI Data fusion is performed according to the formula: The heat dissipation temperature SRT is obtained; where α, β, and γ are all weight coefficients; when the heat dissipation temperature is higher than the set threshold, according to the incremental PID algorithm: Δn = K p ·(e t -e t-1 )+K i ·e t +K d ·(e t -2e t-1 -e t-2 ), nnew=n+Δn to calculate the fan speed n new , where Δn is the incremental adjustment value of the fan speed; Kp is the proportional gain, Ki is the integral gain, and Kd is the differential gain, which is set through the human-computer interaction module; e t is the current temperature error, defined as: e t =SRT-T target , where T target is the set temperature target value; e t-1 and e t-2 are the temperature errors at the previous and two previous time points respectively; n new is the adjusted fan speed; the intelligent control module increases the fan speed n to enhance the heat dissipation effect; on the contrary, when the heat dissipation temperature is lower than the set threshold, the fan speed is reduced to save energy; Then calculate the correlation coefficient r between temperature and fan speed Tn , when there is a positive correlation between temperature T and fan speed n, the fan speed increases with the temperature, and the cooling system operates well in responding to temperature changes; when there is no correlation between temperature T and fan speed n, that is, r Tn =0, the fan speed n reaches the maximum and cannot increase with the temperature. The fan heat dissipation cannot meet the heat dissipation requirements of the high-voltage distribution cabinet, and the system generates a heat dissipation enhancement signal.

5. A high-voltage power distribution cabinet heat dissipation system based on big data according to claim 4, characterized in that: When the heat dissipation enhancement signal is received, the cooling and heat dissipation is started, and the cooling power of the air conditioner is dynamically adjusted according to the heat dissipation demand. The specific process of obtaining the cooling strength of the air conditioner according to the temperature deviation and demand analysis is as follows: When the heat dissipation enhancement signal is received, the cooling and heat dissipation is started, and the cooling power of the air conditioner is dynamically adjusted according to the heat dissipation demand. According to the temperature deviation and demand, the formula: P AC =Kac·(SRT-Ttarget) to calculate the cooling intensity of the air conditioner; where Kac is the proportional coefficient of the air conditioner cooling power.

6. A high-voltage power distribution cabinet heat dissipation system based on big data according to claim 1, characterized in that: It also includes a data acquisition module, a human-computer interaction module and a data storage module; The data acquisition module collects the temperature T, humidity H, current I data and the speed n of the heat dissipation device inside the power distribution cabinet in real time through high-precision sensors installed at key positions inside the power distribution cabinet, and transmits the collected data to the data processing and analysis module; The data storage module is used to store and acquire data; The human-computer interaction module realizes communication and control between the system and the operator, and displays key data inside the power distribution cabinet in real time through the graphical user interface; the operator adjusts the control parameters of the system through the human-computer interaction module.

Images