Distributed emergency takeover method for new energy station and intelligent control device thereof

Abstract

The invention discloses a new energy station distributed emergency takeover method and an intelligent control device thereof, and the method is characterized in that a sensor used for monitoring the operation temperature of each new energy charging pile is arranged in each new energy charging pile, and each corresponding sensor transmits data to a central emergency judgment module in a wireless manner; and the central emergency judgment module judges whether the corresponding charging pile reaches a high-temperature threshold value or not, carries out emergency takeover on the charging pile which reaches the high-temperature threshold value, and controls the cooling assembly to cool the charging pile. Excessive or insufficient cooling is avoided; a deep learning integer and a historical maximum slope point are fused, and it is ensured that the cooling amplitude can break through a current threshold value and can also restrain potential risk points; a precise linear function is generated by inputting a critical point and a target point, and a temperature curve smoothly returns to a safety interval.

Description

Technical Field

[0001] The present invention relates to the technical field of safety control of new energy power systems, and in particular to a distributed emergency takeover method for new energy stations and an intelligent control device thereof, which is suitable for early response to failure scenarios of new energy stations such as wind farms, photovoltaic power stations, and energy storage systems. Background Art

[0002] The emergency takeover system of traditional new energy stations (taking cooling takeover technology as the research object) has the following defects:

[0003] Insufficient adaptability: The cooling emergency strategy based on preset rules cannot provide appropriate cooling effects while controlling costs, and lacks adaptability.

[0004] Insufficient curve data processing capabilities: The real-time operation data and historical data characteristics of the curve were not integrated through an accurate fusion model, resulting in a decision-making deviation rate of over 30%. Summary of the Invention

[0005] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of this application to avoid obscuring the purpose of this section, the abstract and the title of the invention, and such simplifications or omissions should not be used to limit the scope of the present invention.

[0006] In view of the above-mentioned problems existing in the existing emergency takeover system of new energy stations, the present invention is proposed.

[0007] Therefore, the technical problem solved by the present invention is to solve the problems of insufficient adaptability strategy and insufficient curve data processing capability of the existing new energy station emergency takeover system.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions: a distributed emergency takeover method for new energy stations, wherein a sensor for monitoring the operating temperature of each new energy charging pile is installed in each new energy charging pile, and each corresponding sensor transmits data to a central emergency judgment module wirelessly. The central emergency judgment module determines whether the corresponding charging pile has reached a high temperature threshold, and takes emergency takeover of the charging pile that has reached the high temperature threshold, and controls the cooling component to cool the charging pile; the central emergency judgment module determines whether the corresponding sensor detects an abnormality, specifically including the following steps: S1: The set temperature sensor obtains the temperature data of the corresponding charging pile in the operation stage in real time; S2: In a two-dimensional coordinate system, a temperature-time curve is constructed based on the acquired temperature data; S3: A preset temperature threshold, when the detected temperature data reaches the temperature threshold, emergency supervision is enabled; S4: The cooling component is controlled to start, and the charging pile is cooled according to the extracted cooling parameters; S5: Real-time operation to check the status of each charging pile.

[0009] As a preferred solution of the distributed emergency takeover method for new energy stations described in the present invention, in which: in S1, after obtaining each temperature data, it also includes data preprocessing of each data; wherein the data preprocessing step specifically includes: data cleaning and data noise reduction.

[0010] As a preferred solution of the distributed emergency takeover method for new energy stations described in the present invention, when constructing a temperature-time curve, the time sequence is used as the X-axis and the detected temperature data is used as the Y-axis to construct a two-dimensional coordinate system, and the real-time collected temperature data is input into the two-dimensional coordinate system to complete the construction.

[0011] As a preferred solution of the distributed emergency takeover method for new energy stations described in the present invention, in which: in step S4, cooling the charging pile according to the extracted cooling parameters specifically includes: taking the program linear cooling function y=kx+b as a benchmark, obtaining the k value parameter according to the temperature-time curve; obtaining the time dimension L of cooling according to the temperature-time curve; obtaining the degree dimension H of cooling according to the temperature-time curve.

[0012] As a preferred solution of the distributed emergency takeover method for new energy stations of the present invention, the time dimension L of the cooling is obtained according to the following model:

[0013]

[0014] Among them, L is the time dimension of cooling; t1 is the time when the temperature-time curve reaches the preset temperature threshold; N reference points (N≥3) are taken at uniform time intervals on the temperature-time curve, K P is the slope of the point on the temperature-time curve where the preset temperature threshold is reached; K1 is the slope of the first reference point; KP-1 is the slope of change at the P-1th reference point; K P-2 is the slope of change at the P-2th reference point; ln2.36 is the robust adjustment constant.

[0015] As a preferred solution of the distributed emergency takeover method for new energy stations of the present invention, the degree of cooling dimension H is obtained according to the following model:

[0016]

[0017] Among them, H is the degree of cooling; H1 is the preset temperature threshold; N reference points (N≥3) are taken at uniform time intervals on the temperature-time curve, K P is the slope of the point on the temperature-time curve where the preset temperature threshold is reached; K1 is the slope of the first reference point; K P-1 is the slope of change at the P-1th reference point; M is a deep learning integer; H Kmax is the temperature value corresponding to the point with the maximum transformation slope on the temperature-time curve; ln2.36 is the robust adjustment constant.

[0018] As a preferred solution of the distributed emergency takeover method for new energy stations described in the present invention, when obtaining the program linear cooling function y=kx+b, (t1, H1) and (L+t1, H) are input into the function.

[0019] In order to solve the above technical problems, the present invention provides the following technical solutions: a distributed emergency takeover intelligent control device for new energy stations, comprising the following components: a temperature data acquisition component, which acquires the temperature data of the corresponding charging pile in the operation stage in real time through an installed temperature sensor; a data preprocessing unit, which is embedded in the temperature data acquisition component and is used to perform data preprocessing on the collected temperature data; a central emergency judgment module, which is wirelessly connected to the temperature data acquisition component, obtains the preprocessed temperature data, determines whether the corresponding charging pile has reached a high temperature threshold, and takes emergency takeover of the charging pile that has reached the high temperature threshold, and controls the cooling component to cool the charging pile; a cooling component, which is signal-connected to the central emergency judgment module, receives the cooling parameters obtained by the central emergency judgment module, and cools the charging pile according to the corresponding cooling parameters.

[0020] As a preferred solution of the distributed emergency takeover intelligent control device for new energy stations described in the present invention, it also includes a cooling analysis unit embedded in the central emergency judgment module, which obtains the time dimension and degree dimension of cooling based on the obtained temperature-time curve.

[0021] The present invention provides a distributed emergency takeover method for a new energy station and an intelligent control device thereof, which have the following beneficial effects:

[0022] 1. Improve emergency response efficiency and accuracy

[0023] Dynamic threshold determination: By building a temperature-time curve in real time and combining it with a preset high-temperature threshold, it can accurately trigger emergency takeover, increasing response speed by more than 30% compared to traditional fixed rules.

[0024] Data preprocessing optimization: Integrated data cleaning (3σ principle / IQR method / sliding window) and noise reduction (low-pass filtering / Kalman filtering) eliminate outliers and noise interference, improving data reliability to 99.2%;

[0025] 2. Intelligent cooling strategy optimization

[0026] Time dimension L: A mathematical model is constructed based on the slope characteristics of the temperature curve, and a robust adjustment constant is introduced to dynamically calculate the optimal cooling time to avoid excessive or insufficient cooling;

[0027] Degree dimension H: Integrates deep learning integers with historical maximum slope points to ensure that the cooling range can both break through the current threshold and suppress potential risk points;

[0028] Linear cooling function: By inputting the critical point and target point, a precise linear function is generated to achieve a smooth return of the temperature curve to the safe range. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be derived from these drawings without inventive effort. Among them:

[0030] Figure 1 This is a flow chart of a method provided by the central emergency judgment module of the present invention for determining whether a corresponding sensor detects an abnormality.

[0031] Figure 2 This is a schematic diagram of the determination of the temperature-time curve provided by the present invention.

[0032] Figure 3 This is a system module diagram of the distributed emergency takeover intelligent control device for new energy stations provided by the present invention. DETAILED DESCRIPTION

[0033] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0034] The emergency takeover system of traditional new energy stations (taking cooling takeover technology as the research object) has the following defects:

[0035] Insufficient adaptability: The cooling emergency strategy based on preset rules cannot provide appropriate cooling effects while controlling costs, and lacks adaptability.

[0036] Insufficient curve data processing capabilities: The real-time operation data and historical data characteristics of the curve were not integrated through an accurate fusion model, resulting in a decision-making deviation rate of over 30%.

[0037] Therefore, see Figure 1 and Figure 2 The present invention provides a distributed emergency takeover method for new energy stations. A sensor for monitoring the operating temperature of each new energy charging pile is installed in the charging pile. Each corresponding sensor transmits data to a central emergency judgment module via wireless means. The central emergency judgment module determines whether the corresponding charging pile has reached a high temperature threshold, and performs emergency takeover for the charging pile that has reached the high temperature threshold, and controls the cooling component to cool the charging pile.

[0038] The central emergency judgment module determines whether the corresponding sensor detects an abnormality, specifically including the following steps:

[0039] S1: The set temperature sensor obtains the temperature data of the corresponding charging pile in real time during the operation phase;

[0040] S2: In the two-dimensional coordinate system, a temperature-time curve is constructed based on the acquired temperature data;

[0041] S3: Preset temperature threshold. When the detected temperature data reaches the temperature threshold, emergency supervision is enabled.

[0042] S4: Control the cooling component to start and cool the charging pile according to the extracted cooling parameters;

[0043] S5: Check the status of each charging pile in real time.

[0044] It should be noted that the sensor used to measure the operating temperature in the present invention is an existing conventional temperature sensor, which will not be described in detail here.

[0045] It should be noted that the wireless communication protocol adopted in the present invention is an existing conventional transmission protocol, which will not be described in detail here.

[0046] It should be noted that the high temperature threshold selected in the present invention is generally defined as about 60 degrees Celsius. Users can make corresponding adjustments based on actual conditions, which does not affect the essence of the algorithm of the present invention.

[0047] It should be noted that the cooling technology used in the present invention is an existing mature charging pile cooling technology, such as fan activation, gas cooling, etc., which will not be elaborated here.

[0048] Furthermore, in S1, after obtaining each temperature data, it also includes performing data preprocessing on each data;

[0049] Among them, the data preprocessing steps specifically include: data cleaning and data noise reduction.

[0050] Specifically:

[0051] ① Data Cleaning: conventional cleaning steps, which users can select or modify based on actual conditions;

[0052] 1.1 Removing Outliers

[0053] method:

[0054] 3σ principle: Assuming that the data follows a normal distribution, outliers that exceed the mean ±3σ are eliminated.

[0055] IQR (interquartile range) method: calculate the upper and lower quartiles (Q1 / Q3), and eliminate values ​​below Q1-1.5IQR or above Q3+1.5IQR.

[0056] Sliding window method: For time series data, use a sliding window (such as a window length of 1 minute) to calculate the local mean and standard deviation, and mark abnormal points that deviate from the threshold.

[0057] 1.2 Handling Missing Values

[0058] Filling strategy:

[0059] Linear interpolation: Suitable for scenarios where data trends are stable.

[0060] Polynomial fitting: For nonlinear trend data, use quadratic or cubic polynomial interpolation.

[0061] Time Series Forecasting: Predict missing values ​​using ARIMA models or LSTM neural networks.

[0062] ② Noise Reduction: conventional noise reduction steps, which users can select or modify based on actual conditions;

[0063] Low-pass filtering: suppresses high-frequency noise (such as electromagnetic interference) and preserves temperature change trends.

[0064] Digital filter: Use Butterworth or Chebyshev type I filter.

[0065] Kalman filter: Dynamically estimates system state and is suitable for real-time noise suppression.

[0066] Specifically, when constructing the temperature-time curve, a two-dimensional coordinate system is constructed with the time sequence as the X-axis and the detected temperature data as the Y-axis. The real-time collected temperature data is input into the two-dimensional coordinate system to complete the construction.

[0067] Furthermore, in step S4, cooling the charging pile according to the extracted cooling parameters specifically includes:

[0068] Based on the program linear cooling function y=kx+b, the k value parameter is obtained according to the temperature-time curve;

[0069] Obtain the time dimension L of cooling based on the temperature-time curve;

[0070] The degree of cooling dimension H is obtained based on the temperature-time curve.

[0071] Furthermore, the time dimension L of the cooling is obtained according to the following model:

[0072]

[0073] Among them, L is the time dimension of cooling; t1 is the time when the temperature-time curve reaches the preset temperature threshold; N reference points (N≥3) are taken at uniform time intervals on the temperature-time curve, K P is the slope of the point on the temperature-time curve where the preset temperature threshold is reached; K1 is the slope of the first reference point; K P-1 is the slope of change at the P-1th reference point; K P-2 is the slope of change at the P-2th reference point; ln2.36 is the robust adjustment constant.

[0074] It should be noted that, see Figure 2 When generating the above model, the following situation must be considered first: when the charging pile is in operation, no matter how the temperature curve changes, its overall trend is definitely gradually rising. The higher the temperature of the external environment, the faster it rises. When the temperature of the curve rises to the threshold point P, its change trend is still gradually rising, and its K P Greater than or equal to 0; when K PThe larger the value is, the greater the upward trend is, the greater the need for cooling is, and the greater the need to control the cooling time is. P The smaller the value, the smaller the upward trend, the smaller the need for cooling, and the smaller the need to control the cooling time. Therefore, the slope of the transformation at point P is the independent variable that needs to be considered. P As a basic consideration.

[0075] Model K P There are fractional terms and constant terms in the exponential term. The denominator of the fractional term specifically considers the difference in slope between each selected reference point, reflecting the overall rate of change of the curve before point P. The numerator considers the change trend of the three points closest to point P. The difference in degree between the three points can actually best reflect the change trend at point P. The fraction expresses the degree of change rate contributed by point P to the overall curve. Compared with the traditional K P As a consideration directly incorporated, the present invention takes more comprehensive considerations and has higher accuracy. It is not difficult to understand that the conversion rate characteristic of a temperature curve is not based on the conversion rate of the last point as the only consideration criterion. Each point actually makes a temperature contribution to the temperature curve, but the degree is different.

[0076] Ln2.36 is the robust adjustment constant of the model. After the model is generated, the corresponding overall value needs to be an integer. Therefore, the robustness characteristics of the overall value need to be taken into account, and the overall expression needs to be linear.

[0077] Therefore, ln2.36 is selected as the robust adjustment constant. Of course, when using this model, users can make corresponding adjustments based on ln2.36 according to actual conditions to ensure that the model output value is as close to an integer as possible.

[0078] Furthermore, the degree of cooling dimension H is obtained according to the following model:

[0079]

[0080] Among them, H is the degree of cooling; H1 is the preset temperature threshold; N reference points (N≥3) are taken at uniform time intervals on the temperature-time curve, K P is the slope of the point on the temperature-time curve where the preset temperature threshold is reached; K1 is the slope of the first reference point; K P-1 is the slope of change at the P-1th reference point; M is a deep learning integer; H Kmax is the temperature value corresponding to the point with the maximum transformation slope on the temperature-time curve; ln2.36 is the robust adjustment constant.

[0081] It should be noted that the H selected in the present invention Kmax To consider the bottom line, because in reality, K max The subsequent curve shows a very upward trend, which has the greatest contribution to the temperature of the charging station and the greatest impact. Kmax The following can ensure that the charging pile is within a safe temperature range to the greatest extent possible.

[0082] Specifically, when obtaining the program linear cooling function y=kx+b, (t1, H1) and (L+t1, H) are input into the function.

[0083] Additionally, to illustrate this solution, see Figure 3 The present invention also provides a distributed emergency takeover intelligent control device for a new energy station, comprising the following components:

[0084] The temperature data acquisition component obtains the temperature data of the corresponding charging pile in the operation stage in real time through the installed temperature sensor;

[0085] The data preprocessing unit is embedded in the temperature data acquisition component and is used to preprocess the collected temperature data;

[0086] The central emergency judgment module is wirelessly connected to the temperature data acquisition component to obtain pre-processed temperature data, determine whether the corresponding charging pile has reached the high temperature threshold, and take emergency control of the charging pile that has reached the high temperature threshold, controlling the cooling component to cool the charging pile;

[0087] The cooling component is connected to the central emergency judgment module signal, receives the cooling parameters obtained by the central emergency judgment module, and cools the charging pile according to the corresponding cooling parameters.

[0088] Furthermore, it also includes a cooling analysis unit, which is embedded in the central emergency judgment module and obtains the time dimension and degree dimension of cooling based on the obtained temperature-time curve.

[0089] In order to verify the beneficial effects of the present invention, the following simulation experiments are performed:

[0090] Experimental verification design

[0091] 1. Experimental Design

[0092] Experimental Dimension Experimental group (present invention) Control group (traditional method) Test indicators Response speed Dynamic threshold + model calculation Fixed threshold (60°C) Trigger time, cooling start delay Cooling efficiency L / H two-dimensional model Fixed cooling time (15 minutes) Temperature recovery time, energy consumption ratio Data robustness 3σ / IQR cleaning + Kalman filtering No preprocessing Outlier recognition rate, data reliability Complex scenarios Exponential temperature rise curve Linear cooling strategy Overshoot rate, risk suppression rate

[0093] 2. Experimental scenario construction

[0094] Scene Number Scenario Description Temperature curve characteristics S1 Conventional high temperature trigger Linear rise (slope 0.8℃ / min) S2 Sudden temperature rise events Exponential rise (initial slope 1.2°C / min) S3 Abnormal data interference Contains 5% random noise + 3 missing values S4 Collaborative cooling of multiple charging piles 5 triggers at the same time, 5 minutes apart

[0095] 3. Data Collection Specifications

[0096] Data Type Sampling frequency Accuracy requirements Collection cycle Temperature raw data 1Hz ±0.5℃ 30min Sensor status data 10Hz ±0.1V 30min Environmental parameters 1Hz ±1% 30min

[0097] Core experimental cases

[0098] Case 1: High temperature threshold trigger response experiment

[0099] Experimental configuration:

[0100] Charging pile number: C1001;

[0101] Initial temperature: 45°C;

[0102] Target threshold: 60°C;

[0103] Cooling component: air cooling system (power 2kW);

[0104] Experimental data:

[0105] Indicator Traditional method (control group) The method of the present invention (experimental group) Improvement Trigger response time (s) 120±15 68±8 43.3%↓ Cooling start delay (s) 45±10 22±5 51.1%↓ Temperature recovery time (min) 15.2±1.8 9.7±1.2 36.2%↓ Energy consumption ratio (kWh / ℃) 0.38±0.05 0.29±0.03 23.7%↓

[0106] Case 2: Complex temperature curve processing experiment

[0107] Experimental configuration:

[0108] Curve type: exponential growth;

[0109] Number of sampling points: N=120 (5-minute interval);

[0110] Model parameter verification:

[0111] Parameter items The first experimental value in the same area The second experimental value in the same area Error rate Time dimension L (min) 8.7 8.5 2.3% Degree dimension H(℃) 15.2 15.0 1.3% Slope correction factor -1.75 -1.70 2.9%

[0112] Cooling effect comparison:

[0113] Indicator Traditional methods Method of the present invention Improvement effect Maximum overshoot temperature (℃) 63.8±1.2 61.2±0.8 4.0%↓ Residual risk rate (%) 18.7±3.2 5.3±1.1 71.6%↓ Curve smoothness There are 3 shocks Only 1 small fluctuation A decrease of 89%

[0114] Case 3: Multi-pile coordinated cooling experiment

[0115] Experimental configuration:

[0116] Number of concurrent piles: 5;

[0117] Trigger interval: 5 minutes;

[0118] Grid capacity limit: 30kW;

[0119] System performance comparison:

[0120] Collaborative Dimension Traditional methods Method of the present invention Optimization effect Energy distribution efficiency 62%±5% 89%±3% 43.5%↑ Response consistency Delay difference ±25s Delay difference ±8s 68%↓ System stability Overload protection triggered 3 times 0 overloads 100% improvement Cumulative cooling capacity (kW·h) 247.5±12.3 218.7±9.8 11.5%↓

[0121] Data Validation Form

[0122] Table 1: Comparison of data preprocessing effects

[0123] Data Type Abnormal rate of raw data Abnormal rate after cleaning Signal-to-noise ratio after noise reduction S1 2.1% 0.03% 23.6dB S2 3.8% 0.12% 21.8dB S3 8.7% 0.05% 19.4dB

[0124] Table 2: Model robustness verification

[0125] Interference Type Model parameter fluctuation range Forecast error rate Recovery success rate Gaussian noise ±5% 2.1%±0.3 98.7% Step interference ±8% 3.2%±0.5 96.5% Communication delay ±15s 4.1%±0.6 94.3%

[0126] Table 3: Full life cycle performance indicators

[0127] Evaluation Dimensions Method of the present invention Industry benchmark Compliance rate Timely response ≤70s ≤120s 41.7%↑ Cooling accuracy ±0.8℃ ±2.5℃ 68.0%↑ System availability 99.97% 99.5% 0.47%↑ Comprehensive energy efficiency ratio 1:4.2 1:2.8 49.3%↑

[0128] Experimental conclusion:

[0129] Response speed increased to 1.76 times that of traditional methods (68s vs 120s);

[0130] Cooling energy consumption is reduced by 23.7%, and the cooling efficiency per unit energy consumption is increased to 0.29kWh / ℃;

[0131] In multi-pile collaboration scenarios, system stability is improved to 2.02 times the industry benchmark;

[0132] The error of the time dimension model L is controlled within ±2.5%, meeting industrial-level control requirements;

[0133] The use of the historical maximum slope point by the degree dimension model H reduces the residual risk rate by 71.6%;

[0134] Dynamic adjustment of the slope correction coefficient k of the linear cooling function improves the smoothness of the temperature curve by 89%.

[0135] The present invention provides a distributed emergency takeover method for a new energy station and an intelligent control device thereof, which have the following beneficial effects:

[0136] 1. Improve emergency response efficiency and accuracy

[0137] Dynamic threshold determination: By building a temperature-time curve in real time and combining it with a preset high-temperature threshold, it can accurately trigger emergency takeover, increasing response speed by more than 30% compared to traditional fixed rules.

[0138] Data preprocessing optimization: Integrated data cleaning (3σ principle / IQR method / sliding window) and noise reduction (low-pass filtering / Kalman filtering) eliminate outliers and noise interference, improving data reliability to 99.2%;

[0139] 2. Intelligent cooling strategy optimization

[0140] Time dimension L: A mathematical model is constructed based on the slope characteristics of the temperature curve, and a robust adjustment constant is introduced to dynamically calculate the optimal cooling time to avoid excessive or insufficient cooling;

[0141] Degree dimension H: Integrates deep learning integers with historical maximum slope points to ensure that the cooling range can both break through the current threshold and suppress potential risk points;

[0142] Linear cooling function: By inputting the critical point and target point, a precise linear function is generated to achieve a smooth return of the temperature curve to the safe range.

[0143] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A distributed emergency takeover method for a new energy station, characterized in that: A sensor for monitoring the operating temperature of each new energy charging pile is installed. Each corresponding sensor transmits data wirelessly to a central emergency judgment module. The central emergency judgment module determines whether the corresponding charging pile has reached a high temperature threshold, and takes emergency control of the charging pile that has reached the high temperature threshold, controlling the cooling component to cool the charging pile. The central emergency judgment module determines whether the corresponding sensor detects an abnormality, specifically including the following steps: S1: The set temperature sensor obtains the temperature data of the corresponding charging pile in real time during the operation phase; S2: In the two-dimensional coordinate system, a temperature-time curve is constructed based on the acquired temperature data; S3: Preset temperature threshold. When the detected temperature data reaches the temperature threshold, emergency supervision is enabled. S4: Control the cooling component to start and cool the charging pile according to the extracted cooling parameters; S5: Check the status of each charging pile in real time.

2. The distributed emergency takeover method for new energy stations according to claim 1 is characterized by: In S1, after obtaining each temperature data, it also includes data preprocessing of each data; Among them, the data preprocessing steps specifically include: data cleaning and data noise reduction.

3. The distributed emergency takeover method for new energy stations according to claim 2 is characterized by: When constructing a temperature-time curve, a two-dimensional coordinate system is constructed with the time sequence as the X-axis and the detected temperature data as the Y-axis. The real-time collected temperature data is input into the two-dimensional coordinate system to complete the construction.

4. The distributed emergency takeover method for new energy stations according to claim 3 is characterized in that: In step S4, cooling the charging pile according to the extracted cooling parameters specifically includes: Taking the programmed linear cooling function y=kx+b as a benchmark, the k value parameter is obtained according to the temperature-time curve; Obtaining the time dimension L of cooling according to the temperature-time curve; The degree dimension H of the cooling is obtained according to the temperature-time curve.

5. The distributed emergency takeover method for new energy stations according to claim 4 is characterized in that: The time dimension L of cooling is obtained according to the following model: Among them, L is the time dimension of cooling; t1 is the time when the temperature-time curve reaches the preset temperature threshold; N reference points (N≥3) are taken at uniform time intervals on the temperature-time curve, K P is the slope of the point on the temperature-time curve where the preset temperature threshold is reached; K1 is the slope of the first reference point; K P-1 is the slope of change at the P-1th reference point; K P-2 is the slope of change at the P-2th reference point; ln2.36 is the robust adjustment constant.

6. The distributed emergency takeover method for new energy stations according to claim 4 is characterized in that: The degree of cooling dimension H is obtained according to the following model: Among them, H is the degree of cooling; H1 is the preset temperature threshold; N reference points (N≥3) are taken at uniform time intervals on the temperature-time curve, K P is the slope of the point on the temperature-time curve where the preset temperature threshold is reached; K1 is the slope of the first reference point; K P-1 is the slope of change at the P-1th reference point; M is a deep learning integer; H Kmax is the temperature value corresponding to the point with the maximum transformation slope on the temperature-time curve; ln2.36 is the robust adjustment constant.

7. The distributed emergency takeover method for new energy stations according to claim 4 is characterized by: When obtaining the program linear cooling function y=kx+b, input (t1, H1) and (L+t1, H) into the function.

8. A distributed emergency takeover intelligent control device for new energy stations, characterized in that: Includes the following components: The temperature data acquisition component obtains the temperature data of the corresponding charging pile in the operation stage in real time through the installed temperature sensor; A data preprocessing unit, embedded in the temperature data acquisition component, for performing data preprocessing on the collected temperature data; The central emergency judgment module is wirelessly connected to the temperature data acquisition component to obtain pre-processed temperature data, determine whether the corresponding charging pile has reached a high temperature threshold, and take emergency control of the charging pile that has reached the high temperature threshold, and control the cooling component to cool the charging pile; The cooling component is connected to the central emergency judgment module signal, receives the cooling parameters obtained by the central emergency judgment module, and cools the charging pile according to the corresponding cooling parameters.

9. The distributed emergency takeover intelligent control device for new energy stations according to claim 8 is characterized by: It also includes a cooling analysis unit, which is embedded in the central emergency judgment module and obtains the time dimension and degree dimension of cooling based on the obtained temperature-time curve.

Images