AI-based light storage charging system historical fault heat dissipation data-driven early warning method

Abstract

The application discloses an AI-based light storage and charging system historical fault heat dissipation data-driven early warning method, relates to the technical field of light storage and charging system fault early warning, and comprises the following steps: integrating and collecting historical operation data of the light storage and charging system; calculating the heat generation and heat dissipation efficiency of the light storage and charging system, and simultaneously analyzing the heat dissipation influence relationship; calibrating the heat dissipation influence relationship through historical environmental data to obtain a heat dissipation calibration influence relationship, and simultaneously analyzing the fault judgment standard of the heat dissipation efficiency based on the historical operation data; monitoring the heat dissipation state of the light storage and charging system in real time, and simultaneously predicting the fault of the light storage and charging system based on the heat dissipation calibration influence relationship and the fault judgment standard; and the application is used to solve the problems that the existing light storage and charging system fault early warning technology is not comprehensive and accurate enough for the fault prediction of the light storage and charging system, so that the light storage and charging system cannot be maintained in time.

Description

Technical Field

[0001] This invention relates to the field of fault early warning technology for photovoltaic, energy storage, and charging systems, specifically to an AI-based early warning method driven by historical fault heat dissipation data of photovoltaic, energy storage, and charging systems. Background Technology

[0002] Fault early warning technology for photovoltaic, energy storage and charging systems refers to an active protection technology that identifies early abnormal signs before a fault occurs through real-time monitoring, data analysis and intelligent algorithms, and issues early warnings. Its core objective is to shift from post-fault maintenance to pre-fault prevention.

[0003] Existing fault prediction technologies for photovoltaic-storage-charging systems typically only predict faults based on the system's own operating parameters, failing to provide a comprehensive forecast of system-wide failures. This is because these systems also include a cooling system, the efficiency of which is closely related to the overall health of the system. If the photovoltaic-storage-charging system malfunctions, its temperature will inevitably fluctuate, affecting the cooling system as well. Furthermore, most existing fault prediction technologies rely on threshold judgments for final prediction; if abnormal changes occur but do not exceed the threshold, an accurate fault diagnosis cannot be made. Prediction can be made based on the heat dissipation system to estimate whether there is a risk of failure in the photovoltaic energy storage and charging system. For example, in the patent application with publication number CN118657509A, a "method and system for operation and maintenance of photovoltaic energy storage and charging system" is disclosed. This solution only predicts the failure based on the current and voltage data of the photovoltaic energy storage and charging system itself, and makes a final judgment through operation and maintenance limits. This method has certain monitoring blind spots and cannot make comprehensive failure predictions for the photovoltaic energy storage and charging system. Existing photovoltaic energy storage and charging system failure early warning technology still has the problem that the failure prediction of the photovoltaic energy storage and charging system is not comprehensive or accurate enough, resulting in the inability to maintain the photovoltaic energy storage and charging system in a timely manner. Summary of the Invention

[0004] This invention aims to at least partially address one of the technical problems in the prior art. It integrates and collects historical operating data of a photovoltaic (PV) energy storage and charging system, including historical operating data, historical environmental data, and historical heat dissipation data. Then, it calculates the pre-heat dissipation temperature and heat dissipation efficiency of the PV energy storage and charging system using these historical operating and heat dissipation data. The relationship between the pre-heat dissipation temperature and heat dissipation efficiency is analyzed to obtain the heat dissipation impact relationship. This relationship is then calibrated using historical environmental data to obtain the heat dissipation calibration impact relationship. Based on this calibration impact relationship and combined with historical operating data, a fault judgment standard for heat dissipation efficiency is analyzed. Finally, the heat dissipation status of the PV energy storage and charging system is monitored in real time. Simultaneously, based on the heat dissipation calibration impact relationship and the fault judgment standard, fault prediction is performed on the PV energy storage and charging system. This addresses the problem that existing PV energy storage and charging system fault early warning technologies are not comprehensive or accurate enough in predicting faults, leading to the inability to maintain the PV energy storage and charging system in a timely manner.

[0005] To achieve the above objectives, this application provides an AI-based early warning method driven by historical fault heat dissipation data of a photovoltaic energy storage and charging system, comprising the following steps:

[0006] The historical operating data of the photovoltaic energy storage and charging system is integrated and collected, including historical operating data, historical environmental data, and historical heat dissipation data;

[0007] Calculate the heat generation and heat dissipation efficiency of the photovoltaic energy storage and charging system, and analyze the relationship between the heat generation and heat dissipation efficiency, which is named the heat dissipation influence relationship.

[0008] The heat dissipation impact relationship is calibrated by using historical environmental data to obtain the heat dissipation calibration impact relationship. At the same time, the fault judgment criteria for heat dissipation efficiency are analyzed based on historical operating data.

[0009] The heat dissipation status of the photovoltaic energy storage and charging system is monitored in real time, and fault prediction of the photovoltaic energy storage and charging system is performed based on the influence of heat dissipation calibration and fault judgment criteria.

[0010] Furthermore, the historical operating data includes the historical system temperature of the photovoltaic energy storage and charging system, the historical environmental data includes the historical ambient temperature, and the historical heat dissipation data includes the historical air outlet volume, air inlet temperature, and air outlet temperature of the photovoltaic energy storage and charging system. In addition, the historical operating data is divided into historical normal operation data and historical abnormal operation data according to whether the photovoltaic energy storage and charging system is faulty.

[0011] Furthermore, the heat generation and heat dissipation efficiency of the photovoltaic energy storage and charging system are calculated, and the relationship between the temperature before heat dissipation and the heat dissipation efficiency is analyzed, which is named the heat dissipation influence relationship. This includes the following sub-steps:

[0012] The temperature before heat dissipation and heat dissipation efficiency of the photovoltaic energy storage and charging system are calculated using historical operating data and historical heat dissipation data.

[0013] The relationship between the temperature before heat dissipation and the heat dissipation efficiency was analyzed to obtain the influence relationship on heat dissipation.

[0014] Furthermore, calculating the pre-heating temperature and heat dissipation efficiency of the photovoltaic-storage-charging system using historical operating data and historical heat dissipation data includes the following sub-steps:

[0015] The temperature and heat dissipation of the photovoltaic energy storage and charging system before heat dissipation can be obtained by using the heat conduction formula Q=m×c×ΔT, where Q represents heat, m represents the mass of the object, c represents the specific heat capacity of the object, and ΔT represents the temperature change.

[0016] By calculating the difference between the air outlet temperature and the air inlet temperature, the temperature change after heat exchange between the heat dissipation system and the photovoltaic energy storage and charging system can be obtained, denoted as ΔT1.

[0017] Obtain the mass of the air and the specific heat capacity of the air in the area where the photovoltaic storage and charging system is located, denoted as m1 and c1 respectively. Substitute ΔT1, m1 and c1 into ΔT, m and c in the heat conduction formula respectively to obtain the heat dissipation, denoted as QS.

[0018] The components in the photovoltaic-storage-charging system that can generate heat are named heat-generating components. The mass and specific heat capacity of the heat-generating components in the photovoltaic-storage-charging system are obtained and denoted as m2 and c2, respectively.

[0019] Substitute QS into Q in the heat conduction formula, and simultaneously substitute m2 and c2 into m and c in the heat conduction formula to obtain the heat dissipation temperature difference of the heat-generating component, denoted as TC.

[0020] Add TC to the system temperature to obtain the temperature of the photovoltaic energy storage and charging system before heat dissipation, denoted as TA. Calculate TC / TA to obtain the heat dissipation efficiency.

[0021] Furthermore, the relationship between the temperature before heat dissipation and the heat dissipation efficiency was analyzed, and the influence of heat dissipation was obtained through the following sub-steps:

[0022] Establish a two-dimensional coordinate system with the temperature before heat dissipation as the X-axis and the heat dissipation efficiency as the Y-axis, and name it Temperature Heat Dissipation Trend Chart. Enter the heat dissipation efficiency into the Temperature Heat Dissipation Trend Chart according to the temperature before heat dissipation.

[0023] A function is fitted to the temperature heat dissipation trend graph, and the fitted function is named the temperature heat dissipation trend function, which is the heat dissipation influence relationship.

[0024] Furthermore, the heat dissipation impact relationship is calibrated using historical environmental data to obtain the heat dissipation calibration impact relationship. Simultaneously, the fault judgment criteria for heat dissipation efficiency are analyzed based on historical operating data, including the following sub-steps:

[0025] The heat dissipation influence relationship is calibrated by using historical environmental data to obtain the heat dissipation calibration influence relationship;

[0026] Fault judgment criteria based on the impact of heat dissipation calibration and combined with historical operating data analysis of heat dissipation efficiency.

[0027] Furthermore, the heat dissipation impact relationship is calibrated using historical environmental data, and the heat dissipation calibration impact relationship includes the following sub-steps:

[0028] Name the coordinate points in the temperature heat dissipation trend graph as temperature heat dissipation trend points, and obtain the ambient temperature from the historical operating data to which the temperature heat dissipation trend points belong, and name it the influencing temperature.

[0029] The values ​​of X and Y at the temperature heat dissipation trend points are labeled as PX and PY, respectively. PX is substituted into the temperature heat dissipation trend function to solve for the efficiency before calibration, denoted as PCE.

[0030] Calculate PY / PCE, and name the result as the efficiency calibration parameter, denoted as EP;

[0031] A two-dimensional coordinate system is established with the temperature of influence as the horizontal axis and the efficiency calibration parameter as the vertical axis. This system is named the heat dissipation calibration analysis chart. The EP is entered into the heat dissipation calibration analysis chart according to the temperature of influence.

[0032] A function is fitted to the heat dissipation calibration analysis graph, and the fitted function is named the heat dissipation calibration function. The heat dissipation calibration function is the heat dissipation calibration influence relationship.

[0033] Furthermore, the fault judgment criteria based on the influence of heat dissipation calibration and combined with historical operating data analysis of heat dissipation efficiency include the following sub-steps:

[0034] The coordinate points obtained by analyzing and constructing historical normal operation data and historical abnormal operation data in the heat dissipation calibration analysis graph are named historical normal points and historical abnormal points, respectively.

[0035] Construct a curve for the heat dissipation calibration function in the heat dissipation calibration analysis graph, and name it the heat dissipation calibration curve;

[0036] Move the heat dissipation calibration curve vertically downwards until all historical normal points are above the heat dissipation calibration curve to obtain the normal boundary of heat dissipation calibration.

[0037] Move the heat dissipation calibration curve vertically downwards until it intersects with the historical anomaly point for the first time to obtain the heat dissipation calibration anomaly boundary;

[0038] Name the area between the normal boundary of heat dissipation calibration and the abnormal boundary of heat dissipation calibration as the fuzzy area, and copy an abnormal boundary of heat dissipation calibration and rename it as the fuzzy auxiliary line.

[0039] The fuzzy guide line is moved vertically from the abnormal boundary of heat dissipation calibration to the normal boundary of heat dissipation calibration. The number of historical abnormal points above the fuzzy guide line and the number of historical normal points below the fuzzy guide line are counted in real time and denoted as QU and QD, respectively.

[0040] The total number of historical normal points and historical abnormal points within the fuzzy area is represented by the symbol F. The result of (QU+QD) / F is named the error probability.

[0041] Continuously move the fuzzy auxiliary line and calculate the error probability. Name the fuzzy auxiliary line with the smallest error probability as the fault judgment standard.

[0042] Furthermore, the heat dissipation status of the photovoltaic-storage-charging system is monitored in real time, and fault prediction of the photovoltaic-storage-charging system is performed based on the influence of heat dissipation calibration and fault judgment criteria, including the following sub-steps:

[0043] Under the premise that no fault is found in the self-test system of the photovoltaic storage and charging system, the system temperature, ambient temperature, air volume, air inlet temperature and air outlet temperature of the photovoltaic storage and charging system are acquired in real time and named as system real-time temperature, ambient real-time temperature, air volume, air inlet real-time temperature and air outlet real-time temperature respectively. The ambient real-time temperature is denoted as TK.

[0044] The real-time pre-heating temperature and heat dissipation efficiency of the photovoltaic energy storage and charging system are calculated based on the real-time temperature of the system, the real-time volume of the exhaust air, the real-time temperature of the air inlet, and the real-time temperature of the exhaust air. These are named the real-time pre-heating temperature and the real-time heat dissipation efficiency, respectively, and the real-time heat dissipation efficiency is denoted as RE.

[0045] Based on the real-time temperature before heat dissipation, the temperature heat dissipation trend function, the real-time heat dissipation efficiency, and the real-time ambient temperature, we can analyze whether there are any fault risks in the photovoltaic energy storage and charging system.

[0046] Furthermore, analyzing the potential fault risks of the photovoltaic energy storage and charging system based on the real-time temperature before heat dissipation, the temperature-heat dissipation trend function, the real-time heat dissipation efficiency, and the real-time ambient temperature includes the following sub-steps:

[0047] Substitute the real-time temperature before heat dissipation into the temperature heat dissipation trend function to obtain the baseline efficiency, denoted as BE. Calculate RE / BE and label the calculation result as H.

[0048] Substitute the coordinates (TK,H) into the heat dissipation calibration analysis chart and name it the heat dissipation real-time calibration point. Determine whether the heat dissipation real-time calibration point is above the fault judgment standard. If yes, output a normal system signal; otherwise, output an abnormal system signal.

[0049] If an abnormal signal is output from the system, a warning message will be sent to the maintenance department.

[0050] The beneficial effects of this invention are as follows: This invention integrates and collects historical operating data of the photovoltaic energy storage and charging system, including historical operating data, historical environmental data, and historical heat dissipation data. Then, it calculates the pre-heat dissipation temperature and heat dissipation efficiency of the photovoltaic energy storage and charging system using the historical operating data and historical heat dissipation data. Furthermore, it analyzes the relationship between the pre-heat dissipation temperature and the heat dissipation efficiency to obtain the heat dissipation impact relationship. The advantage is that the system temperature monitored in the photovoltaic energy storage and charging system is the temperature after heat dissipation; therefore, it is necessary to first restore the system temperature to the pre-heat dissipation temperature and then analyze the heat dissipation efficiency of the heat dissipation system. The heat dissipation system has different heat dissipation efficiencies for different pre-heat dissipation temperatures, thus obtaining the heat dissipation impact relationship. Based on this, it is possible to determine whether the heat dissipation efficiency is abnormal. If the heat dissipation efficiency is abnormal, it indicates an abnormality in either the photovoltaic energy storage and charging system or the heat dissipation system. In such cases, maintenance is required, improving the accuracy and comprehensiveness of fault early warning for the photovoltaic energy storage and charging system.

[0051] This invention calibrates the heat dissipation impact relationship using historical environmental data to obtain a heat dissipation calibration impact relationship. Then, based on this calibration impact relationship and combined with historical operating data, it analyzes the fault judgment criteria for heat dissipation efficiency. Finally, it monitors the heat dissipation status of the photovoltaic-storage-charging system in real time. Simultaneously, it predicts faults in the photovoltaic-storage-charging system based on the heat dissipation calibration impact relationship and the fault judgment criteria. The advantage lies in the fact that heat dissipation efficiency is also affected by ambient temperature. Therefore, by calibrating the heat dissipation impact relationship using historical environmental data, and then analyzing the fault judgment criteria, it can more accurately judge abnormalities in heat dissipation efficiency, improving the accuracy and rationality of fault early warning for the photovoltaic-storage-charging system. Attached Figure Description

[0052] Figure 1 This is a flowchart of the steps of the method of the present invention;

[0053] Figure 2 This is a schematic diagram of the temperature and heat dissipation trend of the present invention;

[0054] Figure 3 This is a schematic diagram of the heat dissipation calibration analysis diagram of the present invention;

[0055] Figure 4 This is a schematic diagram of the historical normal points, historical abnormal points, and heat dissipation calibration curves of the present invention.

[0056] Figure 5 This is a schematic diagram of the normal boundary and abnormal boundary of heat dissipation calibration according to the present invention. Detailed Implementation

[0057] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0058] Example 1, please refer to Figure 1 As shown, this application provides an AI-based early warning method driven by historical fault heat dissipation data of a photovoltaic energy storage and charging system, including the following steps:

[0059] Step S1: Integrate and collect historical operating data of the photovoltaic-storage-charging system. The historical operating data includes historical operating data, historical environmental data, and historical heat dissipation data. The historical operating data includes the historical system temperature in the photovoltaic-storage-charging system, the historical environmental data includes the historical ambient temperature, and the historical heat dissipation data includes the historical air outlet area, air inlet temperature, and air outlet temperature in the photovoltaic-storage-charging system. In addition, the historical operating data is divided into historical normal operation data and historical abnormal operation data according to whether the photovoltaic-storage-charging system is faulty.

[0060] In practice, a historical operating data set includes a system temperature, an ambient temperature, an air outlet area, an air inlet temperature, and an air outlet temperature. If the photovoltaic storage and charging system has a fault, the historical operating data collected at this time is the historical abnormal operating data; otherwise, it is the historical normal operating data.

[0061] Step S2 involves calculating the heat generation and heat dissipation efficiency of the photovoltaic energy storage and charging system, and analyzing the relationship between heat generation and heat dissipation efficiency, termed the heat dissipation influence relationship. Step S2 includes the following sub-steps:

[0062] Step S201: Calculate the pre-heating temperature and heat dissipation efficiency of the photovoltaic energy storage and charging system using historical operating data and historical heat dissipation data.

[0063] Step S201 includes the following sub-steps:

[0064] Step S2011: The temperature and heat dissipation of the photovoltaic energy storage and charging system before heat dissipation can be obtained according to the heat conduction formula Q=m×c×ΔT, where Q represents heat, m represents the mass of the object, c represents the specific heat capacity of the object, and ΔT represents the temperature change.

[0065] Step S2012: Calculate the difference between the air outlet temperature and the air inlet temperature to obtain the temperature change after heat exchange between the heat dissipation system and the photovoltaic energy storage and charging system, denoted as ΔT1.

[0066] Step S2013: Obtain the mass of the air and the specific heat capacity of the air in the area where the photovoltaic storage and charging system is located, denoted as m1 and c1 respectively. Substitute ΔT1, m1 and c1 into ΔT, m and c in the heat conduction formula respectively to obtain the heat dissipation, denoted as QS.

[0067] In practical implementation, for example, in a certain historical operating data point, the system temperature is 62℃, the ambient temperature is 28℃, the air outlet area is 0.01m², the air inlet temperature is 32℃, and the air outlet temperature is 45℃. The air mass and specific heat capacity are obtained because the measured temperature is the air temperature when calculating heat dissipation. The air mass m1 can be obtained by multiplying the air volume by the air density, and the air volume can be obtained by multiplying the average wind speed by the air outlet area. The air density and average wind speed can be directly obtained; the average wind speed is 4m². Given an air density of 1.164 kg / m³, the calculated m1 = 4 m / s × 0.01 m² × 1.164 kg / m³ = 0.0466 kg / s. Rounding the result to four decimal places, this means the vent will discharge 0.0466 kg of air per second. If we consider a 5-second interval for evaluation, analyzing whether the heat dissipation efficiency is abnormal within 5 seconds, then m1 is actually 0.0466 kg / s × 5s = 0.233 kg. Furthermore, the specific heat capacity of the air, c1, is 1 × 10⁻⁶ m / s. 3 J / (kg·℃), and at the same time, ΔT1 is calculated to be 45℃-32℃=13℃. Substituting ΔT1, m1 and c1 into ΔT, m and c in the heat conduction formula respectively, QS is obtained as 3029J.

[0068] Step S2014: Name the component in the photovoltaic storage and charging system that can generate heat as the heating component, and obtain the mass and specific heat capacity of the heating component in the photovoltaic storage and charging system, denoted as m2 and c2 respectively.

[0069] Step S2015: Substitute QS into Q in the heat conduction formula, and substitute m2 and c2 into m and c in the heat conduction formula to solve for the heat dissipation temperature difference of the heat-generating component, denoted as TC.

[0070] Step S2016: Add TC to the system temperature to obtain the temperature of the photovoltaic energy storage and charging system before heat dissipation, denoted as TA. Calculate TC / TA to obtain the heat dissipation efficiency.

[0071] In practice, when calculating the temperature before heat dissipation, the temperature of the outer shell of the heat-generating component is measured. Therefore, it is necessary to obtain the mass and specific heat capacity of the outer shell of the heat-generating component. We obtain m² as 4 kg and c² as 900 J / (kg·℃). Substituting QS into the heat conduction formula (Q), and simultaneously substituting m² and c² into the heat conduction formula (m and c), we get 3029 J = 2 kg × 700 J / (kg·℃) × ΔT, where ΔT is TC. Solving for TC, we obtain TC as 2.2℃. The calculation results are rounded to one decimal place, and finally, the sum of these values ​​gives the temperature TA before heat dissipation as 64.2℃. This means that the temperature of the heat-generating component in the photovoltaic energy storage and charging system was 64.2℃ 5 seconds ago, and the heat dissipation system reduced the temperature of the heat-generating component within 5 seconds. The temperature was 2.2℃, and a judgment cycle was set every 5 seconds. The judgment cycle was set by the monitoring personnel themselves and there were no specific requirements. Because both heat generation and heat dissipation are continuous processes, it is impossible to know the actual temperature of the photovoltaic energy storage and charging system when no heat dissipation system is involved. Since the photovoltaic energy storage and charging system must dissipate heat, otherwise a malfunction will occur, the heat dissipation efficiency can only be periodically evaluated by setting a judgment cycle. The final calculated heat dissipation efficiency was 2.2℃ / 64.2℃ = 0.0343. The calculation result was rounded to four decimal places. Since the heat dissipation efficiency was evaluated periodically, the calculated heat dissipation efficiency value was very small. However, the heat dissipation efficiency value calculated each time was very small and had no impact on the overall analysis.

[0072] Step S202: Analyze the relationship between the temperature before heat dissipation and the heat dissipation efficiency to obtain the heat dissipation influence relationship;

[0073] Step S202 includes the following sub-steps:

[0074] Please see Figure 2 As shown, in step S2021, a two-dimensional coordinate system is established with the temperature before heat dissipation as the X-axis and the heat dissipation efficiency as the Y-axis, named the temperature heat dissipation trend chart, and the heat dissipation efficiency is entered into the temperature heat dissipation trend chart according to the temperature before heat dissipation.

[0075] Step S2022: Perform function fitting on the temperature heat dissipation trend graph, and name the fitted function as the temperature heat dissipation trend function. The temperature heat dissipation trend function is the heat dissipation influence relationship.

[0076] In practice, the temperature and heat dissipation trend graph is constructed as follows: Figure 2 As shown, the temperature heat dissipation trend function obtained through function fitting is Y1=0.00002×X1 2 -0.0016×X1+0.0576, where Y1 is the heat dissipation efficiency and X1 is the temperature before heat dissipation.

[0077] Step S3 involves calibrating the heat dissipation impact relationship using historical environmental data to obtain the heat dissipation calibration impact relationship, and simultaneously analyzing the fault judgment criteria for heat dissipation efficiency based on historical operating data. Step S3 includes the following sub-steps:

[0078] Step S301: The heat dissipation influence relationship is calibrated using historical environmental data to obtain the heat dissipation calibration influence relationship;

[0079] Step S301 includes the following sub-steps:

[0080] Step S3011: Name the coordinate points in the temperature heat dissipation trend graph as temperature heat dissipation trend points, and obtain the ambient temperature in the historical operating data to which the temperature heat dissipation trend points belong, and name it as the influencing temperature.

[0081] Step S3012: Mark the X and Y values ​​of the temperature heat dissipation trend points as PX and PY respectively, substitute PX into the temperature heat dissipation trend function, and solve to obtain the efficiency before calibration, denoted as PCE.

[0082] Step S3013: Calculate PY / PCE, and name the calculation result as the efficiency calibration parameter, denoted as EP;

[0083] Please see Figure 3 As shown, in step S3014, a two-dimensional coordinate system is established with the influencing temperature as the horizontal axis and the efficiency calibration parameter as the vertical axis, named the heat dissipation calibration analysis chart, and the EP is entered into the heat dissipation calibration analysis chart according to the influencing temperature.

[0084] Step S3015: Perform function fitting on the heat dissipation calibration analysis chart, and name the fitted function as the heat dissipation calibration function. The heat dissipation calibration function is the heat dissipation calibration influence relationship.

[0085] In specific implementation, taking the data listed in step S201 as an example, the corresponding temperature heat dissipation trend point is (64.2, 0.0343), where 64.2 is PX, 0.0343 is PY, and the corresponding influence temperature is 28℃. Substituting X1=PX into Y1=0.00002×X1 2 The calculation of -0.0016×X1+0.0576 yields an initial efficiency (PCE) of 0.0373, rounded to four decimal places. This initial efficiency represents the heat dissipation efficiency under ideal conditions (without ambient temperature). PY represents the heat dissipation efficiency calculated under conditions of an ambient temperature of 28℃. Further calculation yields an efficiency calibration parameter (EP) of 0.9196, rounded to four decimal places. The efficiency calibration parameter is calculated for each temperature heat dissipation trend point, resulting in a heat dissipation calibration analysis graph as shown below. Figure 3 As shown, the heat dissipation calibration function obtained through function fitting is Y2=0.0002×X2 2-0.02×X2+1.3703, where Y2 is the efficiency calibration parameter and X2 is the temperature affecting the efficiency.

[0086] Step S302: Based on the influence of heat dissipation calibration and combined with historical operating data, analyze the fault judgment criteria for heat dissipation efficiency.

[0087] Step S302 includes the following sub-steps:

[0088] Please see Figure 4 As shown, in step S3021, the coordinate points obtained by analyzing and constructing historical normal operation data and historical abnormal operation data in the heat dissipation calibration analysis diagram are named historical normal points and historical abnormal points, respectively.

[0089] Step S3022: Construct a curve of the heat dissipation calibration function in the heat dissipation calibration analysis graph, and name it the heat dissipation calibration curve;

[0090] Please see Figure 5 As shown, in step S3023, the heat dissipation calibration curve is moved vertically downward until all historical normal points are above the heat dissipation calibration curve, thus obtaining the normal boundary of heat dissipation calibration.

[0091] Step S3024: Move the heat dissipation calibration curve vertically downwards until it intersects with the historical anomaly point for the first time to obtain the heat dissipation calibration anomaly boundary.

[0092] Step S3025: Name the area between the normal boundary of heat dissipation calibration and the abnormal boundary of heat dissipation calibration as the fuzzy area, copy an abnormal boundary of heat dissipation calibration and rename it as the fuzzy auxiliary line.

[0093] Step S3026: Move the fuzzy guide line vertically from the abnormal boundary of heat dissipation calibration to the normal boundary of heat dissipation calibration, and count in real time the number of historical abnormal points above the fuzzy guide line and the number of historical normal points below the fuzzy guide line, denoted as QU and QD respectively.

[0094] Step S3027: Count the total number of historical normal points and historical abnormal points within the fuzzy area, denoted by the symbol F, calculate (QU+QD) / F, and name the calculation result as the error probability;

[0095] Step S3028: Continuously move the fuzzy auxiliary line and calculate the error probability. Name the fuzzy auxiliary line with the smallest error probability as the fault judgment standard.

[0096] In practice, historical normal points and historical abnormal points are distinguished, and a heat dissipation calibration curve is constructed, resulting in historical normal points, historical abnormal points, and the heat dissipation calibration curve, as shown below. Figure 4 As shown, the normal boundary and abnormal boundary of heat dissipation calibration are obtained by moving the device. Figure 5As shown, there are both historical normal points and historical abnormal points within the fuzzy region. Therefore, a fuzzy auxiliary line is constructed. Whenever the fuzzy auxiliary line moves, historical abnormal points above the fuzzy auxiliary line and historical normal points below the fuzzy auxiliary line represent incorrect judgment results. This is because heat dissipation efficiency is only considered abnormal when it is below the normal level. For example, if QU, QD, and F are statistically obtained as 2, 4, and 30 respectively, the error probability can be calculated as (QU+QD) / F=6 / 30=0.2. The fuzzy auxiliary line with the smallest error probability is selected as the fault judgment standard.

[0097] Step S4 involves real-time monitoring of the heat dissipation status of the photovoltaic-storage-charging system, and fault prediction of the system based on the impact of heat dissipation calibration and fault judgment criteria. Step S4 includes the following sub-steps:

[0098] Step S401: Under the premise that no fault is found in the self-test system of the photovoltaic storage and charging system, the system temperature, ambient temperature, air outlet area, air inlet temperature and air outlet temperature of the photovoltaic storage and charging system are acquired in real time and named as system real-time temperature, ambient real-time temperature, air outlet real-time volume, air inlet real-time temperature and air outlet real-time temperature respectively, and the ambient real-time temperature is denoted as TK.

[0099] Step S402: Calculate the real-time pre-heating temperature and heat dissipation efficiency of the photovoltaic energy storage and charging system based on the real-time system temperature, real-time exhaust volume, real-time inlet temperature and real-time outlet temperature, and name them as real-time pre-heating temperature and real-time heat dissipation efficiency, respectively. The real-time heat dissipation efficiency is denoted as RE.

[0100] In practice, in some cases, the self-test system of the photovoltaic-storage-charging system cannot effectively identify abnormalities in the system. These abnormalities are not considered faults, but they will eventually lead to system failures. Therefore, if the self-test system does not detect any faults, the system's abnormalities are assessed and faults are predicted based on the heat dissipation efficiency. The system's real-time temperature is 65℃, the ambient real-time temperature TK is 32℃, the exhaust volume is 0.01m², the inlet temperature is 34℃, and the outlet temperature is 48℃. According to step S201, the real-time temperature before heat dissipation is calculated to be 67.33℃, and the real-time heat dissipation efficiency RE is 0.0346.

[0101] Step S403: Analyze whether there is a risk of failure in the photovoltaic energy storage and charging system based on the real-time temperature before heat dissipation, the temperature heat dissipation trend function, the real-time heat dissipation efficiency, and the real-time ambient temperature.

[0102] Step S403 includes the following sub-steps:

[0103] Step S4031: Substitute the real-time temperature before heat dissipation into the temperature heat dissipation trend function to obtain the baseline efficiency, denoted as BE. Calculate RE / BE and label the calculation result as H.

[0104] Step S4032: Substitute the coordinates (TK,H) into the heat dissipation calibration analysis diagram and name it the heat dissipation real-time calibration point. Determine whether the heat dissipation real-time calibration point is above the fault judgment standard. If yes, output the system normal signal; otherwise, output the system abnormal signal.

[0105] Step S4033: If an abnormal system signal is output, a warning message is sent to the maintenance terminal;

[0106] In practice, X1=0.0346 is substituted into Y1=0.00002×X1 2 -0.0016×X1+0.0576, we obtain the baseline efficiency BE=0.0575. Further calculation yields H=0.0346 / 0.0575=0.6017. The calculation result is rounded to four decimal places. Substituting the coordinates (32,0.6017) into the heat dissipation calibration analysis chart, we obtain the real-time heat dissipation calibration point. It is found that the real-time heat dissipation calibration point is below the fault judgment standard, indicating that the heat dissipation efficiency is at an abnormal level and the photovoltaic energy storage and charging system is at risk of failure. Therefore, the system abnormality signal is output and a warning message is sent to the maintenance end.

[0107] Example 2: This application provides an electronic device, which may include a processor, a communication interface, a memory, and a communication bus. The processor, communication interface, and memory communicate with each other via the communication bus. The memory stores computer-readable instructions, and the processor can call these instructions. When the processor executes a computer-readable instruction, it performs steps such as those in the AI-based early warning method driven by historical fault heat dissipation data of a photovoltaic energy storage and charging system. This achieves the following functions: integrating and recording historical operating data of the photovoltaic energy storage and charging system; calculating the heat generation and heat dissipation efficiency of the photovoltaic energy storage and charging system, and analyzing the heat dissipation impact relationship; calibrating the heat dissipation impact relationship using historical environmental data to obtain a heat dissipation calibration impact relationship, and analyzing fault judgment criteria for heat dissipation efficiency based on historical operating data; and real-time monitoring of the heat dissipation status of the photovoltaic energy storage and charging system, and predicting faults in the system based on the heat dissipation calibration impact relationship and fault judgment criteria.

[0108] Furthermore, when the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0109] Example 3: This application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the AI-based early warning method driven by historical heat dissipation data of a photovoltaic energy storage and charging system provided by the above methods. This method includes: integrating and collecting historical operating data of the photovoltaic energy storage and charging system; calculating the heat generation and heat dissipation efficiency of the photovoltaic energy storage and charging system, and analyzing the heat dissipation influence relationship; calibrating the heat dissipation influence relationship through historical environmental data to obtain the heat dissipation calibration influence relationship, and analyzing the fault judgment criteria for heat dissipation efficiency based on historical operating data; monitoring the heat dissipation status of the photovoltaic energy storage and charging system in real time, and predicting faults in the photovoltaic energy storage and charging system based on the heat dissipation calibration influence relationship and the fault judgment criteria.

[0110] Example 4: This application also provides a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it performs the steps of the above-mentioned AI-based early warning method driven by historical fault heat dissipation data of an optical storage and charging system, to achieve the following functions: integrating and collecting historical operating data of the optical storage and charging system; calculating the heat generation and heat dissipation efficiency of the optical storage and charging system, and analyzing the heat dissipation influence relationship; calibrating the heat dissipation influence relationship through historical environmental data to obtain the heat dissipation calibration influence relationship, and analyzing the fault judgment criteria for heat dissipation efficiency based on historical operating data; monitoring the heat dissipation status of the optical storage and charging system in real time, and predicting faults in the optical storage and charging system based on the heat dissipation calibration influence relationship and the fault judgment criteria.

[0111] Based on the above description of the embodiments, the embodiments of the present invention can be provided as methods, systems, or computer program products. Based on this understanding, the above technical solutions, in essence or in terms of their contribution to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or certain parts of the embodiments.

[0112] In the embodiments provided in this application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division, and there may be other division methods in actual implementation. Furthermore, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces. The indirect coupling or communication connection between systems, modules, and units may be electrical, mechanical, or other forms.

[0113] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. An AI-based early warning method driven by historical fault heat dissipation data of a photovoltaic-storage-charging system, characterized in that, Includes the following steps: Integrate and collect historical data from the photovoltaic energy storage and charging system, including historical operating data, historical environmental data, and historical heat dissipation data; Calculate the heat generation and heat dissipation efficiency of the photovoltaic energy storage and charging system, and analyze the relationship between the heat generation and heat dissipation efficiency, which is named the heat dissipation influence relationship. The heat dissipation impact relationship is calibrated by using historical environmental data to obtain the heat dissipation calibration impact relationship. At the same time, the fault judgment criteria for heat dissipation efficiency are analyzed based on historical operating data. Real-time monitoring of the heat dissipation status of the photovoltaic energy storage and charging system; and fault prediction of the photovoltaic energy storage and charging system based on the influence of heat dissipation calibration and fault judgment criteria. The calculation of the heat generation and heat dissipation efficiency of the photovoltaic energy storage and charging system, along with the analysis of the relationship between the temperature before heat dissipation and the heat dissipation efficiency, termed the heat dissipation influence relationship, includes the following sub-steps: The temperature before heat dissipation and heat dissipation efficiency of the photovoltaic energy storage and charging system are calculated using historical operating data and historical heat dissipation data. The relationship between the temperature before heat dissipation and the heat dissipation efficiency was analyzed to obtain the influence relationship on heat dissipation; Calculating the pre-heating temperature and heat dissipation efficiency of the photovoltaic-storage-charging system using historical operating data and historical heat dissipation data includes the following sub-steps: The temperature and heat dissipation of the photovoltaic energy storage and charging system before heat dissipation can be obtained by using the heat conduction formula Q=m×c×ΔT, where Q represents heat, m represents the mass of the object, c represents the specific heat capacity of the object, and ΔT represents the temperature change. By calculating the difference between the air outlet temperature and the air inlet temperature, the temperature change after heat exchange between the heat dissipation system and the photovoltaic energy storage and charging system can be obtained, denoted as ΔT1. Obtain the mass of the air and the specific heat capacity of the air in the area where the photovoltaic storage and charging system is located, denoted as m1 and c1 respectively. Substitute ΔT1, m1 and c1 into ΔT, m and c in the heat conduction formula respectively to obtain the heat dissipation, denoted as QS. The components in the photovoltaic-storage-charging system that can generate heat are named heat-generating components. The mass and specific heat capacity of the heat-generating components in the photovoltaic-storage-charging system are obtained and denoted as m2 and c2, respectively. Substitute QS into Q in the heat conduction formula, and simultaneously substitute m2 and c2 into m and c in the heat conduction formula to obtain the heat dissipation temperature difference of the heat-generating component, denoted as TC. Add TC to the system temperature to obtain the temperature of the photovoltaic energy storage and charging system before heat dissipation, denoted as TA. Calculate TC / TA to obtain the heat dissipation efficiency. Analyzing the relationship between temperature before heat dissipation and heat dissipation efficiency reveals the following sub-steps regarding the impact of heat dissipation: Establish a two-dimensional coordinate system with the temperature before heat dissipation as the X-axis and the heat dissipation efficiency as the Y-axis, and name it Temperature Heat Dissipation Trend Chart. Enter the heat dissipation efficiency into the Temperature Heat Dissipation Trend Chart according to the temperature before heat dissipation. A function is fitted to the temperature heat dissipation trend graph, and the fitted function is named the temperature heat dissipation trend function, which is the heat dissipation influence relationship.

2. The early warning method based on historical fault heat dissipation data of a photovoltaic energy storage and charging system according to claim 1, characterized in that, The historical operating data includes the historical system temperature of the photovoltaic energy storage and charging system, the historical environmental data includes the historical ambient temperature, and the historical heat dissipation data includes the historical air outlet volume, air inlet temperature, and air outlet temperature of the photovoltaic energy storage and charging system. In addition, the historical operating data is divided into historical normal operation data and historical abnormal operation data according to whether the photovoltaic energy storage and charging system is faulty.

3. The early warning method based on historical fault heat dissipation data of a photovoltaic energy storage and charging system according to claim 2, characterized in that, The heat dissipation impact relationship is calibrated using historical environmental data to obtain the heat dissipation calibration impact relationship. Simultaneously, the fault judgment criteria for heat dissipation efficiency are analyzed based on historical operating data, including the following sub-steps: The heat dissipation influence relationship is calibrated by using historical environmental data to obtain the heat dissipation calibration influence relationship; Fault judgment criteria based on the impact of heat dissipation calibration and combined with historical operating data analysis of heat dissipation efficiency.

4. The early warning method based on historical fault heat dissipation data of a photovoltaic energy storage and charging system according to claim 3, characterized in that, The heat dissipation impact relationship is calibrated using historical environmental data, and the heat dissipation calibration impact relationship includes the following sub-steps: Name the coordinate points in the temperature heat dissipation trend graph as temperature heat dissipation trend points, and obtain the ambient temperature from the historical operating data to which the temperature heat dissipation trend points belong, and name it the influencing temperature. The values ​​of X and Y at the temperature heat dissipation trend points are labeled as PX and PY, respectively. PX is substituted into the temperature heat dissipation trend function to solve for the efficiency before calibration, denoted as PCE. Calculate PY / PCE, and name the result as the efficiency calibration parameter, denoted as EP; A two-dimensional coordinate system is established with the temperature of influence as the horizontal axis and the efficiency calibration parameter as the vertical axis. This system is named the heat dissipation calibration analysis chart. The EP is entered into the heat dissipation calibration analysis chart according to the temperature of influence. A function is fitted to the heat dissipation calibration analysis graph, and the fitted function is named the heat dissipation calibration function. The heat dissipation calibration function is the heat dissipation calibration influence relationship.

5. The early warning method based on historical fault heat dissipation data of a photovoltaic energy storage and charging system according to claim 4, characterized in that, The fault diagnosis criteria based on the impact of heat dissipation calibration and combined with historical operating data analysis of heat dissipation efficiency include the following sub-steps: The coordinate points obtained by analyzing and constructing historical normal operation data and historical abnormal operation data in the heat dissipation calibration analysis graph are named historical normal points and historical abnormal points, respectively. Construct a curve for the heat dissipation calibration function in the heat dissipation calibration analysis graph, and name it the heat dissipation calibration curve; Move the heat dissipation calibration curve vertically downwards until all historical normal points are above the heat dissipation calibration curve to obtain the normal boundary of heat dissipation calibration. Move the heat dissipation calibration curve vertically downwards until it intersects with the historical anomaly point for the first time to obtain the heat dissipation calibration anomaly boundary; Name the area between the normal boundary of heat dissipation calibration and the abnormal boundary of heat dissipation calibration as the fuzzy area, and copy an abnormal boundary of heat dissipation calibration and rename it as the fuzzy auxiliary line. The fuzzy guide line is moved vertically from the abnormal boundary of heat dissipation calibration to the normal boundary of heat dissipation calibration. The number of historical abnormal points above the fuzzy guide line and the number of historical normal points below the fuzzy guide line are counted in real time and denoted as QU and QD, respectively. The total number of historical normal points and historical abnormal points within the fuzzy area is represented by the symbol F. The result of (QU+QD) / F is named the error probability. Continuously move the fuzzy auxiliary line and calculate the error probability. Name the fuzzy auxiliary line with the smallest error probability as the fault judgment standard.

6. The early warning method based on historical fault heat dissipation data of a photovoltaic energy storage and charging system according to claim 5, characterized in that, Real-time monitoring of the heat dissipation status of the photovoltaic energy storage and charging system, and fault prediction based on the impact of heat dissipation calibration and fault judgment criteria, includes the following sub-steps: Under the premise that no fault is found in the self-test system of the photovoltaic storage and charging system, the system temperature, ambient temperature, air volume, air inlet temperature and air outlet temperature of the photovoltaic storage and charging system are acquired in real time and named as system real-time temperature, ambient real-time temperature, air volume, air inlet real-time temperature and air outlet real-time temperature respectively. The ambient real-time temperature is denoted as TK. The real-time pre-heating temperature and heat dissipation efficiency of the photovoltaic energy storage and charging system are calculated based on the real-time temperature of the system, the real-time volume of the exhaust air, the real-time temperature of the air inlet, and the real-time temperature of the exhaust air. These are named the real-time pre-heating temperature and the real-time heat dissipation efficiency, respectively, and the real-time heat dissipation efficiency is denoted as RE. Based on the real-time temperature before heat dissipation, the temperature heat dissipation trend function, the real-time heat dissipation efficiency, and the real-time ambient temperature, we can analyze whether there are any fault risks in the photovoltaic energy storage and charging system.

7. The early warning method based on historical fault heat dissipation data of a photovoltaic energy storage and charging system according to claim 6, characterized in that, Analyzing the potential fault risks of a photovoltaic energy storage and charging system based on real-time temperature before heat dissipation, temperature-heat dissipation trend function, real-time heat dissipation efficiency, and real-time ambient temperature includes the following sub-steps: Substitute the real-time temperature before heat dissipation into the temperature heat dissipation trend function to obtain the baseline efficiency, denoted as BE. Calculate RE / BE and label the calculation result as H. Substitute the coordinates (TK,H) into the heat dissipation calibration analysis chart and name it the heat dissipation real-time calibration point. Determine whether the heat dissipation real-time calibration point is above the fault judgment standard. If yes, output a normal system signal; otherwise, output an abnormal system signal. If an abnormal signal is output from the system, a warning message will be sent to the maintenance department.

Images