Fault monitoring method and system for household integrated energy storage system

Abstract

The invention relates to a fault monitoring method for a household integrated energy storage system, and the method comprises the steps: constructing a building three-dimensional model, and constructing a historical illumination utilization data set; using a light utilization efficiency analysis model to generate a reference illumination utilization rate as a fault analysis standard; acquiring real-time environment illumination data and photovoltaic equipment light receiving data, calculating an actual illumination utilization rate, and comparing the actual illumination utilization rate with a reference value to judge a photovoltaic equipment fault; acquiring historical photoelectric conversion efficiency data of the inverter, constructing a photoelectric conversion data set, and generating photoelectric conversion efficiency in different states; historical output data and electricity demand data of the inverter are obtained, an electricity-output data set is constructed, demand output factors are generated, and expected output data are calculated; acquiring actual power consumption demand data, calculating expected output data, and comparing the expected output data with the actual output data of the inverter to judge the fault of the inverter; and generating a fault monitoring report containing fault type preliminary judgment and maintenance suggestions based on the fault judgment result. The scheme has the effect of improving the fault monitoring accuracy of the household integrated energy storage system.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent monitoring of energy storage systems, and in particular to a fault monitoring method and system for a household integrated energy storage system. Background Art

[0002] With the popularization of the environmental protection concept, household integrated energy storage systems are gradually becoming a hot topic. More and more household users are starting to consider how to use energy efficiently, economically, and environmentally. The household integrated energy storage system realizes the self-sufficiency and efficient management of household energy by integrating photovoltaic modules, energy storage batteries, energy storage inverters, grid connection and metering equipment, etc.

[0003] Existing household integrated energy storage systems mainly rely on real-time monitoring and analysis of equipment operation data for fault monitoring. These systems usually collect data through sensors installed on the equipment, such as voltage, current, temperature, etc., and then use this data to detect the operation status of the equipment and judge whether there is a fault according to the set data threshold.

[0004] In view of the above-mentioned existing technologies, there are some problems in the fault monitoring of household integrated energy storage systems: existing systems often rely on a single data source during fault monitoring, lack the fusion analysis of multi-dimensional data, and are prone to misjudgment or untimely discovery of faults, resulting in a decrease in the accuracy of fault judgment. Summary of the Invention

[0005] In order to improve the accuracy of fault monitoring of household integrated energy storage systems, the present application provides a fault monitoring method and system for household integrated energy storage systems.

[0006] In a first aspect, the above-mentioned object of the present invention of the present application is achieved through the following technical solutions:

[0007] A fault monitoring method for a household integrated energy storage system, the method comprising the steps of:

[0008] Obtain building data and distribution coordinate information of photovoltaic devices, and construct a corresponding three-dimensional building model, wherein the corresponding distribution positions of the photovoltaic devices are set in the three-dimensional building model;

[0009] Obtain historical environmental data and historical working data of photovoltaic devices, and correlate the environmental data and working data based on a preset common time axis to construct a historical light utilization data set;

[0010] Analyze the light utilization data set by a preset light utilization efficiency analysis model to generate a reference light utilization rate corresponding to different environmental data, and the reference light utilization rate is used as a fault analysis standard for photovoltaic devices;

[0011] Obtain real-time ambient light data and light-receiving data of the photovoltaic device to calculate the actual light utilization rate, and compare it with the reference light utilization rate to determine whether there is a fault in the photovoltaic device;

[0012] Obtain the historical photovoltaic conversion efficiency data of the inverter, and correlate the photovoltaic conversion efficiency data with the light utilization rate based on the common time axis to construct a photovoltaic conversion dataset;

[0013] The preset photovoltaic conversion analysis model analyzes the photovoltaic conversion dataset based on the machine learning algorithm to generate the corresponding photovoltaic conversion efficiency when the photovoltaic device is in different states;

[0014] Obtain historical inverter output data and power consumption demand data, and correlate the output data and power consumption demand data based on the common time axis to construct a power consumption-output dataset;

[0015] The preset power consumption-output analysis model analyzes the power consumption-output dataset based on the machine learning algorithm to generate a demand output factor, and the demand output factor is used to calculate the expected output data corresponding to the power consumption demand;

[0016] Obtain the actual power consumption demand data, calculate the expected output data according to the demand output factor, and the expected output data is used as a reference value for fault judgment;

[0017] Obtain the actual output data of the inverter and compare it with the expected output data to determine whether there is a fault in the inverter;

[0018] Generate a fault monitoring report corresponding to the household integrated energy storage system based on the fault judgment results of the photovoltaic device and the inverter, where the monitoring report includes a preliminary judgment of the fault type and corresponding repair suggestions.

[0019] By adopting the above technical solutions, by constructing a three-dimensional building model and combining the distribution coordinate information of photovoltaic devices, the device layout can be more intuitively displayed, providing more accurate basic data for fault monitoring; by obtaining historical environmental data and the working data of photovoltaic devices and correlating them based on a common time axis, a historical light utilization dataset is constructed, providing more comprehensive data support for light utilization efficiency analysis; by generating a reference light utilization rate through a preset light utilization efficiency analysis model, a more accurate standard is provided for photovoltaic device fault analysis; by calculating the actual light utilization rate in real time by obtaining environmental light data and the light-receiving data of photovoltaic devices and comparing it with the reference value, photovoltaic device faults can be discovered more timely; by obtaining the historical photovoltaic-electric conversion efficiency data of the inverter and correlating it with the light utilization rate based on a common time axis, a photovoltaic-electric conversion dataset is constructed, providing more comprehensive data support for photovoltaic-electric conversion efficiency analysis; by generating the photovoltaic-electric conversion efficiency under different states through a preset photovoltaic-electric conversion analysis model, a more accurate reference is provided for inverter fault judgment; by obtaining historical inverter output data and electricity demand data and correlating them based on a common time axis, a power consumption-output dataset is constructed, providing a more comprehensive data basis for power consumption-output analysis; by generating a demand output factor through a preset power consumption-output analysis model, a more accurate basis is provided for calculating the expected output data; by calculating the expected output data by obtaining the actual electricity demand data and comparing it with the actual output data of the inverter, inverter faults can be discovered more timely; finally, a fault monitoring report is generated based on the fault judgment result, providing more detailed fault information and maintenance suggestions, improving the fault handling efficiency. The present invention can more comprehensively and accurately monitor the faults of the household integrated energy storage system, thereby improving the fault monitoring accuracy of the household integrated energy storage system, enhancing the reliability and stability of the system, and reducing the maintenance cost.

[0020] In a preferred example of the present application, it can be further configured as follows: in the step of analyzing the light utilization dataset by a preset light utilization efficiency analysis model to generate the reference light utilization rate corresponding to different environmental data, the following steps are included:

[0021] Obtain historical environmental light data and the light-receiving data of photovoltaic devices, and correlate the environmental light data and the light-receiving data based on a preset common time axis to calculate the corresponding light utilization rate;

[0022] Obtain the historical state data of photovoltaic devices, and correlate the light utilization rate and the state data based on the common time axis to construct a state-light utilization rate dataset, where the state data includes solar panel angle data, solar panel temperature data, and solar panel working area data;

[0023] The pre-set utilization analysis model analyzes the state-illumination utilization dataset based on a machine self-learning algorithm to generate a photovoltaic device state factor, and the device state factor is used to correct the illumination utilization when the photovoltaic device is in different states.

[0024] By adopting the above technical solution, by associating the illumination utilization with the historical state data of the photovoltaic device, a comprehensive dataset including the device state and the illumination utilization can be constructed, which helps to analyze the change of the illumination utilization under different device states, provides data support for subsequent utilization correction, improves the accuracy of fault monitoring, and by generating the photovoltaic device state factor, the illumination utilization under different states can be accurately corrected, improving the accuracy of the light utilization efficiency analysis, which helps to more accurately judge the performance change of the photovoltaic device, timely discover potential faults, and improve the reliability and stability of the system.

[0025] In a preferred example of the present application, it can be further configured as follows: after the step of the pre-set utilization analysis model analyzing the state-illumination utilization dataset based on a machine self-learning algorithm to generate a photovoltaic device state factor, the following steps are included:

[0026] Obtain real-time environmental illumination data, and calculate based on the illumination utilization corresponding to the real-time environmental illumination data to generate an initial predicted illumination utilization;

[0027] Obtain real-time photovoltaic device state data to match the corresponding photovoltaic device state factor, correct the initial predicted illumination utilization based on the photovoltaic device state factor to generate a corrected predicted illumination utilization, and use the corrected predicted illumination utilization as the reference illumination utilization.

[0028] By adopting the above technical solution, the initial predicted illumination utilization can be accurately corrected to generate a reference illumination utilization that more conforms to the actual operating state, which helps to improve the accuracy of fault monitoring, timely discover the performance change of the photovoltaic device, optimize the system operation, and improve the energy utilization efficiency.

[0029] In a preferred example of the present application, it can be further configured as follows: after the step of obtaining historical inverter output data and power consumption demand data, and associating the output data and the power consumption demand data based on the common time axis to construct a power consumption-output dataset, the following steps are included:

[0030] The pre-set power consumption demand model analyzes the power consumption-output dataset based on a machine self-learning algorithm to generate a power consumption demand portrait;

[0031] Generate an electricity demand prediction trend based on the electricity demand profile, where the electricity demand prediction trend is used to predict the electricity demand corresponding to different times within a future period;

[0032] Generate predicted electricity demand data corresponding to the electricity demand prediction trend based on the demand output factor.

[0033] By adopting the above technical solution, by generating predicted electricity demand data, users can more accurately understand the electricity demand at different times in the future, take measures in advance, such as adjusting the operating time of electrical equipment, optimizing the electricity consumption plan, and reducing electricity costs. At the same time, this also helps power companies better manage the grid load and improve the stability and reliability of the grid.

[0034] In a preferred example of the present application, it can be further configured as follows: in the step of analyzing the light utilization data set by a preset light utilization efficiency analysis model to generate a reference light utilization rate corresponding to different environmental data, the light utilization efficiency analysis model is provided with a reference light utilization rate calculation formula to calculate the reference light utilization rate, and the reference light utilization rate calculation formula is as follows:

[0035]

[0036] Where η ref (t) is the reference light utilization rate corresponding to different temperatures, η base is the historical maximum value under clear sky conditions at different temperatures, ΔT(t) is the difference between the real-time temperature and the standard temperature, C(t) is the cloud cover index, α is the temperature correction coefficient, β is the cloud cover correction coefficient, and α and β are generated by a machine learning algorithm.

[0037] By adopting the above technical solution, a dynamic compensation mechanism for temperature and cloud cover is introduced to solve the problem that traditional static thresholds cannot adapt to weather changes, improve the credibility of the reference light utilization rate, and thus reduce the misjudgment rate.

[0038] In a preferred example of the present application, it can be further configured as follows: in the step of analyzing the state-light utilization rate data set by a preset utilization rate analysis model based on a machine learning algorithm to generate a photovoltaic device state factor, where the device state factor is used to correct the light utilization rate when the photovoltaic device is in different states, a photovoltaic device state factor calculation formula is provided:

[0039]

[0040] Where θ is the actual installation inclination angle of the photovoltaic device, θ opt is the optimal inclination angle corresponding to different states, k is the temperature attenuation coefficient, T is the temperature of the solar panel, T optis the optimal operating temperature of the solar panel, η is the area sensitivity factor, and A eff is the effective light-receiving area, and A nom is the nominal area.

[0041] By adopting the above technical solution, cos(θ - θ opt ) is used to calculate the angle deviation, thus replacing the traditional fixed angle coefficient, making the calculation of the angle coefficient more flexible and accurate. By calculating the temperature influence, it is more in line with the actual situation than the existing linear model, thereby improving the reliability of the state factor of the photovoltaic device and improving the accuracy of correction.

[0042] In a second aspect, the above object of the present application is achieved by the following technical solution:

[0043] A fault monitoring device for a household integrated energy storage system, the device includes: a building three-dimensional model construction unit, configured to obtain building data and distribution coordinate information of photovoltaic devices, and construct a corresponding building three-dimensional model, wherein the corresponding distribution positions of the photovoltaic devices are set in the building three-dimensional model;

[0044] A historical light utilization data set construction unit, configured to obtain historical environmental data and historical working data of photovoltaic devices, and correlate the environmental data and working data based on a preset common time axis to construct a historical light utilization data set;

[0045] A reference light utilization rate generation unit, configured to preset a light utilization efficiency analysis model to analyze the light utilization data set to generate reference light utilization rates corresponding to different environmental data, and the reference light utilization rates are used as fault analysis criteria for photovoltaic devices;

[0046] An actual light utilization rate calculation unit, configured to obtain real-time environmental light data and light-receiving data of photovoltaic devices to calculate the actual light utilization rate, and compare it with the reference light utilization rate to determine whether there is a fault in the photovoltaic devices;

[0047] A photoelectric conversion data set construction unit, configured to obtain historical photoelectric conversion efficiency data of an inverter, and correlate the photoelectric conversion efficiency data with the light utilization rate based on the common time axis to construct a photoelectric conversion data set;

[0048] A photoelectric conversion efficiency generation unit, configured to preset a photoelectric conversion analysis model to analyze the photoelectric conversion data set based on a machine learning algorithm to generate photoelectric conversion efficiencies corresponding to different states of photovoltaic devices;

[0049] An electricity-output dataset construction unit for obtaining historical inverter output data and electricity demand data, and correlating the output data and electricity demand data based on the common time axis to construct an electricity-output dataset;

[0050] A demand-output factor generation unit for presetting an electricity-output analysis model to analyze the electricity-output dataset based on a machine self-learning algorithm to generate a demand-output factor, where the demand-output factor is used to calculate the expected output data corresponding to the electricity demand;

[0051] An expected output data calculation unit for obtaining actual electricity demand data and calculating the expected output data according to the demand-output factor, where the expected output data is used as a fault judgment reference value;

[0052] An actual output data acquisition unit for obtaining the actual output data of the inverter and comparing it with the expected output data to determine whether the inverter has a fault;

[0053] A fault monitoring report generation unit for generating a fault monitoring report corresponding to the household integrated energy storage system based on the fault judgment results of the photovoltaic device and the inverter, where the monitoring report includes a preliminary judgment of the fault type and corresponding repair suggestions.

[0054] In a third aspect, the above object of the present application is achieved by the following technical solutions:

[0055] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned fault monitoring method for a household integrated energy storage system are implemented.

[0056] In a fourth aspect, the above object of the present application is achieved by the following technical solutions:

[0057] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned fault monitoring method for a household integrated energy storage system are implemented.

[0058] In summary, the present application includes at least one of the following beneficial technical effects:

[0059] 1. By constructing a 3D building model and combining it with the distribution coordinate information of photovoltaic devices, the device layout can be more intuitively displayed, providing more accurate basic data for fault monitoring. By obtaining historical environmental data and photovoltaic device operation data and correlating them based on a common time axis, a historical light utilization dataset is constructed, providing more comprehensive data support for light utilization efficiency analysis. By generating a reference light utilization rate through a pre-set light utilization efficiency analysis model, a more precise standard is provided for photovoltaic device fault analysis. By calculating the actual light utilization rate in real-time by obtaining environmental light data and light-receiving data of photovoltaic devices and comparing it with the reference value, photovoltaic device faults can be detected more timely. By obtaining historical photovoltaic-to-electric conversion efficiency data of inverters and correlating it with the light utilization rate based on a common time axis, a photovoltaic-to-electric conversion dataset is constructed, providing more comprehensive data support for photovoltaic-to-electric conversion efficiency analysis. By generating the photovoltaic-to-electric conversion efficiency under different states through a pre-set photovoltaic-to-electric conversion analysis model, a more precise reference is provided for inverter fault judgment. By obtaining historical inverter output data and electricity demand data and correlating them based on a common time axis, a power consumption-output dataset is constructed, providing a more comprehensive data basis for power consumption-output analysis. By generating a demand output factor through a pre-set power consumption-output analysis model, a more accurate basis is provided for calculating the expected output data. By calculating the expected output data based on the actual electricity demand data and comparing it with the actual output data of the inverter, inverter faults can be detected more timely. Finally, a fault monitoring report is generated based on the fault judgment result, providing more detailed fault information and repair suggestions, improving the fault handling efficiency. The present invention can more comprehensively and accurately monitor the faults of a household integrated energy storage system, improve the reliability and stability of the system, and reduce the maintenance cost;

[0060] 2. By setting a reference light utilization rate calculation formula, the influence of temperature and cloud cover on the light utilization rate of photovoltaic devices can be comprehensively considered, so as to more accurately calculate the reference light utilization rate under different environmental conditions. Specifically, the temperature correction term in the formula considers the difference between the real-time temperature and the standard temperature, and adjusts the light utilization rate through the temperature correction coefficient α, making the calculation result closer to the device performance under the actual temperature. At the same time, the cloud cover correction term corrects the light utilization rate according to the cloud cover index C(t), and reflects the weakening effect of clouds on the light intensity through the cloud cover correction coefficient β. These two correction coefficients α and β are generated by a machine self-learning algorithm and can be automatically optimized according to historical data, further improving the accuracy and adaptability of the calculation. Through this calculation method that comprehensively considers various environmental factors, this solution can provide a more precise reference standard for the fault monitoring of photovoltaic devices, detect potential faults in a timely manner, and improve the reliability and stability of the system;

[0061] 3. By setting the calculation formula for the photovoltaic device status factor, factors such as the actual installation inclination angle, temperature, and effective light-receiving area of the photovoltaic device can be comprehensively considered to accurately correct the light utilization rate under different states. Specifically, the cosine term cos(θ - θ opt ) in the formula takes into account the deviation between the actual installation inclination angle and the optimal inclination angle. Through the temperature attenuation term , the influence of temperature on the light utilization rate is reflected, while the area-sensitive term takes into account the difference between the effective light-receiving area and the nominal area. By comprehensively considering these factors, this solution can more accurately correct the light utilization rate, provide a more accurate reference standard for the fault monitoring of photovoltaic devices, thereby timely detecting potential faults and improving the reliability and stability of the system. Description of the Drawings

[0062] Figure 1 is a flowchart of a fault monitoring method for a household integrated energy storage system according to an embodiment of the present application;

[0063] Figure 2 is a schematic block diagram of a fault monitoring system for a household integrated energy storage system according to an embodiment of the present application;

[0064] Figure 3 is a schematic diagram of an electronic device according to an embodiment of the present application.

[0065] Reference Numerals in the Drawings:

[0066] 1. Building three-dimensional model construction unit; 2. Historical light utilization data set construction unit; 3. Reference light utilization rate generation unit; 4. Actual light utilization rate calculation unit; 5. Photoelectric conversion data set construction unit; 6. Photoelectric conversion efficiency generation unit; 7. Power consumption-output data set construction unit; 8. Demand output factor generation unit; 9. Expected output data calculation unit; 10. Actual output data acquisition unit; 11. Fault monitoring report generation unit. Detailed Embodiments

[0067] The present application will be further described in detail below with reference to the accompanying drawings.

[0068] In one embodiment, as Figure 1 shown, the present application discloses a fault monitoring method for a household integrated energy storage system, which specifically includes the following steps:

[0069] S1: Obtain building data and distribution coordinate information of photovoltaic devices, and construct a corresponding building three-dimensional model, where the corresponding distribution positions of photovoltaic devices are set in the building three-dimensional model;

[0070] Specifically, obtain the three-dimensional coordinate data of the building and the distribution coordinate information of the photovoltaic devices, construct a three-dimensional model of the building that includes the distribution positions of the photovoltaic panels, and use the three-dimensional model of the building as a basis for subsequent light data and environmental impact data. Constructing the three-dimensional model of the building helps to visually display the distribution of the photovoltaic devices, provides basic data for subsequent light utilization analysis, and improves the accuracy of fault monitoring.

[0071] S2: Obtain historical environmental data and historical working data of the photovoltaic devices, and correlate the environmental data and the working data based on a preset common time axis to construct a historical light utilization dataset.

[0072] Specifically, assume that within the past week, environmental data such as daily light intensity, temperature, and humidity, as well as historical working data such as the output power, voltage, and current of the photovoltaic devices, are correlated through the common time axis to construct a historical light utilization dataset. By correlating historical environmental data and working data, the performance of the photovoltaic devices under different environmental conditions can be analyzed, providing a reference standard for fault analysis.

[0073] S3: Analyze the light utilization dataset using a preset light utilization efficiency analysis model to generate reference light utilization rates corresponding to different environmental data, and the reference light utilization rates are used as fault analysis criteria for the photovoltaic devices.

[0074] Generating reference light utilization rates as fault analysis criteria helps to determine whether the performance of the photovoltaic devices is normal under different environmental conditions and improves the accuracy of fault monitoring.

[0075] S4: Obtain real-time environmental light data and light-receiving data of the photovoltaic devices to calculate the actual light utilization rate, and compare it with the reference light utilization rate to determine whether there are faults in the photovoltaic devices.

[0076] Specifically, obtain real-time environmental light data and light-receiving data of the photovoltaic devices, and calculate the actual light utilization rate. Assume that the current environmental light intensity is 1000W / m 2 , the light-receiving area of the photovoltaic device is 40 square meters, and the actual output power is 30kW. The calculated actual light utilization rate is 75%. Comparing with the reference light utilization rate of 80%, a difference is found, which may indicate that there are faults in the photovoltaic devices. By calculating the actual light utilization rate in real time and comparing it with the reference value, faults in the photovoltaic devices can be detected in a timely manner, improving the real-time performance and accuracy of fault monitoring.

[0077] S5: Obtain historical photovoltaic conversion efficiency data of the inverter, and correlate the photovoltaic conversion efficiency data with the light utilization rate based on the common time axis to construct a photovoltaic conversion dataset.

[0078] Specifically, obtain the photovoltaic conversion efficiency data of the inverter in the past week (or other cycles), correlate it with the light utilization rate data through a common time axis, and construct a photovoltaic conversion data set. By correlating the photovoltaic conversion efficiency data and the light utilization rate data, the performance of the inverter under different light conditions can be analyzed, providing more comprehensive data support for fault analysis.

[0079] S6: The pre-set photovoltaic conversion analysis model analyzes the photovoltaic conversion data set based on a machine learning algorithm to generate the corresponding photovoltaic conversion efficiency when the photovoltaic device is in different states;

[0080] Specifically, the photovoltaic conversion analysis model analyzes the photovoltaic conversion data set to generate the photovoltaic conversion efficiency of the photovoltaic device in different states. For example, when the light utilization rate is 80%, the photovoltaic conversion efficiency is 90%; when the light utilization rate is 60%, the photovoltaic conversion efficiency is 85%. By generating the photovoltaic conversion efficiency in different states, the performance of the inverter can be evaluated more accurately, providing a more precise reference standard for fault judgment.

[0081] S7: Obtain historical inverter output data and power consumption demand data, and correlate the output data and power consumption demand data based on the common time axis to construct a power consumption-output data set;

[0082] S8: The pre-set power consumption-output analysis model analyzes the power consumption-output data set based on a machine learning algorithm to generate a demand output factor, and the demand output factor is used to calculate the expected output data corresponding to the power consumption demand;

[0083] Specifically, the power consumption-output analysis model analyzes the power consumption-output data set to generate a demand output factor. For example, during peak power consumption demand periods, the demand output factor is 1.2, indicating that the inverter needs to provide more output power than usual.

[0084] By generating the demand output factor, the expected output data corresponding to the power consumption demand can be calculated more accurately, providing a more precise reference standard for fault judgment.

[0085] S9: Obtain the actual power consumption demand data and calculate the expected output data according to the demand output factor, and the expected output data is used as a reference value for fault judgment;

[0086] Specifically, assume that the current actual power consumption demand is 20 kW and the demand output factor is 1.2. The calculated expected output data is 24 kW. By calculating the expected output data, a reference value can be provided for fault judgment to help determine whether the inverter is working properly.

[0087] S10: Obtain the actual output data of the inverter and compare it with the expected output data to determine whether there is a fault in the inverter;

[0088] Specifically, by comparing the actual output data and the expected output data, faults in the inverter can be detected in a timely manner, improving the accuracy and timeliness of fault monitoring.

[0089] S11: Generate a fault monitoring report corresponding to the household integrated energy storage system based on the fault judgment results of the photovoltaic equipment and the inverter;

[0090] The monitoring report includes a preliminary judgment of the fault type and corresponding repair suggestions. Specifically, based on the fault judgment results of the photovoltaic equipment and the inverter, a fault monitoring report is generated. The report includes a preliminary judgment of the fault type, such as a decrease in the efficiency of the photovoltaic panel and insufficient output of the inverter, as well as corresponding repair suggestions, such as cleaning the photovoltaic panel and checking the connections of the inverter. Generating the fault monitoring report helps the operation and maintenance personnel quickly understand the system fault situation, take corresponding repair measures, and improve the reliability and operating efficiency of the system.

[0091] Furthermore, assuming that through the fault judgment in steps S4 and S10, it is found that the actual light utilization rate of the photovoltaic equipment is lower than the reference value, indicating that there may be a problem with the efficiency of the photovoltaic panel; at the same time, the actual output data of the inverter is lower than the expected output data, indicating that there may be a problem with insufficient output of the inverter. Based on these judgment results, a fault monitoring report is generated. The content of the monitoring report is as follows:

[0092] Fault judgment result of photovoltaic equipment:

[0093] Fault type: Decrease in the efficiency of the photovoltaic panel

[0094] Possible reasons: Dirt on the surface of the photovoltaic panel, damage or aging of some photovoltaic panels

[0095] Repair suggestions: Clean the surface of the photovoltaic panel, check and replace damaged or aging photovoltaic panels

[0096] Fault judgment result of the inverter:

[0097] Fault type: Insufficient output of the inverter

[0098] Possible reasons: Faults in the internal components of the inverter, loose or damaged connection lines

[0099] Repair suggestions: Check the internal components of the inverter, tighten or replace the connection lines

[0100] In this application, the beneficial effects of the fault monitoring report are as follows:

[0101] Comprehensiveness: The fault monitoring report synthesizes the fault judgment results of photovoltaic devices and inverters, provides comprehensive fault information, and helps operation and maintenance personnel quickly understand the overall operating status of the system.

[0102] Accuracy: The report is based on the comparison of actual data and pre-set reference values to ensure the accuracy of fault judgment and reduce the possibility of misjudgment and missed judgment.

[0103] Guidance: The report provides specific maintenance suggestions to guide operation and maintenance personnel to take effective maintenance measures, improving maintenance efficiency and system reliability.

[0104] Timeliness: Through real-time monitoring and analysis, the fault monitoring report can be generated in a timely manner, ensuring that operation and maintenance personnel can respond quickly, reducing system fault time, and improving system availability and stability.

[0105] User-friendliness: The content of the report is clear and easy to understand. Even non-professionals can quickly grasp the fault situation and maintenance suggestions, improving user satisfaction.

[0106] In summary, for steps S1 - S11, compared with the prior art, this solution can more intuitively display the equipment layout by constructing a building three-dimensional model and combining the distribution coordinate information of photovoltaic devices, providing more accurate basic data for fault monitoring; by obtaining historical environmental data and photovoltaic device operation data and correlating them based on a common time axis, constructing a historical light utilization dataset, providing more comprehensive data support for light utilization efficiency analysis; by generating a reference light utilization rate through a pre-set light utilization efficiency analysis model, providing a more accurate standard for photovoltaic device fault analysis; by calculating the actual light utilization rate in real time by obtaining environmental light data and photovoltaic device light-receiving data and comparing it with the reference value, being able to detect photovoltaic device faults more timely; by obtaining historical inverter photoelectric conversion efficiency data and correlating it with the light utilization rate based on a common time axis, constructing a photoelectric conversion dataset, providing more comprehensive data support for photoelectric conversion efficiency analysis; by generating the photoelectric conversion efficiency in different states through a pre-set photoelectric conversion analysis model, providing a more accurate reference for inverter fault judgment; by obtaining historical inverter output data and electricity demand data and correlating them based on a common time axis, constructing a power consumption-output dataset, providing a more comprehensive data basis for power consumption-output analysis; by generating a demand output factor through a pre-set power consumption-output analysis model, providing a more accurate basis for calculating the expected output data; by obtaining the actual electricity demand data to calculate the expected output data and comparing it with the actual output data of the inverter, being able to detect inverter faults more timely; and finally generating a fault monitoring report based on the fault judgment results, providing more detailed fault information and maintenance suggestions, improving fault handling efficiency. This invention can more comprehensively and accurately monitor the faults of the household integrated energy storage system, improve system reliability and stability, and reduce maintenance costs.

[0107] In step S3: the pre-set light utilization efficiency analysis model analyzes the light utilization data set to generate the reference light utilization rate corresponding to different environmental data, and the steps are as follows:

[0108] S31: Obtain the historical environmental light data and the light-receiving data of the photovoltaic device, and associate the environmental light data and the light-receiving data based on the pre-set common time axis to calculate the corresponding light utilization rate;

[0109] By associating the environmental light data and the light-receiving data of the photovoltaic device, the light utilization rate at different time points can be accurately calculated, providing basic data for subsequent light utilization efficiency analysis. This helps to timely detect the performance changes of the photovoltaic device under different light conditions and improve the accuracy of fault monitoring.

[0110] S32: Obtain the historical state data of the photovoltaic device, and associate the light utilization rate and the state data based on the common time axis to construct a state-light utilization rate data set, where the state data includes the solar panel angle data, the solar panel temperature data, and the solar panel working area data;

[0111] S33: The pre-set utilization rate analysis model analyzes the state-light utilization rate data set based on the machine learning algorithm to generate a photovoltaic device state factor, and the device state factor is used to correct the light utilization rate when the photovoltaic device is in different states.

[0112] In summary, by associating the light utilization rate with the historical state data of the photovoltaic device, a comprehensive data set including the device state and the light utilization rate can be constructed, which helps to analyze the change of the light utilization rate under different device states, provides data support for subsequent utilization rate correction, improves the accuracy of fault monitoring, and can accurately correct the light utilization rate in different states by generating the photovoltaic device state factor, improving the accuracy of light utilization efficiency analysis. This helps to more accurately judge the performance changes of the photovoltaic device, timely detect potential faults, and improve the reliability and stability of the system.

[0113] In step S3, the light utilization efficiency analysis model is set with a reference light utilization rate calculation formula to calculate the reference light utilization rate, and the reference light utilization rate calculation formula is as follows:

[0114]

[0115] where η ref (t) is the reference light utilization rate corresponding to different temperatures, η baseis the historical maximum value under cloudless conditions at different temperatures, ΔT(t) is the difference between the real-time temperature and the standard temperature, C(t) is the cloud cover index, α is the temperature correction coefficient, β is the cloud cover correction coefficient, and α and β are generated by the machine learning algorithm.

[0116] Specifically, by setting the reference light utilization rate calculation formula, the influence of temperature and cloud cover on the light utilization rate of photovoltaic equipment can be comprehensively considered, so as to calculate the reference light utilization rate under different environmental conditions more accurately. Specifically, the temperature correction term in the formula considers the difference between the real-time temperature and the standard temperature, and adjusts the light utilization rate through the temperature correction coefficient α, making the calculation result closer to the equipment performance under the actual temperature. At the same time, the cloud cover correction term corrects the light utilization rate according to the cloud cover index C(t), and reflects the weakening effect of clouds on the light intensity through the cloud cover correction coefficient β. These two correction coefficients α and β are generated by the machine learning algorithm and can be automatically optimized according to historical data, further improving the accuracy and adaptability of the calculation. Through this calculation method that comprehensively considers various environmental factors, this solution can provide a more accurate reference standard for the fault monitoring of photovoltaic equipment, timely detect potential faults, and improve the reliability and stability of the system.

[0117] For step S33, in the utilization rate analysis model preset based on the machine learning algorithm to analyze the state-light utilization rate data set to generate a photovoltaic equipment state factor, and the equipment state factor is used to correct the light utilization rate when the photovoltaic equipment is in different states. In this step, a photovoltaic equipment state factor calculation formula is set:

[0118]

[0119] where θ is the actual installation inclination angle of the photovoltaic equipment, θ opt is the optimal inclination angle corresponding to different states, k is the temperature attenuation coefficient, T is the temperature of the solar panel, T opt is the best working temperature of the solar panel, η is the area sensitivity factor, A eff is the effective light-receiving area, A nom is the nominal area.

[0120] The beneficial effect of this solution is that by setting the photovoltaic equipment state factor calculation formula, factors such as the actual installation inclination angle, temperature, and effective light-receiving area of the photovoltaic equipment can be comprehensively considered to accurately correct the light utilization rate in different states. Specifically, the cosine term cos(θ - θ opt ) in the formula considers the deviation between the actual installation inclination angle and the optimal inclination angle, and reflects the influence of temperature on the light utilization rate through the temperature attenuation term , while the area sensitivity term The difference between the effective light-receiving area and the nominal area is considered. Through the comprehensive consideration of these factors, this solution can more accurately correct the light utilization rate, provide a more accurate reference standard for the fault monitoring of photovoltaic devices, thereby timely detecting potential faults and improving the reliability and stability of the system.

[0121] After step S33: The pre-set utilization rate analysis model analyzes the state-light utilization rate data set based on the machine learning algorithm to generate the photovoltaic device state factor, the following steps are included:

[0122] S331: Obtain real-time ambient light data, and calculate based on the light utilization rate corresponding to the real-time ambient light data to generate an initial predicted light utilization rate;

[0123] Specifically, for example: Assume that at noon on a sunny day, the real-time ambient light data shows that the light intensity is 1000W / m 2 . According to historical data and the pre-set model, the light utilization rate at this time is usually 80%. Therefore, the system calculates that the initial predicted light utilization rate is 80%. By obtaining real-time ambient light data and calculating the initial predicted light utilization rate, the system can quickly respond to environmental changes and provide basic data for subsequent correction of the light utilization rate. This helps to improve the real-time and accuracy of the prediction, ensuring that the system can timely adjust the operating state and optimize energy utilization.

[0124] S332: Obtain real-time photovoltaic device state data to match the corresponding photovoltaic device state factor, correct the initial predicted light utilization rate based on the photovoltaic device state factor to generate a corrected predicted light utilization rate, and use the corrected predicted light utilization rate as the reference light utilization rate.

[0125] Specifically, assume that at noon on the same sunny day, the real-time photovoltaic device state data shows that the actual installation inclination angle of the photovoltaic panel is 30 degrees, the temperature is 35°C, the effective light-receiving area is 45 square meters, and the nominal area is 50 square meters. According to the pre-set photovoltaic device state factor calculation formula, and substituting the example data of this application: Assume that the optimal inclination angle is 40 degrees, the best working temperature is 25°C, the temperature decay coefficient k is 0.1, and the area sensitivity factor η is 0.2. Substitute the data into the calculation to get γ state = 0.349. Therefore, the corrected predicted light utilization rate is: Corrected predicted light utilization rate = 80% × 0.349 ≈ 27.9%. This corrected predicted light utilization rate will be used as the reference light utilization rate.

[0126] Moreover, in the example, the difference between 27.9% and 80% is relatively large, which is greater than the generally set threshold. However, in the example of this application, it exactly conforms to the actual environmental weather conditions. Therefore, it can be seen that by obtaining real-time photovoltaic device status data and matching the corresponding photovoltaic device status factors, the system can accurately correct the initial predicted light utilization rate and generate a reference light utilization rate that more conforms to the actual operating status. This helps to improve the accuracy of fault monitoring, timely detect performance changes of photovoltaic devices, optimize system operation, and improve energy utilization efficiency.

[0127] After step S7: Obtain historical inverter output data and power consumption demand data, and correlate the output data and power consumption demand data based on the common time axis to construct a power consumption-output dataset, the following steps are included:

[0128] S71: A preset power consumption demand model analyzes the power consumption-output dataset based on a machine self-learning algorithm to generate a power consumption demand portrait;

[0129] Specifically, assume that the power consumption-output dataset of a certain household shows that the power consumption peaks on weekdays occur from 7 am to 9 am and from 7 pm to 10 pm, while the power consumption peaks on weekends are more dispersed. The power consumption demand model analyzes these data through a machine self-learning algorithm to generate a power consumption demand portrait, showing the power consumption habits and patterns of this household.

[0130] By generating a power consumption demand portrait, the user's power consumption habits and patterns can be intuitively understood, providing basic data for subsequent power consumption demand prediction. This helps to improve the accuracy and pertinence of prediction, and optimize energy distribution and utilization efficiency.

[0131] S72: Generate a power consumption demand prediction trend based on the power consumption demand portrait, and the power consumption demand prediction trend is used to predict the power consumption demand corresponding to different times in the future period;

[0132] Specifically, based on the above power consumption demand portrait, the system predicts the power consumption demand trend for the next week. For example, it is predicted that the power consumption peaks on weekdays will still occur from 7 am to 9 am and from 7 pm to 10 pm, while the power consumption demand on weekends is relatively stable. This prediction trend can help users plan their power consumption in advance and avoid excessive power consumption during peak hours.

[0133] By generating a power consumption demand prediction trend, users can understand future power consumption demand changes in advance, reasonably arrange power consumption plans, avoid excessive power consumption during peak hours, and reduce power consumption costs. At the same time, this also helps power companies optimize grid load distribution and improve grid operation efficiency.

[0134] S73: Generate predicted power consumption demand data corresponding to the power consumption demand prediction trend based on the demand output factor;

[0135] Specifically, assume that the demand output factor is 1.2, which means that during peak electricity consumption periods, the user's electricity demand will increase by 20% compared to normal. Based on the predicted trend of electricity demand, the system generates specific predicted electricity demand data. For example, the predicted electricity demand from 7 am to 9 am on a certain working day is 10 kW. Considering the demand output factor, the predicted electricity demand data is 12 kW.

[0136] By generating predicted electricity demand data, users can more accurately understand their electricity demand at different times in the future and take measures in advance, such as adjusting the operating time of electrical equipment, optimizing the electricity usage plan, and reducing electricity costs. At the same time, this also helps power companies better manage the grid load and improve the stability and reliability of the grid.

[0137] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0138] In one embodiment, a fault monitoring device for a household integrated energy storage system is provided. The fault monitoring device for the household integrated energy storage system corresponds one-to-one with the fault monitoring method for the household integrated energy storage system in the above embodiment. As Figure 2 shown, the fault monitoring device for the household integrated energy storage system includes a building three-dimensional model construction unit 1, which is used to obtain building data and the distribution coordinate information of photovoltaic devices and construct a corresponding building three-dimensional model, where the corresponding distribution positions of the photovoltaic devices are set in the building three-dimensional model;

[0139] A historical light utilization dataset construction unit 2, which is used to obtain historical environmental data and the historical working data of photovoltaic devices, and correlate the environmental data and working data based on a preset common time axis to construct a historical light utilization dataset;

[0140] A reference light utilization rate generation unit 3, which is used to preset a light utilization efficiency analysis model to analyze the light utilization dataset to generate reference light utilization rates corresponding to different environmental data, and the reference light utilization rates are used as fault analysis criteria for photovoltaic devices;

[0141] An actual light utilization rate calculation unit 4, which is used to obtain real-time environmental light data and the light receiving data of photovoltaic devices to calculate the actual light utilization rate, and compare it with the reference light utilization rate to determine whether there is a fault in the photovoltaic device;

[0142] The photovoltaic conversion data set construction unit 5 is configured to obtain the historical photovoltaic conversion efficiency data of the inverter, and associate the photovoltaic conversion efficiency data with the light utilization rate based on the common time axis to construct a photovoltaic conversion data set;

[0143] The photovoltaic conversion efficiency generation unit 6 is configured to preset a photovoltaic conversion analysis model to analyze the photovoltaic conversion data set based on a machine self-learning algorithm to generate the corresponding photovoltaic conversion efficiency when the photovoltaic device is in different states;

[0144] The power consumption-output data set construction unit 7 is configured to obtain the historical inverter output data and power consumption demand data, and associate the output data and the power consumption demand data based on the common time axis to construct a power consumption-output data set;

[0145] The demand output factor generation unit 8 is configured to preset a power consumption-output analysis model to analyze the power consumption-output data set based on a machine self-learning algorithm to generate a demand output factor, and the demand output factor is used to calculate the expected output data corresponding to the power consumption demand;

[0146] The expected output data calculation unit 9 is configured to obtain the actual power consumption demand data and calculate the expected output data according to the demand output factor, and the expected output data is used as a fault judgment reference value;

[0147] The actual output data acquisition unit 10 is configured to obtain the actual output data of the inverter and compare it with the expected output data to determine whether there is a fault in the inverter;

[0148] The fault monitoring report generation unit 11 is configured to generate a fault monitoring report corresponding to the household integrated energy storage system based on the fault judgment results of the photovoltaic device and the inverter, where the monitoring report includes a preliminary judgment of the fault type and corresponding repair suggestions.

[0149] For the specific limitations of the fault monitoring device for the household integrated energy storage system, reference can be made to the limitations of the fault monitoring method for the household integrated energy storage system in the above text, which will not be elaborated here. Each module in the above-mentioned fault monitoring device for the household integrated energy storage system can be implemented in whole or in part by software, hardware, and their combinations. The above-mentioned modules can be embedded in the processor of the electronic device in hardware form or independent of it, or stored in the memory of the electronic device in software form, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0150] In one embodiment, an electronic device is provided. The electronic device can be a server, and its internal structure diagram can be as Figure 3As shown. The electronic device includes a processor, a memory, a network interface, and a database connected via a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store the database. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, it implements a fault monitoring method for a household integrated energy storage system.

[0151] In one embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented:

[0152] Obtain building data and distribution coordinate information of photovoltaic devices, and construct a corresponding three-dimensional building model, where the corresponding distribution positions of the photovoltaic devices are set in the three-dimensional building model;

[0153] Obtain historical environmental data and historical working data of photovoltaic devices, and correlate the environmental data and working data based on a preset common time axis to construct a historical light utilization data set;

[0154] Analyze the light utilization data set by a preset light utilization efficiency analysis model to generate reference light utilization rates corresponding to different environmental data, and the reference light utilization rates are used as fault analysis criteria for photovoltaic devices;

[0155] Obtain real-time environmental light data and light reception data of photovoltaic devices to calculate the actual light utilization rate, and compare it with the reference light utilization rate to determine whether there is a fault in the photovoltaic devices;

[0156] Obtain historical photovoltaic conversion efficiency data of the inverter, and correlate the photovoltaic conversion efficiency data with the light utilization rate based on the common time axis to construct a photovoltaic conversion data set;

[0157] Analyze the photovoltaic conversion data set by a preset photovoltaic conversion analysis model based on a machine learning algorithm to generate photovoltaic conversion efficiencies corresponding to different states of photovoltaic devices;

[0158] Obtain historical inverter output data and electricity demand data, and correlate the output data and electricity demand data based on the common time axis to construct a power consumption-output data set;

[0159] The pre-set power consumption output analysis model analyzes the power consumption-output data set based on a machine self-learning algorithm to generate a demand output factor, which is used to calculate the expected output data corresponding to the power consumption demand;

[0160] Obtain the actual power consumption demand data, calculate the expected output data according to the demand output factor, and the expected output data is used as a fault judgment reference value;

[0161] Obtain the actual output data of the inverter and compare it with the expected output data to determine whether there is a fault in the inverter;

[0162] Generate a fault monitoring report corresponding to the household integrated energy storage system based on the fault judgment results of the photovoltaic device and the inverter, where the monitoring report includes a preliminary judgment of the fault type and corresponding repair suggestions.

[0163] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0164] Obtain the building data and the distribution coordinate information of the photovoltaic device, and construct a corresponding three-dimensional building model, where the corresponding distribution positions of the photovoltaic device are set in the three-dimensional building model;

[0165] Obtain the historical environmental data and the historical working data of the photovoltaic device, and correlate the environmental data and the working data based on a pre-set common time axis to construct a historical light utilization data set;

[0166] The pre-set light utilization efficiency analysis model analyzes the light utilization data set to generate a reference light utilization rate corresponding to different environmental data, and the reference light utilization rate is used as a fault analysis standard for the photovoltaic device;

[0167] Obtain the real-time environmental light data and the light-receiving data of the photovoltaic device to calculate the actual light utilization rate, and compare it with the reference light utilization rate to determine whether there is a fault in the photovoltaic device;

[0168] Obtain the historical photovoltaic conversion efficiency data of the inverter, and correlate the photovoltaic conversion efficiency data with the light utilization rate based on the common time axis to construct a photovoltaic conversion data set;

[0169] The pre-set photovoltaic conversion analysis model analyzes the photovoltaic conversion data set based on a machine self-learning algorithm to generate the photovoltaic conversion efficiency corresponding to different states of the photovoltaic device;

[0170] Obtain historical inverter output data and power consumption demand data, and correlate the output data and power consumption demand data based on the common time axis to construct a power consumption-output data set;

[0171] The pre-set power consumption-output analysis model analyzes the power consumption-output data set based on the machine learning algorithm to generate a demand-output factor, and the demand-output factor is used to calculate the expected output data corresponding to the power consumption demand;

[0172] Obtain the actual power consumption demand data and calculate the expected output data according to the demand-output factor, and the expected output data is used as a fault judgment reference value;

[0173] Obtain the actual output data of the inverter and compare it with the expected output data to determine whether there is a fault in the inverter;

[0174] Generate a fault monitoring report for the household integrated energy storage system based on the fault judgment results of the photovoltaic device and the inverter, where the monitoring report includes a preliminary judgment of the fault type and corresponding repair suggestions.

[0175] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to the memory, storage, database or other media used in the various embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0176] Those skilled in the art can clearly understand that, for the convenience and conciseness of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be assigned to different functional units and modules according to needs, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0177] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements 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 the present application, and should all be included in the protection scope of the present application.

Claims

1. A fault monitoring method for a household integrated energy storage system, characterized in that: The method comprises the steps of: acquiring building data and distribution coordinate information of photovoltaic equipment, and constructing a corresponding three-dimensional building model, wherein the corresponding distribution positions of the photovoltaic equipment are set in the three-dimensional building model; Acquire historical environmental data and historical operating data of photovoltaic equipment, and associate the environmental data and the operating data based on a preset common time axis to construct a historical light utilization data set; The preset light utilization efficiency analysis model analyzes the light utilization data set to generate reference light utilization rates corresponding to different environmental data, and the reference light utilization rates are used as fault analysis standards for photovoltaic equipment; Acquire real-time ambient light data and light receiving data of the photovoltaic device to calculate the actual light utilization rate, and compare it with the reference light utilization rate to determine whether the photovoltaic device has a fault; Acquire historical photoelectric conversion efficiency data of the inverter, and associate the photoelectric conversion efficiency data with the light utilization rate based on the common time axis to construct a photoelectric conversion data set; The preset photoelectric conversion analysis model analyzes the photoelectric conversion data set based on a machine self-learning algorithm to generate the photoelectric conversion efficiency corresponding to different states of the photovoltaic device; Acquiring historical inverter output data and power demand data, and associating the output data with the power demand data based on the common time axis to construct a power-output data set; The preset power consumption output analysis model analyzes the power consumption-output data set based on a machine self-learning algorithm to generate a demand output factor, and the demand output factor is used to calculate the expected output data corresponding to the power consumption demand; Acquire actual power demand data and calculate expected output data according to the demand output factor, wherein the expected output data is used as a reference value for fault judgment; Obtaining actual output data of the inverter and comparing it with the expected output data to determine whether the inverter is faulty; A fault monitoring report corresponding to the household integrated energy storage system is generated based on the fault judgment results of the photovoltaic equipment and the inverter, wherein the monitoring report includes a preliminary judgment of the fault type and corresponding maintenance suggestions.

2. A fault monitoring method for a household integrated energy storage system according to claim 1, characterized in that: The step of analyzing the light utilization data set by a preset light utilization efficiency analysis model to generate reference light utilization rates corresponding to different environmental data includes the following steps: Acquire historical ambient light data and light receiving data of the photovoltaic device, and associate the ambient light data with the light receiving data based on a preset common time axis to calculate a corresponding light utilization rate; Acquire historical status data of the photovoltaic device, and associate the light utilization rate with the status data based on the common time axis to construct a status-light utilization rate data set, wherein the status data includes solar panel angle data, solar panel temperature data, and solar panel working area data; The preset utilization analysis model analyzes the state-light utilization data set based on a machine self-learning algorithm to generate a photovoltaic device state factor, and the device state factor is used to correct the light utilization when the photovoltaic device is in different states.

3. A fault monitoring method for a household integrated energy storage system according to claim 2, characterized in that: After the step of analyzing the state-light utilization rate data set by the preset utilization rate analysis model based on the machine self-learning algorithm to generate the photovoltaic device state factor, the following steps are included: Acquire real-time ambient light data, and calculate the light utilization rate corresponding to the real-time ambient light data to generate an initial predicted light utilization rate; Real-time photovoltaic device status data is acquired to match the corresponding photovoltaic device status factor, an initial predicted light utilization rate is corrected based on the photovoltaic device status factor to generate a corrected predicted light utilization rate, and the corrected predicted light utilization rate is used as the reference light utilization rate.

4. A fault monitoring method for a household integrated energy storage system according to claim 1, characterized in that: After the step of acquiring historical inverter output data and power demand data, and associating the output data and the power demand data based on the common time axis to construct a power consumption-output data set, the following steps are included: The preset power demand model analyzes the power consumption-output data set based on a machine self-learning algorithm to generate a power demand profile; Generate a power demand forecast trend based on the power demand portrait, where the power demand forecast trend is used to predict the power demand corresponding to different times in a future cycle; The predicted electricity demand data corresponding to the electricity demand prediction trend is generated based on the demand output factor.

5. A fault monitoring method for a household integrated energy storage system according to claim 2, characterized in that: In the step of analyzing the light utilization data set by the preset light utilization efficiency analysis model to generate reference light utilization rates corresponding to different environmental data, the light utilization efficiency analysis model is provided with a reference light utilization rate calculation formula to calculate the reference light utilization rate, and the reference light utilization rate calculation formula is as follows: where η ref (t) is the reference light utilization rate corresponding to different temperatures, η base is the historical maximum value under clear and cloudless conditions corresponding to different temperatures, ΔT(t) is the difference between the real-time temperature and the standard temperature, C(t) is the cloud cover index, α is the temperature correction coefficient, β is the cloud cover correction coefficient, and α and β are generated by the machine self-learning algorithm.

6. A fault monitoring method for a household integrated energy storage system according to claim 3, characterized in that: In the step where the preset utilization analysis model analyzes the state-light utilization data set based on a machine self-learning algorithm to generate a photovoltaic device state factor, the device state factor is used to correct the light utilization rate of the photovoltaic device in different states. A photovoltaic device state factor calculation formula is provided: Where θ is the actual installation inclination angle of the photovoltaic equipment, θ opt is the optimal tilt angle corresponding to different states, k is the temperature attenuation coefficient, T is the solar panel temperature, T opt is the optimal operating temperature of the solar panel, η is the area sensitivity factor, A eff is the effective light receiving area, A nom is the nominal area.

7. A fault monitoring device for a household integrated energy storage system, applied to a fault monitoring method for a household integrated energy storage system according to any one of claims 1 to 6, characterized in that: The device comprises: a building three-dimensional model construction unit (1), which is used to obtain building data and distribution coordinate information of photovoltaic equipment, and to construct a corresponding building three-dimensional model, wherein the corresponding distribution positions of the photovoltaic equipment are set in the building three-dimensional model; A historical light utilization data set construction unit (2) is used to obtain historical environmental data and historical operating data of the photovoltaic device, and associate the environmental data and the operating data based on a preset common time axis to construct a historical light utilization data set; A reference light utilization rate generating unit (3) is used to pre-set a light utilization efficiency analysis model to analyze the light utilization data set to generate reference light utilization rates corresponding to different environmental data, and the reference light utilization rates are used as a fault analysis standard for photovoltaic equipment; An actual light utilization rate calculation unit (4) is used to obtain real-time ambient light data and light receiving data of the photovoltaic device to calculate the actual light utilization rate, and compare it with the reference light utilization rate to determine whether the photovoltaic device has a fault; A photoelectric conversion data set construction unit (5) is used to obtain historical photoelectric conversion efficiency data of the inverter, and associate the photoelectric conversion efficiency data with the light utilization rate based on the common time axis to construct a photoelectric conversion data set; A photoelectric conversion efficiency generating unit (6), which is pre-set with a photoelectric conversion analysis model to analyze the photoelectric conversion data set based on a machine self-learning algorithm to generate photoelectric conversion efficiencies corresponding to different states of the photovoltaic device; A power consumption-output data set construction unit (7), used for acquiring historical inverter output data and power consumption demand data, and associating the output data and the power consumption demand data based on the common time axis to construct a power consumption-output data set; A demand output factor generating unit (8) is used to pre-set an electricity output analysis model to analyze the electricity consumption-output data set based on a machine self-learning algorithm to generate a demand output factor, wherein the demand output factor is used to calculate expected output data corresponding to the electricity demand; An expected output data calculation unit (9), used for obtaining actual power demand data and calculating expected output data according to the demand output factor, wherein the expected output data is used as a reference value for fault judgment; An actual output data acquisition unit (10) is used to acquire actual output data of the inverter and compare it with the expected output data to determine whether the inverter has a fault; A fault monitoring report generating unit (11) is used to generate a fault monitoring report corresponding to the household integrated energy storage system based on the fault judgment results of the photovoltaic device and the inverter.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of a fault monitoring method for a household integrated energy storage system as described in any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of a fault monitoring method for a household integrated energy storage system as described in any one of claims 1 to 6 are implemented.

Images