Solar lighting management system with automatic fault detection function

Abstract

The invention belongs to the technical field of lighting management, and discloses a solar lighting management system with an automatic fault detection function. A solar data set is collected, the solar data set comprises photovoltaic panel data, solar radiation data and conversion data, an environment data set is collected, and the environment data set comprises temperature data, humidity data and dust-containing data; analyzing the environment data set to obtain a fault reference value, processing the environment data set to obtain a fault prediction value, and classifying the fault prediction value to obtain a fault classification result; obtaining a fault decision result; and transmitting the fault reference value, the prediction conversion report and the fault decision result to a display end for display, analyzing the solar data set to obtain an energy efficiency value, and transmitting the energy efficiency value to the display end for display. The method has the remarkable advantages of being good in automatic fault detection effect, high in fault generation prediction capacity and direct in equipment generating capacity display effect.

Description

Technical Field

[0001] The present invention relates to the technical field of lighting management, and more particularly to a solar lighting management system with an automatic fault detection function. Background Art

[0002] Solar lighting uses solar energy as energy, realizes photoelectric conversion through solar cells, accumulates and stores electricity in batteries during the day, and powers electric light sources through controllers at night to achieve the required functional lighting. With the rapid economic development of my country in recent years, solar energy as a new type of clean energy has gradually been widely used in commercial and household fields. Solar lighting, as a field with a wide range of applications at this stage, has gradually emerged with pain points such as the need for manual response to know when lighting equipment fails. Therefore, how to make solar lighting equipment have the function of automatic fault detection and better use of the collected parameters has become a major problem that the current solar lighting industry urgently needs to improve.

[0003] The patent with application publication number CN113531464A discloses a control system of solar street lamps. By setting an environmental detection unit, including a fog concentration detection module, a light intensity detection module, an infrared detection module and a rain detection module, they are respectively used to monitor the fog concentration, light intensity, pedestrian and vehicle traffic signals on the road and the rainfall in the rainy day environment in real time; a dimming module is set between the LED street lamp and the management terminal, and the dimming module is used to automatically adjust the brightness of the LED street lamp through the management terminal control, and automatically turn on the LED street lamp when the light intensity is dark, and automatically reduce the brightness of the LED street lamp when the light is bright. The infrared detection module can automatically detect whether there are vehicles and pedestrians passing by when used at night. When there are no pedestrians and vehicles passing by for a long time, the brightness of the LED street lamp is automatically reduced to save energy. By setting a rain detection module, the brightness of the LED street lamp can be appropriately adjusted to ensure lighting conditions on rainy days. Therefore, by setting the environmental detection unit, the adaptability of the LED street lamp to environmental working conditions can be improved.

[0004] However, although the above-mentioned control system of solar street lights has increased the functionality of the system to a certain extent by adding a variety of functional identification modules, under the current circumstances, solar lighting equipment is extremely susceptible to environmental influences and thus malfunctions. This requires the solar lighting management system to have an automatic fault detection function to achieve real-time feedback on faults and minimize the time difference from the occurrence of a fault to the repair result. In addition, since some solar lighting equipment is installed in special scenarios, this requires long-term and stable operation of the solar lighting equipment. This requires the solar lighting management system to have a fault prediction function to avoid inconvenience or economic losses to users due to lighting equipment failures. Since solar radiation is the main energy supply condition for solar lighting equipment, it is necessary to consider the direct impact of future solar radiation on power generation.

[0005] In view of this, the present invention proposes a solar lighting management system with automatic fault detection function to solve the above problem. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solutions: comprising: A solar energy data collection module is used to collect solar energy data sets, which include photovoltaic panel data, solar radiation data and conversion data; An environmental data collection module is used to collect environmental data sets, including temperature data, humidity data, and dust content data; Data preprocessing module, used to standardize solar data set and environmental data set; Further, data standardization methods include: The solar data set and the environmental data set are Z-score standardized, that is, the mean and standard deviation of the solar data set and the environmental data set are used to standardize the data; The specific conversion function is: ,in is the mean of all sample data, is the standard deviation of all sample data; A fault reference value generation module is used to analyze the environmental data set to obtain a fault reference value, process the environmental data set to obtain a fault prediction value, and classify the fault prediction value to obtain a fault classification result; Further, the environmental data set is analyzed in the following ways: The preset temperature threshold interval (Q1, Q2) is: when the temperature data is less than Q1, the value is 2; when the temperature data is greater than Q1 and less than Q2, the value is 1; when the temperature data is greater than Q2, the value is 2; The preset humidity threshold Q3, when the humidity data is less than Q3, the value is 1, when the temperature data is greater than Q3, the value is 2; The dust content threshold Q4 is preset. When the dust content data is less than Q4, the value is 1, and when the dust content data is greater than Q4, the value is 2; By substituting into the calculation formula: Get the fault reference value, where is the temperature data, is the humidity data, For dusty data, , and are the corresponding weight factors respectively; A fault reference threshold interval (W1, W2) is preset. When the fault reference value is less than W1, operation improvement information is output to the user interaction module through the communication unit. When the fault reference value is greater than W1 and less than W2, operation alarm information is output to the user interaction module through the communication unit. When the fault reference value is greater than W2, operation danger information is output to the user interaction module through the communication unit. The operation completeness information includes a description of the normal operation status of the current equipment, the operation alarm information includes a description of the abnormal operation status of the current equipment, and the operation danger information includes a description of the dangerous operation status of the current equipment; Furthermore, the steps of processing the environmental data set include: E1: Based on the historical environmental data set, by substituting into the calculation formula: Get the initial prediction value, where is the comprehensive slope value, is the unit of time; E2: Collect L groups of historical feature vectors as sample sets; E2: Collect L groups of historical feature vectors as sample sets; E3: Establish an environmental classification model based on the sample set, obtain the historical feature vector in the sample set, preset the normal data cluster L1, warning data cluster L2 and alarm data cluster L3, and select three data points as the original cluster centers in the training set through artificial setting, representing the normal data cluster L1, warning data cluster L2 and alarm data cluster L3 respectively; E4: By substituting into the calculation formula: Get the distance between data items, calculate the distance between the data items in the training set and the normal data cluster L1, warning data cluster L2 and alarm data cluster L3, and assign the data items to the data cluster with the closest distance, and get three new data clusters as the initial cluster centers, where and is the coordinate value of the data point, and For two data points, The value of the sub-data item, is the number of sub-data items; E5: Calculate the means of the three new data clusters in the initial cluster center respectively, and use them as the new original cluster center for recalculation; E6: Repeat E4 and E5 until the preset number of iterations is reached to obtain an environmental prediction classification model; E7: Input the feature vector into the environmental prediction classification model and output the fault prediction value; Furthermore, the methods for classifying the fault prediction values ​​include: A fault prediction threshold interval (R1, R2) is preset. When the fault prediction value is less than R1, a normal signal is generated. When the fault prediction value is greater than R1 and less than R2, an early warning signal is generated. When the fault prediction value is greater than R2, a warning signal is generated. The normal signal includes a group of fields representing that the operation status of the solar lighting equipment is normal, the early warning signal includes a group of fields representing that the operation status of the solar lighting equipment is abnormal, and the warning signal includes a group of fields representing that the operation status of the solar lighting equipment is seriously abnormal; Pack normal signals, early warning signals and warning signals to obtain fault classification results; A database module, used for storing solar energy data sets, environmental data sets, fault reference values, and historical fault reference values; Further, the solar energy dataset is processed in the following ways: By substituting into the calculation formula: Get the power generation reference value, where is the photovoltaic panel data, is the solar radiation data, To transform data; Obtain a set of future solar radiation data, marked as Y1, Y2, Y3...Ym in fixed time units; Get a set of historical conversion data, marked as U1, U2, U3...Um in fixed time units; Calculate the conversion efficiency loss value. The specific calculation process is: ,in is the initial conversion efficiency value, that is The efficiency value is 0, For time, is the decay rate constant; Calculate the predicted conversion value. The specific calculation process is: ,in ; When the predicted conversion value is obtained, a predicted conversion report is generated; Intelligent decision-making module, used to process the fault classification results and obtain fault decision results; Furthermore, the method for processing the fault classification result includes: When the fault classification result is a normal signal, a normal SMS is displayed to the display terminal through the user interaction module; when the fault classification result is an early warning signal, an early warning SMS is displayed to the display terminal through the user interaction module; when the fault classification result is a warning signal, a warning SMS is displayed to the display terminal through the user interaction module; Normal text messages include information about the normal operation of solar lighting equipment and reminding users to check the equipment regularly; The warning message includes an explanation of the abnormal operating status of the solar lighting equipment, reminding the user to check the solar lighting equipment, observe whether the indicator light is always on, whether the lighting equipment is working properly, and whether there is dust accumulation on the solar photovoltaic panels; The warning message includes a description of the serious abnormality of the operation status of the solar lighting equipment, reminding the user to immediately turn off the lighting equipment, stay away from the equipment operation area and contact relevant maintenance personnel; Pack normal SMS, warning SMS and warning SMS to get fault decision results; A user interaction module is used to transmit the fault reference value, prediction conversion report and fault decision result to the display end for display, analyze the solar energy data set, obtain the energy efficiency value, and transmit it to the display end for display; Further, the solar data set is analyzed in the following ways: By reading the value of the smart meter, the actual power generation value is obtained ; By substituting into the calculation formula: Get the energy efficiency value; Further, S1: collecting solar energy data set, the solar energy data set includes photovoltaic panel data, solar radiation data and conversion data; S2: Collect environmental data sets, which include temperature data, humidity data, and dust data; S3: Data standardization of solar data set and environmental data set; S4: Analyze the environmental data set to obtain a fault reference value, process the environmental data set to obtain a fault prediction value, and classify the fault prediction value to obtain a fault classification result; S5: storing the solar energy data set, the environmental data set, the fault reference value, and the historical fault reference value; S6: Process the solar energy data set to obtain a prediction conversion report; S7: Process the fault classification result to obtain a fault decision result; S8: The fault reference value, the prediction conversion report and the fault decision result are transmitted to the display end for display, the solar energy data set is analyzed to obtain the energy efficiency value, and the energy efficiency value is transmitted to the display end for display.

[0007] The technical effects and advantages of a solar lighting management system with automatic fault detection function of the present invention are as follows: The present invention analyzes the environmental data set through a fault reference value generation module, and the obtained fault reference value can enable the lighting equipment to perform real-time detection when in use, avoiding the inconvenience caused by no one noticing when the lighting equipment stops running. By processing the environmental data set, the fault prediction value obtained can effectively predict the faults of the lighting equipment caused by environmental factors, and then take corresponding treatment measures in advance, greatly reducing the time cost of maintenance, and to a certain extent avoiding the loss caused by the lighting equipment stopping running. By processing the fault classification results, the fault decision results obtained can assist the user to complete the corresponding measures for different states of the lighting equipment. By processing the solar data set, the predicted conversion report obtained can accurately predict the final impact on the power generation of the solar lighting equipment due to the difference in solar radiation and the reduction in conversion efficiency in the future, thereby greatly improving the overall coordination ability of the solar lighting management system for energy storage and use allocation. By analyzing the solar data set, the energy efficiency value obtained can intuitively show the difference between the theoretical power generation and the actual power generation of the solar photovoltaic panel, so that the user can directly observe the power generation life of the solar lighting equipment. In general, the present invention has the significant advantages of good automatic fault detection effect, strong ability to predict fault generation and direct effect of displaying the power generation of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A schematic diagram of a solar lighting management system with automatic fault detection function according to the present invention; Figure 2 The figure is a schematic diagram of a solar lighting management method with automatic fault detection function according to the present invention. DETAILED DESCRIPTION

[0009] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0010] Example 1

[0011] See also Figure 1 As shown, the solar lighting management system with automatic fault detection function described in this embodiment includes: A solar energy data collection module is used to collect solar energy data sets, which include photovoltaic panel data, solar radiation data and conversion data; It should be explained that by connecting to the equipment data platform, the total area of ​​solar photovoltaic panels and solar energy conversion efficiency are collected to obtain photovoltaic panel data and conversion data; the solar radiation in the specified area is collected through the solar radiation measuring instrument to obtain solar radiation data; An environmental data collection module is used to collect environmental data sets, including temperature data, humidity data and dust content data; It should be explained that by installing temperature and humidity sensors, the temperature and humidity in the specified area are collected respectively to obtain temperature data and humidity data; by using a dust concentration detector, the dust content of the air in the specified area is collected to obtain dust content data; Data preprocessing module, used to standardize solar data set and environmental data set; Further, data standardization methods include: The solar data set and the environmental data set are Z-score standardized, that is, the mean and standard deviation of the solar data set and the environmental data set are used to standardize the data; The specific conversion function is: ,in is the mean of all sample data, is the standard deviation of all sample data; It should be explained that the sample data are the solar energy dataset and the environmental dataset; A fault reference value generation module is used to analyze the environmental data set to obtain a fault reference value, process the environmental data set to obtain a fault prediction value, and classify the fault prediction value to obtain a fault classification result; Further, the methods for analyzing the environmental data set include: The preset temperature threshold interval (Q1, Q2) is: when the temperature data is less than Q1, the value is 2; when the temperature data is greater than Q1 and less than Q2, the value is 1; when the temperature data is greater than Q2, the value is 2; The preset humidity threshold Q3, when the humidity data is less than Q3, the value is 1, when the temperature data is greater than Q3, the value is 2; The dust content threshold Q4 is preset. When the dust content data is less than Q4, the value is 1, and when the dust content data is greater than Q4, the value is 2; It should be explained that the thresholds in the temperature threshold interval, humidity threshold, and dust content threshold are obtained by analyzing the historical environmental data set corresponding to the period when the historical equipment failed; By substituting into the calculation formula: Get the fault reference value, where is the temperature data, is the humidity data, For dusty data, , and are the corresponding weight factors respectively; A fault reference threshold interval (W1, W2) is preset. When the fault reference value is less than W1, operation improvement information is output to the user interaction module through the communication unit. When the fault reference value is greater than W1 and less than W2, operation alarm information is output to the user interaction module through the communication unit. When the fault reference value is greater than W2, operation danger information is output to the user interaction module through the communication unit. It should be explained that the thresholds in the fault reference threshold interval are obtained through manual input; The operation completeness information includes a description of the normal operation status of the current equipment, the operation alarm information includes a description of the abnormal operation status of the current equipment, and the operation danger information includes a description of the dangerous operation status of the current equipment; Furthermore, the steps of processing the environmental data set include: E1: Based on the historical environmental data set, by substituting into the calculation formula: Get the initial prediction value, where is the comprehensive slope value, is the unit of time; It should be explained that the comprehensive slope value is calculated by the formula: Get, where is the temperature change slope, is the humidity change slope, is the humidity change slope, , and are the corresponding weight factors respectively, and the historical environmental datasets are M groups of historical environmental datasets collected within a specified time range in a specified area; E2: Collect L groups of historical feature vectors as sample sets; It needs to be explained that the feature vector is the initial prediction value; E3: Establish an environmental classification model based on the sample set, obtain the historical feature vector in the sample set, preset the normal data cluster L1, warning data cluster L2 and alarm data cluster L3, and select three data points as the original cluster centers in the training set through artificial setting, representing the normal data cluster L1, warning data cluster L2 and alarm data cluster L3 respectively; E4: By substituting into the calculation formula: Get the distance between data items, calculate the distance between the data items in the training set and the normal data cluster L1, warning data cluster L2 and alarm data cluster L3, and assign the data items to the data cluster with the closest distance, and get three new data clusters as the initial cluster centers, where and is the coordinate value of the data point, and For two data points, The value of the sub-data item, is the number of sub-data items; E5: Calculate the means of the three new data clusters in the initial cluster center respectively, and use them as the new original cluster center for recalculation; E6: Repeat E4 and E5 until the preset number of iterations is reached to obtain an environmental prediction classification model; E7: Input the feature vector into the environmental prediction classification model and output the fault prediction value; Further, the methods for classifying the fault prediction values ​​include: A fault prediction threshold interval (R1, R2) is preset. When the fault prediction value is less than R1, a normal signal is generated. When the fault prediction value is greater than R1 and less than R2, an early warning signal is generated. When the fault prediction value is greater than R2, a warning signal is generated. It should be explained that the fault prediction threshold interval is obtained through manual input; The normal signal includes a group of fields representing that the operation status of the solar lighting equipment is normal, the early warning signal includes a group of fields representing that the operation status of the solar lighting equipment is abnormal, and the warning signal includes a group of fields representing that the operation status of the solar lighting equipment is seriously abnormal; Pack normal signals, early warning signals and warning signals to obtain fault classification results; A database module, used for storing solar energy data sets, environmental data sets, fault reference values, and historical fault reference values; The prediction conversion analysis module is used to process the solar energy data set to obtain a prediction conversion report; Further, the solar energy data set is processed in the following ways: By substituting into the calculation formula: Get the power generation reference value, where is the photovoltaic panel data, is the solar radiation data, To transform data; Obtain a set of future solar radiation data, marked as Y1, Y2, Y3...Ym in fixed time units; It needs to be explained that the fixed time unit is day, week or month; Get a set of historical conversion data, marked as U1, U2, U3...Um in fixed time units; Calculate the conversion efficiency loss value. The specific calculation process is: ,in is the initial conversion efficiency value, that is The efficiency value is 0, For time, is the decay rate constant; Calculate the predicted conversion value. The specific calculation process is: ,in ; When the predicted conversion value is obtained, a predicted conversion report is generated; Intelligent decision-making module, used to process the fault classification results and obtain fault decision results; Further, the method of processing the fault classification result includes: When the fault classification result is a normal signal, a normal SMS is displayed to the display terminal through the user interaction module; when the fault classification result is an early warning signal, an early warning SMS is displayed to the display terminal through the user interaction module; when the fault classification result is a warning signal, a warning SMS is displayed to the display terminal through the user interaction module; Normal text messages include information about the normal operation of solar lighting equipment and reminding users to check the equipment regularly; The warning message includes an explanation of the abnormal operating status of the solar lighting equipment, reminding the user to check the solar lighting equipment, observe whether the indicator light is always on, whether the lighting equipment is working properly, and whether there is dust accumulation on the solar photovoltaic panels; The warning message includes a description of the serious abnormality of the operation status of the solar lighting equipment, reminding the user to immediately turn off the lighting equipment, stay away from the equipment operation area and contact relevant maintenance personnel; Pack normal SMS, warning SMS and warning SMS to get fault decision results; A user interaction module is used to transmit the fault reference value, prediction conversion report and fault decision result to the display end for display, analyze the solar energy data set, obtain the energy efficiency value, and transmit it to the display end for display; Further, the solar energy datasets can be analyzed by: By reading the value of the smart meter, the actual power generation value is obtained ; By substituting into the calculation formula: Get the energy efficiency value; The present embodiment has the beneficial effect that the environmental data set is analyzed by the fault reference value generation module, and the obtained fault reference value can enable the lighting equipment to be detected in real time when in use, so as to avoid the inconvenience caused by no one noticing when the lighting equipment stops running. The fault prediction value obtained by processing the environmental data set can effectively predict the faults of the lighting equipment caused by environmental factors, and then take corresponding treatment measures in advance, which greatly reduces the time cost of maintenance and avoids the loss caused by the lighting equipment stopping running to a certain extent. The fault decision result obtained by processing the fault classification result can assist the user to complete the corresponding measures for different states of the lighting equipment. The predicted conversion report obtained by processing the solar energy data set can accurately predict the final impact on the power generation of the solar lighting equipment due to the difference in solar radiation and the reduction in conversion efficiency in the future, thereby greatly improving the overall coordination ability of the solar lighting management system for energy storage and use allocation. The energy efficiency value obtained by analyzing the solar energy data set can intuitively show the difference between the theoretical power generation and the actual power generation of the solar photovoltaic panel, so that the user can directly observe the power generation life of the solar lighting equipment. In general, the present invention has the significant advantages of good automatic fault detection effect, strong ability to predict fault generation and direct effect of displaying the power generation of the equipment.

[0012] Example 2

[0013] See also Figure 2 As shown, the part not described in detail in this embodiment is described in the description of embodiment 1, and a solar lighting management method with automatic fault detection function is provided, comprising: S1: collecting a solar energy data set, the solar energy data set comprising photovoltaic panel data, solar radiation data and conversion data; S2: Collect environmental data sets, which include temperature data, humidity data, and dust data; S3: Data standardization of solar data set and environmental data set; S4: Analyze the environmental data set to obtain a fault reference value, process the environmental data set to obtain a fault prediction value, and classify the fault prediction value to obtain a fault classification result; S5: storing the solar energy data set, the environmental data set, the fault reference value, and the historical fault reference value; S6: Process the solar energy data set to obtain a prediction conversion report; S7: Process the fault classification result to obtain a fault decision result; S8: The fault reference value, the prediction conversion report and the fault decision result are transmitted to the display end for display, the solar energy data set is analyzed to obtain the energy efficiency value, and the energy efficiency value is transmitted to the display end for display.

[0014] Example 3

[0015] This embodiment discloses an electronic device, including 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 operation mode of the solar lighting management method with automatic fault detection function provided above is implemented.

[0016] Since the electronic device introduced in this embodiment is an electronic device used to implement a solar lighting management method with an automatic fault detection function in the embodiment of the present application, based on the solar lighting management method with an automatic fault detection function introduced in the embodiment of the present application, a person skilled in the art can understand the specific implementation of the electronic device of the present embodiment and its various variations, so how the electronic device implements the method in the embodiment of the present application is not described in detail here. As long as a person skilled in the art implements the electronic device used in the solar lighting management method with an automatic fault detection function in the embodiment of the present application, it belongs to the scope of protection of this application.

[0017] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0018] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical users in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A solar lighting management system with automatic fault detection function, characterized in that: include: A solar energy data collection module is used to collect solar energy data sets, which include photovoltaic panel data, solar radiation data and conversion data; An environmental data collection module is used to collect environmental data sets, including temperature data, humidity data and dust content data; Data preprocessing module, used to standardize solar data set and environmental data set; A fault reference value generation module is used to analyze the environmental data set to obtain a fault reference value, process the environmental data set to obtain a fault prediction value, and classify the fault prediction value to obtain a fault classification result; A database module, used for storing solar energy data sets, environmental data sets, fault reference values, and historical fault reference values; The prediction conversion analysis module is used to process the solar energy data set to obtain a prediction conversion report; Intelligent decision-making module, used to process the fault classification results and obtain fault decision results; The user interaction module is used to transmit the fault reference value, prediction conversion report and fault decision result to the display end for display, analyze the solar energy data set, obtain the energy efficiency value, and transmit it to the display end for display.

2. A solar lighting management system with automatic fault detection function according to claim 1, characterized in that: Ways to normalize data include: The solar data set and the environmental data set are Z-score standardized, that is, the mean and standard deviation of the solar data set and the environmental data set are standardized; the specific conversion function is: ,in is the mean of all sample data, is the standard deviation of all sample data.

3. A solar lighting management system with automatic fault detection function according to claim 2, characterized in that: Methods for analyzing environmental datasets include: The preset temperature threshold interval (Q1, Q2) is: when the temperature data is less than Q1, the value is 2; when the temperature data is greater than Q1 and less than Q2, the value is 1; when the temperature data is greater than Q2, the value is 2; The preset humidity threshold Q3, when the humidity data is less than Q3, the value is 1, when the temperature data is greater than Q3, the value is 2; The dust content threshold Q4 is preset. When the dust content data is less than Q4, the value is 1, and when the dust content data is greater than Q4, the value is 2; By substituting into the calculation formula: Get the fault reference value, where is the temperature data, is the humidity data, For dusty data, , and are the corresponding weight factors respectively; A fault reference threshold interval (W1, W2) is preset. When the fault reference value is less than W1, operation improvement information is output to the user interaction module through the communication unit. When the fault reference value is greater than W1 and less than W2, operation alarm information is output to the user interaction module through the communication unit. When the fault reference value is greater than W2, operation danger information is output to the user interaction module through the communication unit. The operation perfection information includes an explanation that the current equipment operation status is normal, the operation alarm information includes an explanation that the current equipment operation status is abnormal, and the operation danger information includes an explanation that the current equipment operation status is dangerous.

4. A solar lighting management system with automatic fault detection function according to claim 3, characterized in that: The steps to process the environmental dataset include: E1: Based on the historical environmental data set, by substituting into the calculation formula: Get the initial prediction value, where is the comprehensive slope value, is the unit of time; E2: Collect L groups of historical feature vectors as sample sets; E3: Establish an environmental classification model based on the sample set, obtain the historical feature vector in the sample set, preset the normal data cluster L1, warning data cluster L2 and alarm data cluster L3, and select three data points as the original cluster centers in the training set through artificial setting, representing the normal data cluster L1, warning data cluster L2 and alarm data cluster L3 respectively; E4: By substituting into the calculation formula: Get the distance between data items, calculate the distance between the data items in the training set and the normal data cluster L1, warning data cluster L2 and alarm data cluster L3, and assign the data items to the data cluster with the closest distance, and get three new data clusters as the initial cluster centers, where and is the coordinate value of the data point, and For two data points, The value of the sub-data item, is the number of sub-data items; E5: Calculate the means of the three new data clusters in the initial cluster center respectively, and use them as the new original cluster center for recalculation; E6: Repeat E4 and E5 until the preset number of iterations is reached to obtain an environmental prediction classification model; E7: Input the feature vector into the environmental prediction classification model and output the fault prediction value.

5. A solar lighting management system with automatic fault detection function according to claim 4, characterized in that: Ways to categorize the failure prediction values ​​include: A fault prediction threshold interval (R1, R2) is preset. When the fault prediction value is less than R1, a normal signal is generated. When the fault prediction value is greater than R1 and less than R2, an early warning signal is generated. When the fault prediction value is greater than R2, a warning signal is generated. The normal signal includes a group of fields representing that the operation status of the solar lighting equipment is normal, the early warning signal includes a group of fields representing that the operation status of the solar lighting equipment is abnormal, and the warning signal includes a group of fields representing that the operation status of the solar lighting equipment is seriously abnormal; Normal signals, early warning signals and warning signals are packaged to obtain fault classification results.

6. A solar lighting management system with automatic fault detection function according to claim 5, characterized in that: The solar data set is processed in the following ways: By substituting into the calculation formula: Get the power generation reference value, where is the photovoltaic panel data, is the solar radiation data, To transform data; Obtain a set of future solar radiation data, marked as Y1, Y2, Y3...Ym in fixed time units; It needs to be explained that the fixed time unit is day, week or month; Get a set of historical conversion data, marked as U1, U2, U3...Um in fixed time units; Calculate the conversion efficiency loss value. The specific calculation process is: ,in is the initial conversion efficiency value, that is The efficiency value is 0, For time, is the decay rate constant; Calculate the predicted conversion value. The specific calculation process is: ,in ; When the predicted conversion value is obtained, a predicted conversion report is generated.

7. A solar lighting management system with automatic fault detection function according to claim 6, characterized in that: Methods for processing fault classification results include: When the fault classification result is a normal signal, a normal SMS is displayed to the display terminal through the user interaction module; when the fault classification result is an early warning signal, an early warning SMS is displayed to the display terminal through the user interaction module; when the fault classification result is a warning signal, a warning SMS is displayed to the display terminal through the user interaction module; Normal text messages include information about the normal operation of solar lighting equipment and reminding users to check the equipment regularly; The warning message includes an explanation of the abnormal operating status of the solar lighting equipment, reminding the user to check the solar lighting equipment, observe whether the indicator light is always on, whether the lighting equipment is working properly, and whether there is dust accumulation on the solar photovoltaic panels; The warning message includes a description of the serious abnormality of the operation status of the solar lighting equipment, reminding the user to immediately turn off the lighting equipment, stay away from the equipment operation area and contact relevant maintenance personnel; Normal SMS, warning SMS and warning SMS are packaged to obtain fault decision results.

8. A solar lighting management system with automatic fault detection function according to claim 7, characterized in that: The solar data set can be analyzed by: By reading the value of the smart meter, the actual power generation value is obtained ; By substituting into the calculation formula: Get the energy efficiency value.

9. A solar lighting management method with automatic fault detection function, implemented according to any one of claims 1 to 8, characterized in that: The following steps are included: S1: Collect solar energy data sets, which include photovoltaic panel data, solar radiation data, and conversion data: S2: Collect environmental data sets, which include temperature data, humidity data, and dust data; S3: Data standardization of solar data set and environmental data set; S4: Analyze the environmental data set to obtain a fault reference value, process the environmental data set to obtain a fault prediction value, and classify the fault prediction value to obtain a fault classification result; S5: storing the solar energy data set, the environmental data set, the fault reference value, and the historical fault reference value; S6: Process the solar energy data set to obtain a prediction conversion report; S7: Process the fault classification result to obtain a fault decision result; S8: The fault reference value, the prediction conversion report and the fault decision result are transmitted to the display end for display, the solar energy data set is analyzed to obtain the energy efficiency value, and the energy efficiency value is transmitted to the display end for display.

Images