A photovoltaic power station component early warning method and system

Abstract

The present application discloses an early warning method and system for photovoltaic power station components, including: obtaining weather information in weather forecasts, obtaining current values ​​and voltage values ​​of photovoltaic components in different weather information; and marking them as fault values ​​according to different gradients; performing correlation analysis based on weather information and standard values ​​to obtain influencing factors of current values ​​and voltage values; abnormal data acquisition: obtaining first abnormal data and second abnormal data according to the time data and the standard value; comparison processing: comparing the first abnormal data and the second abnormal data with the fault value to obtain an estimated value; if the estimated value is outside the fault value, then continue to obtain the first abnormal data, obtain the second abnormal data, and perform comparison processing in sequence; if the estimated value is within the fault value, then output it as an early warning result. The early warning method and system can timely and effectively detect abnormal components and give early warnings, thereby enhancing the power output capability and stability of photovoltaic power stations.

Description

Technical Field

[0001] The present application relates to the field of solar photovoltaic power stations, and in particular to an early warning method and system for photovoltaic power station components. Background Art

[0002] With the development of the photovoltaic industry and the increasing installed capacity of photovoltaic new energy, the normal operation of photovoltaic modules, the most basic equipment in the photovoltaic field, is the basis for ensuring the continuous, stable and efficient power generation of photovoltaic power stations. Photovoltaic modules are the equipment with the largest number of modules in photovoltaic power stations. To ensure the normal operation of modules, it is necessary to monitor the operating status of the modules in a timely manner and issue early warnings in case of abnormal operating status. This can not only save operation and maintenance costs, but also greatly improve the work efficiency of operation and maintenance personnel, and enable operation and maintenance personnel to accurately and quickly find problematic modules. In order to maintain the continuous, efficient and stable power generation of photovoltaic modules, a large amount of manpower and material resources must be invested, and the workload is high to find problematic modules. This maintenance and early warning method is difficult and has low timeliness. Sensors and communication equipment are installed under photovoltaic modules to warn photovoltaic modules, but the procurement, installation and maintenance costs of the equipment are high, which increases the cost of enterprises.

[0003] To this end, the present application provides an early warning method for photovoltaic power station components to solve the above-mentioned problems. Summary of the invention

[0004] The early warning method and system for photovoltaic power station components provided in the present application can timely predict whether the photovoltaic components of the photovoltaic power station are in normal operating state, timely and effectively detect and warn abnormal components, and enhance the power output capacity and stability of the photovoltaic power station.

[0005] In order to solve the above technical problems, the present application provides an early warning method for photovoltaic power station components, including:

[0006] Get weather information from the weather forecast;

[0007] Obtain the current value and voltage value of the photovoltaic module in different weather information as standard values;

[0008] Obtain the current and voltage changes of the faulty photovoltaic modules in different weather information before the first time, and mark them as fault values ​​according to different gradients;

[0009] Perform correlation analysis on the weather information and the standard value to obtain influencing factors of the current value and the voltage value; obtain a historical weather time point similar to the current weather as time data based on the influencing factors;

[0010] Abnormal data acquisition: acquiring first abnormal data and second abnormal data according to the time data and the standard value;

[0011] Comparison processing: comparing the first abnormal data, the second abnormal data and the fault value to obtain an estimated value;

[0012] If the estimated value is outside the fault value, continue to perform the abnormal data acquisition step and the comparison processing step;

[0013] If the estimated value is within the fault value, it is output as a warning result.

[0014] The weather information includes: wind speed, wind direction, cloud cover, temperature and humidity in the weather forecast.

[0015] The frequency of executing the early warning method is 1-60 minutes.

[0016] Wherein, the acquisition of the first abnormal data includes:

[0017] S1: Obtain the difference between the maximum current and the minimum current of the component in the time data to obtain a first difference;

[0018] S2: Obtain the current mean value of all branches under each inverter at each moment in the first time;

[0019] S3: obtaining a branch whose current value at each moment is less than the current mean value among all branches of each inverter within the first time period, and obtaining a filtering branch;

[0020] S4: Obtain a difference between the current of the filtering branch and the current mean value to obtain a second difference value;

[0021] S5: Compare the second difference with the first difference, output the branch where the second difference is smaller than the first difference, and count the number of occurrences to determine the first abnormal data.

[0022] Wherein, the acquisition of the second abnormal data includes:

[0023] Step 1: subtract the current at the previous moment from the current at the later moment in multiple time periods in all branches under each inverter within the first time period to obtain a two-dimensional matrix of current differences;

[0024] Step 2: Obtain weather change factors of the weather information before the first time and the weather information after the first time, and output the weather change factors as current change factors;

[0025] Step 3: Compare the current difference of the two-dimensional matrix with the current change factor, output the branch that is greater than the current change factor, and count the number of occurrences to determine the second abnormal data.

[0026] In addition, the present application also provides an early warning system for photovoltaic power station components, including:

[0027] An acquisition unit is used to acquire weather information in a weather forecast, and to acquire current values ​​and voltage values ​​of photovoltaic modules in different weather information as standard values; to acquire current and voltage changes of photovoltaic modules that have failed in different weather information before the first time, and to mark them as fault values ​​according to different gradients;

[0028] A first processing unit is used to perform a correlation analysis based on the weather information and the standard value to obtain the influencing factors of the current value and the voltage value; and to obtain the historical weather time point similar to the current weather as the time data based on the influencing factors;

[0029] A second processing unit is used for acquiring the abnormal data, and acquiring the first abnormal data and the second abnormal data according to the time data and the standard value;

[0030] A third processing unit, configured to compare and process the first abnormal data, the second abnormal data and the fault value to obtain an estimated value;

[0031] A judgment processing unit, judging whether the estimated value is within the fault value;

[0032] Output unit: if the estimated value is outside the fault value, continue to perform the abnormal data acquisition step and the comparison processing step;

[0033] If the estimated value is within the fault value, it is output as a warning result.

[0034] At the same time, the present application also provides a computer-readable storage medium, in which a computer program is stored, and when the program is executed by a processor, the steps of any of the above methods are implemented.

[0035] The present application also provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the above methods when executing the computer program.

[0036] This application collects weather data and real-time data of all branch currents under the power station inverter, and uses machine learning methods to provide early warning of photovoltaic components that may fail in photovoltaic power stations, thereby reducing the manpower and material resources for photovoltaic power station operation and maintenance. It can timely predict whether the photovoltaic components of the photovoltaic power station are in normal operation, and discover abnormal problems of problematic photovoltaic components in advance, so that the power station operation and maintenance can complete the transformation from problem solving to problem prevention, so as to achieve continuous, stable and efficient power generation of the power station, thereby enhancing the power output capacity and stability of the photovoltaic power station. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solution of the present application, the following briefly introduces the drawings required for use in the embodiments. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without inventiveness.

[0038] Figure 1 A schematic diagram of a flow chart of an early warning method provided by an embodiment of the present invention;

[0039] Figure 2 A schematic diagram of a first abnormal data processing flow provided by an embodiment of the present invention;

[0040] Figure 3 A schematic diagram of a first abnormal data processing flow provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to enable those skilled in the art to better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0042] Figure 1 A schematic diagram of a flow chart of an early warning method provided by an embodiment of the present invention; Figure 2 A schematic diagram of a first abnormal data processing flow provided by an embodiment of the present invention; Figure 3 The first abnormal data processing flow diagram provided by the embodiment of the present invention is as follows. Figure 1-3 As shown, an early warning method for photovoltaic power station components includes:

[0043] Get the weather information in the weather forecast and store the weather data in the database. The real-time weather data and historical weather information data in the photovoltaic module area can be obtained in real time through the weather data in the existing weather forecast database. Or different equipment such as temperature and humidity measuring instruments, wind speed and direction measuring instruments, temperature acquisition modules, etc. can be used for collection. Of course, weather information data acquisition is not limited to the above two methods. The acquired data distribution is transmitted to the server in a bus time-division multiplexing manner and maintained in the database. Some of the acquired data information is shown in Tables 1-1 and 1-2 below:

[0044] Table 1-1

[0045]

[0046] Table 1-2

[0047]

[0048] At the same time, the current and voltage values ​​of the photovoltaic components obtained in different weather information are used as standard values; the current and voltage data values ​​of the inverter are obtained in real time through the current and voltage acquisition module. The voltage and current data of the same inverter are shown in Table 1-3 below.

[0049] Table 1-3

[0050]

[0051] In actual acquisition, the current and voltage values ​​of the photovoltaic modules are monitored in real time through monitoring equipment and matched with the weather information data. That is, the weather data in each time period is matched with the current and voltage data of each inverter at that time. The matching is done by the processor

[0052] As above Figure 1-3 As shown in the figure, there is faulty component information in the acquired current and voltage information data, such as PV8 current, which is abnormal data. The current and voltage changes of the faulty photovoltaic components in different weather information before the first time are marked as faulty components with fault values ​​according to different gradients. The first time refers to a certain time, which can be any time within the data monitoring.

[0053] According to the weather information and standard values, correlation analysis is performed to obtain the influencing factors of current and voltage values; according to the influencing factors, the historical weather time points similar to the current weather are obtained as time data. The correlation analysis uses the Pearson correlation analysis method to determine the influencing factors.

[0054] The analysis method similar to the current weather adopts the following calculation formula, coef = ((nWCoef-hWCoef)**2+(nTCoef1-hTCoef1)**2+(nDCoef-hDCoef)**2+(nTCoef2-hTCoef2)**2, find the minimum coef value as the date similar to the weather of the current day. It should be noted that the letters represent the meaning of n: now, h: history, T: temperature, and D: duration.

[0055] Abnormal data acquisition: obtain the first abnormal data and the second abnormal data according to the time data and the standard value;

[0056] The first abnormal data acquisition is to perform horizontal data processing on the components within the time data;

[0057] like Figure 2 Shown: These include:

[0058] S1: Obtain the difference between the maximum current and the minimum current of the component in the time data to obtain a first difference;

[0059] S2: Obtain the current mean value of all branches under each inverter at each moment in the first time;

[0060] S3: Obtain the branch whose current value at each moment is less than the current mean value among all branches of each inverter within the first time, and obtain the filtering branch;

[0061] S4: Obtain the difference between the current of the filtering branch and the current mean value to obtain a second difference value;

[0062] S5: Compare the second difference with the first difference, output the branch where the second difference is smaller than the first difference, and count the number of occurrences to determine the first abnormal data.

[0063] Through horizontal data processing, it is easier to find problematic components by comparing them with other components under the same weather conditions.

[0064] Acquisition of second abnormal data: performing longitudinal processing according to the first abnormal data;

[0065] like Figure 3 As shown, including:

[0066] Step 1: subtract the current at the previous moment from the current at the later moment in multiple time periods in all branches under each inverter in the first time period to obtain a two-dimensional matrix of current differences;

[0067] Step 2: Obtain weather change factors of weather information before the first time and weather information after the first time, and output the weather change factors as current change factors;

[0068] Step 3: Compare the current difference of the two-dimensional matrix with the current change factor, output the branch that is greater than the current change factor, and count the number of occurrences to determine the second abnormal data.

[0069] Through longitudinal processing, the instantaneous current and voltage changes are determined to determine whether they exceed the threshold and whether the component is abnormal.

[0070] Comparison processing: comparing the first abnormal data, the second abnormal data and the fault value to obtain an estimated value;

[0071] If the estimated value is outside the fault value, the first abnormal data acquisition, the second abnormal data acquisition, and the comparison processing are continued in sequence;

[0072] If the estimated value is within the fault value, the output is a warning result.

[0073] Among them, weather information includes: wind speed, wind direction, cloud cover, temperature and humidity in the weather forecast.

[0074] Among them, the frequency of executing the early warning method is 1-60min.

[0075] In addition, the present application also provides an early warning system for photovoltaic power station components, including:

[0076] An acquisition unit is used to acquire weather information in a weather forecast, and to acquire current values ​​and voltage values ​​of photovoltaic modules in different weather information as standard values; to acquire current and voltage changes of photovoltaic modules that have failed in different weather information before the first time, and to mark them as fault values ​​according to different gradients;

[0077] The first processing unit is used to perform correlation analysis based on weather information and standard values ​​to obtain influencing factors of current values ​​and voltage values; and to obtain historical weather time points similar to the current weather as time data based on the influencing factors;

[0078] The second processing unit is used for acquiring abnormal data, and acquiring first abnormal data and second abnormal data according to the time data and the standard value;

[0079] A third processing unit is used for comparison processing, comparing the first abnormal data, the second abnormal data and the fault value to obtain an estimated value;

[0080] A judgment processing unit judges whether the estimated value is within the fault value;

[0081] Output unit: if the estimated value is outside the fault value, continue with the abnormal data acquisition step and the comparison processing step;

[0082] If the estimated value is within the fault value, the output is a warning result.

[0083] In the present application, the early warning system embodiment of the photovoltaic power station component is basically similar to the early warning method embodiment of the photovoltaic power station component. For relevant matters, please refer to the introduction of the early warning method embodiment of the photovoltaic power station component of the photovoltaic power station.

[0084] At the same time, the computer-readable storage medium provided by the present application stores a computer program in the storage medium, and when the program is executed by the processor, the steps of the early warning method of the photovoltaic power station component are implemented. Among them, the computer-readable storage medium may include but is not limited to any type of disk, including floppy disk, optical disk, DVD, CD-ROM, micro drive and magneto-optical disk, ROM, RAM, EPROM, EEPROM, DRAM, VRAM, flash memory device, magnetic card or optical card, nano system (including molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0085] The computer device of the present application 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 early warning method for photovoltaic power station components are implemented.

[0086] The computer device may also be a personal digital assistant, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The data operation and execution steps of the early warning method of the photovoltaic power station component are realized through a processor, a memory, an input device, an output device, and the like.

[0087] This application collects weather data and real-time data of all branch currents under the power station inverter, and uses machine learning methods to provide early warning of photovoltaic components that may fail in photovoltaic power stations, thereby reducing the manpower and material resources for photovoltaic power station operation and maintenance. It can timely predict whether the photovoltaic components of the photovoltaic power station are in normal operation, and discover abnormal problems of problematic photovoltaic components in advance, so that the power station operation and maintenance can complete the transformation from problem solving to problem prevention, so as to achieve continuous, stable and efficient power generation of the power station, thereby enhancing the power output capacity and stability of the photovoltaic power station.

[0088] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0089] The functional units in the embodiments of the present invention may all be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units. It should be understood that the present application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes may be made without departing from the scope thereof. The above-described embodiments of the present application do not constitute a limitation on the scope of protection of the present application.

Claims

1. An early warning method for photovoltaic power station components, It is characterized in that include: Get weather information from the weather forecast; Obtain the current value and voltage value of the photovoltaic module in different weather information as standard values; Obtain the current and voltage changes of the faulty photovoltaic modules in different weather information before the first time, and mark them as fault values ​​according to different gradients; Perform correlation analysis on the weather information and the standard value to obtain influencing factors of the current value and the voltage value; obtain a historical weather time point similar to the current weather as time data based on the influencing factors; Abnormal data acquisition: acquiring first abnormal data and second abnormal data according to the time data and the standard value; The acquisition of the first abnormal data includes: S1: Obtain the difference between the maximum current and the minimum current of the component in the time data to obtain a first difference; S2: Obtain the current mean value of all branches under each inverter at each moment in the first time; S3: obtaining a branch whose current value at each moment is less than the current mean value among all branches of each inverter within the first time period, and obtaining a filtering branch; S4: Obtain a difference between the current of the filtering branch and the current mean value to obtain a second difference value; S5: Compare the second difference with the first difference, output the branch where the second difference is smaller than the first difference, and count the number of occurrences to determine the first abnormal data; Comparison processing: comparing the first abnormal data, the second abnormal data and the fault value to obtain an estimated value; If the estimated value is outside the fault value, continue to perform the abnormal data acquisition step and the comparison processing step; If the estimated value is within the fault value, it is output as a warning result.

2. The early warning method for photovoltaic power station components according to claim 1, It is characterized in that The weather information includes: wind speed, wind direction, cloud cover, temperature and humidity in the weather forecast.

3. The early warning method for photovoltaic power station components according to claim 1, It is characterized in that The frequency of executing the early warning method is 1-60 minutes.

4. The early warning method for photovoltaic power station components according to claim 3, It is characterized in that The acquisition of the second abnormal data includes: Step 1: subtract the current at the previous moment from the current at the later moment in multiple time periods in all branches under each inverter within the first time period to obtain a two-dimensional matrix of current differences; Step 2: Obtain weather change factors of the weather information before the first time and the weather information after the first time, and output the weather change factors as current change factors; Step 3: Compare the current difference of the two-dimensional matrix with the current change factor, output the branch that is greater than the current change factor, and count the number of occurrences to determine the second abnormal data.

5. An early warning system for photovoltaic power station components, based on the early warning method for photovoltaic power station components according to any one of claims 1 to 4, It is characterized in that include: An acquisition unit, used to acquire weather information in a weather forecast, and to acquire current values ​​and voltage values ​​of photovoltaic modules in different weather information as standard values; Obtain the current and voltage changes of the faulty photovoltaic modules in different weather information before the first time, and mark them as fault values ​​according to different gradients; A first processing unit is used to perform a correlation analysis based on the weather information and the standard value to obtain the influencing factors of the current value and the voltage value; and to obtain the historical weather time point similar to the current weather as the time data based on the influencing factors; A second processing unit is used for acquiring abnormal data, and acquiring first abnormal data and second abnormal data according to the time data and the standard value; A third processing unit, configured to compare and process the first abnormal data, the second abnormal data and the fault value to obtain an estimated value; A judgment processing unit, judging whether the estimated value is within the fault value; Output unit: if the estimated value is outside the fault value, continue to perform the abnormal data acquisition step and the comparison processing step; If the estimated value is within the fault value, it is output as a warning result.

6. A computer-readable storage medium, It is characterized in that The storage medium stores a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 4.

7. A computer device, It is characterized in that The computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method according to any one of claims 1 to 4 when executing the computer program.

Images