Fault monitoring method, device and equipment of photovoltaic terminal, medium and program product

Abstract

The invention provides a fault monitoring method and device for photovoltaic terminals, equipment, a medium and a program product. The method comprises the following steps: processing historical operation data to obtain standard historical operation data of each photovoltaic terminal; comparing the real-time operation data with standard historical operation data, and obtaining a monitoring signal of each photovoltaic terminal according to a comparison result; screening out an abnormal signal of the photovoltaic terminal from the monitoring signal, and inputting an abnormal operation index of the photovoltaic terminal corresponding to the abnormal signal into a fault risk prediction model to obtain a fault risk prediction probability of the corresponding photovoltaic terminal; comparing the fault risk prediction probability with a preset value, and outputting fault risk information of the corresponding photovoltaic terminal according to a comparison result; and outputting fault information of the corresponding photovoltaic terminal according to the fault signal of the photovoltaic terminal. Effective monitoring and prediction of the risk of the photovoltaic terminal are realized, the photovoltaic terminal can be overhauled in time according to the prediction result, and the failure rate of the photovoltaic terminal is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of data monitoring and processing, and in particular to a fault monitoring method, device, equipment, medium and program product for a photovoltaic terminal. Background Art

[0002] In order to effectively manage the photovoltaic terminals within each power station, it is usually necessary to establish a centralized management platform to centrally monitor the data of the photovoltaic terminals and analyze the operating status of the photovoltaic terminals, so that the operation and maintenance department can monitor the data and perform operation and maintenance management of multiple photovoltaic terminals.

[0003] In the existing related technologies, a centralized management platform can perform fault detection on different photovoltaic terminals and output fault information of the photovoltaic terminals.

[0004] However, in the prior art, the centralized management platform can only detect faults of photovoltaic terminals, but lacks the means to predict the risk of photovoltaic terminal faults. Therefore, there is a problem of increased failure rate due to untimely maintenance of photovoltaic terminals. Summary of the invention

[0005] The present application provides a photovoltaic terminal fault monitoring method, device, equipment, medium and program product to solve the problem that the centralized management platform in the prior art can only detect photovoltaic terminal faults, but lacks the means to predict the risk of photovoltaic terminal faults. Therefore, there is a problem of increased failure rate due to untimely maintenance of photovoltaic terminals.

[0006] In a first aspect, the present application provides a photovoltaic terminal fault monitoring method, which is applied to a computer device, comprising:

[0007] Obtain historical and real-time operation data of each photovoltaic terminal;

[0008] Standardizing the historical operation data to obtain standard historical operation data of each photovoltaic terminal;

[0009] Comparing the real-time operation data with the standard historical operation data to obtain a first comparison result of each photovoltaic terminal;

[0010] According to the first comparison result, a monitoring signal of each photovoltaic terminal is obtained, wherein the monitoring signal includes: an abnormal signal of the photovoltaic terminal, a normal signal of the photovoltaic terminal or a fault signal of the photovoltaic terminal;

[0011] Screening out abnormal signals of the photovoltaic terminal from the monitoring signals, and inputting abnormal operation indicators of the photovoltaic terminal corresponding to the abnormal signals into the fault risk prediction model to obtain the corresponding fault risk prediction probability of the photovoltaic terminal;

[0012] Comparing the fault risk prediction probability with the fault prediction preset value to obtain a second comparison result of the corresponding photovoltaic terminal;

[0013] According to the second comparison result, outputting the corresponding fault risk information of the photovoltaic terminal;

[0014] According to the fault signal of the photovoltaic terminal, the fault information of the corresponding photovoltaic terminal is output.

[0015] In a possible design, the historical operation data is standardized to obtain standard historical operation data of each photovoltaic terminal, including: sorting the historical operation data in a preset order to obtain a sorting result; determining the detection level of the historical operation data based on the sorting result; using a kurtosis test method to calculate the kurtosis observation value corresponding to any historical operation data based on the sorting number of any historical operation data, the average value of the historical operation data and any historical operation data; determining the critical value in the kurtosis test method based on the detection level; if any kurtosis observation value is greater than or equal to the critical value, determining that the historical operation data corresponding to any kurtosis observation value belongs to an outlier data point; if any kurtosis observation value is less than the critical value, determining that the historical operation data corresponding to any kurtosis observation value belongs to a non-outlier data point; standardizing the historical operation data belonging to the non-outlier point to obtain standard historical operation data of each photovoltaic terminal.

[0016] In a possible design, a kurtosis test method is used to calculate the kurtosis observation value corresponding to any historical operation data according to the ranking number of any historical operation data, the average value of the historical operation data and any historical operation data. The calculation formula is:

[0017]

[0018] In the formula, bk(n) represents the kurtosis observation value corresponding to any historical operation data, n is the number of sorting of historical operation data in a preset order, is the average value of historical running data, x i is the i-th historical running data.

[0019] In a possible design, the historical operation data belonging to the non-outlier point is standardized to obtain the standard historical operation data of each photovoltaic terminal, and the calculation formula is:

[0020]

[0021] Where b(n) represents the standard historical operating data of the photovoltaic terminal. represents the average value of the historical running data belonging to the non-outlier point, and s′ represents the standard deviation of the historical running data belonging to the non-outlier point.

[0022] In a possible design, the first comparison result includes: the real-time operation data is within the standard historical operation data interval, and the real-time operation data is not within the standard historical operation data interval; accordingly, the monitoring signal of each photovoltaic terminal is obtained according to the first comparison result, wherein the monitoring signal includes: an abnormal signal of the photovoltaic terminal, a normal signal of the photovoltaic terminal or a fault signal of the photovoltaic terminal, including: if the real-time operation data is within the standard historical operation data interval, it is determined that the photovoltaic terminal is operating normally, and a normal signal of the photovoltaic terminal is obtained; if the real-time operation data is not within the standard historical operation data interval, it is determined that the photovoltaic terminal is operating abnormally; if the real-time operation data of the photovoltaic terminal that is operating abnormally is greater than or equal to a preset fault threshold, it is determined that the photovoltaic terminal is operating faulty, and a fault signal of the photovoltaic terminal is obtained; if the real-time operation data of the photovoltaic terminal that is operating abnormally is less than the preset fault threshold, it is determined that the photovoltaic terminal is operating abnormally, and an abnormal signal of the photovoltaic terminal is obtained.

[0023] In one possible design, an abnormal signal of a photovoltaic terminal is screened out from the monitoring signal, and an abnormal operating indicator of the photovoltaic terminal corresponding to the abnormal signal is input into a fault risk prediction model to obtain a corresponding fault risk prediction probability of the photovoltaic terminal, including: obtaining an abnormal operating indicator of the photovoltaic power generation power and an abnormal operating indicator of the operating temperature of the corresponding photovoltaic terminal according to the abnormal signal; and inputting the abnormal operating indicator of the photovoltaic power generation power and the abnormal operating indicator of the operating temperature of the photovoltaic terminal into a fault risk prediction model to obtain a corresponding fault risk prediction probability of the photovoltaic terminal.

[0024] In a possible design, the abnormal operation index of the photovoltaic power generation power and the abnormal operation index of the operating temperature of the photovoltaic terminal are input into the fault risk prediction model to obtain the corresponding fault risk prediction probability of the photovoltaic terminal. The fault risk prediction model formula is:

[0025]

[0026] In the formula, G represents the predicted probability of failure risk of the photovoltaic terminal, y = 1 represents the photovoltaic terminal operation failure, y = 0 represents the photovoltaic terminal operation normal, M P Indicates the abnormal operation index of photovoltaic power generation of photovoltaic terminal, M T Indicates the abnormal operating index of the operating temperature of the photovoltaic terminal, α, β 1 and β 2 Represents the coefficients of the failure risk prediction model.

[0027] In a possible design, the calculation formula of the abnormal operation index of the photovoltaic power generation power of the photovoltaic terminal is:

[0028] M P =∑Δ P偏 *t P

[0029] Where M P Indicates the abnormal operation index of the photovoltaic power generation power of the photovoltaic terminal, Δ P偏 It represents the offset of the real-time power generation in the real-time operation data relative to the standard power generation in the standard historical operation data, t p Indicates that the photovoltaic terminal is in Δ P偏 The running time in the state.

[0030] In a possible design, the calculation formula of the abnormal operation index of the operating temperature of the photovoltaic terminal is:

[0031] M T =∑Δ T偏 *t T

[0032] Where M T Indicates the abnormal operation index of the photovoltaic power generation power of the photovoltaic terminal, Δ T偏 It represents the offset of the real-time operating temperature in the real-time operating data relative to the standard operating temperature in the standard historical operating data, t T Indicates that the photovoltaic terminal is in Δ T偏 The running time in the state.

[0033] In a possible design, before obtaining the historical operating data and real-time operating data of each photovoltaic terminal, it also includes: sending a preset network link communication detection message to each photovoltaic terminal; receiving each feedback message from each photovoltaic terminal to the message; if the feedback message from any photovoltaic terminal is not received, it is determined that a communication failure has occurred in the network link of any photovoltaic terminal.

[0034] In a possible design, after receiving each feedback message from each photovoltaic terminal in response to the message, it also includes: if the feedback message from any photovoltaic terminal is received, recording the feedback time node of the feedback message corresponding to any photovoltaic terminal; obtaining the sending time node of the message to any photovoltaic terminal; calculating the feedback duration of the message according to the sending time node and the feedback time node; if the feedback duration is greater than or equal to the preset overdue duration, determining that a communication failure occurs in the network link of any photovoltaic terminal; if the feedback duration is less than the preset overdue duration, determining that the network link of any photovoltaic terminal is unobstructed.

[0035] In a possible design, after determining that a communication failure occurs in the network link of any of the photovoltaic terminals, it also includes: obtaining network link information of the photovoltaic terminal where the communication failure occurs; and sending the network link information to a terminal of an operation and maintenance personnel.

[0036] In a second aspect, the present application provides a photovoltaic terminal fault monitoring device, which is applied to computer equipment, including:

[0037] The first acquisition module is used to acquire the historical operation data and real-time operation data of each photovoltaic terminal;

[0038] Processing module: used for standardizing the historical operation data to obtain standard historical operation data of each photovoltaic terminal;

[0039] A first comparison module: used for comparing the real-time operation data with the standard historical operation data to obtain a first comparison result of each photovoltaic terminal;

[0040] A generating module: used for obtaining the monitoring signal of each photovoltaic terminal according to the first comparison result, wherein the monitoring signal includes: an abnormal signal of the photovoltaic terminal, a normal signal of the photovoltaic terminal or a fault signal of the photovoltaic terminal;

[0041] A first calculation module: used for screening out abnormal signals of photovoltaic terminals from the monitoring signals, and inputting abnormal operation indicators of photovoltaic terminals corresponding to the abnormal signals into a fault risk prediction model to obtain a corresponding fault risk prediction probability of the photovoltaic terminals;

[0042] A second comparison module: used to compare the fault risk prediction probability with the fault prediction preset value to obtain a second comparison result of the corresponding photovoltaic terminal;

[0043] A first output module: configured to output corresponding fault risk information of the photovoltaic terminal according to the second comparison result;

[0044] The second output module is used to output the fault information of the corresponding photovoltaic terminal according to the fault signal of the photovoltaic terminal.

[0045] In a third aspect, the present application provides a computer device, comprising: at least one processor and a memory;

[0046] The memory stores computer-executable instructions;

[0047] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the fault monitoring method for the photovoltaic terminal as described in the first aspect and various possible designs of the first aspect.

[0048] In a fourth aspect, the present application provides a computer storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the fault monitoring method of the photovoltaic terminal as described in the first aspect and various possible designs of the first aspect is implemented.

[0049] In a fifth aspect, the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the fault monitoring method of the photovoltaic terminal as described in the first aspect and various possible designs of the first aspect.

[0050] The photovoltaic terminal fault monitoring method, device, equipment, medium and program product provided by the present application first standardizes the historical operation data of each photovoltaic terminal to obtain standard historical operation data; then, the real-time operation data is compared with the standard historical operation data to generate a monitoring signal; the abnormal signal in the monitoring signal is further analyzed, and the fault risk prediction model is used to predict the fault risk probability of the photovoltaic terminal corresponding to the abnormal signal, and the fault risk probability is compared with the fault prediction preset value; finally, the fault risk information of the corresponding photovoltaic terminal and the fault information of the photovoltaic terminal corresponding to the fault signal in the monitoring signal are output according to the comparison result. Effective monitoring and prediction of photovoltaic terminal risks are achieved, and photovoltaic terminals can be repaired in time according to the prediction results, reducing the failure rate of photovoltaic terminals. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0052] Figure 1 An application scenario diagram of the fault monitoring method for a photovoltaic terminal provided in an embodiment of the present application;

[0053] Figure 2 A schematic diagram of a flow chart of a fault monitoring method for a photovoltaic terminal provided in an embodiment of the present application;

[0054] Figure 3 A schematic diagram of the structure of a fault monitoring device for a photovoltaic terminal provided in an embodiment of the present application;

[0055] Figure 4 A schematic diagram of the hardware structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0057] Photovoltaic power generation is a clean and renewable energy source. With the advancement of technology and the reduction of costs, its application is becoming more and more extensive around the world. Power stations are usually composed of many photovoltaic terminals. In order to ensure that each photovoltaic terminal can operate efficiently and stably and optimize the performance of the entire power station, these terminals need to be effectively monitored and managed.

[0058] At present, in the existing related technologies, the centralized management platform can only detect faults of photovoltaic terminals, but lacks the means to predict the risk of photovoltaic terminal failures. Therefore, there will be a problem of increased failure rate due to untimely maintenance of photovoltaic terminals.

[0059] In order to solve the above technical problems, the embodiments of the present application propose the following technical concepts: the inventor first obtains and analyzes the historical and real-time operation data of the photovoltaic terminal, thereby generating monitoring signals containing abnormalities, normality or faults; then uses the fault risk prediction model to evaluate the fault risk prediction probability corresponding to the abnormal signal, and compares the fault risk prediction probability with the fault prediction preset value, and finally outputs the fault risk information and fault information of the corresponding photovoltaic terminal. The following is a detailed description using a detailed embodiment.

[0060] Figure 1 This is an application scenario diagram of the photovoltaic terminal fault monitoring method provided in the embodiment of the present application. Figure 1 As shown, the application scenario includes: a computer device 101 and multiple photovoltaic terminals 102 .

[0061] It is understandable that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the object identification method. In other feasible implementations of the present application, the above architecture may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently, which can be determined according to the actual application scenario and is not limited here. Figure 1 The components shown may be implemented in hardware, software, or a combination of software and hardware.

[0062] In the specific implementation process, the computer device 101 can be used to obtain the historical operation data and real-time operation data of each photovoltaic terminal, process the historical operation data and the real-time operation data, and output the fault risk information of the corresponding photovoltaic terminal and the fault information of the corresponding photovoltaic terminal.

[0063] The photovoltaic terminal 102 , which may be a solar panel or an inverter, may be used to provide historical operation data and real-time operation data to the computer device 101 .

[0064] In addition, the network architecture and business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Ordinary technicians in this field can know that with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0065] based on Figure 1 In the application scenario, the embodiment of the present application provides a fault monitoring method for a photovoltaic terminal, and the execution subject can be Figure 1 The computer device shown is not particularly limited in the embodiments of the present application. Figure 2 A schematic diagram of a fault monitoring method for a photovoltaic terminal provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the method includes:

[0066] S201: Acquire historical operation data and real-time operation data of each photovoltaic terminal.

[0067] Among them, the historical operation data includes: the power generation power and operating temperature of the photovoltaic terminal.

[0068] Among them, the operating environment of the photovoltaic terminal: ambient temperature: no special requirements; storage temperature: no special requirements; relative humidity: not more than 85%; atmospheric pressure: no special requirements.

[0069] S202: Standardize the historical operation data to obtain standard historical operation data of each photovoltaic terminal.

[0070] Among them, S202 specifically includes:

[0071] S2021: Sort the historical operation data according to a preset order to obtain a sorting result.

[0072] The preset order may be: sorting from small to large or from large to small.

[0073] S2022: Determine the detection level of the historical operation data based on the sorting results.

[0074] The detection level is the degree of abnormality that one hopes to detect in a statistical test.

[0075] S2023: Use the kurtosis test method to calculate the kurtosis observation value corresponding to any historical operating data based on the ranking number of any historical operating data, the average value of the historical operating data and any historical operating data.

[0076] Specifically, the kurtosis test method is used to calculate the kurtosis observation value corresponding to any historical operation data according to the ranking number of any historical operation data, the average value of the historical operation data and any historical operation data. The calculation formula is:

[0077]

[0078] In the formula, bk(n) represents the kurtosis observation value corresponding to any historical operation data, n is the number of sorting of historical operation data in a preset order, is the average value of historical running data, x i is the i-th historical running data.

[0079] S2024: Determine the critical value in the kurtosis test method based on the detection level.

[0080] Among them, according to the detection level and the number of photovoltaic terminals, the kurtosis test critical value table is searched to determine the corresponding critical value. This critical value is pre-calculated based on statistical principles and can usually be found in statistics books or professional literature.

[0081] S2025: If any kurtosis observation value is greater than or equal to the critical value, it is determined that the historical operating data corresponding to any kurtosis observation value belongs to an outlier data point.

[0082] Among them, outlier data points refer to data points that deviate greatly from other historical operating data. Outlier data points may be caused by measurement errors, data input errors, or the uniqueness of the sample itself.

[0083] S2026: If any kurtosis observation value is less than the critical value, it is determined that the historical operating data corresponding to any kurtosis observation value belongs to a non-outlier data point.

[0084] Among them, non-outlier data points usually follow the general distribution pattern of the data and help to depict the trends and patterns of the overall data.

[0085] S2027: Perform standardization calculation on the historical operation data belonging to non-outliers to obtain standard historical operation data of each photovoltaic terminal.

[0086] Specifically, the historical operation data belonging to non-outliers are standardized to obtain the standard historical operation data of each photovoltaic terminal. The calculation formula is:

[0087]

[0088] Where b(n) represents the standard historical operating data of the photovoltaic terminal. It represents the average value of the historical running data belonging to non-outliers, and s′ represents the standard deviation of the historical running data belonging to non-outliers.

[0089] S203: Compare the real-time operation data with the standard historical operation data to obtain a first comparison result of each photovoltaic terminal.

[0090] The first comparison result includes: a power generation comparison result and an operating temperature comparison result.

[0091] Among them, the power generation comparison result: if the power generation in the real-time operation data is lower than the power generation in the standard historical operation data, it may indicate that the performance of the photovoltaic terminal has declined or there are potential problems; the operating temperature comparison result: if the operating temperature in the real-time operation data is higher than the operating temperature in the standard historical operation data, it may indicate that the photovoltaic terminal is overheating, with performance decline or potential problems.

[0092] S204: obtaining monitoring signals of each photovoltaic terminal according to the first comparison result, wherein the monitoring signals include: abnormal signals of the photovoltaic terminal, normal signals of the photovoltaic terminal or fault signals of the photovoltaic terminal.

[0093] Among them, if the first comparison result shows that the power generation power and the operating temperature are close to but do not exceed the range of the power generation power and the operating temperature in the standard historical operating data, the monitoring signal is displayed as an abnormal signal; if the first comparison result shows that the power generation power and the operating temperature do not exceed the range of the power generation power and the operating temperature in the standard historical operating data, the monitoring signal is displayed as a normal signal; if the first comparison result shows that the power generation power and the operating temperature exceed the range of the power generation power and the operating temperature in the standard historical operating data, the monitoring signal is displayed as a fault signal.

[0094] S205: Filter out abnormal signals of the photovoltaic terminal from the monitoring signals, and input the abnormal operation index of the photovoltaic terminal corresponding to the abnormal signal into the fault risk prediction model to obtain the corresponding fault risk prediction probability of the photovoltaic terminal.

[0095] Among them, after prediction by the fault risk prediction model, it is obtained that the probability of failure of the corresponding photovoltaic terminal within the next 48 hours is 30%.

[0096] The abnormal operation index of the photovoltaic terminal corresponding to the abnormal signal includes: an abnormal operation index of photovoltaic power generation and an abnormal operation index of operating temperature.

[0097] Among them, the fault risk prediction model is trained based on a large amount of historical operation data and real-time operation data.

[0098] S206: Compare the fault risk prediction probability with the fault prediction preset value to obtain a second comparison result of the corresponding photovoltaic terminal.

[0099] Exemplarily, the fault prediction preset value may be 25%. By comparing the 30% fault probability predicted by the fault risk prediction model with the 25% fault prediction preset value, a second comparison result may be obtained: the photovoltaic terminal has a high fault risk.

[0100] S207: Outputting corresponding fault risk information of the photovoltaic terminal according to the second comparison result.

[0101] S208: Outputting corresponding photovoltaic terminal fault information according to the photovoltaic terminal fault signal.

[0102] In summary, the historical operation data of each photovoltaic terminal is first standardized to obtain standard historical operation data; then, the real-time operation data is compared with the standard historical operation data to generate a monitoring signal; the abnormal signal in the monitoring signal is further analyzed, and the fault risk prediction model is used to predict the fault risk probability of the photovoltaic terminal corresponding to the abnormal signal, and the fault risk probability is compared with the fault prediction preset value; finally, the fault risk information of the corresponding photovoltaic terminal and the fault information of the photovoltaic terminal corresponding to the fault signal in the monitoring signal are output according to the comparison result. Effective monitoring and prediction of photovoltaic terminal risks are achieved, and photovoltaic terminals can be repaired in time according to the prediction results, reducing the failure rate of photovoltaic terminals.

[0103] On the basis of the above embodiment, the first comparison result includes: the real-time operation data is within the standard historical operation data interval, and the real-time operation data is not within the standard historical operation data interval. This embodiment also describes the process of obtaining the monitoring signal of each photovoltaic terminal according to the first comparison result, and the process of obtaining the corresponding photovoltaic terminal fault risk prediction probability, which are described in detail as follows:

[0104] S301: If the real-time operation data is within the standard historical operation data range, it is determined that the photovoltaic terminal is operating normally, and a normal signal of the photovoltaic terminal is obtained.

[0105] S302: If the real-time operation data is not within the standard historical operation data range, it is determined that the photovoltaic terminal is operating abnormally.

[0106] S303: If the real-time operation data of the abnormally operating photovoltaic terminal is greater than or equal to a preset fault threshold, it is determined that the photovoltaic terminal has an operation fault, and a fault signal of the photovoltaic terminal is obtained.

[0107] S304: If the real-time operation data of the abnormally operating photovoltaic terminal is less than a preset fault threshold, it is determined that the photovoltaic terminal is operating abnormally, and an abnormal signal of the photovoltaic terminal is obtained.

[0108] S305: Acquire abnormal operating indicators of photovoltaic power generation power and operating temperature of the corresponding photovoltaic terminal according to the abnormal signal.

[0109] S306: Inputting the abnormal operation index of the photovoltaic power generation power and the abnormal operation index of the operation temperature of the photovoltaic terminal into the fault risk prediction model to obtain the corresponding fault risk prediction probability of the photovoltaic terminal.

[0110] Specifically, the abnormal operation index of the photovoltaic power generation power and the abnormal operation index of the operating temperature of the photovoltaic terminal are input into the fault risk prediction model to obtain the corresponding fault risk prediction probability of the photovoltaic terminal. The fault risk prediction model formula is:

[0111]

[0112] In the formula, G represents the predicted probability of failure risk of the photovoltaic terminal, y = 1 represents the photovoltaic terminal operation failure, y = 0 represents the photovoltaic terminal operation normal, M P Indicates the abnormal operation index of photovoltaic power generation of photovoltaic terminal, M T Indicates the abnormal operating index of the operating temperature of the photovoltaic terminal, α, β 1 and β 2 Represents the coefficients of the failure risk prediction model.

[0113] Among them, the historical operation data are classified according to whether the photovoltaic terminal finally fails, and several groups of historical operation data of photovoltaic terminals with failures and several groups of historical operation data of photovoltaic terminals without failures are obtained; then, based on these two groups of data, the maximum likelihood method is used to perform α, β 1 and β 2 Calculate α and β 1 and β 2 Whether the significance requirements of the fault risk prediction model parameters are met.

[0114] Among them, the calculation formula of the abnormal operation index of photovoltaic power generation power of the photovoltaic terminal is:

[0115] M P =∑Δ P偏 *t P

[0116] Where M P Indicates the abnormal operation index of the photovoltaic power generation power of the photovoltaic terminal, Δ P偏 It represents the offset of the real-time power generation in the real-time operation data relative to the standard power generation in the standard historical operation data, t p Indicates that the photovoltaic terminal is in Δ P偏 The running time in the state.

[0117] Among them, the calculation formula of the abnormal operation index of the operating temperature of the photovoltaic terminal is:

[0118] M T =ΣΔ T偏 *t T

[0119] Where M T Indicates the abnormal operation index of the photovoltaic power generation power of the photovoltaic terminal, Δ T偏 It represents the offset of the real-time operating temperature in the real-time operating data relative to the standard operating temperature in the standard historical operating data, t T Indicates that the photovoltaic terminal is in Δ T偏 The running time in the state.

[0120] In summary, by judging whether the real-time operating data falls within the standard historical operating data range, the operating status of the photovoltaic terminal can be determined, and the normal, abnormal or fault signal of the photovoltaic terminal can be obtained. Potential problems can be discovered in advance, so that preventive maintenance measures can be implemented to ensure that the photovoltaic terminal can always be in a relatively good operating state, thereby improving the energy output and efficiency of the entire power station.

[0121] In addition, by inputting the abnormal operation indicators of the photovoltaic terminal corresponding to the abnormal signal into the fault risk prediction model to obtain the corresponding fault risk prediction probability of the photovoltaic terminal, the accuracy and precision of fault prediction for the photovoltaic terminal are improved, and the identification of potential faults in the early stages is realized, thereby reducing invalid inspections and repairs and reducing the overall operation and maintenance costs.

[0122] Based on the above embodiment, this embodiment further describes a process of determining whether a communication failure occurs in a network link of any photovoltaic terminal, which is described in detail as follows:

[0123] S401: Sending a preset network link communication detection message to each photovoltaic terminal.

[0124] Among them, a photovoltaic terminal information set D is established according to the operation information of all photovoltaic terminals, D = {d1, d2, ..., dn}, where dn is the operation information of the photovoltaic terminal labeled n, and n is the number of current photovoltaic terminals.

[0125] Among them, the network link communication detection message is a data packet in a specific format, which is used to test and verify the communication quality, reliability and connectivity of the network link. Some common network link communication detection messages include: trace route command messages, DNS (Domain Name System) query messages and custom detection messages.

[0126] Exemplarily, the trace route command tool sends a series of UDP (User Datagram Protocol) messages with increasing lifetimes to each photovoltaic terminal.

[0127] S402: receiving feedback messages from each photovoltaic terminal in response to the message.

[0128] Exemplarily, after receiving the UDP message, each photovoltaic terminal will return an ICMP (Internet Control Message Protocol) timeout message.

[0129] Specifically, after receiving each feedback message of each photovoltaic terminal to the message, it also includes:

[0130] S4021: If a feedback message from any photovoltaic terminal is received, a feedback time node of the feedback message corresponding to any photovoltaic terminal is recorded.

[0131] S4022: Obtain the sending time node of the message to any photovoltaic terminal.

[0132] S4023: Calculate the feedback duration of the message according to the sending time node and the feedback time node.

[0133] S4024: If the feedback duration is greater than or equal to the preset overdue duration, it is determined that a communication failure occurs in the network link of any photovoltaic terminal.

[0134] S4025: If the feedback time is less than the preset overdue time, it is determined that the network link of any photovoltaic terminal is unobstructed.

[0135] S403: If no feedback message is received from any photovoltaic terminal, it is determined that a communication failure occurs in the network link of any photovoltaic terminal.

[0136] Specifically, after determining that a communication failure occurs in a network link of any photovoltaic terminal, the method further includes:

[0137] S4031: Obtain network link information of the photovoltaic terminal where the communication failure occurs.

[0138] The network link information may include: node information, physical channel information, data link information and / or routing protocol information.

[0139] S4032: Send network link information to the terminal of the operation and maintenance personnel.

[0140] In summary, the feedback time of the message is calculated by the sending time node of the message sent by any photovoltaic terminal and the feedback time node of the feedback message corresponding to any photovoltaic terminal, and then the feedback time is used to determine whether a communication failure occurs in the network link of any photovoltaic terminal. The status of the network link can be monitored in real time, and communication failures can be quickly discovered, so that maintenance and repair can be carried out in time. In addition, existing communication facilities and protocols are used, and no additional hardware investment is required, saving costs.

[0141] Figure 3 This is a schematic diagram of the structure of a fault monitoring device for a photovoltaic terminal provided in an embodiment of the present application. Figure 3 As shown, the fault monitoring device of the photovoltaic terminal is applied to computer equipment, including: a first acquisition module 501, a processing module 502, a first comparison module 503, a generation module 504, a first calculation module 505, a second comparison module 506, a first output module 507 and a second output module 508.

[0142] The first acquisition module 501 is used to acquire the historical operation data and real-time operation data of each photovoltaic terminal.

[0143] Processing module 502: used for standardizing the historical operation data to obtain standard historical operation data of each photovoltaic terminal.

[0144] The first comparison module 503 is used to compare the real-time operation data with the standard historical operation data to obtain a first comparison result of each photovoltaic terminal.

[0145] The generating module 504 is used to obtain the monitoring signal of each photovoltaic terminal according to the first comparison result, wherein the monitoring signal includes: an abnormal signal of the photovoltaic terminal, a normal signal of the photovoltaic terminal or a fault signal of the photovoltaic terminal.

[0146] The first calculation module 505 is used to filter out abnormal signals of photovoltaic terminals from monitoring signals, and input abnormal operation indicators of photovoltaic terminals corresponding to the abnormal signals into the fault risk prediction model to obtain the corresponding fault risk prediction probability of photovoltaic terminals.

[0147] The second comparison module 506 is used to compare the fault risk prediction probability with the fault prediction preset value to obtain a second comparison result of the corresponding photovoltaic terminal.

[0148] The first output module 507 is used to output the corresponding fault risk information of the photovoltaic terminal according to the second comparison result.

[0149] The second output module 508 is used to output the fault information of the corresponding photovoltaic terminal according to the fault signal of the photovoltaic terminal.

[0150] In one possible design, the processing module 502 is specifically used to sort the historical operation data in a preset order to obtain a sorting result; determine the detection level of the historical operation data based on the sorting result; use the kurtosis test method to calculate the kurtosis observation value corresponding to any historical operation data based on the sorting number of any historical operation data, the average value of the historical operation data and any historical operation data; determine the critical value in the kurtosis test method based on the detection level; if any kurtosis observation value is greater than or equal to the critical value, determine that the historical operation data corresponding to any kurtosis observation value belongs to an outlier data point; if any kurtosis observation value is less than the critical value, determine that the historical operation data corresponding to any kurtosis observation value belongs to a non-outlier data point; perform standardization calculation on the historical operation data belonging to non-outliers to obtain standard historical operation data of each photovoltaic terminal.

[0151] Among them, the kurtosis test method is used to calculate the kurtosis observation value corresponding to any historical operation data according to the ranking number of any historical operation data, the average value of the historical operation data and any historical operation data. The calculation formula is:

[0152]

[0153] In the formula, bk(n) represents the kurtosis observation value corresponding to any historical operation data, n is the number of sorting of historical operation data in a preset order, is the average value of historical running data, x i is the i-th historical running data.

[0154] Among them, the historical operation data belonging to non-outliers is standardized to obtain the standard historical operation data of each photovoltaic terminal. The calculation formula is:

[0155]

[0156] Where b(n) represents the standard historical operating data of the photovoltaic terminal. It represents the average value of the historical running data belonging to non-outliers, and s′ represents the standard deviation of the historical running data belonging to non-outliers.

[0157] In one possible design, the first comparison result includes: the real-time operation data is within the standard historical operation data interval, and the real-time operation data is not within the standard historical operation data interval; the generation module 504 is specifically used to determine that the photovoltaic terminal is operating normally if the real-time operation data is within the standard historical operation data interval, and obtain the normal signal of the photovoltaic terminal; if the real-time operation data is not within the standard historical operation data interval, then determine that the photovoltaic terminal is operating abnormally; if the real-time operation data of the photovoltaic terminal that is operating abnormally is greater than or equal to a preset fault threshold, then determine that the photovoltaic terminal is operating abnormally, and obtain the fault signal of the photovoltaic terminal; if the real-time operation data of the photovoltaic terminal that is operating abnormally is less than the preset fault threshold, then determine that the photovoltaic terminal is operating abnormally, and obtain the abnormal signal of the photovoltaic terminal.

[0158] In one possible design, the calculation module 505 is specifically used to obtain the abnormal operation index of the photovoltaic power generation power and the abnormal operation index of the operating temperature of the corresponding photovoltaic terminal according to the abnormal signal; and input the abnormal operation index of the photovoltaic power generation power and the abnormal operation index of the operating temperature of the photovoltaic terminal into the fault risk prediction model to obtain the fault risk prediction probability of the corresponding photovoltaic terminal.

[0159] Among them, the abnormal operation index of the photovoltaic power generation power and the abnormal operation index of the operating temperature of the photovoltaic terminal are input into the fault risk prediction model to obtain the corresponding fault risk prediction probability of the photovoltaic terminal. The fault risk prediction model formula is:

[0160]

[0161] In the formula, G represents the predicted probability of failure risk of the photovoltaic terminal, y = 1 represents the photovoltaic terminal operation failure, y = 0 represents the photovoltaic terminal operation normal, M P Indicates the abnormal operation index of photovoltaic power generation of photovoltaic terminal, M T Indicates the abnormal operating index of the operating temperature of the photovoltaic terminal, α, β 1 and β 2 Represents the coefficients of the failure risk prediction model.

[0162] Among them, the calculation formula of the abnormal operation index of photovoltaic power generation power of the photovoltaic terminal is:

[0163] M P =ΣΔ P偏 *t P

[0164] Where M P Indicates the abnormal operation index of the photovoltaic power generation power of the photovoltaic terminal, Δ P偏 It represents the offset of the real-time power generation in the real-time operation data relative to the standard power generation in the standard historical operation data, t pIndicates that the photovoltaic terminal is in Δ P偏 The running time in the state.

[0165] Among them, the calculation formula of the abnormal operation index of the operating temperature of the photovoltaic terminal is:

[0166] M T =ΣΔ T偏 *t T

[0167] Where M T Indicates the abnormal operation index of the photovoltaic power generation power of the photovoltaic terminal, Δ T偏 It represents the offset of the real-time operating temperature in the real-time operating data relative to the standard operating temperature in the standard historical operating data, t T Indicates that the photovoltaic terminal is in Δ T偏 The running time in the state.

[0168] In a possible design, the above device further includes:

[0169] The first sending module 509 is specifically used to send a preset network link communication detection message to each photovoltaic terminal.

[0170] Receiving module 510: specifically used to receive each feedback message from each photovoltaic terminal to the message.

[0171] The first determination module 511 is specifically configured to determine that a communication failure occurs in a network link of any photovoltaic terminal if no feedback message is received from any photovoltaic terminal.

[0172] In a possible design, the above device further includes:

[0173] The recording module 512 is specifically configured to record the feedback time node of the feedback message corresponding to any photovoltaic terminal if a feedback message from any photovoltaic terminal is received.

[0174] The second acquisition module 513 is specifically used to acquire a sending time node of sending a message to any photovoltaic terminal.

[0175] The second calculation module 514 is specifically configured to calculate the feedback duration of the message according to the sending time node and the feedback time node.

[0176] The second determination module 515 is specifically configured to determine that a communication failure occurs in the network link of any photovoltaic terminal if the feedback duration is greater than or equal to a preset overdue duration.

[0177] The third determination module 516 is specifically used to determine whether the network link of any photovoltaic terminal is unobstructed if the feedback time is less than the preset overdue time.

[0178] In a possible design, the above device further includes:

[0179] The third acquisition module 517 is specifically used to acquire the network link information of the photovoltaic terminal where the communication failure occurs.

[0180] The second sending module 518 is specifically used to send the network link information to the terminal of the operation and maintenance personnel.

[0181] The device provided in this embodiment can be used to execute the technical solution of the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be repeated here.

[0182] Figure 4 Schematic diagram of the hardware structure of the computer device provided in the embodiment of the present application. Figure 4 As shown, the computer device includes: at least one processor 601 and a memory 602; the memory stores computer execution instructions; at least one processor executes the computer execution instructions stored in the memory, so that at least one processor executes the fault monitoring method of the photovoltaic terminal as above.

[0183] Optionally, the memory 602 may be independent or integrated with the processor 601 .

[0184] When the memory 602 is independently provided, the computer device further includes a bus 603 for connecting the memory 602 and the processor 601 .

[0185] The embodiment of the present application further provides a computer storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the above photovoltaic terminal fault monitoring method is implemented.

[0186] The embodiment of the present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the fault monitoring method of the photovoltaic terminal as described above is implemented.

[0187] 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. For example, the device embodiments described above are only schematic. For example, the division of the above modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0188] The modules described above as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to implement the solution of this embodiment.

[0189] In addition, each functional module in each embodiment of the present application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The above-mentioned module-composed unit can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0190] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the above-mentioned method in each embodiment of the present application.

[0191] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor.

[0192] The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, etc.

[0193] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0194] The above storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), electrically erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The storage medium can be any available medium that can be accessed by a general or special computer.

[0195] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic device or a main control device.

[0196] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0197] Finally, it should be noted that 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 aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A photovoltaic terminal fault monitoring method, characterized in that: Applicable to computer equipment, including: Obtain historical and real-time operation data of each photovoltaic terminal; Standardizing the historical operation data to obtain standard historical operation data of each photovoltaic terminal; Comparing the real-time operation data with the standard historical operation data to obtain a first comparison result of each photovoltaic terminal; According to the first comparison result, a monitoring signal of each photovoltaic terminal is obtained, wherein the monitoring signal includes: an abnormal signal of the photovoltaic terminal, a normal signal of the photovoltaic terminal or a fault signal of the photovoltaic terminal; Screening out abnormal signals of the photovoltaic terminal from the monitoring signals, and inputting abnormal operation indicators of the photovoltaic terminal corresponding to the abnormal signals into the fault risk prediction model to obtain the corresponding fault risk prediction probability of the photovoltaic terminal; Comparing the fault risk prediction probability with the fault prediction preset value to obtain a second comparison result of the corresponding photovoltaic terminal; According to the second comparison result, outputting the corresponding fault risk information of the photovoltaic terminal; According to the fault signal of the photovoltaic terminal, the fault information of the corresponding photovoltaic terminal is output.

2. The method according to claim 1, characterized in that The standardizing of the historical operation data to obtain the standard historical operation data of each photovoltaic terminal includes: Sorting the historical operation data according to a preset order to obtain a sorting result; Determining the detection level of the historical operation data according to the sorting result; The kurtosis test method is adopted to calculate the kurtosis observation value corresponding to any historical operation data according to the ranking number of any historical operation data, the average value of the historical operation data and any historical operation data; Determining a critical value in the kurtosis test method according to the detection level; If any kurtosis observation value is greater than or equal to the critical value, it is determined that the historical operation data corresponding to the any kurtosis observation value belongs to an outlier data point; If any kurtosis observation value is less than the critical value, it is determined that the historical operation data corresponding to the any kurtosis observation value belongs to a non-outlier data point; The historical operation data belonging to the non-outlier points is standardized and calculated to obtain the standard historical operation data of each photovoltaic terminal.

3. The method according to claim 2, characterized in that The kurtosis test method is used to calculate the kurtosis observation value corresponding to any historical operation data according to the ranking number of any historical operation data, the average value of the historical operation data and any historical operation data. The calculation formula is: In the formula, bk(n) represents the kurtosis observation value corresponding to any historical operation data, n is the number of sorting of historical operation data in a preset order, x is the average value of historical operation data, and x is the average value of historical operation data. i is the i-th historical running data.

4. The method according to claim 2, characterized in that: The calculation formula for performing standardized calculation on the historical operation data belonging to the non-outlier points to obtain the standard historical operation data of each photovoltaic terminal is: Where b(n) represents the standard historical operating data of the photovoltaic terminal. represents the average value of the historical running data belonging to the non-outlier point, and s′ represents the standard deviation of the historical running data belonging to the non-outlier point.

5. The method according to claim 1, characterized in that in, The first comparison result includes: the real-time operation data is within the standard historical operation data interval, and the real-time operation data is not within the standard historical operation data interval; Correspondingly, the monitoring signal of each photovoltaic terminal is obtained according to the first comparison result, wherein the monitoring signal includes: an abnormal signal of the photovoltaic terminal, a normal signal of the photovoltaic terminal or a fault signal of the photovoltaic terminal, including: If the real-time operation data is within the standard historical operation data interval, it is determined that the photovoltaic terminal is operating normally, and a normal signal of the photovoltaic terminal is obtained; If the real-time operation data is not within the standard historical operation data interval, it is determined that the photovoltaic terminal is operating abnormally; If the real-time operation data of the abnormally operating photovoltaic terminal is greater than or equal to a preset fault threshold, the photovoltaic terminal is judged to be operating at fault, and a fault signal of the photovoltaic terminal is obtained; If the real-time operation data of the photovoltaic terminal that is not operating normally is less than a preset fault threshold, it is determined that the photovoltaic terminal is operating abnormally, and an abnormal signal of the photovoltaic terminal is obtained.

6. The method according to claim 1, characterized in that The step of screening out the abnormal signal of the photovoltaic terminal from the monitoring signal and inputting the abnormal operation index of the photovoltaic terminal corresponding to the abnormal signal into the fault risk prediction model to obtain the corresponding fault risk prediction probability of the photovoltaic terminal includes: Acquire an abnormal operating index of the photovoltaic power generation power and an abnormal operating index of the operating temperature of the corresponding photovoltaic terminal according to the abnormal signal; The abnormal operation index of the photovoltaic power generation power and the abnormal operation index of the operation temperature of the photovoltaic terminal are input into the fault risk prediction model to obtain the corresponding fault risk prediction probability of the photovoltaic terminal.

7. The method according to claim 6, characterized in that The abnormal operation index of the photovoltaic power generation power and the abnormal operation index of the operating temperature of the photovoltaic terminal are input into the fault risk prediction model to obtain the corresponding fault risk prediction probability of the photovoltaic terminal. The fault risk prediction model formula is: In the formula, G represents the predicted probability of failure risk of the photovoltaic terminal, y = 1 represents the photovoltaic terminal operation failure, y = 0 represents the photovoltaic terminal operation normal, M P Indicates the abnormal operation index of photovoltaic power generation of photovoltaic terminal, M T represents the abnormal operation index of the operating temperature of the photovoltaic terminal, and α, β1 and β2 represent the coefficients of the fault risk prediction model.

8. The method according to claim 7, characterized in that The calculation formula of the abnormal operation index of the photovoltaic power generation power of the photovoltaic terminal is: M P =∑Δ P偏 *t P Where M P Indicates the abnormal operation index of the photovoltaic power generation power of the photovoltaic terminal, Δ P偏 It represents the offset of the real-time power generation in the real-time operation data relative to the standard power generation in the standard historical operation data, t p Indicates that the photovoltaic terminal is in Δ P偏 The running time in the state.

9. The method according to claim 7, characterized in that: The calculation formula of the abnormal operation index of the operating temperature of the photovoltaic terminal is: M T =∑Δ T偏 *t T Where M T Indicates the abnormal operation index of the photovoltaic power generation power of the photovoltaic terminal, Δ T偏 It represents the offset of the real-time operating temperature in the real-time operating data relative to the standard operating temperature in the standard historical operating data, t T Indicates that the photovoltaic terminal is in Δ T偏 The running time in the state.

10. The method according to any one of claims 1 to 9, characterized in that: Before obtaining the historical operation data and real-time operation data of each photovoltaic terminal, the method further includes: Sending a preset network link communication detection message to each photovoltaic terminal; receiving each feedback message from each photovoltaic terminal in response to the message; If the feedback message from any photovoltaic terminal is not received, it is determined that a communication failure occurs in the network link of any photovoltaic terminal.

11. The method according to claim 10, characterized in that After receiving each feedback message from each photovoltaic terminal to the message, the method further includes: If the feedback message from any photovoltaic terminal is received, the feedback time node of the feedback message corresponding to any photovoltaic terminal is recorded; Obtaining a sending time node for sending the message to any photovoltaic terminal; Calculating the feedback duration of the message according to the sending time node and the feedback time node; If the feedback duration is greater than or equal to the preset overdue duration, it is determined that a communication failure occurs in the network link of any photovoltaic terminal; If the feedback duration is less than the preset overdue duration, it is determined that the network link of any photovoltaic terminal is unobstructed.

12. The method according to claim 11, characterized in that After determining that a communication failure occurs in the network link of any photovoltaic terminal, the method further includes: Acquiring network link information of the photovoltaic terminal where the communication failure occurs; The network link information is sent to the terminal of the operation and maintenance personnel.

13. A fault monitoring device for a photovoltaic terminal, characterized in that: Applicable to computer equipment, including: The first acquisition module is used to acquire the historical operation data and real-time operation data of each photovoltaic terminal; Processing module: used for standardizing the historical operation data to obtain standard historical operation data of each photovoltaic terminal; A first comparison module: used for comparing the real-time operation data with the standard historical operation data to obtain a first comparison result of each photovoltaic terminal; A generating module: used for obtaining the monitoring signal of each photovoltaic terminal according to the first comparison result, wherein the monitoring signal includes: an abnormal signal of the photovoltaic terminal, a normal signal of the photovoltaic terminal or a fault signal of the photovoltaic terminal; A first calculation module: used for screening out abnormal signals of photovoltaic terminals from the monitoring signals, and inputting abnormal operation indicators of photovoltaic terminals corresponding to the abnormal signals into a fault risk prediction model to obtain a corresponding fault risk prediction probability of the photovoltaic terminals; A second comparison module: used to compare the fault risk prediction probability with the fault prediction preset value to obtain a second comparison result of the corresponding photovoltaic terminal; A first output module: configured to output corresponding fault risk information of the photovoltaic terminal according to the second comparison result; The second output module is used to output the fault information of the corresponding photovoltaic terminal according to the fault signal of the photovoltaic terminal.

14. A computer device, characterized in that: include: at least one processor and memory; The memory stores computer-executable instructions; The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the fault monitoring method for a photovoltaic terminal according to any one of claims 1 to 12.

15. A computer storage medium, characterized in that The computer storage medium stores computer executable instructions, and when the processor executes the computer executable instructions, the fault monitoring method for the photovoltaic terminal according to any one of claims 1 to 12 is implemented.

16. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the fault monitoring method for a photovoltaic terminal as claimed in any one of claims 1 to 12 is implemented.

Images