Methods, devices and computer equipment for diagnosing photovoltaic system faults

Abstract

This invention discloses a method, apparatus, and computer device for fault diagnosis of photovoltaic systems. The method includes: acquiring target power data of a target device in the photovoltaic system within an edge processing device; the target power data being obtained based on sensor data; determining the actual measurement data of the target device based on the target power data; predicting the state of the target device based on a target state model corresponding to the target device, obtaining predicted result data for the target device; and detecting whether a fault has occurred in the target device based on the actual measurement data and the predicted result data, obtaining a detection result. This invention solves the technical problem of low monitoring efficiency in photovoltaic system monitoring in related technologies.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric power, in particular to a photovoltaic system fault diagnosis method and device and computer equipment. BACKGROUND

[0002] In the related art, with the rise of the photovoltaic industry, the state monitoring and operation optimization of the photovoltaic system have been paid more and more attention, in order to reduce the total cost of the photovoltaic power station in the entire life cycle of the photovoltaic system. For large-scale photovoltaic power stations, installing accurate state monitoring systems can improve the investment return ratio. However, for household and commercial photovoltaic systems, considering the hardware and software costs, the state monitoring system has not been widely promoted.

[0003] However, in the related art, in order to monitor the photovoltaic system, a method generally used is to arrange various collection devices at the site of the photovoltaic power station of the photovoltaic system, and then the collection devices transmit the collected data to a remote background, and the monitoring state of the photovoltaic system is determined based on the processing of the data by the background. However, when such a processing method is used to monitor the photovoltaic system, the time to obtain the monitoring result is generally long, the response is slow, and the monitoring efficiency is low.

[0004] Therefore, in the related art, there is a problem of low monitoring efficiency in monitoring the photovoltaic system.

[0005] In view of the above problems, no effective solution has been proposed so far. SUMMARY

[0006] The embodiments of the present application provide a photovoltaic system fault diagnosis method, device and computer equipment, to at least solve the technical problem of low monitoring efficiency in monitoring the photovoltaic system in the related art.

[0007] According to an aspect of an embodiment of the present application, a photovoltaic system fault diagnosis method is provided, comprising: in an edge processing device of a photovoltaic system, obtaining target power data of a target device in the photovoltaic system, the target power data being obtained based on a sensor; determining actual measurement data of the target device based on the target power data; predicting the state of the target device based on a target state model corresponding to the target device to obtain prediction result data of the target device; and detecting whether the target device has failed based on the actual measurement data and the prediction result data to obtain a detection result.

[0008] Optionally, in the case that the target device is a photovoltaic array in the photovoltaic system, the obtaining the target power data of the target device in the photovoltaic system comprises: receiving direct current voltage data collected by a direct current voltage sensor at a direct current side of the photovoltaic system, and receiving direct current current data collected by a direct current current sensor at the direct current side of the photovoltaic system, wherein the target power data comprises the direct current voltage data and the direct current current data; and the determining the actual measurement data of the target device based on the target power data comprises: determining a measurement power of the photovoltaic array based on the direct current voltage data and the direct current current data, wherein the actual measurement data comprises the measurement power.

[0009] Optionally, the predicting the state of the target device based on the target state model corresponding to the target device to obtain prediction result data of the target device comprises: the target state model corresponding to the photovoltaic array is a photovoltaic array state model, and the predicting the state of the photovoltaic array based on the photovoltaic array state model to obtain a prediction power of the photovoltaic array, wherein the prediction result data comprises the prediction power.

[0010] Optionally, before the predicting the state of the photovoltaic array based on the photovoltaic array state model to obtain a prediction power of the photovoltaic array, the method further comprises: obtaining an initial illumination intensity and an initial temperature value of the photovoltaic array, a time illumination intensity and a time temperature value of the photovoltaic array at a predetermined time, and a first model coefficient; and determining the photovoltaic array state model based on the initial illumination intensity, the initial temperature value, the time illumination intensity, the time temperature value, and the first model coefficient.

[0011] Optionally, the determining the photovoltaic array state model based on the initial illumination intensity, the initial temperature value, the time illumination intensity, the time temperature value, and the first model coefficient comprises: determining the photovoltaic array state model by the following manner:

[0012]

[0013] wherein m 2 is square meter, W is watt, is watt per square meter, P mp (t) is the prediction power at the predetermined time, G0 is the initial illumination intensity, G(t) is the time illumination intensity at the predetermined time, ΔT(t) is a difference between the time temperature value T(t) at the predetermined time and the initial temperature value T0, and m0-m2 and n0-n3 are the first model coefficient.

[0014] Optionally, in the case that the target device is an inverter in the photovoltaic system, the obtaining the target power data of the target device in the photovoltaic system comprises: receiving AC voltage data collected by an AC voltage sensor at an AC side of the photovoltaic system in the photovoltaic system, and receiving AC current data collected by an AC current sensor at the AC side of the photovoltaic system in the photovoltaic system, wherein the target power data comprises the AC voltage data and the AC current data; the determining the actual measurement data of the target device based on the target power data comprises: determining a measurement energy of the inverter based on the AC voltage data and the AC current data, wherein the actual measurement data comprises the measurement energy.

[0015] Optionally, the predicting the state of the target device based on the target state model corresponding to the target device to obtain prediction result data of the target device comprises: the target state model corresponding to the inverter is an inverter state model, and the predicting the state of the inverter based on the inverter state model to obtain a prediction energy of the inverter, wherein the prediction result data comprises the prediction energy.

[0016] Optionally, before the predicting the state of the inverter based on the inverter state model to obtain a prediction energy of the inverter, the method further comprises: obtaining an initial energy output by the inverter, a time energy of the inverter at a predetermined time, and a second model coefficient; and determining the inverter state model based on the initial energy, the time energy, and the second model coefficient.

[0017] Optionally, the determining the inverter state model based on the initial energy, the time energy, and the second model coefficient comprises: determining the inverter state model by the following manner:

[0018] E pac = h0+ h1E dc

[0019]

[0020] wherein the E dc is an average output energy of the photovoltaic array in one hour, the E pac is the prediction energy of the inverter at the predetermined time, the P dc (t) is an output power of the photovoltaic array in the photovoltaic system at the predetermined time, and the h0-h1 are the second model coefficients.

[0021] Optionally, the detecting whether the target device fails based on the actual measurement data and the prediction result data comprises: obtaining a difference between the actual measurement data and the prediction result data; and determining that the target device fails when the difference is greater than a predetermined threshold.

[0022] According to another aspect of the present application, there is provided a photovoltaic system fault diagnosis apparatus, comprising: a first obtaining module configured to obtain target power data of a target device in a photovoltaic system in an edge processing device of the photovoltaic system, the target power data being obtained based on a sensor; a determining module configured to determine actual measurement data of the target device based on the target power data; a second obtaining module configured to predict a state of the target device based on a target state model corresponding to the target device, to obtain prediction result data of the target device; and a detecting module configured to detect whether the target device fails based on the actual measurement data and the prediction result data, to obtain a detection result.

[0023] According to still another aspect of the present application, there is provided a computer device, comprising: a memory and a processor, the memory storing a computer program; and the processor configured to execute the computer program stored in the memory, the computer program being configured to cause the processor to execute the photovoltaic system fault diagnosis method according to any one of the preceding aspects.

[0024] In the embodiments of the present application, the actual measurement data and the prediction result data are obtained in an edge processing device of a photovoltaic system, and the actual measurement data is compared with the prediction result data to obtain a detection result of whether a target device fails, which effectively saves the time for data transmission and processing in a remote control center, effectively improves the data processing efficiency of the photovoltaic system, and solves the technical problem of low monitoring efficiency in the related art. BRIEF DESCRIPTION OF DRAWINGS

[0025] The accompanying drawings, which are included to provide a further understanding of the present application and constitute a part of this application, illustrate embodiments of the present application and together with the description serve to explain the present application. In the drawings:

[0026] Figure 1 is a flowchart of a photovoltaic system fault diagnosis method according to an embodiment of the present application;

[0027] Figure 2 is a schematic diagram of a photovoltaic system state intelligent diagnosis apparatus according to an embodiment of the present application;

[0028] Figure 3 is a structural block diagram of a photovoltaic system fault diagnosis device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0029] In order to make the personnel in the art better understand the present application scheme, the technical scheme in the embodiments of the present application will be described clearly and completely below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0030] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily limit to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0031] According to an embodiment of the present application, a method embodiment of a photovoltaic system fault diagnosis method is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in a different order.

[0032] Figure 1 is a flowchart of a photovoltaic system fault diagnosis method according to an embodiment of the present application, as shown in Figure 1 The method comprises the following steps:

[0033] Step S102, in the edge processing device of the photovoltaic system, target power data of a target device in the photovoltaic system is acquired, and the target power data is obtained based on a sensor;

[0034] As an optional embodiment, the execution subject of the photovoltaic system fault diagnosis method described above can be an edge processing device of the photovoltaic system, which is located locally in the photovoltaic system and belongs to an edge computing device in a network composed of the photovoltaic system and a remote control center. For example, when the photovoltaic system corresponds to a photovoltaic array located at a specific location, the remote control center can remotely communicate with a plurality of photovoltaic systems corresponding to photovoltaic arrays located at different locations, and the plurality of photovoltaic systems corresponding to photovoltaic arrays located at different locations can have their own corresponding edge processing devices.

[0035] As an optional embodiment, when different target devices in the photovoltaic system are monitored, the target power data obtained is different. For example, in the case where the target device is a photovoltaic array in the photovoltaic system, the target power data of the target device in the photovoltaic system is obtained by receiving direct current voltage data collected by a direct current voltage sensor at the direct current side of the photovoltaic system and receiving direct current current data collected by a direct current current sensor at the direct current side of the photovoltaic system, wherein the target power data includes the direct current voltage data and the direct current current data.

[0036] As an optional embodiment, in the case where the target device is an inverter in the photovoltaic system, the target power data of the target device in the photovoltaic system is obtained by receiving alternating current voltage data collected by an alternating current voltage sensor at the alternating current side of the photovoltaic system and receiving alternating current current data collected by an alternating current current sensor at the alternating current side of the photovoltaic system, wherein the target power data includes the alternating current voltage data and the alternating current current data.

[0037] Step S104, determining actual measurement data of the target device based on the target power data;

[0038] As an optional embodiment, correspondingly, in the case where the target device is a photovoltaic array in the photovoltaic system, the actual measurement data of the target device is determined based on the target power data, including determining the measurement power of the photovoltaic array based on the direct current voltage data and the direct current current data, wherein the actual measurement data includes the measurement power.

[0039] As an optional embodiment, correspondingly, the actual measurement data of the target device is determined based on the target power data, including determining the measurement energy of the inverter based on the alternating current voltage data and the alternating current current data, wherein the actual measurement data includes the measurement energy

[0040] Step S106, predicting the state of the target device based on the target state model corresponding to the target device to obtain prediction result data of the target device;

[0041] As an optional embodiment, the corresponding target state model can also be different when the target device is different. For example, when the target device is a photovoltaic array, the target state model corresponding to the photovoltaic array is a photovoltaic array state model, and when the target device is an inverter, the target state model corresponding to the inverter is an inverter state model. The following is an example of the target device being a photovoltaic array and an inverter, respectively.

[0042] For example, when the target device is a photovoltaic array, predicting the state of the target device based on the target state model corresponding to the target device to obtain the prediction result data of the target device can include: the target state model corresponding to the photovoltaic array is a photovoltaic array state model, predicting the state of the photovoltaic array based on the photovoltaic array state model to obtain the predicted power of the photovoltaic array, wherein the prediction result data includes the predicted power.

[0043] As an optional embodiment, before predicting the state of the photovoltaic array based on the photovoltaic array state model to obtain the predicted power of the photovoltaic array, the photovoltaic array state model can be obtained in various ways, for example, the following method can be used to obtain: obtaining the initial irradiance and initial temperature values of the photovoltaic array, the time irradiance and time temperature values of the photovoltaic array at a predetermined time, and the first model coefficients; determining the photovoltaic array state model based on the initial irradiance, the initial temperature values, the time irradiance, the time temperature values, and the first model coefficients.

[0044] As an optional embodiment, determining the photovoltaic array state model based on the initial irradiance, the initial temperature values, the time irradiance, the time temperature values, and the first model coefficients includes: determining the photovoltaic array state model by the following method:

[0045]

[0046] wherein m2 is square meter, W is watt, W / m2, which is the basic unit of irradiance, P mp (t) is the predicted power at a predetermined time, G0 is the initial irradiance, G(t) is the time irradiance at a predetermined time, ΔT(t) is the difference between the time temperature value T(t) at a predetermined time and the initial temperature value T0, and m0~m2 and n0~n3 are the first model coefficients.

[0047] For another example, when the above target device is an inverter, predicting the state of the target device based on the target state model corresponding to the target device to obtain the prediction result data of the target device includes: the target state model corresponding to the inverter is an inverter state model, predicting the state of the inverter based on the inverter state model to obtain the predicted energy of the inverter, wherein the prediction result data includes the predicted energy.

[0048] As an optional embodiment, before predicting the state of the inverter based on the inverter state model and obtaining the predicted energy of the inverter, the method further comprises: obtaining initial energy output by the inverter, time energy of the inverter at a predetermined time, and second model coefficients; and determining the inverter state model based on the initial energy, the time energy, and the second model coefficients.

[0049] As an optional embodiment, determining the inverter state model based on the initial energy, the time energy, and the second model coefficients comprises: determining the inverter state model by the following manner:

[0050] E pac =h0+h1E dc

[0051]

[0052] wherein, the above E dc is the average output energy of the photovoltaic array in one hour, E pac is the predicted energy of the inverter at the predetermined time, P dc (t) is the output power of the photovoltaic array in the photovoltaic system at the predetermined time, and h0-h1 are the second model coefficients. In step S108, based on the actual measurement data and the prediction result data, it is detected whether the target device fails, and a detection result is obtained.

[0053] As an optional embodiment, when the actual measurement data and the prediction result data are used to detect whether the target device fails and obtain the detection result, a plurality of manners can also be used. For example, a difference between the actual measurement data and the prediction result data can be obtained first; then, based on a comparison between the difference and a threshold, the detection result is obtained. For example, in a case where the difference is greater than a predetermined threshold, it is determined that the target device fails.

[0054] Through the above steps, based on the actual measurement data and the prediction result data obtained in the edge processing device of the photovoltaic system, and by comparing the actual measurement data with the prediction result data, the detection result of whether the target device fails is obtained. Compared with the related art in which only the data of the photovoltaic system is collected in the edge processing device of the photovoltaic system, and the related processing is transmitted to the remote control center for processing, the time for data transmission and processing in the remote control center is effectively saved, the data processing efficiency of the photovoltaic system is effectively improved, and the problem of low monitoring efficiency in the related art is solved.

[0055] Based on the above embodiments and preferred embodiments, an optional implementation manner is provided.

[0056] In related technologies, photovoltaic (PV) monitoring systems, used to monitor PV systems, are typically used for diagnosing and maintaining the performance of PV power generation systems. Currently, various commercial PV monitoring system products exist, which can track the status of PV systems from the module and inverter levels, assess system performance, and detect system faults. However, these commercial products typically cannot locate abnormal PV panels or help repair damaged PV panels. For example, some low-cost PV monitoring systems use a multi-sensor architecture, including voltage, current, light, and temperature sensors, to monitor the status of PV panels. The acquired sampling data is transmitted to a central server via a wireless sensor network for performance evaluation. Additionally, some PV monitoring systems use low-cost power line carrier communication schemes for data transmission. These commercial monitoring system products generally have two limitations. First, they simply collect and transmit data from PV panels and inverters; specific data analysis and fault diagnosis are performed remotely in the background, resulting in slow response times. Second, they lack edge prediction capabilities for system performance.

[0057] To address the aforementioned issues, this optional embodiment provides a photovoltaic system status intelligent diagnostic device. Figure 2 This is a schematic diagram of a photovoltaic system status intelligent diagnostic device provided according to an embodiment of the present invention, such as... Figure 2 As shown, this device is located locally within the photovoltaic system, i.e., on the edge device of the photovoltaic system, relative to the remote control center. The relevant functional processing of this device includes the following.

[0058] (1) The real-time voltage V at the grid connection point of the photovoltaic system on the AC side is obtained through the power data measurement function of the device. ac (t) and current i ac (t) Data. The inverter in the photovoltaic system collects the output voltage v of the DC-side photovoltaic array in real time. dc (t) and current i dc (t) data, and transmit this data to the device via the inverter's built-in communication interface. The aforementioned power data measurement function can read voltage and current data at the inverter's grid connection point through voltage transformers (PT) and current transformers (CT). The communication interface can be a wired interface such as RS-485, CAN, or Ethernet, or a wireless communication interface such as 4G or Zigbee.

[0059] (2) The device uses its edge computing capabilities to calculate and process the AC side voltage and current, and DC side voltage and current data, to obtain the output power P of the photovoltaic array. dc (t) and the inverter's output power P ac(t). The aforementioned edge computing capability can be a high-performance embedded processor built into the device to perform calculations on the relevant sampled data and make decisions based on the calculation results.

[0060] (3) The photovoltaic array will transmit the real-time data T generated by its own temperature sensor and light sensor. A and G A The data is transmitted to the device via a communication interface.

[0061] (4) The device predicts the maximum output power P of the photovoltaic array using the built-in photovoltaic array state model and inverter state model. mp (t) and the inverter's output power P g (t). Based on the prediction results, the average output energy E of the photovoltaic array within a predetermined time period (e.g., 1 hour) is calculated using the sliding time window method. dc and the average output energy E of the inverter pac The photovoltaic array state model can be selected based on the physical characteristics of photovoltaic arrays made of different materials, choosing a specific mechanistic model. The inverter state model can be selected based on the linear relationship between the inverter's output energy and input energy within a certain load range, choosing a specific univariate linear model. The sliding time window method can calculate the average value of all data within a certain time window, which can filter out noise in the data to some extent.

[0062] The mechanism model selected for the aforementioned photovoltaic array state model, taking crystalline silicon material as an example, can be...

[0063]

[0064] Where, m 2 W is for square meters, and W is for watts. Light intensity is measured in watts per square meter (W / m²), which is the basic unit of light intensity. G0 represents the initial light intensity, and G(t) is the real-time light intensity data collected by the light sensor. ΔT(t) is the difference between the real-time temperature data T(t) collected by the temperature sensor and the initial temperature T0. m0~m2 and n0~n3 are model coefficients. In this embodiment, a light intensity greater than 200 W / m² is mainly considered. 2 The situation.

[0065] The model parameters of the aforementioned photovoltaic array state model can also be obtained in various ways. For example, they can be determined using least squares regression based on historical data over a certain period. For ease of description, relevant variables are represented by the following symbols: illuminance G, ambient temperature T, and maximum output power P. Assume that k sets of observations (G1, T1, P1), (G2, T2, P2), ..., (G... k ,T k,P k ), objective function in,

[0066]

[0067]

[0068]

[0069] The regression model is Q = m T A T Am-2m T A T P+P T P. The minimum point can be obtained by taking the partial derivative of the regression model function, as shown below:

[0070] m=(A T A) -1 A T P.

[0071] When the inverter state model mentioned above is a univariate linear model, the univariate linear model can be represented as follows:

[0072] E pac =h0+h1E dc

[0073]

[0074] Where h0~h1 are the model coefficients of the inverter state model mentioned above, E dc E represents the average output energy of the photovoltaic array over one hour. pac P predicts the inverter's energy at a predetermined time. dc (t) represents the output power of the photovoltaic array in the photovoltaic system at a predetermined time.

[0075] The model coefficients of the inverter state model described above can be obtained as follows: based on historical data over a certain period, parameters are identified using least squares regression. Assume that k sets of observations (E...) are obtained. dc1 E pac1 ), (E dc2 E pac2 ), ..., (E dck E pack ), objective function Among them, E pacie E is an estimated value. paci These are measured values. The regression model is... The minimum point can be obtained by taking the partial derivative of the regression model function, as shown below:

[0076]

[0077]

[0078] (5) The actual measured output power P of the photovoltaic array dc (t) and the photovoltaic array output power P predicted by the model mp The two are compared, and the relative error ΔP(t) is calculated in real time. When ΔP(t) exceeds a certain threshold |δ p When |δ| is reached, it is determined that the photovoltaic array performance has severely degraded or malfunctioned. The aforementioned threshold |δ| is used to determine this. p Adjustments can be made based on the actual design of the photovoltaic array and the selection of components, drawing on historical experience values ​​and expert databases. The inverter output energy E obtained from actual measurements will be used. ac Inverter output energy E obtained from model prediction pac The two are compared, and their relative error ΔE is calculated in real time. When ΔE exceeds a certain threshold δ... e When this occurs, it is determined that the inverter efficiency has severely decreased or a malfunction has occurred. The aforementioned threshold δ... e Adjustments can be made based on the actual design of the inverter and the selection of components, using historical experience values ​​and expert databases.

[0079] (6) Both actual measurement data and model prediction results can be transmitted to the back-end control center via the device's communication interface for real-time monitoring, analysis, and storage. This back-end control center can be located within the power distribution automation system. Simultaneously, when the photovoltaic system experiences performance degradation or malfunctions, the device can report the problem to the back-end control center. After analysis, the back-end control center issues decision instructions to the device. Ultimately, the device uses the communication interface to address the issues with the photovoltaic system.

[0080] In an optional embodiment of the present invention, relevant parameters in the photovoltaic system are monitored and analyzed in real time locally through the inverter's own data acquisition function or a dedicated intelligent acquisition terminal. Based on advanced models and algorithms, the relevant states of the photovoltaic system are predicted, and the results are compared with the real-time acquired data to assess the relevant states of the photovoltaic system. This function helps to promptly detect performance degradation or internal faults in the photovoltaic system, improving the accuracy and purposefulness of operation and maintenance. Simultaneously, it enhances the safety and reliability of the power distribution network.

[0081] In this embodiment of the invention, a photovoltaic system fault diagnosis device is also provided. Figure 3 This is a structural block diagram of a photovoltaic system fault diagnosis device provided according to an embodiment of the present invention, such as... Figure 3As shown, the device includes: a first acquisition module 32, a determination module 34, a second acquisition module 36, and a detection module 38. The device will be described below.

[0082] The first acquisition module 32 is used to acquire target power data of the target device in the photovoltaic system in the edge processing device of the photovoltaic system. The target power data is obtained based on sensor acquisition. The determination module 34 is connected to the first acquisition module 32 and is used to determine the actual measurement data of the target device based on the target power data. The second acquisition module 36 is connected to the determination module 34 and is used to predict the state of the target device based on the target state model corresponding to the target device to obtain the prediction result data of the target device. The detection module 38 is connected to the second acquisition module 36 and is used to detect whether the target device has failed based on the actual measurement data and the prediction result data to obtain the detection result.

[0083] In this embodiment of the invention, a computer device is also provided, comprising: a memory and a processor, wherein the memory stores a computer program; and the processor is configured to execute the computer program stored in the memory, wherein the computer program, when running, causes the processor to execute any of the above-described photovoltaic system fault diagnosis methods.

[0084] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0085] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0086] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0087] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0088] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0089] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0090] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A photovoltaic system fault diagnostic method characterized by, Comprise: In the edge processing device of the photovoltaic system, obtaining target power data of a target device in the photovoltaic system, the target power data being based on sensor collection; Based on the target power data, determining the actual measurement data of the target device; Based on the target state model corresponding to the target device, the state of the target device is predicted to obtain the prediction result data of the target device; Based on the actual measurement data and the prediction result data, detecting whether the target device fails, and obtaining a detection result; Wherein, in the case that the target device is a photovoltaic array in the photovoltaic system, the target state model is a photovoltaic array state model: ， wherein, is in square meters, W is in watts, is in watts per square meter, is a predicted power at a predetermined time, is an initial light intensity, is a time light intensity at the predetermined time, is a time temperature value at the predetermined time is a difference between an initial temperature value , ~ and ~ is a first model coefficient;​​ Wherein, in the case that the target device is an inverter in the photovoltaic system, the target state model is an inverter state model: ， ， wherein the is the one-hour PV array average output energy, the is the inverter predicted energy at the predetermined time, the is the output power of the PV array in the PV system at the predetermined time, the ~ is the second model coefficient.

2. The method of claim 1, wherein, In the case that the target device is a photovoltaic array in the photovoltaic system, The target power data of the target device in the photovoltaic system is obtained, including: receiving direct current voltage data collected by a direct current voltage sensor on the direct current side of the photovoltaic system, and receiving direct current current data collected by a direct current current sensor on the direct current side of the photovoltaic system, wherein the target power data includes the direct current voltage data and the direct current current data; The actual measurement data of the target device is determined based on the target power data, including: determining the measurement power of the photovoltaic array based on the direct current voltage data and the direct current current data, wherein the actual measurement data includes the measurement power.

3. The method of claim 2, wherein, The state of the target device is predicted based on the target state model corresponding to the target device to obtain the prediction result data of the target device, including: The target state model corresponding to the photovoltaic array is a photovoltaic array state model, and the state of the photovoltaic array is predicted based on the photovoltaic array state model to obtain the predicted power of the photovoltaic array, wherein the prediction result data includes the predicted power.

4. The method of claim 3, wherein, Before the state of the photovoltaic array is predicted based on the photovoltaic array state model to obtain the predicted power of the photovoltaic array, it further includes: Obtaining the initial light intensity and the initial temperature value of the photovoltaic array, the time light intensity and the time temperature value of the photovoltaic array at a predetermined time, and the first model coefficient; Based on the initial light intensity, the initial temperature value, the time light intensity, the time temperature value, and the first model coefficient, the photovoltaic array state model is determined.

5. The method of claim 1, wherein, In the case that the target device is an inverter in the photovoltaic system, The target power data of the target device in the photovoltaic system is obtained, including: receiving alternating current voltage data collected by an alternating current voltage sensor on the alternating current side of the photovoltaic system, and receiving alternating current current data collected by an alternating current current sensor on the alternating current side of the photovoltaic system, wherein the target power data includes the alternating current voltage data and the alternating current current data; The determining the actual measurement data of the target device based on the target power data comprises: determining a measured energy of the inverter based on the alternating voltage data and the alternating current data, wherein the actual measurement data comprises the measured energy.

6. The method of claim 5, wherein, The predicting the state of the target device based on the target state model corresponding to the target device to obtain prediction result data of the target device comprises: The target state model corresponding to the inverter is an inverter state model, and the predicting the state of the inverter based on the inverter state model to obtain predicted energy of the inverter, wherein the prediction result data comprises the predicted energy.

7. The method of claim 6, wherein, Before the predicting the state of the inverter based on the inverter state model to obtain predicted energy of the inverter, the method further comprises: obtaining initial energy output by the inverter, time energy of the inverter at a predetermined time, and a second model coefficient; determining the inverter state model based on the initial energy, the time energy, and the second model coefficient.

8. The method according to any one of claims 1 to 7, characterized in that, The detecting whether the target device fails based on the actual measurement data and the prediction result data to obtain a detection result comprises: obtaining a difference between the actual measurement data and the prediction result data; determining that the target device fails in a case where the difference is greater than a predetermined threshold.

9. A photovoltaic system failure diagnosis apparatus applied to the photovoltaic system failure diagnosis method of claim 1, characterized by, Comprise: The first obtaining module is configured to obtain target power data of a target device in a photovoltaic system in an edge processing device of the photovoltaic system, wherein the target power data is obtained based on a sensor; The determining module is configured to determine actual measurement data of the target device based on the target power data; The second obtaining module is configured to predict a state of the target device based on a target state model corresponding to the target device to obtain prediction result data of the target device; The detecting module is configured to detect whether the target device fails based on the actual measurement data and the prediction result data to obtain a detection result.

10. A computer device, comprising: Comprise: a memory and a processor, The memory stores a computer program; The processor is configured to execute the computer program stored in the memory, and the computer program, when running, causes the processor to execute the photovoltaic system fault diagnosis method in any one of claims 1 to 8.

Images