Fault locating method, fault locating device and storage medium for photovoltaic system

Abstract

The application discloses a fault positioning method and device of a photovoltaic system and a storage medium. The application utilizes a machine learning algorithm to construct a fault identification model for a generated midpoint voltage vector, so as to obtain a voltage feature interval for avoiding fault misjudgment. The system fault position is positioned and the fault type is judged based on the topology structure of the photovoltaic system and the voltage feature interval. By determining a voltage feature interval, misjudgment can be avoided.

Description

Technical Field

[0001] This invention relates to the field of new energy technology, and in particular to a fault location method, fault location device and storage medium for a photovoltaic system. Background Technology

[0002] With the development of solar photovoltaic power generation, the capacity of photovoltaic power generation systems is constantly expanding, and the types of system failures are also becoming more diversified. Therefore, it is particularly important to quickly and accurately locate the position and type of failure in a photovoltaic system.

[0003] Currently, the input voltage of a DC-DC converter is typically acquired, and the midpoint voltage vector corresponding to the input voltage is calculated using Fourier transform or wavelet transform algorithms. Then, based on the characteristics of the midpoint voltage vector, an inherent fault identification algorithm is used to determine the fault type. However, traditional fault location algorithms have limitations. For novel faults, when parameters differ at different installation locations of similar equipment within the same photovoltaic system, using traditional fault location algorithms for fault diagnosis can easily lead to misjudgments, which is detrimental to the stability of the entire system. Summary of the Invention

[0004] This application provides a fault location method, fault location device, and storage medium for photovoltaic systems, aiming to solve the problem of misjudgment of photovoltaic system faults.

[0005] This application provides a fault location method for a photovoltaic system, the fault location method for a photovoltaic system including:

[0006] Obtain the first input voltage of the DC-DC converter and the second input voltage of the photovoltaic inverter;

[0007] Determine the normal state voltage set and the fault type voltage set based on the first input voltage and the second input voltage;

[0008] Determine the first midpoint voltage vector corresponding to the normal state voltage set, and determine the second midpoint voltage vector corresponding to the fault type voltage set;

[0009] The voltage characteristic range is determined based on the first midpoint voltage vector and the second midpoint voltage vector;

[0010] The fault location and fault type are determined based on the voltage characteristic range and the topology of the photovoltaic system.

[0011] Optionally, determining the normal state voltage set based on the first input voltage and the second input voltage includes:

[0012] Cluster analysis is performed on the first input voltage and the second input voltage respectively to obtain the first normal state voltage set corresponding to the DC-DC converter and the second normal state voltage set corresponding to the photovoltaic inverter.

[0013] The normal state voltage set is generated based on the first normal state voltage set and the second normal state voltage set.

[0014] Optionally, determining the fault type voltage set based on the first input voltage and the second input voltage includes:

[0015] Outlier analysis is performed on the first input voltage and the second input voltage respectively to obtain the first outlier voltage set corresponding to the DC-DC converter and the second outlier voltage set corresponding to the photovoltaic inverter;

[0016] A first fault type voltage set is generated based on the first outlier voltage set, and a second fault type voltage set is generated based on the second outlier voltage set;

[0017] The fault type voltage set is determined based on the first fault type voltage set and the second fault type voltage set.

[0018] Optionally, the steps of generating a first fault type voltage set based on the first outlier voltage set and generating a second fault type voltage set based on the second outlier voltage set include:

[0019] Determine the first voltage feature corresponding to the first outlier voltage set and the second voltage feature corresponding to the second outlier voltage set;

[0020] The first fault type voltage set corresponding to the DC-DC converter is determined based on the first voltage characteristic, and the second fault type voltage set corresponding to the photovoltaic inverter is determined based on the second voltage characteristic.

[0021] Optionally, the steps of determining the first midpoint voltage vector corresponding to the normal state voltage set and determining the second midpoint voltage vector corresponding to the fault type voltage set include:

[0022] The voltage signals of the normal state voltage set and the voltage signals of the fault type voltage set are processed by Hilbert-Huang transform respectively to obtain the instantaneous amplitude, instantaneous phase and instantaneous frequency;

[0023] The first midpoint voltage vector corresponding to the normal state voltage set and the second midpoint voltage vector corresponding to the fault type voltage set are generated based on the instantaneous amplitude, instantaneous phase, and instantaneous frequency, respectively.

[0024] Optionally, the step of determining the voltage characteristic interval based on the first midpoint voltage vector and the second midpoint voltage vector includes:

[0025] The hyperplane is determined based on the first midpoint voltage vector;

[0026] The upper and lower boundary interfaces of the hyperplane are determined based on the second midpoint voltage vector.

[0027] The voltage characteristic range is obtained based on the upper boundary interface and the lower boundary interface.

[0028] Optionally, the step of determining the upper and lower boundary interfaces of the hyperplane based on the second midpoint voltage vector includes:

[0029] The distance between the hyperplane and the boundary interface is determined based on the second midpoint voltage vector.

[0030] When the distance condition is met, the upper boundary interface and the lower boundary interface of the hyperplane are determined according to the distance, and the distance between the upper boundary interface and the hyperplane is equal to the distance between the lower boundary interface and the hyperplane.

[0031] Optionally, the step of determining the fault location and fault type based on the voltage characteristic range and the topology of the photovoltaic system includes:

[0032] The input and output voltages of the DC-DC converter and the photovoltaic inverter are determined according to the topology of the photovoltaic system.

[0033] Generate datasets corresponding to the incoming line voltage and the outgoing line voltage;

[0034] The fault location and fault type are determined based on the dataset and the voltage characteristic range.

[0035] Optionally, the step of determining the fault location and fault type based on the dataset and the voltage characteristic range includes:

[0036] Determine the datasets corresponding to the upper boundary interface that is greater than the voltage feature interval and / or the lower boundary interface that is less than the voltage feature interval;

[0037] The fault location and fault type are determined based on the dataset.

[0038] Optionally, the steps of obtaining the first input voltage of the DC-DC converter and the second input voltage of the photovoltaic inverter include:

[0039] The first input voltage is determined based on the output voltage of the photovoltaic array;

[0040] The second input voltage is determined based on the output loop voltage of the DC-DC converter.

[0041] In addition, to achieve the above objectives, the present invention also provides a fault location device for a photovoltaic system, comprising: a memory, a processor, and a fault location program for the photovoltaic system stored in the memory and executable on the processor, wherein the fault location program for the photovoltaic system, when executed by the processor, implements the steps of the fault location method for the photovoltaic system described above.

[0042] In addition, to achieve the above objectives, the present invention also provides a computer-readable storage medium storing a fault location program for a photovoltaic system, wherein the fault location program for the photovoltaic system, when executed by a processor, implements the steps of the fault location method for the photovoltaic system described above.

[0043] This application provides a technical solution for fault location in a photovoltaic system, including a fault location device and a storage medium. The solution involves acquiring the input voltages of the DC-DC converter and the photovoltaic inverter, determining their respective normal state voltage sets and fault type voltage sets based on these input voltages, determining their respective first midpoint voltage vectors based on the normal state voltage sets, and determining their respective second midpoint voltage vectors based on the fault type voltage sets. A voltage characteristic interval is then determined based on the first and second midpoint voltage vectors. Finally, based on this voltage characteristic interval and the photovoltaic system's topology, the system fault location and fault type are determined, thus avoiding misjudgments. Attached Figure Description

[0044] Figure 1 This is a flowchart illustrating the first embodiment of the fault location method for a photovoltaic system according to the present invention.

[0045] Figure 2 This is a schematic diagram of the photovoltaic system of the present invention;

[0046] Figure 3 This is a schematic diagram of the topology of the photovoltaic system of the present invention;

[0047] Figure 4 This is a schematic diagram of the structure of the fault location device for the photovoltaic system involved in the embodiment of the present invention.

[0048] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. The accompanying drawings are only one embodiment and not the entirety of the invention. Detailed Implementation

[0049] With the development of solar photovoltaic power generation, the capacity of photovoltaic power generation systems is constantly expanding, and the types of system failures are also becoming more diversified. Traditional fault location methods can no longer meet the needs of the ever-evolving systems, making a technical means to quickly and accurately locate the position and type of failure in a photovoltaic system particularly important.

[0050] Current fault location methods involve acquiring the input voltage of the DC-DC converter, calculating the midpoint voltage vector using Fourier transform or wavelet transform algorithms, and then identifying the fault type based on the characteristics of the midpoint voltage vector using an inherent fault discrimination algorithm. However, Fourier transform is insufficient for processing nonlinear, non-stationary signals (i.e., signals whose frequency changes over time), and it can only obtain the overall frequency components of a signal without knowing the timing of each component's occurrence. Wavelet transform algorithms require manual selection of the wavelet basis, which is difficult in practical engineering. Due to the constraint that a signal cannot be too concentrated in both the time and frequency domains, improving time accuracy often comes at the expense of frequency accuracy. Therefore, wavelet transform is not the optimal solution for handling abrupt signals like faults. Furthermore, traditional fault location algorithms have limitations; novel faults cannot be quickly and accurately identified using traditional fault judgment algorithms, leading to frequent misjudgments. Misjudging novel fault characteristics can even affect the stability of the entire system. Most research on the location of novel faults assumes that the fault characteristics are consistent, ignoring the parameter differences between different installation locations of similar equipment within the same photovoltaic system.

[0051] To address the issues of novel fault types and location misjudgments mentioned above, this application proposes a fault location method for photovoltaic systems. This method involves acquiring the input voltages of the DC-DC converter and the photovoltaic inverter, determining their respective normal state voltage sets and fault type voltage sets based on their input voltages, then determining their respective first midpoint voltage vectors based on their normal state voltage sets, and their respective second midpoint voltage vectors based on their respective fault type voltage sets. A voltage characteristic interval is then determined based on the corresponding first and second midpoint voltage vectors. Finally, based on this voltage characteristic interval and the photovoltaic system topology, the method performs system fault location and fault type judgment, thus avoiding misjudgments.

[0052] In addition, this application uses the Hilbert-Huang transform algorithm to calculate the midpoint voltage vector, which can effectively improve the accuracy of the midpoint voltage vector at the time of the fault, making the obtained data samples more stable and accurate.

[0053] In addition, this application also uses the Support Vector Machine (SVM) machine learning algorithm. By training with data samples at the time of failure and then continuously optimizing the algorithm with data samples, the fault can be located quickly and accurately.

[0054] To better understand the above technical solutions, exemplary embodiments of this disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of this disclosure to those skilled in the art.

[0055] like Figure 2 As shown, this application provides a photovoltaic system comprising: a photovoltaic array, a DC-DC converter (i.e., a DC-DC inverter), a DC-AC converter (i.e., a photovoltaic inverter), and cables connected to the photovoltaic array. The photovoltaic array is connected to the DC-DC converter, which has a capacitor connected in parallel. The DC-AC converter also has a capacitor connected in parallel. The photovoltaic array converts solar energy into electrical energy, outputting a DC voltage. This DC voltage is then used for maximum power point tracking (MPPT) control via the DC-DC converter. The output of the DC-DC circuit is connected to a DC bus with a voltage of several hundred volts via cables. Finally, the DC-AC converter converts the DC voltage into three-phase AC voltage.

[0056] like Figure 1 As shown, in the first embodiment of this application, the fault location method for a photovoltaic system is applied to a fault location device for a photovoltaic system. Specifically, the fault location method for a photovoltaic system includes the following steps:

[0057] Step S110: Obtain the first input voltage of the DC-DC converter and the second input voltage of the photovoltaic inverter.

[0058] In this embodiment, the DC-DC converter, also known as a DC-DC converter, is a DC conversion device that transforms a DC base power supply into other voltage types. The photovoltaic inverter, also known as a DC-AC converter, is an inverter that converts the variable DC voltage generated by a photovoltaic array into AC power at the mains frequency. This AC power can be fed back to the commercial power transmission system or used by off-grid power equipment.

[0059] Optionally, the first input voltage is the output voltage of the photovoltaic array, and the first input voltage of the DC-DC converter can be determined based on the output voltage of the photovoltaic array; the second input voltage is essentially the output loop voltage of the DC-DC converter, and the second input voltage of the photovoltaic inverter can be determined based on the output loop voltage of the DC-DC converter. Optionally, the first input voltage and the second input voltage for a preset duration can be obtained to increase the amount of sample data and improve the accuracy of subsequent fault location.

[0060] Step S120: Determine the normal state voltage set and the fault type voltage set based on the first input voltage and the second input voltage.

[0061] In this embodiment, after obtaining the first input voltage of the DC-DC converter and the second input voltage of the photovoltaic inverter, the first input voltage of the DC-DC converter and the second input voltage of the photovoltaic inverter can be analyzed to obtain the normal state voltage set and the fault type voltage set.

[0062] Optionally, the first input voltage of the DC-DC converter and the second input voltage of the photovoltaic inverter can be analyzed separately to obtain the normal state voltage set and fault type voltage set corresponding to the DC-DC converter, and the normal state voltage set and fault type voltage set corresponding to the photovoltaic inverter.

[0063] Optionally, the analysis processes for the DC-DC converter and the photovoltaic inverter are independent. The first input voltage of the DC-DC converter can be analyzed to obtain a first normal state voltage set and a first fault type voltage set corresponding to the DC-DC converter; similarly, the second input voltage of the photovoltaic inverter can be analyzed to obtain a second normal state voltage set and a second fault type voltage set corresponding to the photovoltaic inverter. Then, a normal state voltage set is generated based on the first and second normal state voltage sets, and a fault type voltage set is generated based on the first and second fault type voltage sets.

[0064] Optionally, cluster analysis can be performed on the first input voltage to obtain a first normal state voltage set corresponding to the DC-DC converter; and cluster analysis can be performed on the second input voltage of the photovoltaic inverter to obtain a second normal state voltage set corresponding to the photovoltaic inverter; thereby obtaining a normal state voltage set based on the first normal state voltage set and the second normal state voltage set.

[0065] Optionally, outlier analysis can be performed on the first input voltage to obtain a first outlier voltage set corresponding to the DC-DC converter; a first fault type voltage set can be generated based on the first outlier voltage set; and outlier analysis can be performed on the second input voltage to obtain a second outlier voltage set corresponding to the photovoltaic inverter; a second fault type voltage set can be generated based on the second outlier voltage set; thus, a fault type voltage set is obtained based on the first fault type voltage set and the second fault type voltage set.

[0066] Optionally, during the process of generating a first fault type voltage set based on the first outlier voltage set and a second fault type voltage set based on the second outlier voltage set, the voltage characteristics in the outlier voltage sets can be analyzed to derive the fault type voltage sets. Specifically, the first voltage characteristic corresponding to the first outlier voltage set and the second voltage characteristic corresponding to the second outlier voltage set can be determined; the first fault type voltage set corresponding to the DC-DC converter can be determined based on the first voltage characteristic, and the second fault type voltage set corresponding to the photovoltaic inverter can be determined based on the second voltage characteristic. For example, if the grid voltage and frequency are too low or too high, it is a grid error fault; if the photovoltaic system's insulation resistance to ground is less than 2 megohms, it is an isolation fault. Each fault type has its corresponding voltage characteristics. When the photovoltaic power generation system is operating normally, this voltage characteristic is an interval, not a constant value. This application can use the Support Vector Machine (SVM) algorithm to train the boundary interface through data samples, optimize the local optimum, and obtain the global optimum. Using the SVM machine learning algorithm, through training with data samples at the fault time and then continuously optimizing the algorithm with data samples, the fault can be located quickly and accurately.

[0067] Step S130: Determine the first midpoint voltage vector corresponding to the normal state voltage set, and determine the second midpoint voltage vector corresponding to the fault type voltage set;

[0068] In this embodiment, the midpoint voltage vector of the DC-DC converter is the voltage to ground at the upper end of the second capacitor connected in parallel across the two ends of the DC-DC converter. The midpoint voltage vector of the photovoltaic inverter is the voltage to ground at the upper end of the capacitor connected in parallel across the photovoltaic inverter. The corresponding midpoint voltage vectors can be obtained by performing Hilbert-Huang transforms on the normal state voltage sets of the DC-DC converter and the fault type voltage sets at the time of the fault, respectively.

[0069] Optionally, the voltage signals in the normal state voltage set and the voltage signals in the fault type voltage set can be processed by Hilbert-Huang transform respectively to generate a first midpoint voltage vector corresponding to the normal state voltage set and a second midpoint voltage vector corresponding to the fault type voltage set.

[0070] Optionally, Hilbert-Huang transforms can be performed on the first normal-state voltage set corresponding to the DC-DC converter and the second normal-state voltage set corresponding to the photovoltaic inverter to obtain the midpoint voltage vectors of the first and second normal-state voltage sets respectively; then, a first midpoint voltage vector is generated based on the midpoint voltage vectors of the first and second normal-state voltage sets. Similarly, Hilbert-Huang transforms can be performed on the first fault-state voltage set corresponding to the DC-DC converter and the second fault-state voltage set corresponding to the photovoltaic inverter to obtain the midpoint voltage vectors of the first and second fault-state voltage sets respectively; then, a second midpoint voltage vector is generated based on the midpoint voltage vectors of the first and second fault-state voltage sets.

[0071] Optionally, the voltage signals in the normal state voltage set and the voltage signals in the fault type voltage set can be processed by Hilbert-Huang transform to obtain instantaneous amplitude, instantaneous phase and instantaneous frequency; and the first midpoint voltage vector corresponding to the normal state voltage set and the second midpoint voltage vector corresponding to the fault type voltage set can be generated according to the instantaneous amplitude, instantaneous phase and instantaneous frequency.

[0072] Specifically, suppose a voltage signal s(t) is expressed using the Hilbert-Huang transform formula: The analytic signal of the original voltage signal is obtained as: z(t)=s(t)+jH[s(t)] (analytic signal). Then, based on this analytic signal and the Hilbert-Huang transform formula, the following can be calculated:

[0073] Calculate the instantaneous amplitude:

[0074] Calculate the instantaneous phase:

[0075] Calculate the instantaneous frequency:

[0076] The instantaneous amplitude, instantaneous phase, and instantaneous frequency corresponding to the normal state voltage set can be calculated using the above method. Then, a first midpoint voltage vector corresponding to the normal state voltage set can be formed based on these instantaneous amplitude, instantaneous phase, and instantaneous frequency. This first midpoint voltage vector can be the midpoint voltage vector corresponding to the first normal state voltage set for a DC-DC converter, or it can be the midpoint voltage vector corresponding to the second normal state voltage set for a photovoltaic inverter. Similarly, the instantaneous amplitude, instantaneous phase, and instantaneous frequency corresponding to the fault type voltage set can be calculated using the above method. Then, a second midpoint voltage vector corresponding to the fault state voltage set can be formed based on these instantaneous amplitude, instantaneous phase, and instantaneous frequency. This second midpoint voltage vector can be the midpoint voltage vector corresponding to the first fault state voltage set for a DC-DC converter, or it can be the midpoint voltage vector corresponding to the second fault state voltage set for a photovoltaic inverter.

[0077] In summary, this application uses the Hilbert-Huang transform algorithm to calculate the midpoint voltage vector, which can effectively improve the accuracy of the voltage vector at the fault moment, and the obtained data samples are more stable and accurate.

[0078] Step S140: Determine the voltage characteristic range based on the first midpoint voltage vector and the second midpoint voltage vector.

[0079] In this embodiment, after determining the first midpoint voltage vector and the second midpoint voltage vector, a fault identification model can be further constructed using the support vector machine (SVM) algorithm to obtain a voltage feature range that avoids fault misjudgment.

[0080] Optionally, the obtained first midpoint voltage vector under normal conditions can be used as a data modeling model. The Support Vector Machine (SVM) algorithm can be applied, and the obtained second midpoint voltage vector at the fault moment can be used as a training and testing sample for the fault identification model. By using the SVM machine learning algorithm, and through training with fault moment data samples and continuous data sample optimization, the fault can be located quickly and accurately.

[0081] Optionally, the hyperplane can be determined first based on the first midpoint voltage vector. Specifically, the instantaneous amplitude, instantaneous phase, and instantaneous frequency of the first midpoint voltage vector corresponding to the normal-state voltage set of the DC-DC converter after Hilbert-Huang transform can be selected as support vectors. The optimal classification line, called the hyperplane, is found through the support vectors. Next, after determining the hyperplane, the upper and lower boundary interfaces of the hyperplane are determined based on the second midpoint voltage vector. Specifically, after determining the hyperplane, two parallel lines passing through the support vectors and parallel to the decision surface can be defined as boundary interfaces, namely the upper boundary interface and the lower boundary interface. Finally, the voltage characteristic interval can be determined based on the region between the upper and lower boundary interfaces. Among them, the sample data corresponding to the upper boundary interface or the lower boundary interface can be used to determine the fault location.

[0082] Optionally, determining the upper and lower boundary interfaces of the hyperplane based on the second midpoint voltage vector can specifically involve: determining the distance between the hyperplane and the boundary interfaces based on the second midpoint voltage vector; and, when the distance meets a certain condition, determining the upper and lower boundary interfaces of the hyperplane based on the distance, wherein the distance between the upper boundary interface and the hyperplane is equal to the distance between the lower boundary interface and the hyperplane. The condition for satisfying the distance can be predetermined based on each fault type or each device.

[0083] Among them, the hyperplane is represented by w. T x+b=0 represents the distance between the hyperplane and the boundary interface: in, And the upper boundary interface is The lower boundary interface is

[0084] Optionally, the midpoint voltage vector corresponding to each fault type, including the midpoint voltage vectors corresponding to both photovoltaic inverters and DC-DC converters, can be used as training samples. The fault identification model is trained according to the fault type and fault location, obtaining the optimal upper and lower boundary interfaces, i.e., the voltage characteristic interval. For example, 60% of the midpoint voltage vectors corresponding to the fault types of DC-DC converters can be selected as training samples. The fault identification model is trained according to the fault type and fault location, obtaining the distances between the upper and lower boundary interfaces and the hyperplane, i.e., the voltage characteristic interval corresponding to that fault type. The remaining 40% of the data samples are then used as test samples to test the fault identification model. Similarly, 60% of the midpoint voltage vectors corresponding to the fault types of photovoltaic inverters can be selected as training samples. The fault identification model is trained according to the fault type and fault location, obtaining the distances between the upper and lower boundary interfaces and the hyperplane, i.e., the voltage characteristic interval corresponding to that fault type. The remaining 40% of the data samples are then used as test samples to test the fault identification model.

[0085] Step S150: Determine the fault location and fault type based on the voltage characteristic range and the topology of the photovoltaic system.

[0086] In this embodiment, after determining the voltage characteristic range, i.e., after training the model, the fault location and fault type can be determined by combining the current photovoltaic system topology. Specifically, the fault location is determined based on the characteristics of the incoming and outgoing line voltages within the topology, further pinpointing the fault location.

[0087] Optionally, the input and output voltages of the DC-DC converter and the photovoltaic inverter can be determined separately according to the topology of the photovoltaic system; a dataset corresponding to the input and output voltages can be generated; and the fault location and fault type can be determined based on the dataset and voltage characteristic intervals. The input and output voltages can be those of the DC-DC converter or the photovoltaic inverter. The voltage characteristic intervals corresponding to these input and output voltages are determined, thereby identifying the fault location and fault type.

[0088] Optionally, the dataset above the upper boundary interface or below the lower boundary interface is considered the fault location. Specifically, the datasets corresponding to the upper boundary interface (greater than the voltage characteristic range) and / or the lower boundary interface (less than the voltage characteristic range) can be determined; the fault location and fault type are determined based on the datasets. By using a trained model and based on the basic topology and voltage characteristic range of the photovoltaic power generation system, system fault location and fault type determination are performed to avoid misjudgment of system faults.

[0089] Optionally, the fault location of the photovoltaic system in this application may be at least one of the following: the DC-DC converter, the photovoltaic array, the line cable, and the photovoltaic inverter; that is, the fault location may be one or more locations. For example, refer to... Figure 3 The diagram shows the topology of a photovoltaic system. If the photovoltaic inverter 1 collects abnormal input voltage data from line 2 and the system determines it to be a fault, and the DC-DC converter 2 collects abnormal data and the system determines it to be a fault, then the fault location can be determined to be on the photovoltaic module 2 side; if the photovoltaic inverter 1 collects abnormal input voltage data from line 2 and the system determines it to be a fault, and the DC-DC converter 2 collects normal data, then the fault location can be determined to be on the line 2 side.

[0090] This embodiment, based on the aforementioned technical solution, obtains the input voltages of the DC-DC converter and the photovoltaic inverter, and determines their respective normal state voltage sets and fault type voltage sets based on these input voltages. Then, it determines the first midpoint voltage vector based on the normal state voltage set and the second midpoint voltage vector based on the fault type voltage set. A voltage characteristic interval is determined based on the first and second midpoint voltage vectors. Finally, based on this voltage characteristic interval and the photovoltaic system topology, system fault location and fault type are determined, avoiding misjudgments. Furthermore, using the Hilbert-Huang transform algorithm to calculate the midpoint voltage vector effectively improves the accuracy of the midpoint voltage vector at the fault moment, making the obtained data samples more stable and accurate. In addition, by using the Support Vector Machine (SVM) machine learning algorithm, through training with fault-time data samples and continuous data sample optimization, fault location can be quickly and accurately achieved.

[0091] like Figure 4 As shown, Figure 4 This is a schematic diagram of the hardware operating environment involved in the embodiments of the present invention.

[0092] It should be noted that, Figure 4 This can be a schematic diagram of the hardware operating environment of the fault location device for a photovoltaic system.

[0093] like Figure 4As shown, the fault location device for this photovoltaic system may include: a processor 1001, such as a CPU; a memory 1005; a user interface 1003; a network interface 1004; and a communication bus 1002. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may optionally include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed RAM or a stable, non-volatile memory, such as a disk drive. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0094] Those skilled in the art will understand that Figure 4 The fault location device structure of the photovoltaic system shown in the figure does not constitute a limitation on the fault location device of the photovoltaic system. It may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0095] like Figure 4 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a fault location program for the photovoltaic system. The operating system is a program that manages and controls the hardware and software resources of the photovoltaic system's fault location device, as well as the operation of the photovoltaic system's fault location program and other software or programs.

[0096] exist Figure 4 In the fault location device of the photovoltaic system shown, the user interface 1003 is mainly used to connect to the terminal and communicate with the terminal; the network interface 1004 is mainly used to connect to the back-end server and communicate with the back-end server; the processor 1001 can be used to call the fault location program of the photovoltaic system stored in the memory 1005.

[0097] In this embodiment, the photovoltaic system fault location device includes: a memory 1005, a processor 1001, and a photovoltaic system fault location program stored in the memory and executable on the processor, wherein:

[0098] When processor 1001 calls the fault location program for the photovoltaic system stored in memory 1005, it performs the following operations:

[0099] Obtain the first input voltage of the DC-DC converter and the second input voltage of the photovoltaic inverter;

[0100] Determine the normal state voltage set and the fault type voltage set based on the first input voltage and the second input voltage;

[0101] Determine the first midpoint voltage vector corresponding to the normal state voltage set, and determine the second midpoint voltage vector corresponding to the fault type voltage set;

[0102] The voltage characteristic range is determined based on the first midpoint voltage vector and the second midpoint voltage vector;

[0103] The fault location and fault type are determined based on the voltage characteristic range and the topology of the photovoltaic system.

[0104] When processor 1001 calls the fault location program for the photovoltaic system stored in memory 1005, it also performs the following operations:

[0105] Cluster analysis is performed on the first input voltage and the second input voltage respectively to obtain the first normal state voltage set corresponding to the DC-DC converter and the second normal state voltage set corresponding to the photovoltaic inverter.

[0106] The normal state voltage set is generated based on the first normal state voltage set and the second normal state voltage set.

[0107] When processor 1001 calls the fault location program for the photovoltaic system stored in memory 1005, it also performs the following operations:

[0108] Outlier analysis is performed on the first input voltage and the second input voltage respectively to obtain the first outlier voltage set corresponding to the DC-DC converter and the second outlier voltage set corresponding to the photovoltaic inverter;

[0109] A first fault type voltage set is generated based on the first outlier voltage set, and a second fault type voltage set is generated based on the second outlier voltage set;

[0110] The fault type voltage set is determined based on the first fault type voltage set and the second fault type voltage set.

[0111] When processor 1001 calls the fault location program for the photovoltaic system stored in memory 1005, it also performs the following operations:

[0112] Determine the first voltage feature corresponding to the first outlier voltage set and the second voltage feature corresponding to the second outlier voltage set;

[0113] The first fault type voltage set corresponding to the DC-DC converter is determined based on the first voltage characteristic, and the second fault type voltage set corresponding to the photovoltaic inverter is determined based on the second voltage characteristic.

[0114] When processor 1001 calls the fault location program for the photovoltaic system stored in memory 1005, it also performs the following operations:

[0115] The voltage signals of the normal state voltage set and the voltage signals of the fault type voltage set are processed by Hilbert-Huang transform respectively to obtain the instantaneous amplitude, instantaneous phase and instantaneous frequency;

[0116] The first midpoint voltage vector corresponding to the normal state voltage set and the second midpoint voltage vector corresponding to the fault type voltage set are generated based on the instantaneous amplitude, instantaneous phase, and instantaneous frequency, respectively.

[0117] When processor 1001 calls the fault location program for the photovoltaic system stored in memory 1005, it also performs the following operations:

[0118] The hyperplane is determined based on the first midpoint voltage vector;

[0119] The upper and lower boundary interfaces of the hyperplane are determined based on the second midpoint voltage vector.

[0120] The voltage characteristic range is obtained based on the upper boundary interface and the lower boundary interface.

[0121] When processor 1001 calls the fault location program for the photovoltaic system stored in memory 1005, it also performs the following operations:

[0122] The distance between the hyperplane and the boundary interface is determined based on the second midpoint voltage vector.

[0123] When the distance condition is met, the upper boundary interface and the lower boundary interface of the hyperplane are determined according to the distance, and the distance between the upper boundary interface and the hyperplane is equal to the distance between the lower boundary interface and the hyperplane.

[0124] When processor 1001 calls the fault location program for the photovoltaic system stored in memory 1005, it also performs the following operations:

[0125] The input and output voltages of the DC-DC converter and the photovoltaic inverter are determined according to the topology of the photovoltaic system.

[0126] Generate datasets corresponding to the incoming line voltage and the outgoing line voltage;

[0127] The fault location and fault type are determined based on the dataset and the voltage characteristic range.

[0128] When processor 1001 calls the fault location program for the photovoltaic system stored in memory 1005, it also performs the following operations:

[0129] Determine the datasets corresponding to the upper boundary interface that is greater than the voltage feature interval and / or the lower boundary interface that is less than the voltage feature interval;

[0130] The fault location and fault type are determined based on the dataset.

[0131] When processor 1001 calls the fault location program for the photovoltaic system stored in memory 1005, it also performs the following operations:

[0132] The first input voltage is determined based on the output voltage of the photovoltaic array;

[0133] The second input voltage is determined based on the output loop voltage of the DC-DC converter.

[0134] This invention provides an embodiment of a fault location method for photovoltaic systems. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than that shown here.

[0135] Based on the same inventive concept, this application also provides a computer-readable storage medium storing a fault location program for a photovoltaic system. When the fault location program for the photovoltaic system is executed by a processor, it implements the various steps of the fault location method for the photovoltaic system as described above and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0136] Since the storage medium provided in this application embodiment is the storage medium used to implement the method of this application embodiment, those skilled in the art can understand the specific structure and variations of the storage medium based on the method described in this application embodiment, and therefore will not be repeated here. All storage media used in the method of this application embodiment are within the scope of protection of this application.

[0137] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0138] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0139] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0140] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0141] It should be noted that any reference signs placed between parentheses in the claims should not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0142] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0143] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A fault location method for a photovoltaic system, characterized in that, The method includes: Obtain the first input voltage of the DC-DC converter and the second input voltage of the photovoltaic inverter; Determine the normal state voltage set and the fault type voltage set based on the first input voltage and the second input voltage; The voltage signals in the normal state voltage set and the voltage signals in the fault type voltage set are processed by Hilbert-Huang transform to generate the first midpoint voltage vector corresponding to the normal state voltage set and the second midpoint voltage vector corresponding to the fault type voltage set. The voltage feature interval is determined based on the first midpoint voltage vector and the second midpoint voltage vector. The first midpoint voltage vector is used as a data model to determine the hyperplane, and the second midpoint voltage vector is used as a training and testing sample to train the model to determine the upper and lower boundary interfaces of the hyperplane. The voltage feature interval is obtained based on the upper and lower boundary interfaces. The fault location and fault type are determined based on the voltage characteristic range and the topology of the photovoltaic system.

2. The method as described in claim 1, characterized in that, The normal state voltage set determined based on the first input voltage and the second input voltage includes: Cluster analysis is performed on the first input voltage and the second input voltage respectively to obtain the first normal state voltage set corresponding to the DC-DC converter and the second normal state voltage set corresponding to the photovoltaic inverter. The normal state voltage set is generated based on the first normal state voltage set and the second normal state voltage set.

3. The method as described in claim 1, characterized in that, The fault type voltage set determined based on the first input voltage and the second input voltage includes: Outlier analysis is performed on the first input voltage and the second input voltage respectively to obtain the first outlier voltage set corresponding to the DC-DC converter and the second outlier voltage set corresponding to the photovoltaic inverter; A first fault type voltage set is generated based on the first outlier voltage set, and a second fault type voltage set is generated based on the second outlier voltage set; The fault type voltage set is determined based on the first fault type voltage set and the second fault type voltage set.

4. The method as described in claim 3, characterized in that, The steps of generating a first fault type voltage set based on the first outlier voltage set and generating a second fault type voltage set based on the second outlier voltage set include: Determine the first voltage feature corresponding to the first outlier voltage set and the second voltage feature corresponding to the second outlier voltage set; The first fault type voltage set corresponding to the DC-DC converter is determined based on the first voltage characteristic, and the second fault type voltage set corresponding to the photovoltaic inverter is determined based on the second voltage characteristic.

5. The method as described in claim 1, characterized in that, The step of performing Hilbert-Huang transform processing on the voltage signals in the normal state voltage set and the voltage signals in the fault type voltage set to generate the first midpoint voltage vector corresponding to the normal state voltage set and the second midpoint voltage vector corresponding to the fault type voltage set includes: The voltage signals of the normal state voltage set and the voltage signals of the fault type voltage set are processed by Hilbert-Huang transform respectively to obtain the instantaneous amplitude, instantaneous phase and instantaneous frequency; The first midpoint voltage vector corresponding to the normal state voltage set and the second midpoint voltage vector corresponding to the fault type voltage set are generated based on the instantaneous amplitude, instantaneous phase, and instantaneous frequency, respectively.

6. The method as described in claim 1, characterized in that, The step of determining the voltage characteristic interval based on the first midpoint voltage vector and the second midpoint voltage vector includes: The hyperplane is determined based on the first midpoint voltage vector; The upper and lower boundary interfaces of the hyperplane are determined based on the second midpoint voltage vector. The voltage characteristic range is obtained based on the upper boundary interface and the lower boundary interface.

7. The method as described in claim 6, characterized in that, The step of determining the upper and lower boundary interfaces of the hyperplane based on the second midpoint voltage vector includes: The distance between the hyperplane and the boundary interface is determined based on the second midpoint voltage vector. When the distance condition is met, the upper boundary interface and the lower boundary interface of the hyperplane are determined according to the distance, and the distance between the upper boundary interface and the hyperplane is equal to the distance between the lower boundary interface and the hyperplane.

8. The method as described in claim 6, characterized in that, The steps for determining the fault location and fault type based on the voltage characteristic range and the topology of the photovoltaic system include: The input and output voltages of the DC-DC converter and the photovoltaic inverter are determined according to the topology of the photovoltaic system. Generate datasets corresponding to the incoming line voltage and the outgoing line voltage; The fault location and fault type are determined based on the dataset and the voltage characteristic range.

9. The method as described in claim 8, characterized in that, The step of determining the fault location and fault type based on the dataset and the voltage characteristic range includes: Determine the datasets corresponding to the upper boundary interface that is greater than the voltage feature interval and / or the lower boundary interface that is less than the voltage feature interval; The fault location and fault type are determined based on the dataset.

10. The method as described in claim 1, characterized in that, The steps of obtaining the first input voltage of the DC-DC converter and the second input voltage of the photovoltaic inverter include: The first input voltage is determined based on the output voltage of the photovoltaic array; The second input voltage is determined based on the output loop voltage of the DC-DC converter.

11. A fault location device for a photovoltaic system, characterized in that, The fault location device for the photovoltaic system includes: a memory, a processor, and a fault location program for the photovoltaic system stored in the memory and executable on the processor. When the fault location program for the photovoltaic system is executed by the processor, it implements the steps of the fault location method for the photovoltaic system as described in any one of claims 1-10.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a fault location program for a photovoltaic system, which, when executed by a processor, implements the steps of the fault location method for a photovoltaic system as described in any one of claims 1-10.

Images