CN218734201U - Photovoltaic module fault diagnosis equipment - Google Patents

Abstract

The utility model discloses a photovoltaic module fault diagnosis equipment, include: the device comprises a shell, an inverter interface, a processing device and a display device, wherein the inverter interface and the display device are connected with the processing device, the processing device comprises a current sampling unit, a voltage sampling unit and a diagnosis unit, the current sampling unit is used for acquiring the working current of the photovoltaic component to be detected based on the inverter interface, the voltage sampling unit is used for acquiring the working voltage of the photovoltaic component to be detected based on the inverter interface, and the diagnosis unit is used for analyzing and processing the working current and the working voltage of the photovoltaic component to be detected based on a fault diagnosis model and determining the fault type of the photovoltaic component to be detected; the display device is used for displaying the fault type of the photovoltaic module to be tested. According to the technical scheme, after the photovoltaic module fault diagnosis device is connected with the photovoltaic module to be detected, the accurate fault type is rapidly determined and displayed according to the obtained working current and working voltage of the photovoltaic module to be detected, so that the user can observe conveniently, and the user experience is improved.

Description

Photovoltaic module fault diagnosis equipment

Technical Field

The embodiment of the utility model provides a relate to the photovoltaic technology field, especially relate to a photovoltaic module failure diagnosis equipment.

Background

Photovoltaic power stations are generally established in regions with abundant solar energy resources, such as coastal regions and desert regions, and the environments of these regions are severe, so that photovoltaic modules are easily damaged, the power generation capacity of the photovoltaic power stations is affected, and meanwhile, the user cost is increased. The photovoltaic modules are periodically detected due to the fact that the environments of the photovoltaic modules are complex, the types of generated faults are various, the fault types of the fault photovoltaic modules are determined, fault repairing is conducted on the basis of the fault types, safety of a photovoltaic power station can be improved, and user loss is reduced.

The photovoltaic module fault diagnosis equipment in the prior art comprises an image acquisition device and a processing device, wherein the image acquisition device can acquire image information of a photovoltaic module, and the processing device can determine a faulty photovoltaic module and a fault type of the faulty photovoltaic module based on an image recognition technology.

However, in the prior art, the requirements of acquiring the image information of the photovoltaic module on the image acquisition device and the environment are high, and the image recognition technology can only detect partial surface faults, is difficult to detect internal faults, and has poor fault detection effect.

SUMMERY OF THE UTILITY MODEL

The utility model provides a photovoltaic module fault diagnosis equipment to the realization carries out fault diagnosis to photovoltaic module fast.

The embodiment of the utility model provides a photovoltaic module fault diagnosis equipment, include: the photovoltaic module fault diagnosis device comprises a shell, an inverter interface, a processing device and a display device, wherein the inverter interface and the display device are connected with the processing device, the processing device comprises a current sampling unit, a voltage sampling unit and a diagnosis unit, the current sampling unit is used for acquiring the working current of a photovoltaic module to be detected based on the inverter interface, the voltage sampling unit is used for acquiring the working voltage of the photovoltaic module to be detected based on the inverter interface, and the diagnosis unit is used for analyzing and processing the working current and the working voltage of the photovoltaic module to be detected based on a fault diagnosis model and determining the fault type of the photovoltaic module to be detected; the display device is used for displaying the fault type of the photovoltaic module to be tested.

The utility model discloses technical scheme provides a photovoltaic module failure diagnosis equipment, include: the photovoltaic module fault diagnosis device comprises a shell, an inverter interface, a processing device and a display device, wherein the inverter interface and the display device are connected with the processing device, the processing device comprises a current sampling unit, a voltage sampling unit and a diagnosis unit, the current sampling unit is used for acquiring the working current of a photovoltaic module to be detected based on the inverter interface, the voltage sampling unit is used for acquiring the working voltage of the photovoltaic module to be detected based on the inverter interface, and the diagnosis unit is used for analyzing and processing the working current and the working voltage of the photovoltaic module to be detected based on a fault diagnosis model and determining the fault type of the photovoltaic module to be detected; the display device is used for displaying the fault type of the photovoltaic module to be tested. According to the technical scheme, the photovoltaic module fault diagnosis equipment can be connected with the photovoltaic module to be detected based on the inverter interface, the compatibility of the photovoltaic module fault diagnosis equipment is improved, further, the working current of the photovoltaic module to be detected can be obtained based on the current sampling unit contained by the processing device, the working voltage of the photovoltaic module to be detected is obtained based on the voltage sampling unit contained by the processing device, the working current and the working voltage of the photovoltaic module to be detected are analyzed and processed based on the pre-trained fault diagnosis module arranged in the diagnosis unit contained by the processing device, the fault type of the photovoltaic module to be detected is determined, the accurate fault type of the photovoltaic module to be detected is rapidly determined, of course, after the fault type of the photovoltaic module to be detected is determined by the processing device, the photovoltaic module fault diagnosis equipment can be sent to the display device, the fault type of the photovoltaic module to be detected is displayed based on the display device, the fault type of the photovoltaic module to be detected is convenient for a user to observe, the fault type of the photovoltaic module to be detected, the photovoltaic module fault diagnosis equipment is low in cost, convenient to carry and small in environmental influence, and user experience is further improved.

Further, the current sampling unit is further configured to: and in at least one historical period, acquiring a working current of the photovoltaic module to be detected at preset time intervals based on the inverter interface until a preset number of historical working currents are acquired.

Further, the voltage sampling unit is further configured to: and in at least one historical period, acquiring a working voltage of the photovoltaic module to be tested at preset time intervals based on the inverter interface until a preset number of historical working voltages are acquired.

Further, the processing device further comprises: and the temperature sampling unit is used for acquiring a current temperature value.

Further, the processing apparatus further includes: the illumination sampling unit is used for acquiring the current illumination intensity.

Further, still include: the communication interface is used for being in communication connection with a server so as to send the working current, the working voltage and the fault type of the photovoltaic module to be tested to the server.

Further, the processing device is configured to: and sending a preset number of the historical working currents, a preset number of the historical working voltages and historical fault types corresponding to the historical working currents and the historical working voltages to a server based on the communication interface, so that the server performs model training on a Transformer neural network model by taking the preset number of the historical working currents, the preset number of the historical working voltages and the historical fault types corresponding to the historical working currents and the historical working voltages as a training data set, and the fault diagnosis model is obtained.

Further, still include: the photovoltaic module fault diagnosis device comprises a battery and a charging interface, wherein the battery is used for providing power for the photovoltaic module fault diagnosis device, and the charging interface is used for charging the battery.

Further, the method also comprises the following steps: handles disposed on both sides of the housing.

Further, still include: the heat dissipation device is used for providing a heat dissipation opening so as to reduce the internal temperature of the photovoltaic module fault diagnosis equipment.

The relevant content of the present application will be more concise and understandable in the following description.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.

Fig. 1 is a schematic structural diagram of a photovoltaic module fault diagnosis device provided by an embodiment of the present invention;

fig. 2 is a schematic structural diagram of another photovoltaic module fault diagnosis device provided by an embodiment of the present invention;

fig. 3 is a rear view of another photovoltaic module fault diagnosis apparatus provided by an embodiment of the present invention;

fig. 4 is a side view of another photovoltaic module fault diagnosis apparatus provided by an embodiment of the present invention;

fig. 5 is a schematic view of another processing device in a photovoltaic module fault diagnosis apparatus according to an embodiment of the present invention.

Reference numerals:

110-shell, 120-inverter interface, 130-display device, 140-communication interface, 141-USB interface, 142-serial communication interface, 143-485 communication interface, 150-battery, 160-charging interface, 170-handle and 180-heat dissipation device.

Detailed Description

The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.

The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone.

The terms "first" and "second" and the like in the description and drawings of the present application are used for distinguishing different objects or for distinguishing different processes for the same object, and are not used for describing a specific order of the objects.

Furthermore, the terms "including" and "having," and any variations thereof, as referred to in the description of the present application, are intended to cover non-exclusive inclusions. For example, a process, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements but may include other steps or elements not expressly listed or inherent to such process, system, article, or apparatus.

It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described herein as "exemplary" or "e.g.," is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "such as" is intended to present concepts related in a concrete fashion.

In the description of the present application, the meaning of "a plurality" means two or more unless otherwise specified.

Fig. 1 is the embodiment of the utility model provides a structural schematic diagram of photovoltaic module failure diagnosis equipment, this embodiment is applicable in the condition that needs carry out quick failure diagnosis to photovoltaic module, as shown in fig. 1, photovoltaic module failure diagnosis equipment includes: the photovoltaic module failure diagnosis device comprises a shell 110, an inverter interface 120, a processing device and a display device 130, wherein the processing device is arranged inside the shell 110 of the photovoltaic module failure diagnosis device and is not shown in fig. 1. The inverter interface 120 and the display device 130 are both connected to the processing device, the processing device includes a current sampling unit, a voltage sampling unit, and a diagnosis unit, the current sampling unit is configured to obtain a working current of a photovoltaic module to be detected based on the inverter interface, the voltage sampling unit is configured to obtain a working voltage of the photovoltaic module to be detected based on the inverter interface, and the diagnosis unit is configured to analyze and process the working current and the working voltage of the photovoltaic module to be detected based on a fault diagnosis model, and determine a fault type of the photovoltaic module to be detected; the display device 120 is configured to display the fault type of the photovoltaic module to be tested.

The housing 110 is a support of the photovoltaic module fault diagnosis device, the inverter interface 120 is disposed on a first side of the housing and connected with the processing device, and the display device 130 is disposed on a top surface of the housing and connected with the processing device.

In order to realize the fault diagnosis of the photovoltaic module, the internal hardware of the photovoltaic module fault diagnosis device is a key component. After the photovoltaic module fault diagnosis device is connected to the photovoltaic module to be detected through the inverter interface 120, the working current of the photovoltaic module to be detected can be obtained based on the current sampling unit included in the processing device, the working current is sent to the diagnosis unit included in the processing device, the working voltage of the photovoltaic module to be detected can be obtained based on the voltage sampling unit included in the processing device, the working voltage is sent to the diagnosis unit included in the processing device, the diagnosis unit can analyze and process the working current and the working voltage of the photovoltaic module to be detected based on a built-in pre-trained fault diagnosis model, label information corresponding to the working current and the working voltage is determined, the diagnosis unit can also determine the fault type of the photovoltaic module to be detected according to the label information corresponding to the working current and the working voltage of the photovoltaic module to be detected, of course, the processing device can send the fault type of the photovoltaic module to be detected to the display device 130 to display the fault type of the photovoltaic module to be detected.

After the photovoltaic module fault diagnosis device is connected to the photovoltaic module to be detected through the inverter interface 120, the photovoltaic module fault diagnosis device can be started to obtain working current and working voltage, and determine the fault type of the photovoltaic module to be detected according to the working current and the working voltage, so that the more accurate fault type of the photovoltaic module to be detected can be quickly determined, and the photovoltaic module fault diagnosis device has the advantages of stronger compatibility with the photovoltaic module to be detected, lower cost, convenience in carrying and less environmental influence.

The embodiment of the utility model provides a photovoltaic module failure diagnosis equipment, include: the photovoltaic module fault diagnosis device comprises a shell, an inverter interface, a processing device and a display device, wherein the inverter interface and the display device are connected with the processing device, the processing device comprises a current sampling unit, a voltage sampling unit and a diagnosis unit, the current sampling unit is used for acquiring the working current of a photovoltaic module to be detected based on the inverter interface, the voltage sampling unit is used for acquiring the working voltage of the photovoltaic module to be detected based on the inverter interface, and the diagnosis unit is used for analyzing and processing the working current and the working voltage of the photovoltaic module to be detected based on a fault diagnosis model and determining the fault type of the photovoltaic module to be detected; the display device is used for displaying the fault type of the photovoltaic module to be tested. According to the technical scheme, the photovoltaic module fault diagnosis equipment can be connected with the photovoltaic module to be detected based on the inverter interface, the compatibility of the photovoltaic module fault diagnosis equipment is improved, further the working current of the photovoltaic module to be detected can be obtained based on the current sampling unit contained in the processing device, the working voltage of the photovoltaic module to be detected is obtained based on the voltage sampling unit contained in the processing device, the working current and the working voltage of the photovoltaic module to be detected are analyzed and processed based on the pre-trained fault diagnosis module arranged in the diagnosis unit contained in the processing device, the label information corresponding to the working current and the working voltage is determined, the fault type of the photovoltaic module to be detected is determined according to the label information corresponding to the working current and the working voltage of the photovoltaic module to be detected, the accurate fault type of the photovoltaic module to be detected is rapidly determined, certainly, the processing device can send the fault type of the photovoltaic module to be detected to the display device after the fault type of the photovoltaic module to be detected is determined, the fault diagnosis equipment of the photovoltaic module to be detected can display the fault type of the photovoltaic module to be detected based on the display device, the photovoltaic module is convenient for a user to observe the fault type of the photovoltaic module to be detected, the photovoltaic module, the fault diagnosis equipment of the photovoltaic module to be detected, the photovoltaic module is low in cost and convenient to carry, the user is less influenced by the environment, and further, and the experience of the photovoltaic module is improved.

Fig. 2 is a schematic structural diagram of another photovoltaic module fault diagnosis device provided by the embodiment of the present invention, fig. 3 is a rear view of another photovoltaic module fault diagnosis device provided by the embodiment of the present invention, fig. 4 is a side view of another photovoltaic module fault diagnosis device provided by the embodiment of the present invention, and fig. 5 is a schematic diagram of a processing apparatus in another photovoltaic module fault diagnosis device provided by the embodiment of the present invention, and this embodiment is embodied on the basis of the above-mentioned embodiment. As shown in fig. 2, in the present embodiment, the photovoltaic module fault diagnosis apparatus may include: the housing 110, the inverter interface 120, the processing device, the display device 130, and the communication interface 140 may further include a battery 150 and a charging interface 160 as shown in fig. 3, and may further include a handle 170 and a heat sink 180 as shown in fig. 4. Likewise, the processing device is disposed inside the housing 110 of the photovoltaic module failure diagnosis apparatus, which is not shown in fig. 2. The inverter interface 120 and the display device 130 are both connected to the processing device. As shown in fig. 5, the processing apparatus includes a current sampling unit, a voltage sampling unit, a diagnosis unit, a temperature sampling unit, and an illumination sampling unit, where the current sampling unit is configured to obtain a working current of a to-be-detected photovoltaic module based on the inverter interface 120, the voltage sampling unit is configured to obtain a working voltage of the to-be-detected photovoltaic module based on the inverter interface 120, the temperature sampling unit is configured to obtain a current temperature value, the illumination sampling unit is configured to obtain a current illumination, and the diagnosis unit is configured to analyze the working current and the working voltage of the to-be-detected photovoltaic module based on a fault diagnosis model, so as to determine a fault type of the to-be-detected photovoltaic module; the display device 130 is used for displaying the fault type of the photovoltaic module to be tested; the communication interface 140 is configured to be in communication connection with a server, so as to send the working current, the working voltage, and the fault type of the photovoltaic module to be tested to the server; the battery 150 is used for providing power for the photovoltaic module fault diagnosis device, and the charging interface 160 is used for charging the battery; the handles 170 are disposed at both sides of the housing; the heat sink 180 is used to provide a heat sink to lower the internal temperature of the photovoltaic module fault diagnosis apparatus.

The housing 110 is a support for a photovoltaic module fault diagnostic device that may include three sets of inverter interfaces 120, each set of inverter interfaces 120 being disposed on a first side of the housing. Namely, the photovoltaic module fault diagnosis device can be connected with three photovoltaic modules to be detected simultaneously so as to respectively determine the fault types of the three photovoltaic modules to be detected.

The current sampling unit is a current sampling circuit, the voltage sampling unit is a voltage sampling circuit, the diagnosis unit is a main control module, the MCIMX6Y2CVM08AB model of an ARM processor can be specifically selected, the temperature sampling unit is a temperature sampling circuit, and the illumination sampling unit is an illumination sampling circuit.

The current sampling circuit is used for acquiring the working current of the photovoltaic component to be detected based on the inverter interface, the voltage sampling circuit is used for acquiring the working voltage of the photovoltaic component to be detected based on the inverter interface, the main control MCU module is used for analyzing and processing the working current and the working voltage of the photovoltaic component to be detected based on a built-in pre-trained fault diagnosis model, label information corresponding to the working current and the working voltage is determined, and the fault type of the photovoltaic component to be detected is determined according to the label information corresponding to the working current and the working voltage of the photovoltaic component to be detected. The main control module may also determine a repair suggestion according to the fault type of the photovoltaic module to be tested, and send the repair suggestion to the display device, so that the display device 130 displays the repair suggestion corresponding to the fault type of the photovoltaic module to be tested.

The temperature sampling circuit is used for obtaining a current temperature value, and the illumination sampling circuit is used for obtaining current illumination intensity.

The photovoltaic module fault diagnosis apparatus further includes a communication interface 140, the communication interface 140 being disposed on a second side of the housing adjacent to the first side. The communication interface 140 includes at least one of a USB interface 141, a serial communication interface 142, and a 485 communication interface 143, the communication interface 140 is connected to the main control module through a communication unit included in the processing device, and is connected to the server in a communication manner, and the communication interface 140 can send the working current, the working voltage, and the fault type of the photovoltaic module to be tested to the server.

The photovoltaic module fault diagnosis device further comprises a battery 150 and a charging interface 160, the battery is arranged in a battery groove of a third side face, adjacent to the first side face and opposite to the second side face, of the shell 110, the charging interface 160 is electrically connected with the battery 150, the charging interface 160 is used for being connected with a charging device to charge the battery 150 in the battery groove, and the battery 150 is used for supplying power to the photovoltaic module fault diagnosis device. Of course, the charging interface 160 may also directly supply power to the photovoltaic module fault diagnosis device.

As shown in fig. 4, the photovoltaic module fault diagnosis apparatus further includes handles 170, the handles 170 are disposed on the second side and the third side of the housing 110, and the handles 170 facilitate a user to carry the photovoltaic module fault diagnosis apparatus. The photovoltaic module fault diagnosis apparatus further includes a heat sink 180, and the heat sink 180 may be disposed at a third side of the housing 110 for providing a heat sink to lower an internal temperature of the photovoltaic module fault diagnosis apparatus.

Of course, the photovoltaic module fault diagnosis device may further include a mechanical switch disposed on the top surface of the housing, a key and an indicator light, the mechanical switch may be configured to turn on or turn off the photovoltaic module fault diagnosis device, the key includes an "up" key, a "down" key, a "left" key, a "right" key, an "ok" key and a "cancel" key, and is configured to perform human-computer interaction, the indicator light may include a work indicator light and a communication indicator light, the communication indicator light may include a wireless communication indicator light and a wired communication indicator light, when the photovoltaic module fault diagnosis device may normally operate, the work indicator light displays based on the first display mode, when the photovoltaic module fault diagnosis device may normally perform wireless communication, the wireless communication indicator light displays based on the second display mode, when the photovoltaic module fault diagnosis device may normally perform wired communication, the wired communication indicator light displays based on the third display mode.

The photovoltaic module fault diagnosis apparatus may further include a tool box disposed at the second side of the housing 110 for receiving a general photovoltaic module maintenance tool.

The processing device further comprises a charging unit, a heat dissipation unit, a communication unit, a display unit, a key unit, an indicator light unit and a storage unit, wherein the charging unit can be a charging circuit, the heat dissipation unit can be a heat dissipation circuit, the communication unit can be a communication circuit, the display unit can be a display circuit, the key unit can be a key circuit, the indicator light unit can be an indicator light circuit, the storage unit can be a storage circuit, and the communication circuit comprises at least one of a USB communication circuit, a serial communication circuit, a wireless communication circuit and a 485 communication circuit. The charging circuit is used for connecting the charging interface and the battery, the communication circuit is used for connecting the communication interface and the processing device, the display circuit is used for connecting the display device and the processing device, the key circuit is used for connecting the key and the processing device, the indicator light circuit is used for connecting the indicator light and the processing device, and the storage circuit is used for connecting the processing device and also used for storing data so as to store a working circuit, working voltage and fault type of the photovoltaic module to be tested.

Table 1 shows technical specification parameters of the photovoltaic module fault diagnosis device, and as shown in table 1, the photovoltaic module fault diagnosis device can meet detection requirements of a wider range of photovoltaic modules.

TABLE 1 technical Specification parameter Table of diagnostic apparatus

Further, the current sampling unit is further configured to: and in at least one historical period, acquiring one working current of the photovoltaic module to be detected at preset time intervals on the basis of the inverter interface until a preset number of historical working currents are acquired.

Further, the voltage sampling unit is further configured to: and in at least one historical period, acquiring a working voltage of the photovoltaic module to be tested at preset time intervals based on the inverter interface until a preset number of historical working voltages are acquired.

Further, the processing device is configured to: and sending a preset number of the historical working currents, a preset number of the historical working voltages and historical fault types corresponding to the historical working currents and the historical working voltages to a server based on the communication interface, so that the server performs model training on a Transformer neural network model by taking the preset number of the historical working currents, the preset number of the historical working voltages and the historical fault types corresponding to the historical working currents and the historical working voltages as a training data set, and the fault diagnosis model is obtained.

Specifically, the current sampling unit can obtain a working current of the photovoltaic module to be tested at preset time intervals in at least one historical period of at least one sampling point until a preset number of historical working currents are obtained; the voltage sampling unit can obtain a working voltage of the photovoltaic module to be tested at preset time intervals in at least one historical period of at least one sampling point until a preset number of historical working voltages are obtained.

The history time period may be a time period before and after the history time, for example, the history time period may be five minutes before 9 o 'clock and five minutes after 9 o' clock, five minutes before 13 o 'clock and five minutes after 13 o' clock, five minutes before 16 o 'clock and five minutes after 16 o' clock. Therefore, 2000 sets of the historical operating current and the historical operating voltage can be randomly acquired within ten minutes of five minutes before 9 dots and five minutes after 9 dots, within ten minutes of five minutes before 13 dots and five minutes after 13 dots, within five minutes before 16 dots and within ten minutes after 16 dots, and 6000 sets of the historical operating voltage and the historical operating current can be acquired in total. In order to ensure the diversity of the historical operating voltage and the historical operating current, the historical operating voltage and the historical operating current can be obtained at a plurality of photovoltaic modules, that is, 2000 groups of historical operating current and historical operating voltage can be randomly obtained at three photovoltaic modules within ten minutes of five minutes before 9 points and five minutes after 9 points, within ten minutes of five minutes before 13 points and five minutes after 13 points, within five minutes before 16 points and within ten minutes after 16 points and five minutes, and then 18000 groups of historical operating current and historical operating voltage can be obtained.

Further, the processing device may transmit a preset number of historical operating currents, a preset number of historical operating voltages, and historical fault types corresponding to the historical operating currents and the historical operating voltages to the server based on the communication interface.

The server can input the historical working current into a pre-trained data filtering model so that the data filtering model performs cluster analysis on the historical working current to divide the historical working current into normal current data and abnormal current data and determine the normal current data as target historical working current; inputting the historical working voltage into a pre-trained data filtering model so that the data filtering model performs cluster analysis on the historical working voltage, so that the historical working voltage is divided into normal voltage data and abnormal low-voltage data, and the normal voltage data is determined as target historical working voltage.

The acquired historical working current and historical working voltage may have abnormal data, so that the historical working current can be filtered based on the data filtering model to obtain the target historical working current, and the historical working voltage can be filtered based on the data filtering model to obtain the target historical working voltage.

The data filtering model is an abnormal data filtering model constructed by a density-based clustering algorithm DBSCAN, the DBSCAN belongs to an unsupervised machine learning algorithm, historical working current is processed through the data filtering model to obtain target historical working current, and historical working voltage is processed through the data filtering model to obtain target historical working voltage, so that abnormal data are filtered.

Specifically, the normal historical operating current and the abnormal historical operating current are obviously different, and the normal historical operating voltage are obviously different. The historical working current is input into a pre-trained data filtering model, the data filtering model can perform cluster analysis on the historical working current, the historical working current is divided into normal current data and abnormal current data, then the abnormal current data can be discarded, the normal current data is determined as the target historical working current, and filtering of the abnormal historical working current is achieved. The historical working voltage is input into a pre-trained data filtering model, the data filtering model can perform cluster analysis on the historical working voltage, the historical working voltage is divided into normal voltage data and abnormal voltage data, then the abnormal voltage data can be discarded, the normal voltage data is determined as the target historical working voltage, and filtering of the abnormal historical working voltage is achieved.

In addition, when the data filtering model carries out cluster analysis, the radius of a neighboring region around a point and the number of at least points contained in the neighboring region can be adjusted, so that the accuracy of the data filtering model is improved, and the accurate filtering of historical working current and historical working voltage is realized.

The server can also determine historical characteristics and target historical tag information corresponding to the target historical operating current and the target historical operating voltage. Specifically, the historical working current and the historical working current of the photovoltaic to be measured, which are obtained at the same sampling point in the same historical period, can be determined as a current-voltage data set; performing nonlinear curve fitting on each current-voltage data set to determine historical characteristics corresponding to each group of historical operating current and historical operating current in each current-voltage data set; and respectively clustering each group of historical working current and historical working current in each current-voltage data set based on a clustering algorithm to determine historical label information corresponding to each group of historical working current and historical working current.

Wherein the historical characteristics include at least one of a short circuit current value, an open circuit voltage value, a peak power, a maximum power point voltage, a maximum power point current, and a fill factor.

The historical working current and the historical working current cannot accurately describe curves corresponding to current-voltage data sets acquired in the same historical period at the same sampling point, so the historical working current and the historical working current acquired in the same historical period at the same sampling point need to be analyzed to determine curve characteristics of the curves corresponding to the current-voltage data sets. Specifically, the historical operating current and the historical operating current acquired at the same sampling point in the same historical period may be determined as a current-voltage data set, the current-voltage data set may be subjected to nonlinear curve fitting, and a curve characteristic of a curve corresponding to the current-voltage data set may be determined, for example, at least one of a short circuit current value, an open circuit voltage value, a peak power, a maximum power point voltage, a maximum power point current, and a fill factor may be determined. Further, the curve characteristic may be determined as historical operating currents for each set of historical operating currents in the current-voltage data set and corresponding historical characteristics for the historical operating currents.

And respectively clustering each group of historical working current and historical working current in each current-voltage data set based on a clustering algorithm to determine each group of historical working current and historical label information corresponding to the historical working current.

Specifically, the parameters of the clustering algorithm may be set: neighborhood r, minimum number of samples minP. Firstly, determining each group of historical working current and historical working current in a current-voltage data set, and if at least minP groups of other historical working currents and historical working currents exist in the neighborhood r range of any group of historical working current and historical working current, calling the group of historical working current and historical working current as core objects; randomly selecting an unexploded core object P1, creating a new cluster N1, forming a set C1 by the historical working current, the historical working current and other groups of historical working currents in the neighborhood range, and adding all groups of historical working currents and historical working currents in the set C1 into the cluster N1; traversing other core objects P1i in the set C1, forming a set C1i by the core objects and other groups of historical working currents and historical working currents which are not traversed in the neighborhood range of the core objects, and adding all data in the set C1i into the cluster N1 until all groups of historical working currents and historical working currents added into the cluster N1 are traversed; and reselecting an unexploded core object, repeating the steps until all core objects in the current-voltage data set are traversed, labeling the historical working current and the historical working current which are clustered into different clusters, determining that the historical working current and the historical label information corresponding to the historical working current which are classified into a normal data cluster are 0, determining that the historical working current and the historical label information corresponding to the historical working current which are classified into a short-circuit fault data cluster are 1, determining that the historical working current and the historical label information corresponding to the historical working current which are classified into a shadow shading fault data cluster are 2, and so on until the historical working current and the historical label information corresponding to the historical working current of all fault type data clusters are determined.

The historical working current and the historical working voltage are subjected to data filtering in the previous step, so that the labeling of abnormal data can be reduced, the labeling accuracy can be increased, and the model training effect is improved.

The server can also normalize the target historical working current based on the short-circuit current value; and normalizing the target historical working voltage based on the open-circuit voltage value.

Specifically, the environments of the devices for acquiring the historical operating currents and the historical operating voltages of the groups may be different, and a standard current-voltage curve cannot be obtained. Therefore, the target historical working current and the target historical working voltage can be normalized, and the result after the normalization only changes the magnitude of the numerical value and does not change the shape of the current-voltage curve. Specifically, the target historical operating current may be divided by the short-circuit current value to achieve normalization of the target historical operating current, and the target historical operating voltage may be divided by the open-circuit voltage value to achieve normalization of the target historical operating voltage.

The server can also perform model training on the transform neural network model by taking the target historical working current, the target historical working voltage, and historical characteristics and target historical label information corresponding to the target historical working current and the target historical working voltage as a training data set, and calculate a loss function. And optimizing the model based on a back propagation algorithm until the loss function is converged to obtain the fault diagnosis model.

Specifically, after the target historical working current, the target historical working voltage, and the historical characteristics and the target historical label information corresponding to the target historical working current and the target historical working voltage are input into the Transformer neural network model as a training data set, the Transformer neural network model can determine training label information, determine the training label information and the target historical label information to determine a loss function value, and further perform model optimization based on a back propagation algorithm until the loss function converges to obtain the fault diagnosis model.

The relation among the target historical working current, the target historical working voltage and the target historical label information is continuously learned by the aid of the Transformer neural network model, the weight parameter of each layer in the network model is adjusted, and the fault diagnosis model is determined.

In addition, both the Transformer neural network model and the specific time sequence cyclic neural network model can express sequence characteristics, but because the Transformer neural network model is divided into a plurality of sub-neural networks, the characteristics extracted by the specific time sequence cyclic neural network model are more, the accuracy is higher, and the accuracy of a fault diagnosis model obtained by training the Transformer time sequence cyclic neural network model can reach 99% on a training data set and 94% on a testing data set. Moreover, the Transformer neural network model can be trained in parallel, and the training speed is high.

The method includes the steps that a Transformer neural network model is trained through a large amount of historical target working current, historical target working voltage, historical target characteristics corresponding to the historical target working current and the historical target working voltage and historical target label information to obtain a fault diagnosis model, so that the fault diagnosis model can automatically extract characteristic information corresponding to the working current and the working voltage, and a depth mapping relation between the characteristic information corresponding to the working current, the working voltage, the working current and the working voltage and a fault type is excavated, the robustness of the fault diagnosis model is improved, the fault diagnosis accuracy of the fault diagnosis model is higher, and meanwhile, through continuous acquisition of later-stage data, the model can be continuously optimized and is more intelligent.

Compared with the fault type determination based on the server, the method has the advantages that the dependence on the network is small, the fault diagnosis service with low delay, low energy consumption, high efficiency and safety can be provided, the burden of a communication base station is reduced, and real-time and short-period calculation is supported.

The embodiment of the utility model provides a photovoltaic module failure diagnosis equipment includes: the photovoltaic module failure diagnosis device comprises a shell, an inverter interface, a processing device, a display device, a communication interface, a battery jar, a battery, a charging interface, a handle and a heat dissipation device, wherein the inverter interface and the display device are connected with the processing device; the display device is used for displaying the fault type of the photovoltaic module to be tested; the communication interface is used for being in communication connection with a server so as to send the working current, the working voltage and the fault type of the photovoltaic assembly to be tested to the server; the battery is used for providing power for the photovoltaic module fault diagnosis equipment, and the charging interface is used for charging the battery; the handles are arranged on two sides of the shell; the heat dissipation device is used for providing a heat dissipation opening so as to reduce the internal temperature of the photovoltaic module fault diagnosis equipment. According to the technical scheme, the photovoltaic module fault diagnosis equipment can be connected with the photovoltaic module to be detected based on the inverter interface, the compatibility of the photovoltaic module fault diagnosis equipment is improved, further, the working current of the photovoltaic module to be detected can be obtained based on the current sampling unit contained in the processing device, the working voltage of the photovoltaic module to be detected is obtained based on the voltage sampling unit contained in the processing device, the working current and the working voltage of the photovoltaic module to be detected are analyzed and processed based on the pre-trained fault diagnosis module which is arranged in the diagnosis unit contained in the processing device, the fault type of the photovoltaic module to be detected is determined, the accurate fault type of the photovoltaic module to be detected is rapidly determined, certainly, after the fault type of the photovoltaic module to be detected is determined by the processing device, the fault diagnosis equipment can be sent to the display device, the fault type of the photovoltaic module to be detected is displayed based on the display device, the fault type of the photovoltaic module to be detected can be conveniently observed by a user, the photovoltaic module fault diagnosis equipment is low in cost, convenient to carry, small in environmental influence, and user experience is further improved.

Additionally, the utility model discloses acquisition, storage, use, processing etc. to data among the technical scheme all accord with the relevant regulation of national laws and regulations.

It should be noted that the foregoing is only a preferred embodiment of the present invention and the technical principles applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments illustrated herein, but is capable of various obvious modifications, rearrangements and substitutions without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail with reference to the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the scope of the present invention.

Claims (10)

1. A photovoltaic module failure diagnosis apparatus, comprising: the photovoltaic module fault diagnosis device comprises a shell, an inverter interface, a processing device and a display device, wherein the inverter interface and the display device are connected with the processing device, the processing device comprises a current sampling unit, a voltage sampling unit and a diagnosis unit, the current sampling unit is used for acquiring the working current of a photovoltaic module to be detected based on the inverter interface, the voltage sampling unit is used for acquiring the working voltage of the photovoltaic module to be detected based on the inverter interface, and the diagnosis unit is used for analyzing and processing the working current and the working voltage of the photovoltaic module to be detected based on a fault diagnosis model and determining the fault type of the photovoltaic module to be detected; the display device is used for displaying the fault type of the photovoltaic module to be tested.

2. The photovoltaic module fault diagnosis device according to claim 1, wherein the current sampling unit is further configured to: and in at least one historical period, acquiring a working current of the photovoltaic module to be detected at preset time intervals based on the inverter interface until a preset number of historical working currents are acquired.

3. The photovoltaic module fault diagnosis device according to claim 2, characterized in that the voltage sampling unit is further configured to: and in at least one historical period, acquiring a working voltage of the photovoltaic module to be tested at preset time intervals based on the inverter interface until a preset number of historical working voltages are acquired.

4. The photovoltaic module fault diagnosis device according to claim 1, characterized in that the processing means further comprises: and the temperature sampling unit is used for acquiring a current temperature value.

5. The photovoltaic module fault diagnosis device according to claim 1, characterized in that the processing means further comprises: the illumination sampling unit is used for acquiring the current illumination intensity.

6. The photovoltaic module failure diagnosis apparatus according to claim 3, characterized by further comprising: the communication interface is used for being in communication connection with a server so as to send the working current, the working voltage and the fault type of the photovoltaic module to be tested to the server.

7. The photovoltaic module fault diagnosis device according to claim 6, characterized in that said processing means are adapted to: and sending a preset number of the historical working currents, a preset number of the historical working voltages and historical fault types corresponding to the historical working currents and the historical working voltages to a server based on the communication interface, so that the server performs model training on a Transformer neural network model by taking the preset number of the historical working currents, the preset number of the historical working voltages and the historical fault types corresponding to the historical working currents and the historical working voltages as a training data set, and the fault diagnosis model is obtained.

8. The photovoltaic module failure diagnosis apparatus according to claim 1, characterized by further comprising: the photovoltaic module fault diagnosis device comprises a battery and a charging interface, wherein the battery is used for providing power for the photovoltaic module fault diagnosis device, and the charging interface is used for charging the battery.

9. The photovoltaic module failure diagnosis apparatus according to claim 1, characterized by further comprising: handles disposed on both sides of the housing.

10. The photovoltaic module failure diagnosis apparatus according to claim 1, characterized by further comprising: the heat dissipation device is used for providing a heat dissipation opening so as to reduce the internal temperature of the photovoltaic module fault diagnosis equipment.

Images