Photovoltaic Inverter State Recognition System and Method Based on Four-Fusion Terminal

Abstract

The present invention discloses a photovoltaic inverter status recognition system and method based on a four-in-one fusion terminal, which relates to the technical field of inverter data analysis. It includes an inverter status recognition module, a data to be referenced acquisition module, a reference data selection module, and a status prediction and adjustment module. The inverter status recognition module is used to perform status recognition and monitoring on distributed photovoltaic inverters, and give early warning when abnormal inverter status is detected. The data to be referenced acquisition module is used to collect the historical operation data of the inverter to be referenced, and respectively collect the load information and historical optimization information carried by the current inverter and the inverter to be referenced. The reference data selection module is used to perform model processing on the data to be referenced, and screen out the target reference data according to model matching. The status prediction and adjustment module is used to perform status prediction and adjustment processing on the current inverter based on the target reference data, effectively improving the accuracy of predicting the service life of distributed photovoltaic inverters.

Description

Technical Field

[0001] The present invention relates to the technical field of inverter data analysis, and specifically to a photovoltaic inverter status recognition system and method based on a four-feasibility integrated terminal. Background Art

[0002] Distributed photovoltaic inverters are key devices in solar power generation systems. Their working principle is to convert the direct current generated by each solar panel into alternating current separately, thereby realizing the utilization of solar power, maximizing the power generation efficiency of solar cells, and improving the overall efficiency of the entire power generation system. Real-time monitoring of the status data of distributed photovoltaic inverters can help detect and handle abnormal operating conditions of inverters in a timely manner to reduce the risk of inverter failures, and can also analyze and predict the service life of inverters through the monitored data. Data monitoring of distributed photovoltaic inverters can be achieved through a four-feasibility integrated terminal, which refers to a terminal device with observable, controllable, adjustable, and measurable functions;

[0003] By accurately evaluating the service life of an inverter, regular inspections and replacement of key components can be arranged before the inverter approaches the end of its expected life, avoiding service interruptions caused by sudden failures. When predicting the service life of an inverter, the historical status data of some inverter devices of the same model can be used as a reference to predict the service life of the current device to improve the accuracy of the prediction results. However, in the prior art, only the historical data of devices of the same model are selected as a reference without prior screening. Since the working environments of different inverters are different, the accuracy of the predicted service life cannot be guaranteed, affecting the subsequent inspection work. Summary of the Invention

[0004] The purpose of the present invention is to provide a photovoltaic inverter status recognition system and method based on a four-feasibility integrated terminal to solve the problems raised in the prior art.

[0005] To achieve the above purpose, the present invention provides the following technical solution: A photovoltaic inverter status recognition system based on a four-feasibility integrated terminal, the system includes an inverter status recognition module, a to-be-referenced data acquisition module, a reference data selection module, and a status prediction and adjustment module;

[0006] The distributed photovoltaic inverter is monitored for status recognition through the inverter status recognition module, and a warning is given when an abnormal inverter status is detected;

[0007] The historical operation data of the to-be-referenced inverter is collected through the to-be-referenced data acquisition module, and the load information and historical optimization information of the current inverter and the to-be-referenced inverter are collected respectively;

[0008] The to-be-referred data is modeled by the reference data selection module, a load analysis model and an optimization analysis model are respectively established for the current inverter and the to-be-referred inverter, and the target reference data is screened out according to model matching.

[0009] The state prediction and adjustment module performs state prediction and adjustment processing on the current inverter according to the target reference data.

[0010] Preferably, the inverter state recognition module includes a conversion efficiency monitoring unit and a used time monitoring unit;

[0011] The conversion efficiency monitoring unit is used to monitor the conversion efficiency of the current inverter during operation by using the four-in-one fusion terminal, set a conversion efficiency decrease threshold, and send a warning signal when the monitored decrease value of the conversion efficiency of the current inverter exceeds the threshold. The current inverter refers to the inverter whose service life needs to be predicted currently. The conversion efficiency of the inverter is obtained by dividing the AC output efficiency by the DC input efficiency during the monitored operation of the inverter. The conversion efficiency decrease value is equal to the conversion efficiency after the decrease minus the conversion efficiency before the decrease;

[0012] The four-in-one in the four-in-one fusion terminal refers to observable, measurable, adjustable and controllable. Among them, observable means to realize the panoramic visualization display of low-voltage distributed photovoltaic statistical data, operation status, adjustment control and abnormal alarm; measurable means to realize the minute-level collection of low-voltage distributed photovoltaic user data, realize the 15-minute-level load data collection of all low-voltage distributed photovoltaic users, and realize the load prediction of low-voltage distributed photovoltaic power generation; adjustable means to realize the flexible adjustment of low-voltage distributed photovoltaic power and voltage; controllable means to realize the rigid control of all low-voltage distributed photovoltaic users. Using the four-in-one fusion terminal to monitor the state of distributed photovoltaic inverters can effectively improve the timeliness and accuracy of detecting abnormal data and implementing treatment measures, and can effectively ensure the reliable operation of photovoltaic inverters.

[0013] The used time monitoring unit obtains the used time of the current inverter, and the obtained used time of the current inverter is t.

[0014] Preferably, the to-be-referred data collection module includes an operation data collection unit, a load-bearing load collection unit and an optimization information collection unit;

[0015] The operation data collection unit collects the historical operation data of the inverter that is of the same model as the current inverter and has stopped using. The historical operation data refers to the conversion efficiency data of the inverter during previous operations. The inverter that is of the same model as the current inverter and has stopped using is used as the to-be-referred inverter. Stopped using means that the inverter has stopped using due to the expiration of its service life;

[0016] Obtain the load borne by the reference inverter before the used time reaches t through the load-bearing load acquisition unit, and count the used time of the reference inverter when the corresponding load is collected. The load-bearing load acquisition unit is also used to collect the load borne by the current inverter before the used time reaches t, and count the used time of the current inverter when the corresponding load is collected;

[0017] Obtain the number of times the reference inverter has been optimized before the used time reaches t through the optimization information acquisition unit, and count the used time of the reference inverter each time it is optimized. The optimization information acquisition unit is also used to collect the number of times the current inverter has been optimized before the used time reaches t, and count the used time of the current inverter each time it is optimized. The inverter being optimized means optimizing the components of the inverter. For example, optimizing components such as DC filters, reactors, transformers, etc. After optimizing these components, the conversion efficiency of the inverter can be improved.

[0018] Preferably, the reference data selection module includes a reference data integration unit, an environmental data comparison unit, and a target data screening unit;

[0019] Integrate and process the reference data through the reference data integration unit, establish the historical load-bearing load analysis model and optimization analysis model of the reference inverter and use them as the first load analysis model and the first optimization analysis model respectively, and establish the historical load-bearing load analysis model and optimization analysis model of the current inverter and use them as the second load analysis model and the second optimization analysis model respectively;

[0020] Analyze the working environment matching coefficient between the reference inverter and the current inverter through the environmental data comparison unit based on the bias comparison between the models of the reference inverter and the current inverter;

[0021] Screen out the historical operation data of the target inverter as the target reference data through the target data screening unit.

[0022] Preferably, the state prediction and adjustment module includes a service life prediction unit and an optimization and replacement processing unit;

[0023] Predict the service life of the current inverter by referring to the target reference data through the service life prediction unit;

[0024] Optimize or replace the inverter through the optimization and replacement processing unit before the service life of the current inverter reaches the predicted value.

[0025] Preferably, the load set borne by a randomly selected reference inverter before the used time reaches t is H={H1, H2,... H m}, it is counted that the set of used times of the inverter to be referenced when the corresponding load is collected is \(T = \{T_1, T_2,... T\) m}, and the used times of the inverter to be referenced each time before the used time reaches \(t\) during optimization are \(F = \{F_1, F_2,... F\) g}, \(g\) represents the number of times the inverter to be referenced is optimized before the used time reaches \(t\), and the set of loads borne by the current inverter before the used time reaches \(t\) is \(h = \{h_1, h_2,... h\) n}, it is counted that the set of used times of the current inverter when the corresponding load is collected is \(T\) ’ = \{T_1 ’ , T_2 ’ ,... T n ’ \}, and the used times of the current inverter each time before the used time reaches \(t\) during optimization are \(f = \{f_1, f_2,... f\) k \}, where \(k\) represents the number of times the current inverter is optimized before the used time reaches \(t\), \(m\) represents the number of times a randomly collected inverter to be referenced bears a load, and \(n\) represents the number of times the current inverter bears a load.

[0026] Preferably, the data to be referenced are integrated into the first, second, third, and fourth training samples. The first training sample is \(\{(H_1, T_1), (H_2, T_2),... (H\) m , T m \)}, the second training sample is \(\{(h_1, T_1 ’ ), (h_2, T_2 ’ ),... (h n , T n ’ )\}, the third training sample is \(\{(1, F_1), (2, F_2),... (g, F g )\}, and the fourth training sample is \(\{(1, f_1), (2, f_2),... (k, f k )\}. After performing linear fitting on the first training sample, a first load analysis model is established: , where \(a_1\) and \(b_1\) respectively represent the bias and intercept of the first load analysis model, \(x_1\) represents the variable referring to the load in the first load analysis model, and \(y_1\) represents the variable referring to the used time in the first load analysis model. After performing linear fitting on the second training sample, a second load analysis model is established: , where \(a_2\) and \(b_2\) respectively represent the bias and intercept of the second load analysis model, \(x_2\) represents the variable referring to the load in the second load analysis model, and \(y_2\) represents the variable referring to the used time in the second load analysis model. After performing linear fitting on the third training sample, a first optimization analysis model is established: , C1 and D1 respectively represent the bias and intercept of the first optimization analysis model, X1 represents the variable in the first optimization analysis model that refers to the number of times the inverter is optimized, and Y1 represents the variable in the first optimization analysis model that refers to the used time when the inverter is optimized. After performing linear fitting on the fourth training sample, a second optimization analysis model is established: , C2 and D2 respectively represent the bias and intercept of the second optimization analysis model, X2 represents the variable in the second optimization analysis model that refers to the number of times the inverter is optimized, and Y2 represents the variable in the second optimization analysis model that refers to the used time when the inverter is optimized;

[0027] When predicting the service life of an inverter, the accuracy of the service life prediction result can be improved by referring to the historical parameters of equipment of the same model. Considering that the working environments of inverters may vary, even for inverters of the same model, there may be some inverters with significant differences in the working environment from the current inverter, which may lead to significant differences in historical operating parameters. For example, there are significant differences in the load data carried during operation, and it is possible that some inverters will perform component optimizations during use, and the conversion efficiency after optimization also fluctuates. Therefore, by collecting the historical usage data of the inverters to be referred to, integrating the historical usage data into a model, and screening out the data of the inverters to be referred to with a high degree of matching between the working environment data and the working environment data of the current inverter as the target reference data through data comparison presented by the model, and predicting the remaining service life of the current inverter based on the target reference data, the accuracy of the prediction result of the inverter service life is effectively improved.

[0028] Preferably, the working environment matching coefficient W between a randomly selected inverter to be referred to and the current inverter is calculated according to the following formula:

[0029] W = log a (|a2 - a1| + |C2 - C1|), 0 < a < 1;

[0030] Among them, a represents the base of the log function. Analyze and compare the working environment matching coefficients between different inverters to be referred to and the current inverter, and select the inverter to be referred to with the highest working environment matching coefficient with the current inverter as the target inverter, and screen out the historical operating data of the target inverter as the target reference data;

[0031] By comparing the model biases to analyze the matching situation between the current inverter and the inverter to be referred to, the model bias can intuitively reflect the trend change between the working environment parameters of the two inverters, improving the referenceability of the selected target reference data.

[0032] Preferably, obtain the conversion efficiency of the target inverter during operation after the used time t, and obtain the target inverter when the used time reaches t’ When the conversion efficiency decreases and the decrease value of the conversion efficiency exceeds the conversion efficiency decrease threshold set by the system, the predicted remaining service life of the current inverter is: t ’ -t.

[0033] Preferably, before the remaining service life of the current inverter reaches t ’ -t, optimize the components of the inverter or replace the inverter.

[0034] A method for identifying the state of a photovoltaic inverter based on a four-in-one fusion terminal: The method includes:

[0035] S1: Monitor the state of the distributed photovoltaic inverter and give a warning when an abnormal state of the inverter is detected;

[0036] S2: Collect the historical operation data of the inverter to be referenced, and respectively collect the load information and historical optimization information carried by the current inverter and the inverter to be referenced;

[0037] S3: Model the data to be referenced, establish a load analysis model and an optimization analysis model for the current inverter and the inverter to be referenced respectively, and screen out the target reference data based on model matching;

[0038] S4: Predict and adjust the state of the current inverter based on the target reference data.

[0039] Compared with the prior art, the beneficial effects of the present invention are:

[0040] By referring to the historical parameters of devices of the same model, the present invention can improve the accuracy of the predicted service life. Considering that the working environments of inverters may be different, even though they are inverters of the same model, there may be some inverters with a large difference in the working environment from the current inverter, which may lead to a large difference in historical operation parameters. For example, there is a large difference in the load data carried during operation, and it is possible that some inverters will optimize their components during use, and the conversion efficiency after optimization also fluctuates. Therefore, by collecting the historical usage data of the inverter to be referenced, integrating the historical usage data into a model, and screening out the data of the inverter to be referenced with a high degree of matching of the working environment data with the current inverter's working environment data as the target reference data through data comparison presented by the model, and predicting the remaining service life of the current inverter based on the target reference data, the accuracy of the predicted result of the inverter's service life is effectively improved. Description of the Drawings

[0041] Figure 1 It is a schematic structural diagram of the photovoltaic inverter state recognition system based on the four-in-one fusion terminal of the present invention;

[0042] Figure 2This is a flowchart of the method for identifying the state of a photovoltaic inverter based on a four-in-one fusion terminal according to the present invention. Specific Embodiments

[0043] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0044] Embodiment 1: As Figure 1 shown, this embodiment provides a system for identifying the state of a photovoltaic inverter based on a four-in-one fusion terminal. The system includes: an inverter state identification module, a data to be referenced acquisition module, a reference data selection module, and a state prediction and adjustment module; the inverter state identification module monitors the state of a distributed photovoltaic inverter and issues a warning when an abnormal state is detected; the data to be referenced acquisition module acquires the historical operation data of the inverter to be referenced and respectively acquires the load information and historical optimization information carried by the current inverter and the inverter to be referenced; the reference data selection module performs a modeling process on the data to be referenced, respectively establishes a load analysis model and an optimization analysis model for the current inverter and the inverter to be referenced, and filters out the target reference data based on model matching; the state prediction and adjustment module performs state prediction and adjustment processing on the current inverter based on the target reference data.

[0045] The inverter state identification module includes a conversion efficiency monitoring unit and a used time monitoring unit; the conversion efficiency monitoring unit is used to monitor the conversion efficiency of the current inverter during operation by using a four-in-one fusion terminal, set a conversion efficiency drop threshold, and send a warning signal when the monitored conversion efficiency drop value of the current inverter exceeds the threshold. The current inverter refers to the inverter whose service life needs to be predicted currently. The conversion efficiency of the inverter is obtained by dividing the AC output efficiency by the DC input efficiency during the monitored operation of the inverter. The conversion efficiency drop value is equal to the converted efficiency after the drop minus the converted efficiency before the drop; the used time monitoring unit obtains the used time of the current inverter, and the obtained used time of the current inverter is t.

[0046] The reference data acquisition module includes an operating data acquisition unit, a load carried acquisition unit, and an optimization information acquisition unit; the historical operating data of inverters that are of the same model as the current inverter and have stopped being used is collected through the operating data acquisition unit, where the historical operating data refers to the conversion efficiency data of the inverters during previous operations. The inverters that are of the same model as the current inverter and have stopped being used are regarded as the reference inverters to be referred to, and "stopped being used" means that the inverters have stopped being used due to the expiration of their service life; the load carried by the reference inverter before the used time reaches t is obtained through the load carried acquisition unit, and the used time of the reference inverter when the corresponding load is collected is counted. The load carried acquisition unit is also used to collect the load carried by the current inverter before the used time reaches t, and the used time of the current inverter when the corresponding load is collected is counted; the number of times the reference inverter has been optimized before the used time reaches t is obtained through the optimization information acquisition unit, and the used time of the reference inverter each time it is optimized is counted. The optimization information acquisition unit is also used to collect the number of times the current inverter has been optimized before the used time reaches t, and the used time of the current inverter each time it is optimized is counted. An inverter being optimized means optimizing the components of the inverter. For example, optimizing components such as DC filters, reactors, and transformers can improve the conversion efficiency of the inverter.

[0047] The reference data selection module includes a reference data integration unit, an environmental data comparison unit, and a target data screening unit; the reference data is integrated and processed through the reference data integration unit to establish a historical load carried analysis model and an optimization analysis model of the reference inverter, which are respectively used as the first load analysis model and the first optimization analysis model, and establish a historical load carried analysis model and an optimization analysis model of the current inverter, which are respectively used as the second load analysis model and the second optimization analysis model; the working environment matching coefficient between the reference inverter and the current inverter is analyzed through the environmental data comparison unit based on the bias comparison between the models of the reference inverter and the current inverter; the historical operating data of the target inverter is screened out as the target reference data through the target data screening unit.

[0048] The status prediction and adjustment module includes a service life prediction unit and an optimization and replacement processing unit; the service life of the current inverter is predicted through the service life prediction unit with reference to the target reference data; the inverter is optimized or replaced through the optimization and replacement processing unit before the service life of the current inverter reaches the predicted value.

[0049] The set of loads carried by a randomly selected reference inverter before the used time reaches t is H = {H1, H2,... H m}, and the set of used times of the reference inverter when the corresponding load is collected is T = {T1, T2,... Tm}, where the service life at each optimization of the reference inverter before the service life reaches t is F = {F1, F2,... F g}, g represents the number of optimizations of the reference inverter before the service life reaches t, and the load set carried by the current inverter before the service life reaches t is h = {h1, h2,... h n}, and the service life set of the current inverter when the corresponding load is collected is T ’ = {T1 ’ , T2 ’ ,... T n ’}, and the service life at each optimization of the current inverter before the service life reaches t is f = {f1, f2,... f k}, where k represents the number of optimizations of the current inverter before the service life reaches t, m represents the number of times of collecting the load carried by a randomly selected reference inverter, and n represents the number of times of collecting the load carried by the current inverter.

[0050] Integrate the reference data into the first, second, third, and fourth training samples, and the first training sample is {(H1, T1), (H2, T2),... (H m , T m )}, the second training sample is {(h1, T1 ’ ), (h2, T2 ’ ),... (h n , T n ’ )}, the third training sample is {(1, F1), (2, F2),... (g, F g )}, the fourth training sample is {(1, f1), (2, f2),... (k, f k )}, perform linear fitting on the first training sample and establish the first load analysis model: , where a1 and b1 respectively represent the bias and intercept of the first load analysis model, x1 represents the variable referring to the load in the first load analysis model, and y1 represents the variable referring to the service life in the first load analysis model, where, , , perform linear fitting on the second training sample and establish the second load analysis model: , where a2 and b2 respectively represent the bias and intercept of the second load analysis model, x2 represents the variable referring to the load in the second load analysis model, and y2 represents the variable referring to the service life in the second load analysis model, perform linear fitting on the third training sample and establish the first optimization analysis model: , C1 and D1 represent the bias and intercept of the first optimization analysis model respectively, X1 represents the variable in the first optimization analysis model indicating the number of times the inverter is optimized, Y1 represents the variable in the first optimization analysis model indicating the used time when the inverter is optimized, and the second optimization analysis model is established after linear fitting of the fourth training sample: , C2 and D2 represent the bias and intercept of the second optimization analysis model respectively, X2 represents the variable in the second optimization analysis model indicating the number of times the inverter is optimized, and Y2 represents the variable in the second optimization analysis model indicating the used time when the inverter is optimized. The bias and intercept solution methods of each model are the same.

[0051] The working environment matching coefficient W between a random reference inverter and the current inverter is calculated according to the following formula:

[0052] W=log a (|a2-a1|+|C2-C1|),0 <a<1;

[0053] Wherein, a represents the base of the log function, analyzes and compares the working environment matching coefficients between different reference inverters and the current inverter, selects the reference inverter with the highest working environment matching coefficient with the current inverter as the target inverter, and selects the historical operation data of the target inverter as the target reference data.

[0054] Get the conversion efficiency of the target inverter when it is running after the used time t, and get the conversion efficiency of the target inverter when the used time reaches t ’ When the conversion efficiency decreases and the conversion efficiency decrease value exceeds the conversion efficiency decrease threshold set by the system, the remaining service life of the current inverter is predicted to be: t ’ -t, when the remaining service life of the current inverter reaches t ’ -t Before optimizing the inverter components or replacing the inverter.

[0055] Example 2: Figure 2 As shown, this embodiment provides a photovoltaic inverter state identification method based on four fusion terminals, the method comprising:

[0056] S1: Perform status identification and monitoring on distributed photovoltaic inverters, and take early warning measures when abnormal inverter status is detected;

[0057] S2: Collect historical operation data of the reference inverter and respectively collect load information and historical optimization information of the current inverter and the reference inverter;

[0058] S3: Model the data to be referenced. Establish a load analysis model and an optimization analysis model for the current inverter and the inverter to be referenced respectively, and screen out the target reference data based on model matching.

[0059] S4: Perform state prediction and adjustment processing on the current inverter according to the target reference data.

[0060] For example: The values of a1 in the first load analysis model established for three randomly selected inverters to be referenced are 0.25, 0.20, and 0.12 respectively, the value of a2 in the second load analysis model established for the current inverter is 0.22, the values of C1 in the first optimization analysis model established for the corresponding three inverters to be referenced are 3.21, 4.50, and 3.56 respectively, the value of C2 in the second optimization analysis model established for the current inverter is 3.54. Set the base of the log function to 0.2, and calculate the working environment matching coefficients between the three inverters to be referenced and the current inverter, which are 0.63, 0.01, and 1.32 respectively. The inverter to be referenced with the highest working environment matching coefficient with the current inverter is the third inverter. Take the third inverter as the target inverter, obtain the conversion efficiency of the target inverter during operation after 15 years of use, and obtain that the conversion efficiency of the target inverter decreases and the decrease value exceeds the conversion efficiency decrease threshold set by the system when it has been used for 22 years. Predict the remaining service life of the current inverter to be: 7 years.

[0061] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present invention. Any reference signs in the claims should not be regarded as limiting the claims involved.

Claims

1. A photovoltaic inverter status recognition system based on a four-in-one fusion terminal, characterized in that: It includes an inverter status recognition module, a data to be referenced acquisition module, a reference data selection module, and a status prediction and adjustment module; The distributed photovoltaic inverter is monitored for status recognition through the inverter status recognition module, and early warning processing is performed when an abnormal inverter status is detected; The data to be referenced acquisition module is used to collect the historical operation data of the inverter to be referenced, and respectively collect the load information and historical optimization information carried by the current inverter and the inverter to be referenced; The reference data selection module performs a modeling process on the data to be referenced, respectively establishes a load analysis model and an optimization analysis model for the current inverter and the inverter to be referenced, and filters out the target reference data based on model matching; The status prediction and adjustment module performs status prediction and adjustment processing on the current inverter based on the target reference data; The reference data selection module includes a data to be referenced integration unit, an environmental data comparison unit, and a target data filtering unit; The data to be referenced integration unit integrates the data to be referenced, establishes a historical load analysis model and an optimization analysis model of the inverter to be referenced, and respectively serves as a first load analysis model and a first optimization analysis model, and establishes a historical load analysis model and an optimization analysis model of the current inverter, and respectively serves as a second load analysis model and a second optimization analysis model; The environmental data comparison unit analyzes the working environment matching coefficient between the inverter to be referenced and the current inverter based on the bias comparison between the models of the inverter to be referenced and the current inverter; The target data filtering unit filters out the historical operation data of the target inverter as the target reference data; Calculate the working environment matching coefficient W between a randomly selected inverter to be referenced and the current inverter according to the following formula: W = log a (|a2 - a1| + |C2 - C1|), 0 < a < 1; Where, a represents the base of the log function, a2 represents the bias of the second load analysis model, a1 represents the bias of the first load analysis model, C1 represents the bias of the first optimization analysis model, C2 represents the bias of the second optimization analysis model, analyze and compare the working environment matching coefficients between different inverters to be referenced and the current inverter, and select the inverter to be referenced with the highest working environment matching coefficient with the current inverter as the target inverter, and filter out the historical operation data of the target inverter as the target reference data.

2. The photovoltaic inverter status recognition system based on the four-in-one fusion terminal according to claim 1, characterized in that: The inverter status recognition module includes a conversion efficiency monitoring unit and a used time monitoring unit; The conversion efficiency monitoring unit is used to monitor the conversion efficiency of the current inverter during operation by using a four-in-one fusion terminal, set a conversion efficiency drop threshold, and send a warning signal when the monitored conversion efficiency drop value of the current inverter exceeds the threshold; The used time monitoring unit obtains the used time of the current inverter, and the obtained used time of the current inverter is t.

3. The photovoltaic inverter status recognition system based on the four-in-one fusion terminal according to claim 2, wherein: The data to be referenced acquisition module includes an operation data acquisition unit, a load carried acquisition unit, and an optimization information acquisition unit; Collect the historical operation data of the inverter that is of the same model as the current inverter and has stopped being used through the described operation data collection unit. The historical operation data refers to the conversion efficiency data of the inverter during its previous operation. Use the inverter that is of the same model as the current inverter and has stopped being used as the reference inverter to be referred to. Obtain the load borne by the reference inverter to be referred to before the used time reaches t through the described load bearing collection unit, and count the used time of the reference inverter when the corresponding load is collected. The load bearing collection unit is also used to collect the load borne by the current inverter before the used time reaches t, and count the used time of the current inverter when the corresponding load is collected. Obtain the number of times the reference inverter to be referred to has been optimized before the used time reaches t through the described optimization information collection unit, and count the used time of the reference inverter when it is optimized each time. The optimization information collection unit is also used to collect the number of times the current inverter has been optimized before the used time reaches t, and count the used time of the current inverter when it is optimized each time.

4. The photovoltaic inverter state recognition system based on a four-in-one fusion terminal according to claim 1, wherein: The state prediction and adjustment module includes a service life prediction unit and an optimization and replacement processing unit. Predict the service life of the current inverter by referring to the target reference data through the service life prediction unit. Perform optimization or replacement processing on the inverter through the optimization and replacement processing unit before the service life of the current inverter reaches the predicted value.

5. The photovoltaic inverter status recognition system based on the four-in-one fusion terminal according to claim 4, characterized in that: The set of loads borne by a randomly selected reference inverter before its usage time reaches t is H = {H1, H2,... H m}, the set of usage times of the reference inverter when the corresponding loads are collected is T = {T1, T2,... T m}, the usage times of the reference inverter each time it is optimized before its usage time reaches t are F = {F1, F2,... F g}, g represents the number of times the reference inverter is optimized before its usage time reaches t, the set of loads borne by the current inverter before its usage time reaches t is h = {h1, h2,... h n}, the set of usage times of the current inverter when the corresponding loads are collected is T ’ = {T1 ’ , T2 ’ ,... T n ’}, the usage times of the current inverter each time it is optimized before its usage time reaches t are f = {f1, f2,... f k}, where k represents the number of times the current inverter is optimized before its usage time reaches t, m represents the number of times a randomly selected reference inverter bears a load, and n represents the number of times the current inverter bears a load.

6. The photovoltaic inverter state recognition system based on a four-in-one fusion terminal according to claim 5, characterized in that: Integrate the data to be referenced into the first, second, third, and fourth training samples. The first training sample is {(H1, T1), (H2, T2),... (H m , T m )}, the second training sample is {(h1, T1 ’ ), (h2, T2 ’ ),... (h n , T n ’ )}, the third training sample is {(1, F1), (2, F2),... (g, F g )}, the fourth training sample is {(1, f1), (2, f2),... (k, f k )}. After performing linear fitting on the first training sample, establish the first load analysis model: y1 = a1 x1 + b1, where a1 and b1 represent the bias and intercept of the first load analysis model respectively, x1 represents the variable referring to the load in the first load analysis model, and y1 represents the variable referring to the used time in the first load analysis model. After performing linear fitting on the second training sample, establish the second load analysis model: y2 = a2 x2 + b2, where a2 and b2 represent the bias and intercept of the second load analysis model respectively, x2 represents the variable referring to the load in the second load analysis model, and y2 represents the variable referring to the used time in the second load analysis model. After performing linear fitting on the third training sample, establish the first optimization analysis model: Y1 = C1 X1 + D1, where C1 and D1 represent the bias and intercept of the first optimization analysis model respectively, X1 represents the variable referring to the number of times the inverter is optimized in the first optimization analysis model, and Y1 represents the variable referring to the used time when the inverter is optimized in the first optimization analysis model. After performing linear fitting on the fourth training sample, establish the second optimization analysis model: Y2 = C2 X2 + D2, where C2 and D2 represent the bias and intercept of the second optimization analysis model respectively, X2 represents the variable referring to the number of times the inverter is optimized in the second optimization analysis model, and Y2 represents the variable referring to the used time when the inverter is optimized in the second optimization analysis model.

7. The photovoltaic inverter status recognition system based on the four-in-one fusion terminal according to claim 1, wherein: Obtain the conversion efficiency when the target inverter operates after the used time t, and it is obtained that when the used time of the target inverter reaches t ’ the conversion efficiency decreases and the value of the decrease in the conversion efficiency exceeds the threshold of the decrease in the conversion efficiency set by the system. Predict that the remaining service life of the current inverter is: t ’ -t. Before the remaining service life of the current inverter reaches t ’ -t, optimize the components of the inverter or replace the inverter.

8. A method for identifying the state of a photovoltaic inverter based on a four-in-one fusion terminal, which is applied to the system for identifying the state of a photovoltaic inverter based on a four-in-one fusion terminal according to any one of claims 1-7, characterized in that: The method includes: S1: Conduct state identification and monitoring on the distributed photovoltaic inverter, and give an early warning when the inverter state is abnormal. S2: Collect the historical operation data of the reference inverter to be referred to, and respectively collect the load bearing information and historical optimization information of the current inverter and the reference inverter to be referred to. S3: Model the reference data to be referred to, establish a load analysis model and an optimization analysis model for the current inverter and the reference inverter to be referred to respectively, and screen out the target reference data based on model matching. S4: Perform state prediction and adjustment processing on the current inverter based on the target reference data.

Images