A photovoltaic transformer and its control method

Abstract

The present invention relates to the technical field of photovoltaic power distribution, in particular to a photovoltaic transformer and its control method. By analyzing historical data to construct a knowledge graph, and then combining the monitoring and analysis of real-time acoustic feature data, the system state of the photovoltaic transformer can be accurately judged. And different processing strategies are adopted for different system states, which not only avoids unnecessary interference with normal operation, but also can timely handle frequent anomalies to ensure the stable operation of the system. At the same time, occasional anomalies are continuously monitored to grasp their development trend, thereby improving the reliability of the operation of the photovoltaic transformer and the intelligent level of management.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power distribution, and particularly to a photovoltaic transformer and its control method. Background Art

[0002] During the actual operation of a photovoltaic system, a photovoltaic transformer may face various operating conditions. Traditional control methods often struggle to accurately and timely address these complex situations. On the one hand, the operating state of the photovoltaic transformer is affected by multiple factors, such as ambient temperature, humidity, load changes, etc. These factors may cause varying degrees of performance fluctuations in the transformer and even trigger abnormal system operation events. On the other hand, existing monitoring and control means lack in-depth mining and effective utilization of historical data.

[0003] From the perspective of historical working data, the photovoltaic transformer generates various acoustic feature data during operation, and there is a potential correlation between this acoustic feature data and system operation abnormal events. For different types of system operation abnormal events, whether frequent or occasional, the corresponding acoustic feature data may vary. However, there is currently a lack of an effective method to systematically analyze the relationship between this acoustic feature data and abnormal events and to construct an intelligent control strategy based on this.

[0004] Most existing control methods for photovoltaic transformers are based on fixed thresholds or simple logical judgments, which appear to be insufficiently flexible and precise when faced with complex and changing actual operating conditions. For example, when the transformer is in an occasional abnormal operation state, if overly aggressive regulation measures are adopted, it may cause unnecessary resource waste or interference with normal operation; while when in a frequent abnormal state, if timely and accurate regulation cannot be carried out, it may lead to further deterioration of the problem, affecting the normal operation of the entire photovoltaic power generation system and even shortening the service life of the photovoltaic transformer.

[0005] Therefore, it is necessary to develop a control method based on historical acoustic feature data mining that can accurately judge the operating state of the photovoltaic transformer and perform intelligent regulation to improve the operating efficiency, reliability, and safety of the photovoltaic transformer, thereby enhancing the performance of the entire photovoltaic power generation system. Summary of the Invention

[0006] The present invention overcomes the deficiencies of the prior art and provides a photovoltaic transformer and its control method.

[0007] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0008] The present invention discloses a control method for a photovoltaic transformer, including the following steps:

[0009] Conduct feature analysis on various system operation abnormal events caused by various historical acoustic feature data generated by the target photovoltaic transformer during its historical operation process, and obtain frequent system operation abnormal events and occasional system operation abnormal events;

[0010] Construct a binary tree knowledge graph based on the historical acoustic feature data corresponding to the frequent system operation abnormal events and occasional system operation abnormal events;

[0011] Obtain the real-time acoustic feature data generated by the target photovoltaic transformer during its real-time operation process through an acoustic sensor at a preset time node, analyze the system state of the target photovoltaic transformer at the current time node according to the real-time acoustic feature data and in combination with the binary tree knowledge graph, and generate an analysis result;

[0012] If the system state of the target photovoltaic transformer at the current time node is in a normal operation state, no regulation and control processing is performed on the target photovoltaic transformer;

[0013] If the system state of the target photovoltaic transformer at the current preset time node is in a state where occasional system operation abnormal events occur, no regulation and control processing is performed on the target photovoltaic transformer, and the operation state of the target photovoltaic transformer is continuously monitored at the next time node;

[0014] If the system state of the target photovoltaic transformer at the current preset time node is in a state where frequent system operation abnormal events occur, regulation and control processing is performed on the target photovoltaic transformer.

[0015] Furthermore, conduct feature analysis on various system operation abnormal events caused by various historical acoustic feature data generated by the target photovoltaic transformer during its historical operation process, and obtain frequent system operation abnormal events and occasional system operation abnormal events. Specifically:

[0016] Obtain various historical acoustic feature data generated by the target photovoltaic transformer during its historical operation process, and count various system operation abnormal events caused by the target photovoltaic transformer when generating various historical acoustic feature data according to the operation log of the target photovoltaic transformer;

[0017] Conduct statistical analysis on various system operation abnormal events caused by the target photovoltaic transformer when generating various historical acoustic feature data, and obtain the number of corresponding system operation abnormal events caused when generating various historical acoustic feature data;

[0018] Perform a ratio processing on the number of corresponding system operation abnormal events caused when generating various historical acoustic feature data and a preset value to obtain the frequency value of the corresponding system operation abnormal events caused when generating various historical acoustic feature data;

[0019] Compare the frequency values of the corresponding system operation abnormal events that occur when generating various historical acoustic feature data with a preset frequency value threshold;

[0020] Label the system operation abnormal events with frequency values greater than the preset frequency value threshold as frequent system operation abnormal events; label the system operation abnormal events with frequency values not greater than the preset frequency value threshold as occasional system operation abnormal events.

[0021] Furthermore, construct a binary tree knowledge graph based on the historical acoustic feature data corresponding to the frequent system operation abnormal events and the occasional system operation abnormal events, specifically:

[0022] Obtain the historical acoustic feature data corresponding to each frequent system operation abnormal event, and obtain the historical acoustic feature data corresponding to each occasional system operation abnormal event;

[0023] Construct a binary tree, and divide the binary tree into two main branches according to the frequent system operation abnormal events and the occasional system operation abnormal events, namely the first main branch and the second main branch;

[0024] Iteratively split the first main branch according to each frequent system operation abnormal event, so as to split a number of frequent system operation abnormal event leaf nodes on the first main branch; among them, the characteristic information of the corresponding frequent system operation abnormal event is stored on each frequent system operation abnormal event leaf node;

[0025] Iteratively split the second main branch according to each occasional system operation abnormal event, so as to split a number of occasional system operation abnormal event leaf nodes on the second main branch; among them, the characteristic information of the corresponding occasional system operation abnormal event is stored on each occasional system operation abnormal event leaf node;

[0026] Store the historical acoustic feature data corresponding to each frequent system operation abnormal event in the corresponding frequent system operation abnormal event leaf node; store the historical acoustic feature data corresponding to each occasional system operation abnormal event in the corresponding occasional system operation abnormal event leaf node; to form a binary tree knowledge graph.

[0027] Furthermore, obtain the real-time acoustic feature data generated by the target photovoltaic transformer during the real-time working process through an acoustic sensor at a preset time node, and analyze the system state of the target photovoltaic transformer at the current time node according to the real-time acoustic feature data and in combination with the binary tree knowledge graph, and generate an analysis result, specifically:

[0028] Acquire the real-time acoustic feature data generated by the target photovoltaic transformer during the real-time operation process through an acoustic sensor at a preset time node; and extract the historical acoustic feature data in each leaf node from the binary tree knowledge graph;

[0029] Introduce the Kendall rank correlation coefficient algorithm, and calculate the Kendall rank correlation coefficient values between the real-time acoustic feature data and the historical acoustic feature data in each leaf node based on the Kendall rank correlation coefficient algorithm;

[0030] Compare all the calculated Kendall rank correlation coefficient values with a preset coefficient value. If all the Kendall rank correlation coefficient values are not greater than the preset coefficient value, it indicates that the system state of the target photovoltaic transformer at the current time node is in a normal operating state;

[0031] If there is at least one Kendall rank correlation coefficient value greater than the preset coefficient value, mark the leaf node corresponding to the Kendall rank correlation coefficient value greater than the preset coefficient value, and determine the feature type of the marked leaf node; among them, the feature type includes the leaf node of the occasional system operation abnormal event and the leaf node of the frequent system operation abnormal event;

[0032] If the feature type of the marked leaf node is the leaf node of the frequent system operation abnormal event, it indicates that the system state of the target photovoltaic transformer at the current preset time node is in a state of frequent occurrence of operation abnormal events;

[0033] If the feature type of the marked leaf node is the leaf node of the occasional system operation abnormal event, it indicates that the system state of the target photovoltaic transformer at the current preset time node is in a state of occasional occurrence of operation abnormal events.

[0034] Furthermore, if the system state of the target photovoltaic transformer at the current preset time node is in a state of frequent occurrence of operation abnormal events, perform a regulation process on the target photovoltaic transformer. Specifically:

[0035] If the system state of the target photovoltaic transformer at the current preset time node is in a state of frequent occurrence of operation abnormal events, acquire the real-time working parameters of the target photovoltaic transformer at the current preset time node;

[0036] Introduce the genetic algorithm, use the real-time working parameters of the target photovoltaic transformer as decision variables, and encode the decision variables to form a chromosome representation to construct an initial population. Each individual in the population represents a possible regulation scheme;

[0037] Determine the key indicators related to the performance of the target photovoltaic transformer, including voltage deviation, power factor, temperature, and efficiency. Assign weights according to the importance of each key indicator for the normal operation of the system, multiply each indicator value by the corresponding weight and sum them up to construct a fitness function that can comprehensively evaluate the quality of the regulation scheme;

[0038] Perform a selection operation. According to the fitness value, adopt a preset selection strategy to select excellent individuals from the current population to enter the next-generation population;

[0039] Perform a crossover operation. According to the set crossover probability, perform gene exchange on the selected individuals to simulate the biological gene recombination process and generate new individuals of the control scheme to increase the diversity of the population;

[0040] Perform a mutation operation. Randomly change the genes in the individuals with a mutation probability less than the preset probability value to form new individuals;

[0041] Continuously iterate the above selection, crossover, and mutation operations. Re-evaluate the individual fitness in each round of iteration until the maximum number of iterations is reached. Then, screen out the control scheme corresponding to the optimal individual in the population to obtain the optimal working parameter control scheme of the target photovoltaic transformer. Among them, the optimal individual is the individual with the highest fitness;

[0042] Regulate the real-time working parameters of the target photovoltaic transformer according to the optimal working parameter control scheme.

[0043] The control method of the photovoltaic transformer further includes the following steps:

[0044] After regulating the real-time working parameters of the target photovoltaic transformer through the optimal working parameter control scheme, obtain the real-time acoustic feature data of the target photovoltaic transformer again, and analyze the system state of the target photovoltaic transformer according to the real-time acoustic feature data in combination with the binary tree knowledge graph;

[0045] If the target photovoltaic transformer is still in a state of frequent occurrence of abnormal operation events after the regulation process, control the target photovoltaic transformer to stop working, generate a warning message, and send the warning message to a preset terminal;

[0046] If the target photovoltaic transformer is in a state of occasional occurrence of abnormal operation events after the regulation process, continue to monitor the operation state of the target photovoltaic transformer at the next time node;

[0047] If the target photovoltaic transformer is in a normal operation state after the regulation process, cancel the continuous monitoring instruction for the state of the target photovoltaic transformer.

[0048] The present invention also discloses a photovoltaic transformer applied to the control method of any one of the above-mentioned photovoltaic transformers. The photovoltaic transformer includes a base and a transformer body, and the transformer body is installed and fixed through the base; heat dissipation fins are provided on the transformer body; a bushing and a controller are provided on the top of the transformer body.

[0049] The present invention also discloses a control system for a photovoltaic transformer. The control system includes a memory and a processor. A control method program for the photovoltaic transformer is stored in the memory. When the control method program for the photovoltaic transformer is executed by the processor, the steps of the control method for the photovoltaic transformer described in any one of the above are implemented.

[0050] The present invention solves the technical defects existing in the background art and has the following beneficial effects: By analyzing historical data to construct a knowledge graph and combining it with the monitoring and analysis of real-time acoustic feature data, the system state of the photovoltaic transformer can be accurately judged. And different processing strategies are adopted for different system states (normal, occasional abnormality, frequent abnormality), which not only avoids unnecessary interference with normal operation, but also can timely handle frequent abnormalities to ensure the stable operation of the system, and continuously monitor occasional abnormalities to grasp their development trend, thereby improving the reliability of the operation of the photovoltaic transformer and the intelligent level of management. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0052] Figure 1 is the overall control method flowchart of this photovoltaic transformer;

[0053] Figure 2 is the partial control method flowchart of this photovoltaic transformer;

[0054] Figure 3 is the structural schematic diagram of this photovoltaic transformer. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0055] In order to more clearly understand the above objects, features and advantages of the present invention, the present invention will be further described in detail below with reference to the drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0056] Many specific details are set forth in the following description in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0057] The present invention discloses a control method for a photovoltaic transformer, as Figure 1 shown, including the following steps:

[0058] S102. Conduct feature analysis on various system operation abnormal events that may be triggered when the target photovoltaic transformer generates various historical acoustic feature data during its historical operation process, and obtain frequently-occurring system operation abnormal events and occasionally-occurring system operation abnormal events;

[0059] S104. Construct a binary tree knowledge graph based on the historical acoustic feature data corresponding to the frequently-occurring system operation abnormal events and occasionally-occurring system operation abnormal events;

[0060] S106. Obtain the real-time acoustic feature data generated by the target photovoltaic transformer during its real-time operation process through an acoustic sensor at a preset time node, analyze the system state of the target photovoltaic transformer at the current time node according to the real-time acoustic feature data and in combination with the binary tree knowledge graph, and generate an analysis result;

[0061] S108. If the system state of the target photovoltaic transformer at the current time node is in a normal operation state, no regulation and control processing is performed on the target photovoltaic transformer;

[0062] S110. If the system state of the target photovoltaic transformer at the current preset time node is in a state where occasionally-occurring abnormal events occur, no regulation and control processing is performed on the target photovoltaic transformer, and the operation state of the target photovoltaic transformer is continuously monitored at the next time node;

[0063] S112. If the system state of the target photovoltaic transformer at the current preset time node is in a state where frequently-occurring abnormal events occur, regulation and control processing is performed on the target photovoltaic transformer.

[0064] Specifically, when the system is in a normal operation state, no regulation and control processing is performed because the transformer is operating normally at this time and no intervention is required. When in a state where occasionally-occurring abnormal events occur, no regulation and control processing is performed but continuous monitoring is carried out. This is because the occasional abnormality may be temporary or have a small impact, and continuous monitoring can further observe its development trend. And when in a state where frequently-occurring abnormal events occur, regulation and control processing is performed because the frequent abnormality indicates that there are relatively serious problems in the system, and timely intervention is required to avoid more serious failures or performance degradation. By analyzing historical data to construct a knowledge graph, and then combining the monitoring and analysis of real-time acoustic feature data, the system state of the photovoltaic transformer can be accurately judged. And different processing strategies are adopted for different system states (normal, occasionally-occurring abnormality, frequently-occurring abnormality), which not only avoids unnecessary intervention in normal operation, but also can timely handle frequently-occurring abnormalities to ensure the stable operation of the system, and at the same time continuously monitor occasionally-occurring abnormalities to master their development trend, thereby improving the reliability of the operation of the photovoltaic transformer and the intelligent level of management.

[0065] Furthermore, perform feature analysis on various system operation abnormal events that will be triggered when the target photovoltaic transformer generates various historical acoustic feature data during the historical working process, and obtain frequently-occurring system operation abnormal events and occasionally-occurring system operation abnormal events, such as Figure 2 as shown below:

[0066] S202. Obtain various historical acoustic feature data generated by the target photovoltaic transformer during the historical working process, and count various system operation abnormal events that will be triggered when the target photovoltaic transformer generates various historical acoustic feature data according to the operation log of the target photovoltaic transformer;

[0067] S204. Conduct statistical analysis on various system operation abnormal events that will be triggered when the target photovoltaic transformer generates various historical acoustic feature data, and obtain the number of corresponding system operation abnormal events that will be triggered when generating various historical acoustic feature data;

[0068] S206. Perform ratio processing on the number of corresponding system operation abnormal events that will be triggered when generating various historical acoustic feature data and a preset value to obtain the frequency value of the corresponding system operation abnormal events that will be triggered when generating various historical acoustic feature data;

[0069] S208. Compare the frequency value of the corresponding system operation abnormal events that will be triggered when generating various historical acoustic feature data with a preset frequency value threshold;

[0070] S210. Label the system operation abnormal events with a frequency value greater than the preset frequency value threshold as frequently-occurring system operation abnormal events; label the system operation abnormal events with a frequency value not greater than the preset frequency value threshold as occasionally-occurring system operation abnormal events.

[0071] Specifically, first, all historical acoustic feature data generated during the past operation of the target photovoltaic transformer need to be obtained, which serve as the basis for subsequent analysis. Meanwhile, according to the operation logs of the transformer, various system operation abnormal events accompanied by these historical acoustic feature data are counted. This step establishes the correlation between the acoustic feature data and the system operation abnormal events, enabling the discovery of potential problem clues from historical data. Statistical analysis is conducted on the system operation abnormal events triggered by each historical acoustic feature data to obtain the number of occurrences. Then, this number is processed by taking the ratio with a preset value to obtain the corresponding frequency value. This frequency value reflects the frequency of the specific historical acoustic feature data triggering system operation abnormal events during the historical operation process. Finally, the calculated frequency value is compared with the preset frequency value threshold. If the frequency value is greater than the preset frequency value threshold, the corresponding system operation abnormal event is labeled as a frequently occurring system operation abnormal event; if the frequency value is not greater than the preset frequency value threshold, it is labeled as an occasionally occurring system operation abnormal event. This labeling method helps to distinguish abnormal events with different severities or occurrence probabilities, providing an important basis for subsequent construction of the binary tree knowledge graph and judgment of the real-time operation status.

[0072] Through the above series of analysis and processing of historical acoustic feature data and system operation abnormal events, frequently occurring system operation abnormal events and occasionally occurring system operation abnormal events can be accurately distinguished. This helps to construct a more accurate binary tree knowledge graph, so that when analyzing the current system state of the target photovoltaic transformer based on real-time acoustic feature data, the type and severity of the abnormality can be judged more specifically.

[0073] Furthermore, a binary tree knowledge graph is constructed based on the historical acoustic feature data corresponding to frequently occurring system operation abnormal events and occasionally occurring system operation abnormal events, specifically as follows:

[0074] Obtain the historical acoustic feature data corresponding to each frequently occurring system operation abnormal event and the historical acoustic feature data corresponding to each occasionally occurring system operation abnormal event;

[0075] Construct a binary tree, and divide the binary tree into two main branches according to the frequently occurring system operation abnormal events and occasionally occurring system operation abnormal events, namely the first main branch and the second main branch;

[0076] Iteratively split the first main branch according to each frequently occurring system operation abnormal event to split out several leaf nodes of frequently occurring system operation abnormal events on the first main branch; among them, the characteristic information of the corresponding frequently occurring system operation abnormal event is stored on each leaf node of frequently occurring system operation abnormal events.

[0077] Iteratively split the second main branch according to each accidental system operation exception event, so as to split a number of accidental system operation exception event leaf nodes on the second main branch; wherein, the characteristic information of the corresponding accidental system operation exception event is stored on each accidental system operation exception event leaf node;

[0078] Store the historical acoustic characteristic data corresponding to each frequent system operation exception event in the corresponding frequent system operation exception event leaf node; store the historical acoustic characteristic data corresponding to each accidental system operation exception event in the corresponding accidental system operation exception event leaf node; so as to form a binary tree knowledge graph.

[0079] Specifically, construct a binary tree structure, and divide the binary tree into two main branches, namely the first main branch and the second main branch, according to the frequent system operation exception event and the accidental system operation exception event. This division method lays a framework foundation for subsequent separate processing of different types of exception events. For the first main branch, iteratively split according to each frequent system operation exception event, so as to generate a number of frequent system operation exception event leaf nodes on this main branch. Each leaf node stores the characteristic information of the corresponding frequent system operation exception event, which enables different frequent exception events to have clear positions and identifications in the binary tree structure. Similarly, for the second main branch, iteratively split according to each accidental system operation exception event to obtain a number of accidental system operation exception event leaf nodes, and each leaf node also stores the characteristic information of the corresponding accidental system operation exception event. Finally, store the historical acoustic characteristic data that triggers each frequent system operation exception event in the corresponding frequent system operation exception event leaf node, and the same is true for accidental system operation exception events. In this way, a binary tree knowledge graph is completely constructed, organizing different types of exception events and their related acoustic characteristic data in an orderly structure.

[0080] By constructing such a binary tree knowledge graph, frequent system operation exception events, accidental system operation exception events and their corresponding historical acoustic characteristic data can be efficiently and orderly organized. When monitoring the real-time operation state of the target photovoltaic transformer, the real-time acoustic characteristic data can be quickly searched and matched in the binary tree knowledge graph to accurately judge whether the current operation state belongs to frequent exception, accidental exception or normal state. This structure helps to improve the analysis efficiency and accuracy, reduce judgment errors, and thus can more accurately take corresponding measures according to different operation states, such as timely regulating and processing for frequent exception states and continuously monitoring for accidental exception states, to ensure the stable operation of the photovoltaic transformer.

[0081] Further, at a preset time node, real-time acoustic feature data generated by the target photovoltaic transformer during real-time operation is acquired through an acoustic sensor, and based on the real-time acoustic feature data and in combination with a binary tree knowledge graph, the system state of the target photovoltaic transformer at the current time node is analyzed to generate an analysis result, specifically:

[0082] At a preset time node, real-time acoustic feature data generated by the target photovoltaic transformer during real-time operation is acquired through an acoustic sensor; and historical acoustic feature data within each leaf node is extracted from the binary tree knowledge graph;

[0083] The Kendall rank correlation coefficient algorithm is introduced, and based on the Kendall rank correlation coefficient algorithm, the Kendall rank correlation coefficient values between the real-time acoustic feature data and the historical acoustic feature data within each leaf node are calculated;

[0084] The calculated Kendall rank correlation coefficient values are all compared with a preset coefficient value. If each of the Kendall rank correlation coefficient values is not greater than the preset coefficient value, it indicates that the system state of the target photovoltaic transformer at the current time node is in a normal operating state;

[0085] If there is at least one Kendall rank correlation coefficient value greater than the preset coefficient value, the leaf node corresponding to the Kendall rank correlation coefficient value greater than the preset coefficient value is marked, and the feature type of the marked leaf node is judged; wherein, the feature type includes a leaf node of an occasional system operation abnormal event and a leaf node of a frequent system operation abnormal event;

[0086] If the feature type of the marked leaf node is a leaf node of a frequent system operation abnormal event, it indicates that the system state of the target photovoltaic transformer at the current preset time node is in a state of frequent occurrence of operation abnormal events;

[0087] If the feature type of the marked leaf node is a leaf node of an occasional system operation abnormal event, it indicates that the system state of the target photovoltaic transformer at the current preset time node is in a state of occasional occurrence of operation abnormal events.

[0088] Specifically, at a preset time node, an acoustic sensor is used to collect real-time acoustic feature data generated by the target photovoltaic transformer during real-time operation. At the same time, historical acoustic feature data stored in each leaf node is extracted from the pre-constructed binary tree knowledge graph. This step provides a data basis for subsequent correlation analysis. The real-time data reflects the current state, and the historical data is the basis for judgment.

[0089] The Kendall rank correlation coefficient algorithm is introduced to calculate the Kendall rank correlation coefficient value between the real-time acoustic feature data and the historical acoustic feature data within each leaf node. The Kendall rank correlation coefficient is a statistic used to measure the correlation between two variables and is used here to measure the similarity between the real-time acoustic features and the historical acoustic features. The calculated Kendall rank correlation coefficient value is compared with a preset coefficient value. If all the Kendall rank correlation coefficient values are not greater than the preset coefficient value, it means that the real-time acoustic feature data has no strong correlation with any historical acoustic feature data that may indicate an anomaly, and thus it can be determined that the system state of the target photovoltaic transformer at the current time node is in a normal operating state.

[0090] If there is at least one Kendall rank correlation coefficient value greater than the preset coefficient value, the corresponding leaf node is marked. Then, the feature type of the marked leaf node is determined. If it is a leaf node of frequent system operation anomaly events, it means that the current real-time acoustic feature data has a strong correlation with the acoustic features related to frequent anomalies in history, and then the system state of the target photovoltaic transformer at the current preset time node is in a state of frequent occurrence of operation anomaly events. If it is a leaf node of occasional system operation anomaly events, it indicates that the system state of the target photovoltaic transformer at the current preset time node is in a state of occasional occurrence of operation anomaly events.

[0091] Through this analysis method based on the Kendall rank correlation coefficient algorithm and combined with the binary tree knowledge graph, the system state of the target photovoltaic transformer at the current time node can be accurately analyzed. It can effectively distinguish between the normal state, the occasional occurrence state of operation anomaly events, and the frequent occurrence state of operation anomaly events. This precise state judgment provides a basis for subsequent different response measures for the photovoltaic transformer. For example, no intervention is required in the normal state, continuous monitoring can be carried out first in the occasional anomaly state, and timely regulation and treatment can be carried out in the frequent anomaly state, thus improving the accuracy and effectiveness of the operation management of the photovoltaic transformer, ensuring its stable operation and improving the reliability of the entire photovoltaic power generation system.

[0092] Furthermore, if the system state of the target photovoltaic transformer at the current preset time node is in a state of frequent occurrence of operation anomaly events, the target photovoltaic transformer is regulated and processed specifically as follows:

[0093] If the system state of the target photovoltaic transformer at the current preset time node is in a state of frequent occurrence of operation anomaly events, the real-time working parameters of the target photovoltaic transformer at the current preset time node are obtained;

[0094] The genetic algorithm is introduced, the real-time working parameters of the target photovoltaic transformer are used as decision variables, and the decision variables are encoded to form a chromosome representation to construct an initial population. Each individual in the population represents a possible regulation scheme;

[0095] Determine the key indicators related to the performance of the target photovoltaic transformer, including voltage deviation, power factor, temperature, and efficiency. Assign weights according to the importance of each key indicator for the normal operation of the system. Multiply each indicator value by the corresponding weight and sum them up to construct a fitness function that can comprehensively evaluate the pros and cons of the control scheme.

[0096] Perform the selection operation. According to the fitness value and using a preset selection strategy, select excellent individuals from the current population to enter the next generation population to ensure the inheritance of the genes of excellent control schemes.

[0097] Perform the crossover operation. According to the set crossover probability, exchange the genes of the selected individuals to simulate the process of biological gene recombination and generate new individuals of the control scheme to increase the diversity of the population.

[0098] Perform the mutation operation. Randomly change the genes in the individuals with a mutation probability less than the preset probability value to form new individuals.

[0099] Continuously iterate the above selection, crossover, and mutation operations. Re-evaluate the individual fitness in each round of iteration until the maximum number of iterations is reached. Then, screen out the control scheme corresponding to the optimal individual in the population to obtain the optimal working parameter control scheme for the target photovoltaic transformer. Among them, the optimal individual is the individual with the highest fitness.

[0100] Regulate the real-time working parameters of the target photovoltaic transformer according to the optimal working parameter control scheme.

[0101] Specifically, when it is determined that the target photovoltaic transformer is in a state with frequent abnormal operation events at the current preset time node, first obtain its real-time operating parameters at that moment (such as input voltage, output voltage, operating temperature, operating humidity, etc.). These operating parameters contain various information about the current operating state of the transformer and are the basis for subsequent search of regulation schemes. Introduce the genetic algorithm, and use the real-time operating parameters as decision variables. Form chromosome representations through encoding to construct an initial population, where each individual in the population represents a possible regulation scheme. This step is the starting point for using the genetic algorithm for optimization search, simulating the initial state of a biological population, and each individual (regulation scheme) has the potential for optimization. Determine the key indicators related to the performance of the target photovoltaic transformer, such as voltage deviation, power factor, temperature, and efficiency, etc. Assign weights according to the importance of these indicators for the normal operation of the system, and multiply each indicator value by the corresponding weight and then sum to construct a fitness function. This function can comprehensively evaluate the advantages and disadvantages of the regulation scheme, and the higher the fitness, the more the regulation scheme can meet the requirements for the normal operation of the transformer. Perform the selection operation, and select excellent individuals from the current population into the next-generation population according to the fitness value using a preset selection strategy. This operation is similar to natural selection in biological evolution, ensuring that the genes of excellent regulation schemes (manifested as the excellent characteristics of individuals in the genetic algorithm) are inherited, and making the population develop in a better direction. According to the set crossover probability, perform gene exchange on the selected individuals to simulate the process of biological gene recombination. In this way, new individual regulation schemes are generated, increasing the diversity of the population and helping to discover more potential excellent regulation schemes. Randomly change the genes in the individuals with a mutation probability less than the preset probability value to form new individuals. The mutation operation can introduce new gene combinations, avoid the population falling into a local optimal solution, further explore the entire solution space, and increase the possibility of finding the global optimal regulation scheme. Continuously iterate the above selection, crossover, and mutation operations, re-evaluate the individual fitness in each round of iteration until the maximum number of iterations is reached. Finally, screen out the regulation scheme corresponding to the optimal individual (the individual with the highest fitness) in the population to obtain the optimal working parameter regulation scheme for the target photovoltaic transformer. Regulate the real-time operating parameters of the target photovoltaic transformer according to the obtained optimal working parameter regulation scheme, so as to improve the operating state of the transformer and make it recover from the frequent abnormal state to a normal or near-normal operating state.

[0102] Through this regulation processing method based on genetic algorithm, when the target photovoltaic transformer is in a state where abnormal operation events occur frequently, it can construct and search for the optimal working parameter regulation scheme according to its current real-time working parameters. By constructing a fitness function to accurately evaluate the advantages and disadvantages of the regulation scheme, and then through iterative optimization of selection, crossover, and mutation operations, local optimal solutions can be effectively avoided, and the possible regulation scheme space can be comprehensively explored. The finally obtained optimal regulation scheme can accurately regulate the real-time working parameters of the target photovoltaic transformer, thereby improving its operating state, enhancing the performance of the photovoltaic transformer, reducing the adverse effects caused by frequent abnormalities, and ensuring the stable operation of the photovoltaic power generation system.

[0103] The control method of the photovoltaic transformer further includes the following steps:

[0104] After regulating the real-time working parameters of the target photovoltaic transformer through the optimal working parameter regulation scheme, obtain the real-time acoustic feature data of the target photovoltaic transformer again, and analyze the system state of the target photovoltaic transformer according to the real-time acoustic feature data and in combination with the binary tree knowledge graph;

[0105] If the target photovoltaic transformer is still in a state where abnormal operation events occur frequently after the regulation process, control the target photovoltaic transformer to stop working, generate a warning message, and send the warning message to a preset terminal;

[0106] If the target photovoltaic transformer is in a state where abnormal operation events occur occasionally after the regulation process, continue to monitor the operating state of the target photovoltaic transformer at the next time node;

[0107] If the target photovoltaic transformer is in a normal operating state after the regulation process, cancel the continuous monitoring instruction for the state of the target photovoltaic transformer.

[0108] Specifically, after regulating the real-time working parameters of the target photovoltaic transformer through the optimal working parameter regulation scheme, obtain its real-time acoustic feature data again, and analyze its system state in combination with the binary tree knowledge graph. This step is to verify the effectiveness of the regulation measures. By using the same analysis method as before (based on acoustic feature data and binary tree knowledge graph), the operating state of the transformer after regulation can be accurately judged. If the target photovoltaic transformer is still in a state where abnormal operation events occur frequently after the regulation process, it indicates that the previous regulation scheme has not effectively solved the problem. At this time, control the target photovoltaic transformer to stop working to avoid possible more serious faults or safety hazards. At the same time, generate a warning message and send it to a preset terminal, so that relevant personnel can timely learn about the situation and take further measures, such as on-site inspection, maintenance, etc.

[0109] If it is in the state of occasional occurrence of abnormal operation events after regulation, it indicates that the regulation measures have certain effects, but the transformer has not fully returned to normal. In this case, continue to monitor the operating state of the target photovoltaic transformer at the next time node to promptly detect possible deterioration of problems.

[0110] When it is in the normal operating state after regulation, cancel the continuous monitoring instruction for the state of the target photovoltaic transformer. This is because the transformer has returned to normal operation and no additional continuous monitoring is required, thus saving monitoring resources and reducing unnecessary operations.

[0111] Through the re - analysis of the state after regulation and corresponding treatment measures, the effectiveness of the regulation plan can be comprehensively evaluated. For the situation where frequent abnormalities still occur after regulation, stop the transformer operation in a timely manner and give an early warning to ensure system safety; for the situation where it turns into occasional abnormalities, continue to monitor to prevent problem deterioration; for the situation where it returns to normal, cancel the monitoring instruction to improve the utilization efficiency of monitoring resources. Overall, it improves the management level of the operating state of photovoltaic transformers and ensures the stable and safe operation of photovoltaic transformers and the entire photovoltaic power generation system.

[0112] In addition, this control method further includes the following steps:

[0113] During the operation of the target photovoltaic transformer, obtain the frequency response characteristics of the target photovoltaic transformer at several preset time nodes;

[0114] Based on discrete wavelet transform, perform multi - layer decomposition operations on the frequency response characteristic data of each time node to obtain wavelet coefficients at different scales;

[0115] For each time node, according to the preset energy calculation rule, calculate the energy values of the wavelet coefficients at each scale; and construct a data structure to store the energy values corresponding to different scales at each time node;

[0116] Taking the scale as the abscissa and the energy values corresponding to different time nodes as the ordinate, generate an energy distribution curve graph of the target photovoltaic transformer within a preset time period;

[0117] Obtain the preset work tasks of the target photovoltaic transformer within a preset time period, and obtain the energy distribution threshold range of the target photovoltaic transformer within the preset time period according to the preset work tasks;

[0118] Determine the upper energy distribution threshold and the lower energy distribution threshold according to the energy distribution threshold range of the target photovoltaic transformer within the preset time period;

[0119] Map the upper energy distribution threshold and the lower energy distribution threshold in the energy distribution curve graph to define a normal working area and an abnormal working area in the energy distribution curve graph;

[0120] Calculate the curve length of the energy distribution curve in the abnormal operating region and the curve length of the energy distribution curve in the normal operating region in the energy distribution curve graph;

[0121] Perform a ratio process on the curve length of the energy distribution curve in the abnormal operating region and the curve length of the energy distribution curve in the normal operating region to obtain the curve length ratio of the energy distribution region;

[0122] Compare the curve length ratio of the energy distribution region with a preset ratio; if the curve length ratio of the energy distribution region is greater than the preset ratio, control the target photovoltaic transformer to stop working, generate a warning message, and send the warning message to a preset terminal.

[0123] It should be noted that the curve length ratio of the energy distribution region is obtained by calculating the ratio of the curve length of the energy distribution curve in the abnormal operating region to the curve length in the normal operating region. It can quantitatively reflect the degree to which the operating state of the target photovoltaic transformer deviates from the normal state from a new perspective. The larger the curve length ratio of the energy distribution region, the higher the proportion of the energy distribution curve in the abnormal region, which also means that the probability of the target photovoltaic transformer being in an abnormal operating state within the preset time period is greater or the duration of the abnormal state is relatively longer; conversely, the smaller the curve length ratio of the energy distribution region, the more the transformer tends to be in a normal operating state within the preset time period. This parameter provides a unique quantitative basis for the state evaluation and fault diagnosis of the photovoltaic transformer.

[0124] It should be noted that during the operation of the target photovoltaic transformer, the frequency response characteristic data is obtained at preset time nodes. Then, multi-level decomposition operations are performed using discrete wavelet transform to obtain wavelet coefficients at different scales. For each time node, the energy values of these wavelet coefficients are calculated according to preset rules, and a data structure is constructed to store the energy values corresponding to different scales at each time node. This series of operations deeply mines and organizes the original frequency response characteristic data. Discrete wavelet transform helps analyze data from multiple scales, and the energy value calculation provides more representative data for subsequent analysis. An energy distribution curve graph is generated with the scale as the abscissa and the energy values corresponding to different time nodes as the ordinate. According to the preset working tasks of the target photovoltaic transformer, the energy distribution threshold range is determined, and then the upper and lower energy distribution thresholds are obtained and mapped onto the curve graph to define the normal and abnormal working regions. This construction method enables the working state region of the transformer to be intuitively observed from the graph, linking the abstract energy distribution with the working state. In the energy distribution curve graph, the curve lengths of the abnormal and normal working regions are calculated respectively, and then the ratio of the two is obtained to get the energy distribution region curve length ratio. This ratio comprehensively reflects the distribution of the energy distribution curve in different working regions and quantifies the working state characteristics of the transformer within the preset time period from a new perspective. The energy distribution region curve length ratio is compared with the preset ratio. If it is greater than the preset ratio, it indicates that the situation in the abnormal working region of the transformer is relatively serious. At this time, the transformer is controlled to stop working and a warning message is sent to the preset terminal. This step realizes the effective monitoring of the working state of the transformer, timely discovers potential serious problems and takes measures to avoid possible more serious failures or damages, ensuring the safe and stable operation of the photovoltaic transformer and the entire photovoltaic system.

[0125] In summary, through multi-step processing of the frequency response characteristic data of the target photovoltaic transformer, constructing an energy distribution curve graph and defining the working region, calculating a special ratio and comparing it with the preset value, the quantitative evaluation and monitoring of the working state of the photovoltaic transformer are realized. It can timely detect the relatively serious situation of the abnormal working state of the transformer, automatically stop the transformer from working and give a warning, effectively improving the safety and reliability of the operation of the photovoltaic transformer, reducing the losses caused by faults, and ensuring the stable operation of the entire photovoltaic power generation system.

[0126] In addition, this control method further includes the following steps:

[0127] Obtain the state transition probability values of the target photovoltaic transformer when operating under various working environment parameter conditions through a big data network;

[0128] Take the working environment parameters as input nodes and the state transition probability values as output nodes, and construct a graph neural network according to the input nodes and output nodes;

[0129] Determine the connection relationship between the working environment parameter input node and the state transition probability value output node in the graph neural network, and construct a conditional transition probability matrix according to the connection relationship between the working environment parameter input node and the state transition probability value output node;

[0130] Construct a state transition probability prediction model, and embed the conditional transition probability matrix into the state transition probability prediction model;

[0131] During the operation of the target photovoltaic transformer, obtain the real-time working environment parameters of the target photovoltaic transformer at a preset time node, and import the real-time working environment parameters into the state transition probability prediction model for prediction;

[0132] Through prediction, obtain the state transition probability value of the target photovoltaic transformer under the condition of real-time working environment parameters;

[0133] If the state transition probability value of the target photovoltaic transformer under the condition of real-time working environment parameters is greater than the preset probability value, restart the state continuous monitoring instruction for the target photovoltaic transformer.

[0134] It should be noted that first, obtain the state transition probability values of the target photovoltaic transformer under different working environment parameters through the big data network, and then construct a graph neural network based on this, set the working environment parameters as the input node, and the state transition probability value as the output node. This step lays a data and structural foundation for subsequent analysis, and uses the characteristics of the graph neural network to process the input-output relationship. After determining the connection relationship between the input and output nodes in the graph neural network, construct a conditional transition probability matrix and embed it into the state transition probability prediction model. The conditional transition probability matrix reflects the probability transfer situation under different input-output relationships. After being embedded in the model, the model can have the ability to predict the state transition probability based on environmental parameters. Obtain the real-time working environment parameters during the operation of the target photovoltaic transformer and import them into the prediction model to obtain the real-time state transition probability value. If this value is greater than the preset probability value, restart the state continuous monitoring instruction. This enables timely adjustment of the monitoring strategy according to the real-time environmental situation and focuses on the possible state transition situations. By constructing a graph neural network, a conditional transition probability matrix, and a state transition probability prediction model, the prediction of the state transition probability of the target photovoltaic transformer based on its working environment parameters is realized. Decide whether to restart the state continuous monitoring instruction according to the prediction result, improve the accuracy and timeliness of the state monitoring of the photovoltaic transformer, and ensure its stable operation.

[0135] The present invention also discloses a photovoltaic transformer, which is applied to any one of the control methods of a photovoltaic transformer as described above, such as Figure 3As shown in the figure, the photovoltaic transformer includes a base 401 and a transformer body 402, and the transformer body is installed and fixed through the base; heat dissipation fins 403 are provided on the transformer body; bushings 404 and a controller 405 are provided at the top of the transformer body.

[0136] The present invention also discloses a control system for a photovoltaic transformer. The control system includes a memory and a processor. A control method program for the photovoltaic transformer is stored in the memory. When the control method program for the photovoltaic transformer is executed by the processor, the control method steps of any one of the above-mentioned photovoltaic transformers are realized.

[0137] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should be covered within the protection scope of the present invention.

Claims

1. A control method for a photovoltaic transformer, characterized in that, Including the following steps: Conduct feature analysis on various system operation abnormal events that may be triggered when the target photovoltaic transformer generates various historical acoustic feature data during its historical operation process, and obtain frequently-occurring system operation abnormal events and occasionally-occurring system operation abnormal events; Construct a binary tree knowledge graph based on the historical acoustic feature data corresponding to the frequently-occurring system operation abnormal events and occasionally-occurring system operation abnormal events; At a preset time node, obtain the real-time acoustic feature data generated by the target photovoltaic transformer during its real-time operation process through an acoustic sensor, and analyze the system state of the target photovoltaic transformer at the current time node according to the real-time acoustic feature data and in combination with the binary tree knowledge graph, and generate an analysis result; If the system state of the target photovoltaic transformer at the current time node is in a normal operation state, no regulation and control processing is performed on the target photovoltaic transformer; If the system state of the target photovoltaic transformer at the current preset time node is in a state where occasionally-occurring system operation abnormal events occur, no regulation and control processing is performed on the target photovoltaic transformer, and the operation state of the target photovoltaic transformer is continuously monitored at the next time node; If the system state of the target photovoltaic transformer at the current preset time node is in a state where frequently-occurring system operation abnormal events occur, regulation and control processing is performed on the target photovoltaic transformer; Among them, at a preset time node, obtain the real-time acoustic feature data generated by the target photovoltaic transformer during its real-time operation process through an acoustic sensor, and analyze the system state of the target photovoltaic transformer at the current time node according to the real-time acoustic feature data and in combination with the binary tree knowledge graph, and generate an analysis result. Specifically: At a preset time node, obtain the real-time acoustic feature data generated by the target photovoltaic transformer during its real-time operation process through an acoustic sensor; and extract the historical acoustic feature data in each leaf node from the binary tree knowledge graph; Introduce the Kendall rank correlation coefficient algorithm, and calculate the Kendall rank correlation coefficient values between the real-time acoustic feature data and the historical acoustic feature data in each leaf node based on the Kendall rank correlation coefficient algorithm; Compare all the calculated Kendall rank correlation coefficient values with a preset coefficient value. If each Kendall rank correlation coefficient value is not greater than the preset coefficient value, it indicates that the system state of the target photovoltaic transformer at the current time node is in a normal operation state; If there is at least one Kendall rank correlation coefficient value greater than the preset coefficient value, mark the leaf node corresponding to the Kendall rank correlation coefficient value greater than the preset coefficient value, and judge the feature type of the marked leaf node; among them, the feature type includes the leaf node of occasionally-occurring system operation abnormal events and the leaf node of frequently-occurring system operation abnormal events; If the feature type of the marked leaf node is the leaf node of frequently-occurring system operation abnormal events, it indicates that the system state of the target photovoltaic transformer at the current preset time node is in a state where frequently-occurring system operation abnormal events occur; If the feature type of the marked leaf node is the leaf node of occasionally-occurring system operation abnormal events, it indicates that the system state of the target photovoltaic transformer at the current preset time node is in a state where occasionally-occurring system operation abnormal events occur.

2. The control method of a photovoltaic transformer according to claim 1, wherein Conduct feature analysis on various system operation abnormal events caused by various historical acoustic feature data generated by the target photovoltaic transformer during its historical operation process, and obtain frequently-occurring system operation abnormal events and occasionally-occurring system operation abnormal events, specifically: Obtain various historical acoustic feature data generated by the target photovoltaic transformer during its historical operation process, and count various system operation abnormal events caused by various historical acoustic feature data generated by the target photovoltaic transformer during its historical operation process according to the operation log of the target photovoltaic transformer; Conduct statistical analysis on various system operation abnormal events caused by various historical acoustic feature data generated by the target photovoltaic transformer during its historical operation process, and obtain the number of corresponding system operation abnormal events caused by generating various historical acoustic feature data; Perform ratio processing on the number of corresponding system operation abnormal events caused by generating various historical acoustic feature data and a preset value to obtain the frequency value of the corresponding system operation abnormal events caused by generating various historical acoustic feature data; Compare the frequency value of the corresponding system operation abnormal events caused by generating various historical acoustic feature data with a preset frequency value threshold; Label the system operation abnormal events with frequency values greater than the preset frequency value threshold as frequently-occurring system operation abnormal events; Label the system operation abnormal events with frequency values not greater than the preset frequency value threshold as occasionally-occurring system operation abnormal events.

3. A control method for a photovoltaic transformer according to claim 2, characterized in that, Construct a binary tree knowledge graph according to the historical acoustic feature data corresponding to the frequently-occurring system operation abnormal events and occasionally-occurring system operation abnormal events, specifically: Obtain the historical acoustic feature data corresponding to each frequently-occurring system operation abnormal event and the historical acoustic feature data corresponding to each occasionally-occurring system operation abnormal event; Construct a binary tree, and divide the binary tree into two main branches according to the frequently-occurring system operation abnormal events and occasionally-occurring system operation abnormal events, namely the first main branch and the second main branch; Iteratively split the first main branch according to each frequently-occurring system operation abnormal event to split out several frequently-occurring system operation abnormal event leaf nodes on the first main branch; among them, the feature information of the corresponding frequently-occurring system operation abnormal event is stored on each frequently-occurring system operation abnormal event leaf node; Iteratively split the second main branch according to each occasionally-occurring system operation abnormal event to split out several occasionally-occurring system operation abnormal event leaf nodes on the second main branch; among them, the feature information of the corresponding occasionally-occurring system operation abnormal event is stored on each occasionally-occurring system operation abnormal event leaf node; Store the historical acoustic feature data corresponding to each frequently-occurring system operation abnormal event in the corresponding frequently-occurring system operation abnormal event leaf node; store the historical acoustic feature data corresponding to each occasionally-occurring system operation abnormal event in the corresponding occasionally-occurring system operation abnormal event leaf node; to form a binary tree knowledge graph.

4. A control method for a photovoltaic transformer according to claim 1, characterized in that, If the system state of the target photovoltaic transformer is in a state of frequent occurrence of operation abnormal events at the current preset time node, then perform regulation processing on the target photovoltaic transformer, specifically: If the system state of the target photovoltaic transformer at the current preset time node is in a state where abnormal operation events frequently occur, then the real-time working parameters of the target photovoltaic transformer at the current preset time node are obtained; Genetic algorithm is introduced, the real-time working parameters of the target photovoltaic transformer are used as decision variables, and the decision variables are encoded into chromosome representation to construct the initial population. Each individual in the population represents a possible regulation scheme. Determine the key indicators related to the performance of the target photovoltaic transformer, including voltage deviation, power factor, temperature and efficiency, assign weights to each key indicator according to its importance to the normal operation of the system, multiply each indicator value by the corresponding weight and sum them up, and construct a fitness function that can comprehensively evaluate the advantages and disadvantages of the control scheme; Execute the selection operation, adopt the preset selection strategy according to the fitness value, and select excellent individuals from the current population to enter the next generation population; Perform crossover operations, exchange genes of selected individuals according to the set crossover probability, simulate the biological gene recombination process, and generate new regulation scheme individuals to increase the diversity of the population; Perform mutation operations to randomly change the genes of individuals whose mutation probability is less than the preset probability value to form new individuals; The above selection, crossover and mutation operations are continuously iterated, and the fitness of the individual is re-evaluated in each round of iteration until the maximum number of iterations is reached, and the control scheme corresponding to the best individual is screened out from the population to obtain the optimal working parameter control scheme of the target photovoltaic transformer; wherein the best individual is the individual with the highest fitness; The real-time operating parameters of the target photovoltaic transformer are regulated according to the optimal operating parameter regulation scheme.

5. A control method for a photovoltaic transformer according to claim 4, characterized in that, The control method of the photovoltaic transformer further comprises the following steps: After the real-time working parameters of the target photovoltaic transformer are regulated by the optimal working parameter regulation scheme, the real-time acoustic feature data of the target photovoltaic transformer is obtained again, and the system state of the target photovoltaic transformer is analyzed according to the real-time acoustic feature data and in combination with the binary tree knowledge graph; If the target photovoltaic transformer is still in a state of frequent abnormal operation after being regulated, the target photovoltaic transformer is controlled to stop working, and an early warning message is generated and sent to a preset terminal; If the target photovoltaic transformer is in a state of occasional abnormal operation after being regulated, the operation state of the target photovoltaic transformer will continue to be monitored at the next time node; If the target photovoltaic transformer is in a normal operating state after being regulated, the instruction for continuous monitoring of the state of the target photovoltaic transformer is released.

6. A photovoltaic transformer, applied to a control method of a photovoltaic transformer according to any one of claims 1 to 5, characterized in that: The photovoltaic transformer comprises a base and a transformer body, and the transformer body is installed and fixed by the base; the transformer body is provided with heat dissipation fins; and the top of the transformer body is provided with a bushing and a controller.

7. A control system for a photovoltaic transformer, characterized in that, The control system includes a memory and a processor. A control method program for a photovoltaic transformer is stored in the memory. When the control method program for the photovoltaic transformer is executed by the processor, the control method steps of the photovoltaic transformer as described in any one of claims 1 to 5 are implemented.

Images