Intelligent fault detection and maintenance system for photovoltaic power station

Abstract

The invention provides an intelligent fault detection and maintenance system for a photovoltaic power station, and relates to the technical field of photovoltaic power station operation and maintenance, and the system comprises a data obtaining module which is used for obtaining the operation data of each station in real time, and summarizing and outputting first data; the preprocessing module is used for preprocessing the first data by utilizing a preset preprocessing method and outputting to-be-analyzed data; the data analysis module is used for performing exception analysis on the to-be-analyzed data by utilizing a preset big data analysis model and outputting an exception analysis result; and the exception handling module is used for selecting an exception handling strategy and an exception handling method matched with the exception analysis result from a strategy and method database, and handling the exception condition of each site based on the exception handling strategy and the exception handling method. According to the invention, intelligent monitoring and fault processing of the operation state of the photovoltaic power station are realized, the fault detection and maintenance efficiency of the photovoltaic power station is improved, and the reliability, stability and safety of the photovoltaic power station are further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power station operation and maintenance, and in particular to an intelligent fault detection and maintenance system for a photovoltaic power station. Background Art

[0002] The fault detection and maintenance system of photovoltaic power plants usually includes traditional monitoring equipment and data acquisition systems, as well as some fault diagnosis methods based on rules and statistical analysis.

[0003] At present, the current photovoltaic power station fault detection and maintenance system still has some shortcomings. Traditional systems can usually only collect limited monitoring data and cannot fully reflect the operating status of photovoltaic power station equipment, making it difficult to detect potential problems in a timely manner. In addition, the current fault diagnosis methods mostly rely on manual experience and rules, which makes it difficult to accurately diagnose complex faults and is prone to missed diagnosis or misdiagnosis.

[0004] Therefore, the present invention provides an intelligent fault detection and maintenance system for a photovoltaic power station. Summary of the invention

[0005] The present invention provides an intelligent fault detection and maintenance system for a photovoltaic power station, which is used to realize intelligent monitoring of the operating status of the photovoltaic power station and fault processing, improve the fault detection and maintenance efficiency of the photovoltaic power station, and further improve the reliability, stability and safety of the photovoltaic power station.

[0006] The present invention provides an intelligent fault detection and maintenance system for a photovoltaic power station, comprising: A data acquisition module, used to acquire the operation data of each site in real time, and summarize and output the first data; A preprocessing module, used to preprocess the first data using a preset preprocessing method and output data to be analyzed; A data analysis module, used to perform anomaly analysis on the data to be analyzed using a preset big data analysis model, and output anomaly analysis results; The exception handling module is used to select an exception handling strategy and method that matches the exception analysis result from the strategy and method database, and handle the abnormal conditions of each site based on the exception handling strategy and method.

[0007] Preferably, the data acquisition module includes: The demand acquisition submodule is used to obtain the user's data monitoring needs in real time through the preset IO port; The data acquisition submodule is used to capture the operation data of each site in real time based on the data monitoring requirements, and summarize the data to obtain the first data.

[0008] Preferably, the data acquisition submodule includes: A data determination unit, used to determine the power station site corresponding to the data to be captured and the data type and data volume under each site based on the data monitoring requirements, and output a demand data comparison table; The data acquisition unit is used to activate and adjust the parameters of the preset monitoring equipment set at each site based on the demand data comparison table, and to acquire the equipment operating parameters in the corresponding site in real time through each preset monitoring device, and summarize them to obtain the first data.

[0009] Preferably, the preprocessing module comprises: A method matching submodule, used for acquiring a preprocessing method matching the first data in a method database; The preprocessing submodule is used to preprocess the first data based on the preprocessing method, and output the data that meets the preset quality requirements as data to be analyzed.

[0010] Preferably, the method matching submodule includes: A feature extraction unit, configured to extract features from the first data, match the extracted features with a preset abnormal data feature library, and collect and summarize the extracted features that meet the preset matching conditions to obtain a first feature set; A method matching unit is used to screen and obtain a matching preprocessing method in a method database based on the first feature set and in combination with a preset feature-method comparison table.

[0011] Preferably, the method matching unit comprises: A feature matching subunit, used to obtain a preprocessing method corresponding to each data feature in the first feature set in combination with the preset feature-method comparison table; The list establishment subunit is used to obtain the data source corresponding to each data feature in the first feature set in the first data, and establish a mapping between the data source, data features and preprocessing methods to construct a data source-feature-method mapping table.

[0012] Preferably, the data analysis module includes: A historical data acquisition submodule is used to obtain the user's data analysis requirements, and based on the data analysis requirements, filter out historical power plant operation data that matches the data to be analyzed in the historical database; A data verification submodule, used to compare and verify the historical power plant operation data using a preset data verification method, and output the historical power plant operation data that meets the preset verification conditions as data to be divided; The data partitioning submodule is used to divide the data to be divided according to the acquired data analysis requirements of the user and to obtain a training set, a test set and a validation set by using a preset data partitioning method; A model selection submodule, used to select a matching first model from a model database based on the data analysis requirement; A model training submodule, used for inputting the training set, the test set and the validation set into the first model for training and optimization, and outputting the first model that meets the preset performance conditions as a preset big data analysis model; A data analysis submodule is used to perform real-time analysis on the data to be analyzed by using the preset big data analysis model to obtain real-time analysis data, and at the same time, perform predictive analysis on the data to be analyzed to obtain predictive analysis data; A chart output submodule, which is used to obtain a real-time analysis chart and a predictive analysis table based on the timestamps corresponding to the real-time analysis data and the predictive analysis data and in combination with a preset chart establishment method; The abnormal feature extraction submodule is used to extract the data features in the real-time analysis graph and the prediction analysis table, and match them with the data features in the preset abnormal feature library, and summarize the successfully matched data features and output them as an abnormal feature set; The state analysis submodule is used to obtain real-time state analysis data and predicted state analysis data matching the data features in the abnormal feature set in combination with a preset feature-state comparison table, and summarize and output a state analysis table; The fault identification submodule is used to determine the fault type and the corresponding safety level corresponding to each abnormal state based on the state analysis table and in combination with a preset state-fault mapping diagram, and output a real-time-prediction analysis report on the fault.

[0013] Preferably, the exception handling module includes: A result analysis submodule, used to analyze the abnormal analysis results and output result analysis data; A keyword extraction submodule, used to identify and extract keywords from the result parsing data and output a keyword set; A factor matching submodule, used to obtain screening factors matching the keyword set in combination with a preset keyword-factor mapping table, and summarize to obtain a factor set; A strategy matching submodule, used to obtain an exception handling strategy matching the factor set and an exception handling method under the corresponding strategy by combining a preset factor-strategy-method comparison table; An abnormality handling submodule is used to handle abnormal conditions in each site based on the abnormality handling strategy and abnormality handling method, and synchronously output handling process data; The effect analysis submodule is used to analyze the effect of the treatment process in combination with preset evaluation indicators and output the abnormal treatment effect analysis results; The optimization submodule is used to optimize the equipment operating parameters, exception handling strategies and exception handling methods in each site based on the analysis results of the exception handling effect, and at the same time, generate a feedback report based on the feedback data obtained, and send the feedback report to users with corresponding permissions.

[0014] The present invention provides an intelligent fault detection and maintenance system for photovoltaic power stations, which realizes intelligent monitoring and fault handling of the operating status of photovoltaic power stations through the organic combination of data acquisition, preprocessing, data analysis and abnormal handling modules. By acquiring operating data in real time and analyzing it through preprocessing and big data analysis models, it can quickly and accurately identify abnormal situations, and implement corresponding processing measures according to the abnormal handling strategy in the strategy method database, thereby improving the operating efficiency and reliability of photovoltaic power stations. The present invention improves the accuracy and efficiency of fault detection, reduces maintenance costs, and reduces downtime, thereby comprehensively improving the operating efficiency, reliability and safety of photovoltaic power stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 It is a schematic diagram of a framework of an intelligent fault detection and maintenance system for a photovoltaic power station provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] like Figure 1 As shown, an embodiment of the present invention provides an intelligent fault detection and maintenance system for a photovoltaic power station, comprising: A data acquisition module, used to acquire the operation data of each site in real time, and summarize and output the first data; A preprocessing module, used to preprocess the first data using a preset preprocessing method and output data to be analyzed; A data analysis module, used to perform anomaly analysis on the data to be analyzed using a preset big data analysis model, and output anomaly analysis results; The exception handling module is used to select an exception handling strategy and method that matches the exception analysis result from the strategy and method database, and handle the abnormal conditions of each site based on the exception handling strategy and method.

[0019] In this embodiment, operating data: data acquired in real time from each site of the photovoltaic power station, including various operating parameters and indicators, such as current, voltage, temperature, etc.; In this embodiment, the first data: the raw data output by the data acquisition module in real time, that is, the unprocessed data collected from each site; In this embodiment, the preset preprocessing method: the data processing method set in the preprocessing module is used to clean, convert or standardize the first data for subsequent analysis and processing; In this embodiment, data to be analyzed: data processed by the preprocessing module, ready for further processing and analysis by the data analysis module; In this embodiment, the preset big data analysis model is a big data analysis model pre-set in the data analysis module, which is used to perform anomaly detection and analysis on the data to be analyzed; In this embodiment, the abnormal analysis result is the abnormal situation analysis result of the data to be analyzed output by the data analysis module, indicating possible problems or abnormalities; In this embodiment, the strategy and method database: a database storing various processing strategies and methods under various abnormal situations, from which the abnormality handling module selects a suitable processing solution; In this embodiment, the abnormality handling strategy and method: the handling strategy and method for specific abnormal situations selected by the abnormality handling module from the strategy and method database according to the abnormality analysis results; In this embodiment, abnormal conditions: abnormal or faulty conditions that may occur in a photovoltaic power station, which need to be monitored and processed by the system, include battery aging, component short circuit, inverter failure, etc.

[0020] The implementation principles and beneficial effects of this embodiment: The present invention realizes intelligent monitoring of the operating status and fault handling of photovoltaic power stations through the collaborative work of data acquisition, preprocessing, data analysis and exception handling modules, combined with preset processing methods and models. The present invention can improve the accuracy and efficiency of fault detection, reduce maintenance costs, and reduce downtime, thereby comprehensively improving the operating efficiency and reliability of photovoltaic power stations.

[0021] An embodiment of the present invention provides an intelligent fault detection and maintenance system for a photovoltaic power station, wherein the data acquisition module comprises: The demand acquisition submodule is used to obtain the user's data monitoring needs in real time through the preset IO port; The data acquisition submodule is used to capture the operation data of each site in real time based on the data monitoring requirements, and summarize the data to obtain the first data.

[0022] In this embodiment, preset IO port: a preset input / output port used for data exchange between the system and an external device or user interface; In this embodiment, data monitoring requirements: the specific requirements or needs of the user or system for the data to be monitored. These requirements can guide the data acquisition submodule to capture the operating data of each site in real time to meet specific monitoring purposes. Specifically, it may include monitoring the temperature, current, voltage and other parameters of each component of the photovoltaic power station, or monitoring the power generation and power curve within a specific time period. The user may want to monitor this data in real time to ensure the normal operation of the photovoltaic power station or to detect abnormal situations in a timely manner.

[0023] The implementation principle and beneficial effects of this embodiment: The present invention obtains the user's data monitoring needs in real time through the demand acquisition submodule, and based on these needs, the data acquisition submodule captures the operation data of each site in real time and summarizes it to obtain the first data. The present invention can flexibly obtain data according to user needs, improve the accuracy and real-time performance of monitoring, help timely discover potential problems existing in each power station site and take corresponding measures, thereby realizing comprehensive monitoring and fault detection of the operating status of the photovoltaic power station.

[0024] An embodiment of the present invention provides an intelligent fault detection and maintenance system for a photovoltaic power station, wherein the data acquisition submodule comprises: A data determination unit, used to determine the power station site corresponding to the data to be captured and the data type and data volume under each site based on the data monitoring requirements, and output a demand data comparison table; The data acquisition unit is used to activate and adjust the parameters of the preset monitoring equipment set at each site based on the demand data comparison table, and to acquire the equipment operating parameters in the corresponding site in real time through each preset monitoring device, and summarize them to obtain the first data.

[0025] In this embodiment, the data to be captured: the data to be captured is determined according to the data monitoring requirements, In this embodiment, power station site: the name, specific location or area of ​​each photovoltaic power station; In this embodiment, data type: the kind or type of data to be captured, such as temperature, current, voltage, etc.; In this embodiment, data volume refers to the amount or data magnitude of data to be captured; In this embodiment, the demand data comparison table: a data capture comparison table determined according to the data monitoring requirements, used to guide the data acquisition unit to perform data capture operations; In this embodiment, preset monitoring equipment: equipment pre-set for monitoring data, which may include sensors, monitoring instruments, etc.; In this embodiment, parameter adjustment: is to adjust the parameters of the monitoring device according to the demand data comparison table to ensure accurate capture of the required data; In this embodiment, the equipment operating parameters are various parameters of the equipment operating status acquired in real time by the monitoring device, for example, the output power of inverter No. 1 in site A, the temperature of the components, etc.

[0026] The implementation principle and beneficial effects of this embodiment: The present invention determines the power station site, data type and data volume corresponding to the data to be captured through the data determination unit, and outputs the demand data comparison table; the data acquisition unit activates and adjusts the monitoring equipment parameters according to the demand data comparison table, obtains the equipment operation parameters in real time and summarizes them to obtain the first data. The present invention can accurately capture data according to specific needs, improve the accuracy and efficiency of data collection, and provide reliable data support for subsequent fault detection and maintenance.

[0027] An embodiment of the present invention provides an intelligent fault detection and maintenance system for a photovoltaic power station, wherein the preprocessing module comprises: A method matching submodule, used for acquiring a preprocessing method matching the first data in a method database; The preprocessing submodule is used to preprocess the first data based on the preprocessing method, and output the data that meets the preset quality requirements as data to be analyzed.

[0028] In this embodiment, the method database: a database storing various preprocessing methods, used to match a suitable preprocessing method according to the first data, including various data processing algorithms, such as filtering, correction, anomaly detection and other methods; In this embodiment, preprocessing method: a method or algorithm for processing raw data to meet specific quality requirements, a processing method for different types of data, such as a smoothing method for temperature data, an anomaly detection method for current data, etc.; In this embodiment, preset quality requirements: pre-set data quality standards or requirements, used to ensure that the processed data meets specific standards, including data accuracy, data integrity, data consistency and other requirements, to ensure that the processed data meets the requirements.

[0029] The implementation principle and beneficial effects of this embodiment: The present invention obtains a preprocessing method matching the first data in a method database through a method matching submodule; the preprocessing submodule processes the first data based on these preprocessing methods, and outputs data to be analyzed that meets the preset quality requirements. The present invention can process the data according to the preprocessing method to ensure that the data quality meets specific standards, thereby improving the data quality and reliability, reducing the impact of noise and abnormal data, and providing more accurate data support for intelligent fault detection and maintenance of the system.

[0030] An embodiment of the present invention provides an intelligent fault detection and maintenance system for a photovoltaic power station, wherein the method matching submodule comprises: A feature extraction unit, configured to extract features from the first data, match the extracted features with a preset abnormal data feature library, and collect and summarize the extracted features that meet the preset matching conditions to obtain a first feature set; A method matching unit is used to screen and obtain a matching preprocessing method in a method database based on the first feature set and in combination with a preset feature-method comparison table.

[0031] In this embodiment, the preset abnormal data feature library: a database storing preset abnormal data features, which is used to match the extracted features and may include various abnormal data features, such as mutation values, abnormal frequencies, etc.; In this embodiment, the preset matching condition: a condition or rule for determining feature matching, which may be a condition such as feature similarity exceeding a certain threshold; In this embodiment, the first feature set is a feature set extracted from the first data and meeting a preset matching condition, such as a spectrum feature, a statistical feature, etc.; In this embodiment, a preset feature-method comparison table: a comparison table between pre-set features and preprocessing methods, used to guide the method matching unit to select an appropriate preprocessing method, may include preprocessing methods for specific features, such as filtering methods for spectral features, correction methods for statistical features, etc.

[0032] The implementation principle and beneficial effects of this embodiment: The present invention extracts features from the first data through a feature extraction unit, and matches the extracted features with a preset abnormal data feature library to obtain a first feature set; the method matching unit screens and obtains a matching preprocessing method in the method database according to the first feature set and the preset feature-method comparison table. The present invention selects a suitable preprocessing method to process the data under the guidance of feature matching and the preset feature-method comparison table to meet specific matching conditions and quality requirements. The present invention can improve the system's ability to identify abnormal data, and select a suitable preprocessing method based on feature matching, providing more accurate data support for fault detection and maintenance. An embodiment of the present invention provides an intelligent fault detection and maintenance system for a photovoltaic power station, wherein the method matching unit comprises: A feature matching subunit, used to obtain a preprocessing method corresponding to each data feature in the first feature set in combination with the preset feature-method comparison table; The list establishment subunit is used to obtain the data source corresponding to each data feature in the first feature set in the first data, and establish a mapping between the data source, data features and preprocessing methods to construct a data source-feature-method mapping table.

[0033] In this embodiment, data source refers to the source of data, which may be different sensors, devices or systems; In this embodiment, data features: features extracted from data sources, which may be various data attributes or features; In this embodiment, the data source-feature-method mapping table: a table that maps the data source, data features and corresponding preprocessing methods, associates different data sources, data features and corresponding preprocessing methods, for example, associates the temperature characteristics of a photovoltaic cell group with a filtering method, and is used to guide the data processing process.

[0034] The implementation principle and beneficial effects of this embodiment: The present invention obtains the preprocessing method corresponding to each data feature in the first feature set through a feature matching subunit combined with a preset feature-method comparison table; the list establishment subunit obtains the data source corresponding to each data feature in the first feature set in the first data, and establishes a mapping between the data source, data features and preprocessing methods, and constructs a data source-feature-method mapping table. The present invention establishes a mapping relationship between the data source, data features and preprocessing methods, which can clearly understand the relationship between data features and data sources, as well as how to select appropriate preprocessing methods to process these data, so that the system can more effectively process data features from different data sources, and improve the accuracy and efficiency of data processing.

[0035] An embodiment of the present invention provides an intelligent fault detection and maintenance system for a photovoltaic power station, wherein the data analysis module comprises: A historical data acquisition submodule is used to obtain the user's data analysis requirements, and based on the data analysis requirements, filter out historical power plant operation data that matches the data to be analyzed in the historical database; A data verification submodule, used to compare and verify the historical power plant operation data using a preset data verification method, and output the historical power plant operation data that meets the preset verification conditions as data to be divided; The data partitioning submodule is used to divide the data to be divided according to the acquired data analysis requirements of the user and to obtain a training set, a test set and a validation set by using a preset data partitioning method; A model selection submodule, used to select a matching first model from a model database based on the data analysis requirement; A model training submodule, used for inputting the training set, the test set and the validation set into the first model for training and optimization, and outputting the first model that meets the preset performance conditions as a preset big data analysis model; A data analysis submodule is used to perform real-time analysis on the data to be analyzed by using the preset big data analysis model to obtain real-time analysis data, and at the same time, perform predictive analysis on the data to be analyzed to obtain predictive analysis data; A chart output submodule, which is used to obtain a real-time analysis chart and a predictive analysis table based on the timestamps corresponding to the real-time analysis data and the predictive analysis data and in combination with a preset chart establishment method; The abnormal feature extraction submodule is used to extract the data features in the real-time analysis graph and the prediction analysis table, and match them with the data features in the preset abnormal feature library, and summarize the successfully matched data features and output them as an abnormal feature set; The state analysis submodule is used to obtain real-time state analysis data and predicted state analysis data matching the data features in the abnormal feature set in combination with a preset feature-state comparison table, and summarize and output a state analysis table; The fault identification submodule is used to determine the fault type and the corresponding safety level corresponding to each abnormal state based on the state analysis table and in combination with a preset state-fault mapping diagram, and output a real-time-prediction analysis report on the fault.

[0036] In this embodiment, data analysis requirements: user requirements for data analysis, including the type of data to be analyzed, time range, etc. For example, the user may need to analyze the power fluctuation of the photovoltaic power station in the past year; In this embodiment, historical database: a database storing past power plant operation data; In this embodiment, historical power station operation data: various operation data of the power station in the past, such as temperature, power, current, etc.; In this embodiment, the preset data verification method: a pre-set method for verifying the accuracy of historical data; In this embodiment, the verification condition is preset: determining whether the historical data meets the required conditions or rules, for example, the standard deviation of certain data does not exceed a certain threshold; In this embodiment, data to be divided: data to be divided after verification; In this embodiment, the preset data partitioning method: a preset method for partitioning data into a training set, a test set, and a validation set; In this embodiment, the training set, the test set, and the validation set are data sets used to train and optimize the selected model; In this embodiment, the model database: a database storing different models for the system to select a suitable model for data analysis, including a neural network model, a support vector machine model, etc.; In this embodiment, the first model: a matching model selected from a model database according to data analysis requirements; In this embodiment, the preset performance condition: the set model performance requirement is used to select the first model that meets the condition for subsequent data analysis, for example, the accuracy of the model needs to reach more than 90%; In this embodiment, real-time analysis data: data results obtained through real-time data analysis, for example, displaying power analysis data of the current photovoltaic power station; In this embodiment, the forecast analysis data: data results obtained by forecasting through a preset big data analysis model, for example, showing the expected power output of the photovoltaic power station in the next 24 hours; In this embodiment, timestamp: time information of data generation; In this embodiment, the preset chart creation method is: a method for converting data into a chart format; In this embodiment, real-time analysis graph: a graph generated based on real-time analysis data, for example, a graph showing a current photovoltaic power station power curve; In this embodiment, the prediction analysis table: a table generated based on the prediction analysis data, for example, a table showing the expected power output of the photovoltaic power station in the next 24 hours; In this embodiment, a preset abnormal feature library: a predefined set of abnormal features, used to match the features extracted from the real-time analysis data and the predictive analysis data, including temperature anomalies, power fluctuation anomalies, etc.; In this embodiment, abnormal feature set: a set of abnormal features extracted from the real-time analysis graph and the prediction analysis table; In this embodiment, the preset feature-state comparison table: a correspondence table between predefined features and states, used to determine the corresponding operating state according to the input abnormal features; In this embodiment, the real-time status analysis data: data for real-time status determination obtained by matching data features in an abnormal feature set; In this embodiment, the predicted state analysis data: data for predicted state determination obtained by matching data features in an abnormal feature set; In this embodiment, the state analysis table: a table summarizing the output real-time state analysis data and predicted state analysis data; In this embodiment, the preset state-fault mapping diagram is a mapping relationship diagram between predefined states, fault types and corresponding safety levels, where state A corresponds to fault type X and state B corresponds to fault type Y; In this embodiment, fault type: the type of abnormal state or problem, for example, X may indicate a battery fault, and Y may indicate an inverter fault; In this embodiment, safety level: the severity level of the fault, for example, X1 is a high level and X2 is a medium level; In this embodiment, real-time and predictive fault analysis report: based on the state analysis table and the state-fault mapping diagram, a real-time and predictive fault analysis report is output. For example, the report shows that there may be a battery fault (high level) at present and an inverter fault (medium level) may occur in the future.

[0037] The implementation principle and beneficial effects of this embodiment: The present invention obtains qualified historical power station operation data from the historical database according to the user's data analysis needs, selects a suitable model for training and optimization after verification and division, and then performs real-time analysis and predictive analysis on the data to be analyzed. The abnormal feature extraction submodule is used to extract abnormal features, the state analysis submodule is used to analyze state data, and the fault identification submodule is used to identify faults and output analysis reports. The present invention can obtain and analyze historical data according to user needs, train preset big data analysis models, analyze data in real time and predict future situations, and finally identify potential faults and provide corresponding analysis reports to help maintenance personnel take corresponding measures, thereby improving the operating efficiency and reliability of photovoltaic power stations and reducing the impact of potential faults on the system.

[0038] An embodiment of the present invention provides an intelligent fault detection and maintenance system for a photovoltaic power station, wherein the abnormality handling module comprises: A result analysis submodule, used to analyze the abnormal analysis results and output result analysis data; A keyword extraction submodule, used to identify and extract keywords from the result parsing data and output a keyword set; A factor matching submodule, used to obtain screening factors matching the keyword set in combination with a preset keyword-factor mapping table, and summarize to obtain a factor set; A strategy matching submodule, used to obtain an exception handling strategy matching the factor set and an exception handling method under the corresponding strategy by combining a preset factor-strategy-method comparison table; An abnormality handling submodule is used to handle abnormal conditions in each site based on the abnormality handling strategy and abnormality handling method, and synchronously output handling process data; The effect analysis submodule is used to analyze the effect of the treatment process in combination with preset evaluation indicators and output the abnormal treatment effect analysis results; The optimization submodule is used to optimize the equipment operating parameters, exception handling strategies and exception handling methods in each site based on the analysis results of the exception handling effect, and at the same time, generate a feedback report based on the feedback data obtained, and send the feedback report to users with corresponding permissions.

[0039] In this embodiment, result analysis data: analysis data of the abnormality analysis result, used for further processing of the abnormality; In this embodiment, keyword identification and extraction: identifying and extracting keywords in the result parsed data; In this embodiment, keyword set: a set of keywords extracted from the result parsing data, for example, "battery temperature abnormality", etc.; In this embodiment, a preset keyword-factor mapping table: a correspondence table between predefined keywords and screening factors; In this embodiment, the screening factor: the screening factor obtained by matching the keyword set is used to obtain the exception handling strategy and the exception handling method; In this embodiment, factor set: a collection of factors of screening factors; In this embodiment, the preset factor-strategy-method comparison table is a comparison table between predefined screening factors, abnormality handling strategies and corresponding handling methods, screening factor A corresponds to abnormality handling strategy X, and the method is to reduce the battery temperature; In this embodiment, the abnormality handling strategy: an abnormality handling strategy formulated for a specific abnormal condition, for example, adopting strategy X, i.e., reducing the battery temperature; In this embodiment, abnormality handling method: a specific method of executing an abnormality handling strategy, for example, lowering the battery temperature by increasing ventilation or reducing the battery load; In this embodiment, handling process data: data generated during the abnormal handling process, recording the specific steps and results of the abnormal handling, for example, recording the handling process for the inverter fault, including the steps and data of diagnosis, repair and restoration of normal operation; In this embodiment, preset evaluation indicators: indicators set in advance for evaluating the effect of abnormal handling, including indicators such as fault handling time, cost, and maintenance effect; In this embodiment, the abnormal handling effect analysis result: the analysis result obtained after evaluating the abnormal handling process is used to judge the quality of the handling effect. For example, the analysis shows that the inverter fault handling time is reduced, the cost is reduced, and the maintenance effect is good. Specifically, assuming that an inverter of a photovoltaic power station fails, the normal operation time is 100 hours, the abnormal handling time is 20 hours, and the fault handling time processing efficiency is: , combined with the evaluation scores under other preset evaluation indicators, substitute into the preset formula to calculate the comprehensive evaluation effect: ,in, Represents the comprehensive evaluation effect value corresponding to n preset evaluation indicators, Represents the total number of preset evaluation indicators, Represents the evaluation score value corresponding to the i-th preset evaluation indicator, represents the weight coefficient corresponding to the i-th preset evaluation index, represents the exponential function, represents the error adjustment coefficient corresponding to n preset evaluation indicators; In this embodiment, feedback data: data obtained based on the treatment effect analysis results and actual conditions, used to optimize equipment operating parameters and abnormal treatment strategies and methods. For example, based on the abnormal treatment effect analysis results and actual conditions, it is found that some inverters need regular maintenance, and the temperature monitoring frequency is increased; In this embodiment, feedback report: a report generated based on feedback data, used to provide optimization suggestions and improvement directions, and sent to users with relevant permissions. For example, the generated report recommends optimizing the inverter maintenance plan and strengthening temperature monitoring, and is sent to operation and maintenance personnel and management personnel.

[0040] The implementation principle and beneficial effects of this embodiment: The present invention formulates corresponding abnormal handling strategies and methods according to the keywords and factors in the abnormal analysis results, and evaluates and optimizes the handling process through the effect analysis and optimization submodules, and finally generates a feedback report and sends it to the relevant users. The present invention can quickly identify key factors and formulate corresponding handling strategies and methods according to abnormal situations, improve the efficiency and accuracy of abnormal handling, optimize equipment operating parameters and abnormal handling strategies and methods through feedback reports, reduce fault handling time and cost, and improve the life and performance of equipment, thereby improving the operating efficiency and reliability of photovoltaic power stations.

[0041] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent fault detection and maintenance system for a photovoltaic power station, characterized in that: include: A data acquisition module, used to acquire the operation data of each site in real time, and summarize and output the first data; A preprocessing module, used to preprocess the first data using a preset preprocessing method and output data to be analyzed; A data analysis module, used to perform anomaly analysis on the data to be analyzed using a preset big data analysis model, and output anomaly analysis results; The exception handling module is used to select an exception handling strategy and method that matches the exception analysis result from the strategy and method database, and handle the abnormal conditions of each site based on the exception handling strategy and method.

2. The intelligent fault detection and maintenance system for a photovoltaic power station according to claim 1, characterized in that: The data acquisition module comprises: The demand acquisition submodule is used to obtain the user's data monitoring needs in real time through the preset IO port; The data acquisition submodule is used to capture the operation data of each site in real time based on the data monitoring requirements, and summarize the data to obtain the first data.

3. The intelligent fault detection and maintenance system for a photovoltaic power station according to claim 2, characterized in that: The data acquisition submodule includes: A data determination unit, used to determine the power station site corresponding to the data to be captured and the data type and data volume under each site based on the data monitoring requirements, and output a demand data comparison table; The data acquisition unit is used to activate and adjust the parameters of the preset monitoring equipment set at each site based on the demand data comparison table, and to acquire the equipment operating parameters in the corresponding site in real time through each preset monitoring device, and summarize them to obtain the first data.

4. The intelligent fault detection and maintenance system for a photovoltaic power station according to claim 1, characterized in that: The preprocessing module comprises: A method matching submodule, used for acquiring a preprocessing method matching the first data in a method database; The preprocessing submodule is used to preprocess the first data based on the preprocessing method, and output the data that meets the preset quality requirements as data to be analyzed.

5. The intelligent fault detection and maintenance system for photovoltaic power station according to claim 4, characterized in that: The method matches the submodule, including: A feature extraction unit, configured to extract features from the first data, match the extracted features with a preset abnormal data feature library, and collect and summarize the extracted features that meet the preset matching conditions to obtain a first feature set; A method matching unit is used to screen and obtain a matching preprocessing method in a method database based on the first feature set and in combination with a preset feature-method comparison table.

6. The intelligent fault detection and maintenance system for a photovoltaic power station according to claim 5, characterized in that: The method matching unit comprises: A feature matching subunit, used to obtain a preprocessing method corresponding to each data feature in the first feature set in combination with the preset feature-method comparison table; The list establishment subunit is used to obtain the data source corresponding to each data feature in the first feature set in the first data, and establish a mapping between the data source, data features and preprocessing methods to construct a data source-feature-method mapping table.

7. The intelligent fault detection and maintenance system for a photovoltaic power station according to claim 1, characterized in that: The data analysis module comprises: A historical data acquisition submodule is used to obtain the user's data analysis requirements, and based on the data analysis requirements, filter out historical power plant operation data that matches the data to be analyzed in the historical database; A data verification submodule, used to compare and verify the historical power plant operation data using a preset data verification method, and output the historical power plant operation data that meets the preset verification conditions as data to be divided; The data partitioning submodule is used to divide the data to be divided according to the acquired data analysis requirements of the user and to obtain a training set, a test set and a validation set by using a preset data partitioning method; A model selection submodule, used to select a matching first model from a model database based on the data analysis requirement; A model training submodule, used for inputting the training set, the test set and the validation set into the first model for training and optimization, and outputting the first model that meets the preset performance conditions as a preset big data analysis model; A data analysis submodule is used to perform real-time analysis on the data to be analyzed by using the preset big data analysis model to obtain real-time analysis data, and at the same time, perform predictive analysis on the data to be analyzed to obtain predictive analysis data; A chart output submodule, which is used to obtain a real-time analysis chart and a predictive analysis table based on the timestamps corresponding to the real-time analysis data and the predictive analysis data and in combination with a preset chart establishment method; The abnormal feature extraction submodule is used to extract the data features in the real-time analysis graph and the prediction analysis table, and match them with the data features in the preset abnormal feature library, and summarize the successfully matched data features and output them as an abnormal feature set; The state analysis submodule is used to obtain real-time state analysis data and predicted state analysis data matching the data features in the abnormal feature set in combination with the preset feature-state comparison table, and summarize and output the state analysis table; The fault identification submodule is used to determine the fault type and the corresponding safety level corresponding to each abnormal state based on the state analysis table and in combination with a preset state-fault mapping diagram, and output a real-time-prediction analysis report on the fault.

8. The intelligent fault detection and maintenance system for a photovoltaic power station according to claim 1, characterized in that: The exception handling module includes: A result analysis submodule, used to analyze the abnormal analysis results and output result analysis data; A keyword extraction submodule, used to identify and extract keywords from the result parsing data and output a keyword set; A factor matching submodule, used to obtain screening factors matching the keyword set in combination with a preset keyword-factor mapping table, and summarize to obtain a factor set; A strategy matching submodule, used to obtain an exception handling strategy matching the factor set and an exception handling method under the corresponding strategy by combining a preset factor-strategy-method comparison table; An abnormality handling submodule is used to handle abnormal conditions in each site based on the abnormality handling strategy and abnormality handling method, and synchronously output handling process data; The effect analysis submodule is used to analyze the effect of the treatment process in combination with preset evaluation indicators and output the abnormal treatment effect analysis results; The optimization submodule is used to optimize the equipment operating parameters, exception handling strategies and exception handling methods in each site based on the analysis results of the exception handling effect, and at the same time, generate a feedback report based on the feedback data obtained, and send the feedback report to users with corresponding permissions.

Images