New energy station fault management system and method

Abstract

The invention discloses a new energy station fault management system and method, and relates to the technical field of station management, and the system comprises a control parameter receiving module which is used for receiving pre-configured control parameters before first new energy station equipment is started; the reference state prediction module predicts a reference operation state matrix of the equipment according to the control parameters; the running state monitoring module is used for receiving an actually monitored running state matrix when the equipment is started; the state comparison module is used for comparing the reference state matrix with the monitoring state matrix to generate an operation state deviation coefficient; and the operation and maintenance identification module generates a fault operation and maintenance identifier when the deviation coefficient is greater than or equal to a threshold value, and sends the fault operation and maintenance identifier to the fault management end. Therefore, the technical effects of improving the fault responsiveness and the management automation degree are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of station management, and in particular to a new energy station fault management system and method. Background Art

[0002] With the rapid development of new energy, new energy stations occupy an increasingly important position in the power system. However, new energy stations have a wide variety of equipment and a complex operating environment. In order to improve the safety and reliability of station operation, an effective fault management system is essential.

[0003] At present, the fault management of new energy stations mainly relies on a combination of manual inspections and regular maintenance. Some stations have introduced automated monitoring systems to collect equipment operation data, analyze the health status of equipment and provide fault warnings.

[0004] , for example: Chinese Patent Publication No.: CN118410441A. A fault warning method, device, equipment, storage medium and program product for a new energy station are disclosed, including: collecting equipment status data of wind turbine equipment from a new energy station, including real-time operation data and point inspection data, and performing fault diagnosis on the wind turbine equipment through a multi-parameter equipment fault diagnosis model to obtain a diagnosis prediction result; generating a three-dimensional visualization page for display based on the diagnosis prediction result, real-time operation data and point inspection data. It can be seen that the fault warning method, device, equipment, storage medium and program product for a new energy station have the following problems: taking a single device as the object, lacking a global fault analysis and management mechanism, the fault diagnosis through a multi-parameter equipment fault diagnosis model relies on the computing power resources of the application scenario, and the response speed is slow, which makes it difficult to meet the real-time and accuracy requirements of the new energy station, and there are technical problems such as low automation, insensitive deviation response and delayed fault handling. Summary of the invention

[0005] The present invention provides a new energy station fault management system and method to solve the technical problems of low automation, insensitive deviation response and delayed fault processing in the prior art, and achieve the technical effect of improving fault responsiveness and management automation.

[0006] In a first aspect, the present invention provides a new energy station fault management system, wherein the system comprises: A control parameter receiving module is used to receive pre-configured control parameters of the first new energy station equipment before the first new energy station equipment is started.

[0007] The reference state prediction module is used to predict the operation state according to the control parameters of the first new energy station equipment to obtain the first new energy station equipment reference operation state matrix.

[0008] The monitoring operation status module is used to receive the first new energy site equipment monitoring operation status matrix when the first new energy site equipment is started according to the first new energy site equipment control parameters.

[0009] A state comparison module is used to compare the first new energy site equipment benchmark operation state matrix and the first new energy site equipment monitoring operation state matrix to generate an operation state deviation coefficient.

[0010] An operation and maintenance identification module, which is used to generate a fault operation and maintenance identification for the first new energy station equipment and send it to the new energy station fault management terminal when the operation status deviation coefficient is greater than or equal to the operation status deviation coefficient threshold.

[0011] A periodic identification module, wherein the periodic identification module is used to generate a periodic operation and maintenance identification for the first new energy station equipment when the operating state deviation coefficient is less than the operating state deviation coefficient threshold, and send it to the new energy station fault management terminal.

[0012] In a second aspect, the present invention further provides a new energy station fault management method, wherein the method comprises: Before the first new energy site equipment is started, the preconfigured first new energy site equipment control parameters are received.

[0013] The operating state is predicted according to the control parameters of the first new energy station equipment to obtain a reference operating state matrix of the first new energy station equipment.

[0014] When the first new energy station equipment is started according to the first new energy station equipment control parameters, the first new energy station equipment monitoring operation status matrix is ​​received.

[0015] The first new energy site equipment benchmark operating state matrix and the first new energy site equipment monitoring operating state matrix are compared to generate an operating state deviation coefficient.

[0016] When the operating status deviation coefficient is greater than or equal to the operating status deviation coefficient threshold, a fault operation and maintenance mark is generated for the first new energy station equipment and sent to the new energy station fault management terminal.

[0017] When the operating status deviation coefficient is less than the operating status deviation coefficient threshold, a periodic operation and maintenance mark is generated for the first new energy station equipment and sent to the new energy station fault management terminal.

[0018] In a third aspect, the present invention further provides an electronic device, comprising: a memory for storing executable instructions; and a processor for executing the executable instructions stored in the memory to implement a new energy station fault management system provided by the present invention.

[0019] In a fourth aspect, the present invention further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements a new energy station fault management system provided by the present invention.

[0020] A new energy station fault management system and method disclosed in the present invention solves the technical problems of low automation, insensitive deviation response, and delayed fault processing, and achieves the technical effect of improving fault responsiveness and management automation. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a structural schematic diagram of a new energy station fault management system of the present invention; Figure 2 A schematic diagram of a new energy station fault management method according to the present invention; Figure 3 It is a schematic diagram of the structure of an exemplary electronic device of the present invention.

[0022] Explanation of the reference numerals: control parameter receiving module 11, reference state prediction module 12, operation state monitoring module 13, state comparison module 14, operation and maintenance identification module 15, cycle identification module 16, processor 31, memory 32, input device 33, output device 34. DETAILED DESCRIPTION

[0023] The technical solution provided in the embodiments of the present invention is to solve the technical problems of low automation, insensitive deviation response and delayed fault processing in the prior art. The overall idea adopted is as follows: First, before the first new energy station equipment is started, the control parameter receiving module is used to receive the pre-configured control parameters of the first new energy station equipment; then, the reference state prediction module predicts the operating state according to the control parameters and generates the reference operating state matrix of the first new energy station equipment; then, after the equipment is started, the monitoring operating state module receives the actual monitored operating state matrix; then, the state comparison module is used to compare the reference operating state matrix with the monitoring operating state matrix, and calculate and generate the operating state deviation coefficient; then, the operation and maintenance identification module generates a fault operation and maintenance identification and sends it to the new energy station fault management end when the deviation coefficient is greater than or equal to the preset threshold; the periodic identification module generates a periodic operation and maintenance identification for the first new energy station equipment when the operating state deviation coefficient is less than the operating state deviation coefficient threshold, and sends it to the new energy station fault management end. The above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods in the specification to better understand the above technical solution. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments used only to explain the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. In addition, it should be noted that for the convenience of description, only the parts related to the present invention, rather than all of them, are shown in the drawings.

[0024] Embodiment 1 Figure 1 The present invention is a schematic diagram of a new energy station fault management system, wherein the system includes: The control parameter receiving module 11 is used to receive pre-configured control parameters of the first new energy station equipment before the first new energy station equipment is started.

[0025] Specifically, before the first new energy station equipment is started, the pre-configured equipment control parameters are first received. The first new energy station equipment control parameters are pre-set according to user needs. The acquisition and application of pre-configured parameters can ensure that the equipment has the optimal operating settings before startup, reduce the adjustment time during equipment operation, and improve the overall response efficiency and performance of the station.

[0026] Specifically, the preconfigured equipment control parameters can be user-defined or automatically generated based on the historical operation data of the station, and are used to define the operating status and behavior of the equipment after startup to ensure that the equipment can start and run efficiently and stably.

[0027] Specifically, the pre-configured parameters can be divided into: power output parameters, which define the target power output of the equipment, such as the output power of wind power generation equipment and the power generation power of photovoltaic power stations; load regulation parameters, which control the response capability of the equipment to external loads; power factor adjustment parameters. For new energy equipment, especially photovoltaic power stations or wind power stations, the adjustment of power factor is very important. The pre-configured parameters include the initial power factor setting to enable effective power management at startup; voltage / current setting values; the starting voltage and current values ​​of the equipment will also be preset in the control parameters to ensure that the equipment enters a stable working state at startup.

[0028] The reference state prediction module 12 is used to predict the operating state according to the control parameters of the first new energy station equipment to obtain the first new energy station equipment reference operating state matrix.

[0029] Specifically, the first new energy station equipment benchmark operating status matrix refers to a multidimensional matrix generated according to the control parameters of the first new energy station equipment, which is used to characterize the expected operating status of the equipment under different operating conditions. The benchmark operating status matrix includes multiple key operating indicators of the equipment under specific time periods, load conditions, and environmental factors, such as output power, voltage, current, power factor, and load response.

[0030] Specifically, the role of the benchmark operating status matrix is ​​to provide the expected performance of the equipment by calculating and predicting the control parameters. The benchmark operating status matrix can help the system understand the future state of the equipment in advance, optimize the operating strategy, and ensure that the equipment can work stably and efficiently under different conditions.

[0031] In some embodiments, the operation state prediction is performed according to the control parameters of the first new energy station equipment to obtain the first new energy station equipment reference operation state matrix, and the execution steps include: Obtain multiple new energy station equipment status attributes; traverse the multiple new energy station equipment status attributes, perform correlation sorting on the first new energy station equipment control attribute set, and obtain multiple groups of related new energy station equipment control attributes; construct multiple new energy station equipment status mappers from the multiple groups of related new energy station equipment control attributes to the multiple new energy station equipment status attributes; according to the multiple new energy station equipment status mappers, perform operating status prediction on the first new energy station equipment control parameters, and obtain the first new energy station equipment benchmark operating status matrix.

[0032] Specifically, energy station equipment includes but is not limited to photovoltaic panels, wind turbines, and energy storage equipment. The status attributes of energy station equipment include: working status, power parameters, energy production, equipment health, environmental factors, maintenance information, and equipment configuration information. The status attributes of new energy station equipment reflect the performance of the equipment under different operating conditions and provide basic data for subsequent operating status predictions. By monitoring and analyzing status attributes, we can better understand the operating status of the equipment, predict the performance of the equipment, and perform necessary maintenance and optimization.

[0033] Specifically, the control attribute set refers to a series of control parameters directly related to the operation of the equipment, such as power factor adjustment, load regulation, and power output setting. By traversing the state attributes of new energy equipment, correlation analysis is performed on the above state attributes and control attribute sets to find out the most relevant control and state attributes.

[0034] Specifically, the correlation between different control attributes and state attributes is analyzed by calculating the correlation coefficient, and which control parameters have a direct impact on the device state are identified. Then, the control attributes and state attributes are sorted and grouped into multiple groups of highly correlated attribute pairs, providing a basis for the subsequent construction of the state mapper.

[0035] Specifically, based on correlation analysis and sorting, multiple groups of related new energy station equipment control attributes are obtained. Each group of related new energy station equipment control attributes are highly correlated and can act together on the equipment status. Each group of related attributes represents a set of control parameters that can jointly affect the status of a certain type of equipment. For example, a group of control attributes may include a power output set value, a load regulation coefficient, and a voltage set value, which together act on the power output status of the equipment.

[0036] Specifically, the relationship between the associated control attributes and state attributes is modeled, and a new energy station equipment state mapper is constructed. The state mapper is used to map control parameters to specific state attributes, thereby providing a tool for predicting the operating status of the equipment. In other words, the state mapper is a function or model that converts control attributes into equipment status, which helps to predict or calculate the operating status of the equipment under specific conditions.

[0037] Specifically, after the state mapper is constructed, the operating status of the control parameters of the first new energy station equipment is predicted through the state mapper. The prediction process inputs the control parameters of the equipment into the corresponding state mapper and calculates the corresponding equipment status. The equipment operating status prediction results include the predicted values ​​of power output, voltage, current, and power factor.

[0038] Specifically, the structured operation status prediction results generate the first new energy station equipment benchmark operation status matrix. The new energy station equipment benchmark operation status matrix is ​​a multi-dimensional structure, usually including time dimension, load dimension and control parameter dimension. Each element in the matrix represents the operation status of the new energy equipment under specific conditions. Multiple elements summarize the expected operation status of the equipment under different conditions, providing a basis for the regulation and optimization of the equipment.

[0039] In some implementations, traversing the multiple new energy station equipment state attributes, performing correlation sorting on the first new energy station equipment control attribute set, and obtaining multiple groups of associated new energy station equipment control attributes include: Obtain a first new energy field station equipment state attribute of the multiple new energy field station equipment state attributes; obtain a first new energy field station equipment control attribute of the first new energy field station equipment control attribute set; take the first new energy field station equipment control attribute as the only variable, perform a correlation analysis on the first new energy field station equipment state attribute, and obtain a first correlation coefficient; when the first correlation coefficient meets the correlation coefficient threshold, add the first new energy field station equipment control attribute into a first group of associated new energy field station equipment control attributes; add the first group of associated new energy field station equipment control attributes into the multiple groups of associated new energy field station equipment control attributes.

[0040] Specifically, each control attribute is extracted from the first new energy station equipment status attribute. The control attribute is a key variable that affects the operating status of the equipment and is set by the user or the system to adjust the operating performance of the equipment. The first new energy station equipment status attribute is any one of multiple new energy station equipment status attributes.

[0041] Specifically, the control attribute of the first new energy station equipment is taken as the only variable, and the corresponding equipment state attribute is subjected to correlation analysis to evaluate the influence of the control attribute on the equipment operation state. Optional methods include Pearson correlation coefficient or Spearman correlation coefficient to quantify the linear or nonlinear relationship between the control attribute and the state attribute.

[0042] Exemplarily, first, a specific control attribute is taken as a variable, and then, correlation analysis is performed on the control attribute and multiple device state attributes one by one to evaluate the sensitivity of each state attribute to the control attribute. The correlation analysis result is represented by a correlation coefficient with a numerical range between -1 and 1. A correlation coefficient close to 1 or -1 indicates that the relationship between the control attribute and the state attribute is strong; a correlation coefficient close to 0 indicates that there is no obvious correlation. The first correlation coefficient obtained is used to quantify the relationship between the device control attribute and the state attribute.

[0043] Specifically, the first correlation coefficient is compared with a preset correlation coefficient threshold to screen out control attributes that have a significant impact on the state attributes. If the correlation coefficient of a control attribute meets the threshold condition, the control attribute is added to the first group of associated new energy station equipment control attributes, wherein the threshold of the correlation coefficient is a preset critical value, which is set based on experience or the requirements of the target station. For example, it is set to 0.7 or 0.8, indicating that a control attribute will be selected into the associated attribute group only if it has a greater impact on the state attribute.

[0044] Specifically, no matter it is positive correlation or negative correlation, as long as the correlation coefficient exceeds the set threshold, the control attribute will be considered to have a significant impact on the device state and will be selected into the associated attribute group.

[0045] Specifically, the identified control attributes with high correlation are combined into a first group of associated new energy station equipment control attributes and added to multiple groups of associated new energy station equipment control attributes. The multiple groups of associated control attributes will be used for subsequent state mapper construction and equipment state prediction, wherein each group of associated attributes represents multiple control attributes, and the multiple control attributes have a strong correlation with the state attributes of the equipment. For example, a group of associated attributes may include output power setting value, voltage setting value and load regulation parameters, which work together on the power output and voltage stability of the equipment.

[0046] By traversing the equipment status attributes and control attribute sets of new energy stations and performing correlation sorting, multiple groups of related control attributes can be identified, providing important input for subsequent equipment operation status prediction and optimization, ensuring that equipment operation can be adjusted according to highly correlated control parameters to improve the overall performance and stability of the equipment.

[0047] Furthermore, taking the first new energy station equipment control attribute as the only variable, a correlation analysis is performed on the first new energy station equipment state attribute to obtain a first correlation coefficient, including: Taking the first new energy station equipment control attribute as the only independent variable of the multiple new energy station equipment status attributes and the first new energy station equipment status attribute as the dependent variable, collecting the first new energy station equipment operation and maintenance cross-sectional data; performing correlation analysis based on the first new energy station equipment operation and maintenance cross-sectional data to obtain a first correlation coefficient.

[0048] Specifically, the operation and maintenance cross-section data refers to the equipment operation and maintenance data collected at a specific time point, including the first new energy station equipment control attribute values ​​and the first new energy station equipment status attributes of multiple new energy station equipment. Then, the correlation analysis method is used to analyze the relationship between the equipment control attributes and the equipment status attributes.

[0049] Further, a correlation analysis is performed based on the first new energy station equipment operation and maintenance section data to obtain a first correlation coefficient, including: According to the first new energy station equipment operation and maintenance section data, extract the one-to-one corresponding first new energy station equipment control attribute characteristic value set and the first new energy station equipment state attribute characteristic value set; sort the first new energy station equipment control attribute characteristic value set in ascending order to obtain a first new energy station equipment control attribute characteristic value sequence; adjust the first new energy station equipment state attribute characteristic value set according to the first new energy station equipment control attribute characteristic value sequence to obtain a first new energy station equipment state attribute characteristic value sequence.

[0050] Construct a correlation analysis function: , in, Characterize the Pearson correlation coefficient, represents the control attribute of the first new energy station equipment, y represents the state attribute of the first new energy station equipment, Characterizing the covariance of the first new energy station equipment control attribute characteristic value sequence and the first new energy station equipment state attribute characteristic value sequence, Characterizes the standard deviation of the characteristic value sequence of the control attribute of the first new energy station equipment, Characterizes the standard deviation of the characteristic value sequence of the first new energy station equipment status attributes.

[0051] The first new energy station equipment control attribute characteristic value sequence and the first new energy station equipment state attribute characteristic value sequence are processed according to the correlation analysis function to obtain the first correlation coefficient.

[0052] Specifically, we first extract a set of characteristic values ​​corresponding to the equipment control attributes and equipment status attributes from the operation and maintenance section data. The characteristic values ​​of the equipment control attributes represent the key operating parameters of the equipment and have different set values ​​in different operating time periods to form a set of characteristic values. The characteristic values ​​of the equipment status attributes are the actual operating performance of the equipment under the characteristic values ​​of the control attributes.

[0053] Then, the device control attribute characteristic value set is sorted in ascending order to obtain the device control attribute characteristic value sequence, ensuring that the variable input of the subsequent correlation analysis has the same order. Then, according to the sorted control attribute characteristic value sequence, the corresponding state attribute characteristic value is adjusted, that is, each data point in the control attribute characteristic value sequence finds the corresponding data in the state attribute characteristic value set and arranges them in the same order, ensuring that the two sets of characteristic values ​​(control attributes and state attributes) are subjected to correlation analysis in the same order to avoid analysis deviations caused by different sorting.

[0054] Specifically, through the Pearson correlation analysis method, a correlation analysis function is constructed to calculate the correlation between the control attribute characteristic value sequence and the state attribute characteristic value sequence. The linear relationship between the two variables can be quantified through the Pearson correlation coefficient.

[0055] In the correlation analysis function, covariance represents the common change trend between two variables. A positive covariance value indicates a positive correlation between the two variables (i.e., an increase in the control attribute will lead to an increase in the state attribute), and a negative covariance value indicates a negative correlation (i.e., an increase in the control attribute will lead to a decrease in the state attribute).

[0056] Specifically, the sorted control attribute eigenvalue sequence and state attribute eigenvalue sequence are respectively input into the correlation analysis function. First, the covariance of the control attribute and the state attribute is calculated, and then their respective standard deviations are calculated. Then, according to the correlation analysis function, the correlation coefficient between the control attribute and the state attribute is calculated. ρ=1 indicates a completely positive correlation, and an increase in the control attribute will cause an equal increase in the state attribute. ρ=-1 indicates a completely negative correlation, and an increase in the control attribute will cause an equal decrease in the state attribute. ρ=0 indicates no correlation, and there is no linear relationship between the control attribute and the state attribute.

[0057] In some implementations, constructing the plurality of sets of associated new energy station equipment control attributes to the plurality of new energy station equipment state attributes comprises: According to the multiple groups of associated new energy field station equipment control attributes, a first group of associated new energy field station equipment control attributes is extracted; according to the first group of associated new energy field station equipment control attributes, a first new energy field station equipment state attribute is extracted from the multiple new energy field station equipment state attributes; with the first new energy field station equipment state attribute as the supervision attribute and the first group of associated new energy field station equipment control attributes as the input attribute, a first new energy field station equipment state mapper is trained and added into the multiple new energy field station equipment state mappers.

[0058] Specifically, first, a first group of associated control attributes is randomly extracted from multiple associated new energy station equipment control attributes that have been grouped before. The first group of associated control attributes is a group of parameters that are determined through correlation analysis and have a strong impact on the equipment state. Then, the historical records of the first group of associated control attributes are extracted from the equipment's operating data as the input data set for training the equipment state mapper.

[0059] Specifically, after extracting the first group of associated control attributes, the first new energy station equipment state attribute associated with the first group of associated control attributes is found from multiple equipment state attributes. This state attribute will be used as the target output of the mapper (i.e., the supervision attribute) to guide the model on how to predict the state performance of the equipment through changes in the control attributes, i.e., for supervising the learning process.

[0060] Next, through the supervised learning method, the extracted first new energy station equipment state attributes are used as supervision attributes (target output), and the first set of associated control attributes are used as input attributes to train the first new energy station equipment state mapper. For example, if the relationship between the state attributes and the control attributes can be modeled by linear or nonlinear regression, a linear regression or polynomial regression model is selected. If the relationship between the state and control attributes is more complex, a machine learning model is used for training, such as a support vector machine, a decision tree, a random forest or a neural network model, so as to capture more complex nonlinear relationships and improve the accuracy of the prediction.

[0061] Specifically, the trained First New Energy Station Equipment State Mapper is added to multiple equipment state mappers, which contain different mapping models of control attributes and state attributes, and are used to predict the performance of equipment under different operating conditions. When it is necessary to predict the operating state of the equipment, the corresponding state mapper model can be dynamically called according to the changes in the control parameters, which helps to make more accurate equipment operation predictions under different load and environmental conditions.

[0062] The monitoring operation status module 13 is used to receive the first new energy station equipment monitoring operation status matrix when the first new energy station equipment is started according to the first new energy station equipment control parameters.

[0063] Specifically, when the first new energy station equipment is initialized and started according to the set control parameters, the equipment's operating status data is received and recorded in real time, and summarized into a monitoring operating status matrix to reflect the actual performance of the equipment under different operating conditions. Among them, the first new energy station equipment monitoring operating status matrix is ​​a multidimensional matrix, which contains the key status data of the equipment at different time points and operating conditions. Unlike the previous benchmark operating status matrix, this matrix is ​​based on the actual monitoring data of the equipment, rather than predicted data.

[0064] Exemplarily, the first new energy station equipment monitoring operation status matrix includes: time dimension, that is, the matrix records the status changes of the equipment at different time points, helping the system understand the performance of the equipment at different operation stages; state parameter dimension, which means that each element in the matrix represents a specific state parameter of the equipment at a certain point in time. Through the real-time data in the matrix, the operation status of the equipment can be continuously tracked to determine whether it is operating normally according to the set control parameters.

[0065] The state comparison module 14 is used to compare the first new energy station equipment benchmark operation state matrix with the first new energy station equipment monitoring operation state matrix to generate an operation state deviation coefficient.

[0066] Specifically, the first new energy station equipment benchmark operating status matrix and the first new energy station equipment monitoring operating status matrix are compared to calculate the operating status deviation coefficient of each status attribute. The deviation coefficient is used to quantify the difference between the actual operating status of the equipment and the expected benchmark status, thereby helping the system monitor and optimize the operating performance of the equipment.

[0067] In some embodiments, comparing the first new energy station equipment benchmark operating state matrix with the first new energy station equipment monitoring operating state matrix to generate an operating state deviation coefficient includes: Construct the running status deviation coefficient comparison function: , in, Characterizes the deviation coefficient of the running state of the i-th attribute, Characterizes the monitoring value of the i-th attribute operation status, Characterizes the benchmark value of the operating status of the i-th attribute, Characterizes the deviation threshold of the running status of the i-th attribute.

[0068] The ratio of the sum of all running state deviation coefficients to the number of running state attributes is calculated and set as the running state deviation coefficient.

[0069] Specifically, in order to compare the monitored operating state of the device with the reference operating state, a corresponding operating state deviation coefficient comparison function is constructed to calculate the deviation of each state attribute. For example, in the operating state deviation coefficient comparison function, when |a i1 −a i0 ∣ (i.e. the difference between the monitored value and the reference value of the i-th attribute) is greater than or equal to the deviation threshold Δ ai When , it can be considered that there is a significant deviation and assigned a value of 1.

[0070] Furthermore, according to the constructed comparison function, each state attribute in the first new energy station equipment monitoring operation state matrix is ​​compared one by one with the benchmark value in the corresponding benchmark operation state matrix, and then, the multiple deviation coefficients obtained are statistically added, and the final operation state deviation coefficient is calculated based on the ratio of the total deviation to the total number of attributes.

[0071] By comparing the benchmark operating status matrix and the monitoring operating status matrix of the first new energy station equipment, the operating status deviation coefficient is calculated to evaluate whether the actual operating status of the equipment is significantly different from the expected status, thereby helping the system to monitor the equipment operation in real time, make timely adjustments and optimizations, and ensure the stable and efficient operation of new energy equipment.

[0072] The operation and maintenance identification module 15 is used to generate a fault operation and maintenance identification for the first new energy station equipment and send it to the new energy station fault management terminal when the operation status deviation coefficient is greater than or equal to the operation status deviation coefficient threshold.

[0073] Specifically, if the operating status deviation coefficient is greater than or equal to the operating status deviation coefficient threshold, that is, the proportion of operating status indicators with operating deviations is greater than the preset control limit, a fault operation and maintenance mark is generated and sent to the new energy station fault management end, where the operating status deviation coefficient threshold is a preset critical value used to determine whether the operating status of the equipment is within the normal range. Preferably, it is determined through historical data analysis or experience.

[0074] Specifically, when the operating status deviation coefficient reaches or exceeds the threshold, it means that the status of the equipment has deviated from expectations and there may be a fault or anomaly. A fault operation and maintenance identification is automatically generated to provide specific fault information to the fault management end, wherein the fault operation and maintenance identification is an identification that describes the abnormal situation of the current operating status of the equipment. Exemplarily, the fault operation and maintenance identification includes: equipment identification information, anomaly type, deviation details, which is used to help operation and maintenance personnel quickly locate problems and guide equipment inspection, maintenance or adjustment.

[0075] The cycle identification module 16 is used to generate a periodic operation and maintenance identification for the first new energy station equipment when the operation status deviation coefficient is less than the operation status deviation coefficient threshold, and send it to the new energy station fault management terminal.

[0076] Specifically, if the operating status deviation coefficient does not exceed the threshold, it can be considered that the status of the equipment meets expectations, and a periodic operation and maintenance mark is generated to operate and maintain the first new energy station equipment based on a predetermined operation and maintenance cycle.

[0077] By monitoring the operating status of the equipment in real time, the system can automatically generate a fault operation and maintenance mark or a periodic operation and maintenance mark and send it to the fault management end of the new energy station according to whether the operating status deviation coefficient exceeds the set threshold, ensuring that the equipment can be maintained and repaired in a timely manner when a failure or abnormality occurs, thereby ensuring the stable operation of the new energy station equipment. When the operation is normal, periodic operation and maintenance is performed based on the predetermined operation and maintenance cycle to maximize the power generation efficiency of the new energy station.

[0078] In summary, the new energy station fault management system provided by the present invention has the following technical effects: Through the control parameter receiving module, before the first new energy site equipment is started, the pre-configured control parameters of the first new energy site equipment are received; the benchmark state prediction module predicts the operation state according to the control parameters of the first new energy site equipment to obtain the benchmark operation state matrix of the first new energy site equipment; the monitoring operation state module receives the monitoring operation state matrix of the first new energy site equipment when the first new energy site equipment is started according to the control parameters of the first new energy site equipment; the state comparison module compares the benchmark operation state matrix of the first new energy site equipment with the monitoring operation state matrix of the first new energy site equipment to generate an operation state deviation coefficient; the operation and maintenance identification module generates a fault operation and maintenance identification for the first new energy site equipment when the operation state deviation coefficient is greater than or equal to the operation state deviation coefficient threshold, and sends it to the new energy site fault management terminal, thereby achieving the technical effect of improving fault responsiveness and management automation.

[0079] Embodiment 2 Figure 2 This is a flow chart of a new energy station fault management method of the present invention. For example, Figure 1 The structural diagram of a new energy station fault management system of the present invention can be used to implement the following Figure 2 The process shown.

[0080] Based on the same concept as the new energy station fault management system in the embodiment, the present invention also provides a new energy station fault management method including: Before the first new energy site equipment is started, the preconfigured first new energy site equipment control parameters are received.

[0081] The operating state is predicted according to the control parameters of the first new energy station equipment to obtain a reference operating state matrix of the first new energy station equipment.

[0082] When the first new energy station equipment is started according to the first new energy station equipment control parameters, the first new energy station equipment monitoring operation status matrix is ​​received.

[0083] The first new energy site equipment benchmark operating state matrix and the first new energy site equipment monitoring operating state matrix are compared to generate an operating state deviation coefficient.

[0084] When the operating status deviation coefficient is greater than or equal to the operating status deviation coefficient threshold, a fault operation and maintenance mark is generated for the first new energy station equipment and sent to the new energy station fault management terminal.

[0085] When the operating status deviation coefficient is less than the operating status deviation coefficient threshold, a periodic operation and maintenance mark is generated for the first new energy station equipment and sent to the new energy station fault management terminal.

[0086] In some implementations, performing an operation state prediction according to the first new energy station equipment control parameter to obtain a first new energy station equipment reference operation state matrix includes: Obtain multiple new energy station equipment status attributes; traverse the multiple new energy station equipment status attributes, perform correlation sorting on the first new energy station equipment control attribute set, and obtain multiple groups of related new energy station equipment control attributes; construct multiple new energy station equipment status mappers from the multiple groups of related new energy station equipment control attributes to the multiple new energy station equipment status attributes; according to the multiple new energy station equipment status mappers, perform operating status prediction on the first new energy station equipment control parameters, and obtain the first new energy station equipment benchmark operating status matrix.

[0087] In some implementations, traversing the multiple new energy station equipment state attributes, performing correlation sorting on the first new energy station equipment control attribute set, and obtaining multiple groups of associated new energy station equipment control attributes include: Obtain a first new energy field station equipment state attribute of the multiple new energy field station equipment state attributes; obtain a first new energy field station equipment control attribute of the first new energy field station equipment control attribute set; take the first new energy field station equipment control attribute as the only variable, perform a correlation analysis on the first new energy field station equipment state attribute, and obtain a first correlation coefficient; when the first correlation coefficient meets the correlation coefficient threshold, add the first new energy field station equipment control attribute into a first group of associated new energy field station equipment control attributes; add the first group of associated new energy field station equipment control attributes into the multiple groups of associated new energy field station equipment control attributes.

[0088] In some implementations, taking the first new energy station equipment control attribute as the only variable, performing a correlation analysis on the first new energy station equipment state attribute to obtain a first correlation coefficient includes: Taking the first new energy station equipment control attribute as the only independent variable of the multiple new energy station equipment status attributes and the first new energy station equipment status attribute as the dependent variable, collecting the first new energy station equipment operation and maintenance cross-sectional data; performing correlation analysis based on the first new energy station equipment operation and maintenance cross-sectional data to obtain a first correlation coefficient.

[0089] In some implementations, performing a correlation analysis based on the first new energy station equipment operation and maintenance section data to obtain a first correlation coefficient includes: According to the first new energy station equipment operation and maintenance section data, extract the one-to-one corresponding first new energy station equipment control attribute characteristic value set and the first new energy station equipment state attribute characteristic value set; sort the first new energy station equipment control attribute characteristic value set in ascending order to obtain a first new energy station equipment control attribute characteristic value sequence; adjust the first new energy station equipment state attribute characteristic value set according to the first new energy station equipment control attribute characteristic value sequence to obtain a first new energy station equipment state attribute characteristic value sequence.

[0090] Construct a correlation analysis function: , in, Characterize the Pearson correlation coefficient, represents the control attribute of the first new energy station equipment, y represents the state attribute of the first new energy station equipment, Characterizing the covariance of the first new energy station equipment control attribute characteristic value sequence and the first new energy station equipment state attribute characteristic value sequence, Characterizes the standard deviation of the characteristic value sequence of the control attribute of the first new energy station equipment, Characterizes the standard deviation of the characteristic value sequence of the first new energy station equipment status attributes.

[0091] The first new energy station equipment control attribute characteristic value sequence and the first new energy station equipment state attribute characteristic value sequence are processed according to the correlation analysis function to obtain the first correlation coefficient.

[0092] In some implementations, constructing the plurality of sets of associated new energy station equipment control attributes to the plurality of new energy station equipment state attributes comprises: According to the multiple groups of associated new energy field station equipment control attributes, a first group of associated new energy field station equipment control attributes is extracted; according to the first group of associated new energy field station equipment control attributes, a first new energy field station equipment state attribute is extracted from the multiple new energy field station equipment state attributes; with the first new energy field station equipment state attribute as the supervision attribute and the first group of associated new energy field station equipment control attributes as the input attribute, a first new energy field station equipment state mapper is trained and added into the multiple new energy field station equipment state mappers.

[0093] In some implementations, comparing the first new energy site equipment benchmark operating state matrix with the first new energy site equipment monitoring operating state matrix to generate an operating state deviation coefficient includes: Construct the running status deviation coefficient comparison function: , in, Characterizes the deviation coefficient of the running state of the i-th attribute, Characterizes the monitoring value of the i-th attribute operation status, Characterizes the benchmark value of the operating status of the i-th attribute, Characterizes the deviation threshold of the running status of the i-th attribute.

[0094] The ratio of the sum of all running state deviation coefficients to the number of running state attributes is calculated and set as the running state deviation coefficient.

[0095] It should be understood that the embodiments mentioned in this specification focus on their differences from other embodiments. The specific embodiments in the aforementioned embodiment one are also applicable to a new energy station fault management method described in embodiment two. For the sake of brevity of the specification, they will not be further elaborated here.

[0096] Embodiment 3 Figure 3 The schematic structural diagram of an exemplary electronic device provided for the present invention shows a block diagram of an exemplary electronic device suitable for implementing an embodiment of the present invention. Figure 3 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention. Figure 3 As shown, the electronic device includes a processor 31, a memory 32, an input device 33 and an output device 34; the number of processors 31 in the electronic device can be one or more. Figure 3 Taking a processor 31 as an example, the processor 31, memory 32, input device 33 and output device 34 in the electronic device can be connected through a bus or other means. Figure 3 The example of connecting through bus is taken in the following.

[0097] The memory 32 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to a new energy station fault management system in an embodiment of the present invention. The processor 31 executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 32, that is, realizing the above-mentioned new energy station fault management system.

[0098] It should be understood that the embodiments disclosed in the present invention and the above description can enable those skilled in the art to use the present invention to implement the present invention. At the same time, the present invention is not limited to the above-mentioned embodiments. It should be understood that those skilled in the art can still modify the technical solutions recorded in the above-mentioned embodiments, or replace some of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A new energy station fault management system, characterized in that: include: A control parameter receiving module, wherein the control parameter receiving module is used to receive pre-configured control parameters of the first new energy station equipment before the first new energy station equipment is started; A reference state prediction module, the reference operating state prediction module is used to predict the operating state according to the control parameters of the first new energy station equipment to obtain a reference operating state matrix of the first new energy station equipment; A monitoring operation status module, the monitoring operation status module is used to receive a first new energy site equipment monitoring operation status matrix when the first new energy site equipment is started according to the first new energy site equipment control parameter; A state comparison module, the state comparison module is used to compare the first new energy site equipment benchmark operation state matrix and the first new energy site equipment monitoring operation state matrix to generate an operation state deviation coefficient; An operation and maintenance identification module, wherein the operation and maintenance identification module is used to generate a fault operation and maintenance identification for the first new energy station equipment and send it to the new energy station fault management terminal when the operation state deviation coefficient is greater than or equal to the operation state deviation coefficient threshold; A periodic identification module, wherein the periodic identification module is used to generate a periodic operation and maintenance identification for the first new energy station equipment when the operating state deviation coefficient is less than the operating state deviation coefficient threshold, and send it to the new energy station fault management terminal.

2. A new energy station fault management system as claimed in claim 1, characterized in that: The operation state prediction is performed according to the control parameters of the first new energy station equipment to obtain a first new energy station equipment reference operation state matrix, including: Obtain the status attributes of multiple new energy station equipment; Traversing the multiple new energy station equipment state attributes, performing correlation sorting on the first new energy station equipment control attribute set, and obtaining multiple groups of related new energy station equipment control attributes; Constructing a plurality of new energy field station equipment state mappers that associate the plurality of sets of new energy field station equipment control attributes to the plurality of new energy field station equipment state attributes; According to the multiple new energy station equipment state mappers, the operation state of the first new energy station equipment control parameter is predicted to obtain the first new energy station equipment reference operation state matrix.

3. A new energy station fault management system as claimed in claim 2, characterized in that: Traversing the multiple new energy station equipment state attributes, performing correlation sorting on the first new energy station equipment control attribute set, and obtaining multiple groups of related new energy station equipment control attributes, including: Obtain a first new energy site equipment state attribute of the plurality of new energy site equipment state attributes; Obtaining the first new energy site equipment control attribute of the first new energy site equipment control attribute set; Taking the first new energy station equipment control attribute as the only variable, performing a correlation analysis on the first new energy station equipment state attribute to obtain a first correlation coefficient; When the first correlation coefficient meets a correlation coefficient threshold, adding the first new energy site equipment control attribute to a first group of associated new energy site equipment control attributes; The first group of associated new energy site equipment control attributes is added to the multiple groups of associated new energy site equipment control attributes.

4. A new energy station fault management system as claimed in claim 3, characterized in that: Taking the first new energy station equipment control attribute as the only variable, performing a correlation analysis on the first new energy station equipment state attribute to obtain a first correlation coefficient, including: Taking the first new energy station equipment control attribute as the only independent variable of the plurality of new energy station equipment state attributes and taking the first new energy station equipment state attribute as the dependent variable, collecting the first new energy station equipment operation and maintenance section data; A correlation analysis is performed based on the first new energy station equipment operation and maintenance cross-sectional data to obtain a first correlation coefficient.

5. A new energy station fault management system as claimed in claim 4, characterized in that: A correlation analysis is performed based on the first new energy station equipment operation and maintenance section data to obtain a first correlation coefficient, including: Extracting a one-to-one corresponding first new energy station equipment control attribute characteristic value set and a first new energy station equipment state attribute characteristic value set according to the first new energy station equipment operation and maintenance section data; Sorting the first new energy site equipment control attribute characteristic value set from small to large to obtain a first new energy site equipment control attribute characteristic value sequence; Adjusting the first new energy station equipment state attribute characteristic value set according to the first new energy station equipment control attribute characteristic value sequence to obtain a first new energy station equipment state attribute characteristic value sequence; Construct a correlation analysis function: ， in, Characterize the Pearson correlation coefficient, represents the control attribute of the first new energy station equipment, y represents the state attribute of the first new energy station equipment, Characterizing the covariance of the first new energy station equipment control attribute characteristic value sequence and the first new energy station equipment state attribute characteristic value sequence, Characterizes the standard deviation of the characteristic value sequence of the control attribute of the first new energy station equipment, The standard deviation of the characteristic value sequence representing the state attribute of the first new energy station equipment; The first new energy station equipment control attribute characteristic value sequence and the first new energy station equipment state attribute characteristic value sequence are processed according to the correlation analysis function to obtain the first correlation coefficient.

6. A new energy station fault management system as claimed in claim 2, characterized in that: Constructing a plurality of new energy field station equipment state mappers that associate the plurality of groups of new energy field station equipment control attributes to the plurality of new energy field station equipment state attributes, comprising: Extracting a first group of associated new energy site equipment control attributes according to the multiple groups of associated new energy site equipment control attributes; Extracting a first new energy station equipment state attribute from the plurality of new energy station equipment state attributes according to the first group of associated new energy station equipment control attributes; Taking the first new energy station equipment state attribute as the supervision attribute and the first group of associated new energy station equipment control attributes as the input attributes, the first new energy station equipment state mapper is trained and added into the multiple new energy station equipment state mappers.

7. A new energy station fault management system as claimed in claim 1, characterized in that: Comparing the first new energy station equipment benchmark operation state matrix with the first new energy station equipment monitoring operation state matrix to generate an operation state deviation coefficient includes: Construct the running status deviation coefficient comparison function: ， in, Characterizes the deviation coefficient of the running state of the i-th attribute, Characterizes the monitoring value of the i-th attribute operation status, Characterizes the benchmark value of the operating status of the i-th attribute, Characterizes the deviation threshold of the running state of the i-th attribute; The ratio of the sum of all running state deviation coefficients to the number of running state attributes is calculated and set as the running state deviation coefficient.

8. A new energy station fault management method, characterized in that: The method is applied to a new energy station fault management system according to any one of claims 1 to 7, and the method comprises: Before the first new energy station equipment is started, receiving pre-configured control parameters of the first new energy station equipment; Performing an operation state prediction based on the control parameters of the first new energy station equipment to obtain a first new energy station equipment benchmark operation state matrix; When the first new energy station equipment is started according to the control parameters of the first new energy station equipment, receiving the first new energy station equipment monitoring operation status matrix; Comparing the first new energy site equipment benchmark operation state matrix with the first new energy site equipment monitoring operation state matrix to generate an operation state deviation coefficient; When the operation state deviation coefficient is greater than or equal to the operation state deviation coefficient threshold, a fault operation and maintenance mark is generated for the first new energy station equipment and sent to the new energy station fault management terminal; When the operating status deviation coefficient is less than the operating status deviation coefficient threshold, a periodic operation and maintenance mark is generated for the first new energy station equipment and sent to the new energy station fault management terminal.

9. An electronic device, characterized in that: The electronic device comprises: A memory for storing executable instructions; A processor, used to implement a new energy station fault management system as described in any one of claims 1 to 7 when executing executable instructions stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a new energy station fault management system as described in any one of claims 1 to 7 is implemented.

Images