Distributed new energy power generation project full life cycle management system

Abstract

The invention relates to the technical field of new energy management, in particular to a distributed new energy power generation project full life cycle management system, which comprises a component fault initial judgment module, a fault set matching and prediction module and a power generation capacity influence analysis module, unreasonable operation parameters of different components in the distributed wind power generation equipment detected by the detector are eliminated by adopting a data analysis method through the component fault initial judgment module, then the eliminated operation parameters are analyzed, the relevance among the different components is analyzed, and when a plurality of components fail at the same time, the components causing damage are rapidly determined according to the relevance; the fault set matching and prediction module combines the components with relevance in the component fault initial judgment module into a fault component set, matches the current fault component set with a historical set, judges the current fault component set as a prediction component, predicts the possible development trend of the current fault, and knows which components have faults subsequently under the similar fault condition; and a worker is helped to take preventive measures in advance.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy management, and more specifically, to a full-life cycle management system for distributed new energy power generation projects. Background Art

[0002] Distributed new energy power generation projects, as a new and promising power generation and comprehensive energy utilization mode, play a key role in the global energy transformation process. These projects adhere to the principles of near-site power generation, grid connection, conversion, and utilization, effectively improving energy utilization efficiency and reducing power transmission losses. Common distributed new energy power generation projects include distributed solar power generation equipment, distributed wind power generation equipment, etc. Among them, distributed wind power generation equipment converts wind energy into electrical energy by relying on wind turbines. When the wind blows through the blades of the wind turbine, the blades start to rotate under the action of the wind force. The rotational motion is transmitted to the generator through the transmission system inside the wind turbine. The generator uses the principle of electromagnetic induction to convert mechanical energy into electrical energy and output it.

[0003] After the installation of distributed wind power generation equipment, the staff will set multiple parameter standards. During the operation of the equipment, the operation parameters of different components in the equipment are detected through multiple different sensors. Then, by comparing the parameter standards of different components with the operation parameters, the faulty components in the equipment are judged. However, when multiple components of the equipment fail simultaneously, or when a fault in a certain component triggers a chain reaction resulting in changes in the operation parameters of other components, it becomes difficult to simply compare the parameter standards to judge the abnormal components. Due to the interweaving of multiple parameter anomalies, it is difficult to clarify the causal relationship and determine the initial fault source. In view of this, we propose a full-life cycle management system for distributed new energy power generation projects. Summary of the Invention

[0004] The purpose of the present invention is to address the problem that distributed new energy power generation projects have broad prospects and play a key role in energy transformation. They adhere to principles such as near-site power generation, etc., can improve energy utilization efficiency and reduce transmission losses. Common types include distributed solar and wind power generation equipment. Among them, distributed wind power generation equipment converts wind energy into electrical energy by means of wind turbines. After the equipment is installed, the staff will set parameter standards and use sensors to detect operation parameters to judge faulty components. However, when multiple components fail simultaneously or trigger a chain reaction, parameter anomalies are interwoven, the causal relationship is difficult to clarify, and it becomes difficult to determine the fault source.

[0005] To achieve the above object, the present invention provides a full-life cycle management system for distributed new energy power generation projects, including a component fault preliminary judgment module, a fault set matching and prediction module, and a power generation amount impact analysis module, wherein:

[0006] Therefore, the component fault preliminary judgment module senses the parameter standards of different components of the distributed wind power generation equipment and the operating parameters of different components, uses data analysis methods to eliminate unreasonable operating parameters, and analyzes the correlations between different components through fault mode correlation analysis. When multiple components fail simultaneously, the faulty components are judged through the correlations between different components, and an alarm signal is output.

[0007] The fault set matching and prediction module senses multiple related components, constructs multiple current faulty component sets and historical faulty component sets according to the chronological order, matches the current faulty component set with the historical faulty component sets, matches the historical faulty component set that is exactly the same as the current faulty component set, and determines the last faulty component according to the chronological order of the component faults in the historical faulty component set as the predicted faulty component. The predicted damaged component and the current faulty component set are jointly output as a reminder signal to the staff.

[0008] The power generation impact analysis module senses the operating parameters corresponding to multiple components after elimination in the component fault preliminary judgment module, calculates the correlation coefficients between the operating parameters of each component and the power generation respectively, retrieves the correlation coefficients of multiple current faulty component sets and the corresponding predicted damaged components, combines the correlation coefficients into a power generation impact value, and compares the maximum impact value. When the fault set matching and prediction module outputs a reminder signal, the maximum impact value is synchronously output.

[0009] As a further improvement of this technical solution, the working principle of the data analysis method in the component fault preliminary judgment module is as follows: Based on the characteristics of the normal distribution, in the normal distribution, 99.7% of the operating parameters will fall within the range of the mean ± 3 times the standard deviation. Therefore, if the operating parameters of different components exceed the range, the operating parameters are judged as abnormal operating parameters, and the abnormal operating parameters are eliminated.

[0010] As a further improvement of this technical solution, the working steps of the fault mode correlation analysis method in the component fault preliminary judgment module are as follows:

[0011] Step 1: Compare the parameter standards of the same component with the operating parameters after elimination. If the operating parameters are not within the parameter standards, the component corresponding to the operating parameters is judged as a faulty component.

[0012] Step 2: After judging that component A is a faulty component, sense the faulty component B in subsequent time nodes until the faulty component Z. When component A is a faulty component and the next faulty component is component B, calculate the frequency of components A and B being faulty components together, and set a frequency threshold. If the frequency of the two components being faulty components together > the frequency threshold, it is judged that there is a correlation between the two components.

[0013] Similarly, if component C is the next faulty component, then calculate the frequency of components A, B, and C being faulty components together. If the frequency > the frequency threshold, then the chronological order of the corresponding time nodes of faulty components A, B, and C is the fault propagation path between faulty components A, B, and C;

[0014] Step 3: If the generated electricity of the distributed wind power generation equipment does not meet the pre-corresponding parameter standards, then judge the power generation fault of the distributed wind power generation equipment. Take the fault that the generated electricity of the distributed wind power generation equipment does not meet the power generation interval as the top event. According to the relevance and fault propagation path between different faulty components, starting from the top event, inversely analyze the tail event that causes the top event to occur, and output an alarm signal to the staff.

[0015] As a further improvement of this technical solution, the calculation formula for the frequency of two components being faulty components together in the component fault preliminary judgment module is as follows:

[0016] The total number of times that sensing component A is a faulty component 、When component A is a faulty component, the number of times that component A and component B are faulty components together is , then the frequency of component A and component B being faulty components together is: .

[0017] As a further improvement of this technical solution, the working principle of inversely analyzing the cause of the top event in the component fault preliminary judgment module is as follows:

[0018] Sense the faulty component Z corresponding to the top event. If the frequency between two faulty components > the frequency threshold at this time, then continue to call out the previous faulty component Z - 1, and judge again whether the frequency > the frequency threshold until the faulty component with the frequency < the frequency threshold. The faulty component at this time is the tail event.

[0019] As a further improvement of this technical solution, the working principle of the fault set matching and prediction module for constructing the current faulty component set and the historical faulty component set is as follows: Sense that there are faulty components judged to be relevant in the component fault preliminary judgment module, which are respectively , and the corresponding fault occurrence times are ;

[0020] Sort the faulty components in chronological order: If the fault occurrence times corresponding to faulty component and faulty component , then faulty component is prior to faulty component in chronological order. In the combined current faulty component set, faulty component is sorted before faulty component Before;

[0021] Sort all relevant faulty components to obtain the current faulty component set , where .

[0022] As a further improvement of this technical solution, the fault set matching and prediction module matches the current faulty component set with multiple historical faulty component sets, and adopts a similarity calculation method based on set elements and order. The specific working principle is as follows:

[0023] Perceive the current faulty component set and the historical faulty component set respectively;

[0024] Compare the component compositions in the current faulty component set and the historical faulty component set. If the components included in the two sets are not exactly the same, the similarity is 0; if the components are the same, then consider the order factor;

[0025] Let be the number of components at the corresponding positions in the two sets that are different, that is, , where is an indicator function. When it is , otherwise , then the set similarity ;

[0026] When , it is determined that the current faulty component set S is exactly the same as the historical faulty component set H.

[0027] As a further improvement of this technical solution, the correlation coefficients between the operating parameters of each component of the power generation impact analysis module and the power generation are calculated by the partial correlation coefficient calculation method:

[0028] The core of the partial correlation coefficient calculation method is that when calculating the relationship between the operating parameter of a certain component and the power generation, the operating parameters of other components are used as control variables to eliminate the interference of the operating parameters of other components on the relationship between the two, and a pure linear correlation relationship between the operating parameter of a certain component and the power generation that is not interfered by other factors is obtained;

[0029] The partial correlation coefficient calculation method calculates the correlation coefficient based on multiple linear regression. Define the operating parameter of a certain component, the power generation, and the operating parameters of other components as variables , and ; then establish the regression equation of with respect to and The regression equation is used to obtain the residuals after regression and The residuals represent the respective variable parts after removing the influence of after the influence is removed and ;

[0030] Then calculate the correlation coefficient between and The correlation coefficient is the partial correlation coefficient between after controlling the influence of and which reflects the true linear correlation degree between and .

[0031] As a further improvement of this technical solution, the power generation impact analysis module senses a total of current fault component sets. The th component set contains fault components, and the corresponding correlation coefficient is . The formula for combining the correlation coefficients into the power generation impact value is: where is the th fault component set;

[0032] Calculate the power generation impact values for all current fault component sets, and the maximum impact value is .

[0033] Compared with the prior art, the beneficial effects of the present invention are:

[0034] In this distributed new energy power generation project full - life - cycle management system, through the component fault preliminary judgment module, the data analysis method is used to eliminate the unreasonable operation parameters of different components in the distributed wind power generation equipment by the detector, and then the operation parameters after elimination are analyzed to analyze the correlation between different components. When multiple components fail simultaneously, the component that causes the damage is quickly determined according to the correlation. The fault set matching and prediction module combines the components with correlation in the component fault preliminary judgment module into a fault component set, matches the current fault component set with the historical set, predicts the components that will be damaged next, defines them as predicted components, outputs a reminder signal to the staff, predicts the possible development trend of the current fault, and understands which components may have subsequent faults in similar fault situations, which helps the staff to make preparations in advance and take preventive measures to prevent the further expansion of the fault.

[0035] Moreover, the power generation impact analysis module analyzes the correlation coefficients between different components and power generation based on the operating parameters after being screened by the component fault preliminary judgment module, combines the correlation coefficients of the predicted component and multiple faulty components into a power generation impact value, and retrieves the maximum impact value. When the fault set matching and prediction module outputs a reminder signal, it simultaneously outputs the faulty component corresponding to the maximum impact data. By determining the maximum impact value through the power generation impact analysis module, the staff can quickly identify the faulty component or component set that has the greatest impact on power generation, take it as the top priority for maintenance, and arrange maintenance resources for processing first, thereby minimizing the impact of faults on power generation to the greatest extent.

[0036] In addition to the purposes, features, and advantages described above, the present invention has other purposes, features, and advantages. The present invention will be further described in detail below with reference to the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 is the overall module schematic diagram of the present invention;

[0038] Figure 2 is the working principle flowchart of the present invention.

[0039] The meanings of the reference numerals in the drawings are as follows:

[0040] 100, component fault preliminary judgment module; 200, fault set matching and prediction module; 300, power generation impact analysis module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0042] Refer to Figure 1 - Figure 2 As shown, the distributed new energy power generation project full-life cycle management system includes a component fault preliminary judgment module 100, a fault set matching and prediction module 200, and a power generation impact analysis module 300;

[0043] Distributed new energy power generation projects, as a new and promising power generation and comprehensive energy utilization model, play a crucial role in the global energy transformation process. These projects adhere to the principle of generating electricity, grid connection, conversion, and utilization in the vicinity, effectively improving energy utilization efficiency and reducing power transmission losses. Common distributed new energy power generation projects include distributed solar power generation equipment, distributed wind power generation equipment, etc. Among them, distributed wind power generation equipment converts wind energy into electrical energy through wind turbines. When the wind blows through the blades of the fan, the blades start to rotate under the action of the wind force. The rotational motion is transmitted to the generator through the transmission system inside the fan. The generator uses the principle of electromagnetic induction to convert mechanical energy into electrical energy and output it;

[0044] After the installation of distributed wind power generation equipment, the staff will set multiple parameter standards. During the operation of the equipment, the operating parameters of different components in the equipment are detected through multiple different sensors, and then, by comparing the parameter standards of different components with the operating parameters, the components with faults in the equipment are judged. However, when multiple components in the equipment fail simultaneously, or when a fault in a certain component triggers a chain reaction resulting in changes in the operating parameters of other components, it becomes difficult to simply compare the parameter standards to determine the abnormal components. Because multiple parameter abnormalities are intertwined, it is difficult to clarify the causal relationship and determine the initial fault source.

[0045] During the operation of wind power generation equipment, the sensors may be interfered by various factors, generating inaccurate or unreasonable data. Therefore, the initial component fault judgment module 100 senses the parameter standards of different components of the distributed wind power generation equipment, and the sensors detect the operating parameters of different components. The data analysis method is used to eliminate unreasonable operating parameters, providing correct basic data for subsequent fault analysis and other work, and avoiding misjudgment or wrong decisions caused by incorrect data;

[0046] The working principle of the data analysis method in the initial component fault judgment module 100 is as follows: Based on the characteristics of the normal distribution, in the normal distribution, 99.7% of the operating parameters will fall within the range of the mean ± 3 times the standard deviation. Therefore, if the operating parameter exceeds the range, the operating parameter is judged as an abnormal operating parameter, and the abnormal operating parameter is eliminated. The expression is as follows:

[0047] The sensed operating parameter is: , the mean of the operating parameter is , and the standard deviation is , if the operating reference satisfies , then the operating reference is marked as an abnormal operating reference.

[0048] Subsequently, the initial component failure judgment module 100 analyzes the correlations among different components through the failure mode correlation analysis method. When multiple components in the distributed wind power generation equipment fail simultaneously, it can quickly identify the faulty components and output an alarm signal.

[0049] The distributed wind power generation equipment consists of multiple components. When multiple components fail simultaneously, by analyzing the correlations among the components through the initial component failure judgment module 100, it is possible to quickly determine which components have failed based on the failure mode and the mutual relationships among the components, rather than blindly checking all components. This greatly saves the time for troubleshooting, improves the maintenance efficiency, reduces the equipment downtime, and decreases the power generation loss caused by equipment failures.

[0050] The working steps of the failure mode correlation analysis method in the initial component failure judgment module 100 are as follows:

[0051] Step 1: Compare the parameter standard of the same component with the remaining operating parameters. If the operating parameters are not within the parameter standard, then judge the component corresponding to the operating parameters as a faulty component. The corresponding expression is as follows:

[0052] The parameter standard of the sensing component A is , and the operating parameter of component A detected by the sensor is . If , then judge component A as a normal component; otherwise, it is a faulty component.

[0053] Step 2: After sensing that component A is a faulty component, sense the faulty components B to Z at subsequent time nodes. When component A is a faulty component and the next faulty component is component B, calculate the frequency of component A and component B being faulty components together, and set a frequency threshold. If the frequency of the two components being faulty components together > the frequency threshold, then judge that there is a correlation between the two components. The corresponding expression is as follows:

[0054] The total number of times component A is sensed as a faulty component , and when component A is a faulty component, the number of times component A and component B are faulty components together is . Then the frequency of component A and component B being faulty components together is: ;

[0055] Similarly, if component C is the next faulty component, calculate the frequency of component A, B, and C being faulty components together. If the frequency > the frequency threshold, then the chronological order of the corresponding time nodes of the faulty components A, B, and C is the fault propagation path among the faulty components A, B, and C.

[0056] Step 3: If the generated power of the distributed wind power generation equipment does not meet the pre-corresponding parameter standards, then judge the power generation failure of the distributed wind power generation equipment. Take the failure that the generated power of the distributed wind power generation equipment does not meet the power generation range as the top event. Starting from the top event, reverse-analyze the tail events that cause the top event according to the relevance between different faulty components and the fault propagation path, and output an alarm signal to the staff;

[0057] The working principle of reverse-analyzing the cause of the top event is as follows:

[0058] Sense the faulty component Z corresponding to the top event. If the frequency between two faulty components is > the frequency threshold at this time, then continue to call out the previous faulty component Z-1, and judge again whether the frequency is > the frequency threshold until the faulty component with frequency < the frequency threshold. The faulty component at this time is the tail event.

[0059] The fault set matching and prediction module 200 is used to, when multiple faulty components appear currently, judge the faulty components with relevance through the component fault preliminary judgment module 100, merge the relevant components into multiple current faulty component sets in chronological order, match them with multiple historical faulty component sets until a historical faulty component set that is exactly the same as it is matched; after matching a historical faulty component set that is exactly the same as the current faulty component set, determine the last faulty component according to the chronological order of the component faults in the historical faulty component set, which is the predicted faulty component, and output a reminder signal to the staff jointly with the predicted damaged component and the current faulty component set;

[0060] Based on the chronological order of the component faults in the component fault preliminary judgment module 100, the fault set matching and prediction module 200 predicts the possible development trend of the current fault, understands which components may have subsequent faults in similar fault situations, helps the staff make preparations in advance and take preventive measures to prevent the fault from further expanding;

[0061] The calculation formula for the fault set matching and prediction module 200 to merge the current faulty component set is as follows: Sense that there are faulty components judged to be relevant in the component fault preliminary judgment module 100, which are respectively , and the corresponding fault occurrence times are ;

[0062] Sort the faulty components in chronological order: If the faulty component and the faulty component correspond to the fault occurrence times , then the faulty component is earlier than the faulty component in chronological order. In the merged current faulty component set, the faulty component Sort the faulty components before;

[0063] After sorting all the relevant faulty components, the current faulty component set is obtained , where ;

[0064] The fault set matching and prediction module 200 matches the current faulty component set with multiple historical faulty component sets, and adopts a similarity calculation method based on set elements and order. The specific working principle is as follows:

[0065] Perceive the current faulty component set and the historical faulty component set ;

[0066] Compare the component compositions in the current faulty component set and the historical faulty component set. If the components included in the two sets are not exactly the same, the similarity is 0; if the components are the same, then consider the order factor;

[0067] Let be the number of components with different corresponding positions in the two sets, that is , where is the indicator function. When it is , otherwise , then the set similarity ;

[0068] When , it is determined that the current faulty component set S is exactly the same as the historical faulty component set H;

[0069] The calculation formula for the fault set matching and prediction module 200 to match and predict faulty components is as follows: Perceive the matched historical faulty component set , each component The corresponding fault occurrence time is , then the predicted faulty component satisfies , that is , where .

[0070] The power generation impact analysis module 300 perceives the operating parameters corresponding to multiple components excluded by the component fault preliminary judgment module 100, and calculates the correlation coefficients between the operating parameters of each component and the power generation respectively;

[0071] Retrieve the correlation coefficients of multiple current faulty component sets and the corresponding predicted damaged components, combine the correlation coefficients into power generation impact values, compare the maximum impact values, and when the fault set matching and prediction module 200 outputs a reminder signal, synchronously output the maximum impact value;

[0072] By comparing the maximum impact value through the power generation impact analysis module 300, the staff can quickly determine the faulty component or component set that has the greatest impact on the power generation, make it the primary focus of maintenance, and prioritize maintenance personnel to handle it, thereby minimizing the impact of the fault on the power generation, improving maintenance efficiency, and reducing economic losses;

[0073] The correlation coefficient between the operating parameters of each component of the power generation impact analysis module 300 and the power generation is calculated by the partial correlation coefficient calculation method:

[0074] The core of the partial correlation coefficient calculation method is to use the operating parameters of other components as control variables when calculating the relationship between the operating parameters of a certain component and the power generation, eliminate the interference of the operating parameters of other components on the relationship between the two, and obtain a pure linear correlation between the operating parameters of a certain component and the power generation without interference from other factors;

[0075] The partial correlation coefficient calculation method calculates the correlation coefficient based on multiple linear regression, defining the operating parameters of a component, power generation and other component operating parameters as variables. , and ; then establish right The regression equation and right The regression equation is used to obtain the residual after regression. and , the residual represents the removal After the impact and The respective changing parts;

[0076] Then calculate and The correlation coefficient between After the impact and The partial correlation coefficient between and The true linear correlation between

[0077] The calculation formula is as follows:

[0078] and The partial correlation coefficient between The calculation formula is: ,in yes and The simple correlation coefficient of yes and The simple correlation coefficient of is and The simple correlation coefficient of is calculated specifically through the Pearson correlation coefficient formula , and ;

[0079] Then substitute it into the partial correlation coefficient formula for calculation , where and are respectively and The th observed values of and are respectively and The means of is the number of observed data;

[0080] The power generation impact analysis module 300 senses a total of current fault component sets. The th component set has fault components, and the corresponding correlation coefficient is . The formula for combining the correlation coefficients into the power generation impact value is: , where is the th fault component set;

[0081] Calculate the power generation impact values of all current fault component sets, and the maximum impact value is .

[0082] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and the descriptions in the specification are only preferred examples of the present invention and are not used to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A full life cycle management system for distributed new energy power generation projects, characterized in that, It includes a component fault preliminary judgment module (100), a fault set matching and prediction module (200), and a power generation amount influence analysis module (300), where: Therefore, the component fault preliminary judgment module (100) senses the parameter standards of different components of the distributed wind power generation equipment and the operating parameters of different components, uses the data analysis method to eliminate unreasonable operating parameters, and analyzes the correlation between different components through the fault mode correlation analysis method. When multiple components fail simultaneously, the faulty components are judged through the correlation between different components, and an alarm signal is output. The fault set matching and prediction module (200) senses multiple related components, constructs multiple current faulty component sets and historical faulty component sets according to the chronological order, matches the current faulty component set with the historical faulty component set, matches the historical faulty component set that is exactly the same as the current faulty component set, and determines the last faulty component according to the chronological order of the component faults in the historical faulty component set as the predicted faulty component, and outputs a reminder signal to the staff together with the predicted damaged components and the current faulty component set. The power generation amount influence analysis module (300) senses the operating parameters corresponding to multiple components after elimination in the component fault preliminary judgment module (100), calculates the correlation coefficients between the operating parameters of each component and the power generation amount respectively, retrieves the correlation coefficients of multiple current faulty component sets and the corresponding predicted damaged components, combines the correlation coefficients into a power generation amount influence value, and compares the maximum influence value. When the fault set matching and prediction module (200) outputs a reminder signal, the maximum influence value is output synchronously.

2. The distributed new energy power generation project full life cycle management system according to claim 1, wherein: The working principle of the data analysis method in the component fault preliminary judgment module (100) is as follows: Based on the characteristics of the normal distribution, in the normal distribution, 99.7% of the operating parameters will fall within the range of the mean ± 3 times the standard deviation. Therefore, if the operating parameters of different components exceed the range, the operating parameters are judged as abnormal operating parameters, and the abnormal operating parameters are eliminated.

3. The distributed new energy power generation project full life cycle management system according to claim 2, characterized in that: The working steps of the fault mode correlation analysis method in the component fault preliminary judgment module (100) are as follows: Step 1: Compare the parameter standards of the same component with the operating parameters after elimination. If the operating parameters are not within the parameter standards, the component corresponding to the operating parameters is judged as a faulty component. Step 2: After judging that component A is a faulty component, sense the faulty component B in the subsequent time nodes until the faulty component Z. When component A is a faulty component and the next faulty component is component B, calculate the frequency of components A and B being faulty components together, and set a frequency threshold. If the frequency of the two components being faulty components together > the frequency threshold, it is judged that there is a correlation between the two components. Similarly, if component C is the next faulty component, calculate the frequency of components A, B, and C being faulty components together. If the frequency > the frequency threshold, the chronological order of the corresponding time nodes of the faulty components A, B, and C is the fault propagation path between the faulty components A, B, and C. Step 3: If the generated power of the distributed wind power generation equipment does not meet the pre-corresponding parameter standards, then judge the power generation failure of the distributed wind power generation equipment. Take the failure of the generated power of the distributed wind power generation equipment not meeting the power generation range as the top event. Starting from the top event, inversely analyze the tail events that cause the top event according to the relevance between different faulty components and the fault propagation path, and output an alarm signal to the staff.

4. The distributed new energy power generation project full life cycle management system according to claim 3, characterized in that: The calculation formula for the frequency of two components being faulty components in the component fault preliminary judgment module (100) is as follows: The total number of times the sensing component A is a faulty component When component A is a faulty component, the number of times that component A and component B are both faulty components is , then the frequency that component A and component B are both faulty components is: .

5. The distributed new energy power generation project full life cycle management system according to claim 4, characterized in that: The working principle of inversely analyzing the cause of the top event in the component fault preliminary judgment module (100) is as follows: Sense the faulty component Z corresponding to the top event. If the frequency between two faulty components at this time > the frequency threshold, then continue to call out the previous faulty component Z-1, and judge again whether the frequency > the frequency threshold until the faulty component with frequency < the frequency threshold. The faulty component at this time is the tail event.

6. The distributed new energy power generation project full life cycle management system according to claim 1, wherein: The working principle of the fault set matching and prediction module (200) for constructing the current fault component set and the historical fault component set is as follows: The number of fault components determined to be relevant in the component fault preliminary judgment module (100) is respectively, and they are , and the corresponding fault occurrence times are ; Sort the failed components in chronological order: If the failure occurrence time corresponding to the failed component is , then the failed component precedes the failed component in chronological order, and in the currently merged set of failed components, the failed component is sorted before the failed component . Sort all relevant faulty components to obtain the current set of faulty components , where .

7. The distributed new energy power generation project full life cycle management system according to claim 6, characterized in that: The fault set matching and prediction module (200) matches the current faulty component set with multiple historical faulty component sets, and adopts a similarity calculation method based on the elements and order of the sets. The specific working principle is as follows: Sense the current faulty component set and the historical faulty component set respectively ;​ Compare the component compositions in the current faulty component set and the historical faulty component set. If the components included in the two sets are not exactly the same, then the similarity is 0; Let be the number of components at corresponding positions in the two sets that are different, i.e., , where is the indicator function, when holds , otherwise , then the set similarity ; When it is determined that the current set of faulty components S is exactly the same as the historical set of faulty components H.

8. The distributed new energy power generation project full life cycle management system according to claim 1, wherein: The correlation coefficients between the operating parameters of each component of the generated power influence analysis module (300) and the generated power are calculated by the partial correlation coefficient calculation method: The core of the partial correlation coefficient calculation method is that when calculating the relationship between the operating parameter of a certain component and the generated power, the operating parameters of other components are used as control variables to eliminate the interference of the operating parameters of other components on the relationship between the two, and obtain the linear correlation relationship between the operating parameter of a certain component and the generated power without being interfered by other factors; The calculation of the partial correlation coefficient for the correlation coefficient is based on multiple linear regression. The operating parameters of a certain component, the power generation, and the operating parameters of other components are defined as variables , and ; Then establish for regression equation and for regression equation, and obtain the residuals and . The residuals represent the respective changing parts of after removing the influence of and ; Then calculate and The correlation coefficient between them. The correlation coefficient is the partial correlation coefficient between after controlling the influence of and which reflects and The true degree of linear correlation between them.

9. The distributed new energy power generation project full life cycle management system according to claim 8, characterized in that: The power generation impact analysis module (300) senses a total of current fault component sets. The th component set contains fault components, and the corresponding correlation coefficient is . The formula for combining the correlation coefficients into the power generation impact value is: , where is the th fault component set; Calculate all power generation impact values of the current faulty component sets , the maximum impact value .

Images