Wind power equipment fault tracing method and system based on fault decoupling multilevel model

Abstract

The invention provides a wind power equipment fault tracing method and system based on a fault decoupling multi-level model, and relates to the technical field of fault intelligent diagnosis. Wind power equipment fault analysis information is collected, a fault decoupling multi-level network model is constructed, and a fault propagation path set of the fault decoupling multi-level network model is obtained; based on reliability characteristics and topological characteristics of all nodes and connecting edges among the nodes in the fault decoupling multilevel network model, node propagation intensity and connecting edge propagation intensity are obtained, and according to a path propagation intensity function, the node propagation intensity and the connecting edge propagation intensity, the propagation intensity of each propagation path in the fault propagation path set is calculated; calculating a path node attribute update value, obtaining a path index of each propagation path according to the path node attribute update value and the path index function, and selecting a propagation path meeting a preset accuracy rate and a preset confidence coefficient in the fault propagation path set as a fault propagation path, and sorting the fault propagation paths according to a preset path index sequence to determine a fault source. According to the invention, the accuracy of fault source positioning can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent fault diagnosis, and in particular to a method and system for tracing the source of a wind power equipment fault based on a fault decoupling multi-level model. Background Art

[0002] As one of the earliest developed and most important renewable energy sources in the integrated energy system, wind energy has great potential in reducing greenhouse gas emissions due to its abundant storage capacity, renewable nature, cleanliness and pollution-free nature. It has become the mainstream direction of global renewable energy development and an important force in promoting industrial upgrading and driving the adjustment of the energy system.

[0003] The Chinese patent with announcement number CN113283603B discloses a refined closed-loop wind turbine fault diagnosis method and system, which includes the following steps: establishing a system knowledge base, mapping the actual fault information to the electrical circuit that can cause the actual fault information to occur; using a data weighting algorithm to calculate the probability of failure of each node element of the electrical circuit, and determine the node element with fault in the electrical circuit; judging the correctness of the diagnosis result, and correcting the weight value corresponding to each node element in the data weighting algorithm. By establishing a system knowledge base, associating the actual fault information with the system knowledge base, and calculating according to the data weighting algorithm, the node element with fault can be accurately and quickly predicted. However, although the method provided by the above application can analyze the occurrence mechanism of the fault to a certain extent, it lacks consideration of the relationship between the various parts in the system, and also does not consider the multiple propagation and propagation of the fault, resulting in a low accuracy rate of fault source location. Therefore, it is very necessary to provide a wind power equipment fault tracing method and system based on a fault decoupling multi-level model to improve the accuracy of fault source location. Summary of the invention

[0004] In view of this, the present invention proposes a wind power equipment fault tracing method and system based on a fault decoupling multi-level model. By adopting a fault decoupling multi-level network model, each node and their mutual relationship can be clearly displayed, reducing the complexity of fault analysis and thus improving the accuracy of fault source location.

[0005] The present invention provides a method for tracing the source of wind power equipment faults based on a fault decoupling multi-level model, the method comprising:

[0006] Collecting wind power equipment fault analysis information, wherein the wind power equipment fault analysis information includes wind power equipment state monitoring variables, wind power equipment fault types, wind power equipment functional structures, and wind power equipment fault coupling relationships;

[0007] Based on the wind power equipment status monitoring variables, the wind power equipment fault type, the wind power equipment functional structure and the wind power equipment fault coupling relationship, a fault decoupling multi-level network model is constructed;

[0008] According to a depth-first search algorithm, the central nodes and bottom-level nodes of the fault decoupling multi-level network model are sequentially traversed to obtain a set of fault propagation paths of the fault decoupling multi-level network model;

[0009] Based on the reliability characteristics and topological characteristics of all nodes and edges between nodes in the fault decoupling multi-level network model, the node propagation strength and the edge propagation strength are obtained, and the propagation strength of each propagation path in the fault propagation path set is calculated according to the path propagation strength function, the node propagation strength and the edge propagation strength;

[0010] Based on the node influence value corresponding to the wind power equipment status monitoring variable and the path node attribute update function, the path node attribute update value is calculated, and according to the path node attribute update value and the path indicator function, the path indicator of each propagation path is obtained;

[0011] A propagation path in the fault propagation path set that meets a preset accuracy and a preset confidence is selected as the fault propagation path, and the fault propagation paths are sorted according to a preset path indicator sequence to determine the fault source.

[0012] On the basis of the above technical solution, preferably, the acquiring of the fault propagation path set of the fault decoupling multi-level network model specifically includes:

[0013] The adjacency matrix of the fault decoupling multi-level network model is calculated, and all propagation paths of the fault decoupling multi-level network model during the fault propagation process are obtained according to the depth-first search algorithm and the adjacency matrix, and all propagation paths that meet the preset path conditions are integrated into a fault propagation path set.

[0014] Based on the above technical solution, preferably, the expression of the node propagation strength is:

[0015]

[0016] Where I represents the cumulative distribution function, represents the probability density distribution, S i represents the topological characteristics of node i, d i represents the out-degree of node i, d j represents the out-degree of node j, n represents the total number of nodes in the fault decoupling multi-level network model, u i represents the propagation strength of node i, h i represents the reliability characteristics of node i, Si Represents the topological characteristics of node i.

[0017] More preferably, the expression of the edge propagation strength is:

[0018]

[0019] Among them, S ij represents the topological features of the edge between node i and node j, b ij represents the number of edges between nodes i and j, w ij represents the propagation strength of the edge between node i and node j, P ij is the reliability feature of the edge between node i and node j, W ij represents the propagation strength of the edge between node i and node j in the layer, represents the failure frequency of lower-layer node j caused by upper-layer node i, Represents the failure frequency of lower-level node i.

[0020] More preferably, the obtaining of the path index of each propagation path specifically includes:

[0021] Calculating the node impact value of each node in the fault decoupling multi-level network model according to the wind power equipment status monitoring variables and the node impact relationship table;

[0022] Based on the node influence value and the path node attribute update function, calculating the path node attribute update value corresponding to the node influence value;

[0023] Based on the path node attribute update value and the path update function, obtaining a path update value corresponding to the path node attribute update value;

[0024] Based on the path update value and the path indicator function, a path indicator corresponding to the path node attribute update value is obtained.

[0025] More preferably, the expression of the path propagation intensity function is:

[0026] p(l ij ) be =W ij

[0027]

[0028] p(l ij )=Πp(l ij ) in ×Πp(l ij ) be

[0029] Among them, p(l ij ) be represents the inter-layer path propagation strength, W ij represents the inter-layer edge propagation strength between node i and node j, u i represents the propagation strength of node i in the path within the layer, l ij represents the propagation characteristics between node i and node j in the intra-layer path, n represents the total number of nodes in the fault decoupling multi-level network model, p(l ij ) in represents the intra-layer path propagation strength, p(l ij ) represents the path propagation strength.

[0030] More preferably, the expression of the path indicator function is:

[0031]

[0032] RI=p(l ij )×Rs

[0033] Among them, P update represents the path node attribute update value of the propagation path root based on the wind power equipment status monitoring variable, represents the node impact value on the propagation path root affected by the wind power equipment status monitoring variable, s represents the number of nodes on the propagation path root affected by the wind power equipment status monitoring variable, Rs represents the path attribute update value of the propagation path root, m represents the number of path node attribute update values ​​under different fault location conditions, It represents the impact value of the wind power equipment fault type on the wind power equipment state monitoring variable, and RI represents the path index.

[0034] More preferably, the method further comprises:

[0035] If the bottom node of the fault propagation path corresponding to the maximum path index shows a propagation state, the fault is a sequential fault;

[0036] If there are two or more fault propagation paths corresponding to the maximum path index, the fault is a concurrent fault;

[0037] If there are two or more fault propagation paths corresponding to the maximum path index, and the high-level node propagation paths of the fault propagation paths are the same, the fault is a high-order fault.

[0038] In a second aspect of the present application, a wind power equipment fault tracing system based on a fault decoupling multi-level model is provided, wherein the wind power equipment fault tracing system comprises an information collection module, a path calculation module, an index calculation module and a fault location module, wherein:

[0039] The information collection module is used to collect wind power equipment fault analysis information, wherein the wind power equipment fault analysis information includes wind power equipment state monitoring variables, wind power equipment fault types, wind power equipment functional structures and wind power equipment fault coupling relationships;

[0040] The path operation module is used to construct a fault decoupling multi-level network model based on the wind power equipment status monitoring variables, the wind power equipment fault type, the wind power equipment functional structure and the wind power equipment fault coupling relationship, and sequentially traverse the central node and the bottom node of the fault decoupling multi-level network model according to the depth-first search algorithm to obtain the fault propagation path set of the fault decoupling multi-level network model;

[0041] The index calculation module is used to obtain the node propagation strength and the edge propagation strength based on the reliability characteristics and topological characteristics of all nodes and the edges between nodes in the fault decoupling multi-level network model, and calculate the propagation strength of each propagation path in the fault propagation path set according to the path propagation strength function, the node propagation strength and the edge propagation strength, calculate the path node attribute update value based on the node influence value corresponding to the wind power equipment status monitoring variable and the path node attribute update function, and obtain the path index of each propagation path according to the path node attribute update value and the path index function;

[0042] The fault location module is used to select a propagation path in the fault propagation path set that meets a preset accuracy and a preset confidence as a fault propagation path, and sort the fault propagation paths according to a preset path indicator order to determine the fault source.

[0043] In a third aspect of the present application, an electronic device is provided, comprising a processor, a memory, a user interface and a network interface, wherein the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory.

[0044] The wind power equipment fault tracing method and system based on the fault decoupling multi-level model provided by the present invention has the following beneficial effects compared with the prior art:

[0045] (1) By systematically collecting the status monitoring variables, fault types, functional structures and coupling relationships of wind power equipment, a comprehensive understanding of the comprehensive status of wind power equipment can be formed, which helps to improve the accuracy and timeliness of fault analysis. The fault decoupling multi-level network model can clearly display each node and their relationships, improve the visualization of the fault propagation path, facilitate tracing the source of the fault, reduce the complexity of fault analysis, and thus improve the accuracy of fault source location. At the same time, the fault propagation paths are sorted based on the path indicator function, which can more intuitively determine which fault propagation paths are more influential, thereby significantly improving the efficiency and accuracy of fault diagnosis.

[0046] (2) By calculating the node influence value of each node, the weight of each node's influence on the fault during the fault propagation process can be more clearly identified, which is helpful for fault location and analysis. At the same time, based on the node influence value and the path node attribute update function, the calculated path node attribute update value provides dynamic feedback on the status of each node, which can accurately reflect the changes in node attributes during the fault propagation process, ensuring the real-time and accuracy of the network model. By combining the path node attribute update value with the path update function, the efficiency of the path can be adjusted in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 A schematic flow chart of a method for tracing the source of a wind power equipment fault based on a fault decoupling multi-level model provided by the present invention;

[0049] Figure 2 A schematic diagram of a fault decoupling multi-level network model provided by the present invention;

[0050] Figure 3 A schematic diagram of the structure of a multi-level network model for fault decoupling in a wind power equipment gearbox system provided by the present invention;

[0051] Figure 4 A schematic diagram of node in-and-out degrees provided by the present invention;

[0052] Figure 5 A multi-level network model for wind power equipment fault decoupling provided by the present invention;

[0053] Figure 6 A schematic diagram of the framework of the wind power equipment fault tracing system provided by the present invention;

[0054] Figure 7 This is a schematic structural diagram of an electronic device provided by the present invention.

[0055] Explanation of the accompanying drawings: 1. Wind power equipment fault tracing system; 11. Information collection module; 12. Path calculation module; 13. Index calculation module; 14. Fault location module; 2. Electronic device; 21. Processor; 22. Communication bus; 23. User interface; 24. Network interface; 25. Memory. DETAILED DESCRIPTION

[0056] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] The present invention discloses a wind power equipment fault tracing method based on a fault decoupling multi-level model. Figure 1 The method includes steps S1 to S6.

[0058] Step S1 : collecting wind power equipment fault analysis information, wherein the wind power equipment fault analysis information includes wind power equipment state monitoring variables, wind power equipment fault types, wind power equipment functional structures, and wind power equipment fault coupling relationships.

[0059] In this step, the wind power equipment status monitoring variables can be installed by vibration sensors, temperature sensors, current sensors, etc., to monitor the vibration, temperature, current and other operating status data of the equipment in real time, or extract real-time status data from the monitoring system and SCADA (supervisory control and data acquisition) system of the wind power equipment, such as power output, speed, hydraulic pressure, etc., or organize and analyze historical fault data to identify key status monitoring variables related to the fault. The fault types of wind power equipment can be obtained by collecting the fault diagnosis manuals provided by the equipment manufacturer, summarizing the common fault types and their characteristics, and obtaining on-site fault maintenance experience and fault mode summary. The collection of the functional structure of wind power equipment can be obtained by obtaining the structural drawings and functional module description documents of the equipment, or conducting on-site observations and tests to supplement the differences between the actual operation and the design documents. The fault coupling relationship of wind power equipment can be analyzed by analyzing the historical fault case records, summarizing the mutual influence and coupling mechanism between different fault types, or by using methods such as fault tree analysis and failure mode and effect analysis (FMEA) to establish a fault coupling relationship model.

[0060] Step S2, constructing a fault decoupling multi-level network model based on wind power equipment status monitoring variables, wind power equipment fault types, wind power equipment functional structures, and wind power equipment fault coupling relationships.

[0061] In this step, a wind power equipment state monitoring model is constructed based on the wind power equipment state monitoring variables, and the system monitoring situation and state monitoring variable characteristics are analyzed; a composite fault analysis model is constructed based on the wind power equipment fault form, fault mechanism and system structure. Based on the diffusion and evolution mechanism of faults / abnormalities between heterogeneous and heterogeneous elements, on the basis of the existing complex system fault statistical data, the hierarchical nature of the complex system structure and fault propagation is considered; based on the fault cause and propagation carrier, the complex system historical fault mode is used as a node, through the system functional structure analysis and fault correlation relationship identification, the propagation relationship of energy flow, information flow and control flow is comprehensively considered, and the coupling influence relationship between elements is used as the edge to construct a fault decoupling multi-level network model. Among them, the state monitoring variable can represent the fault form and system structure, and the composite fault analysis model is constructed based on the fault form, fault mechanism and system structure. The system monitoring situation and the characteristics of the state monitoring variables correspond to the parameters in the wind power equipment fault form, fault mechanism and system structure, such as the state detection variable of the gearbox system is the high-speed shaft drive end bearing temperature.

[0062] In one example, taking the gearbox system, one of the subsystems of the wind power equipment system, as an example, based on the collected data of the wind power equipment gearbox system, the fault propagation model of the gearbox system is roughly divided into four layers: system layer, subsystem layer, component layer and part layer. Figure 2 As shown in the figure, the central node is a virtual node, which represents the overall indicator of the fault coupling effect of the offshore wind turbine, which can be the reliability or performance status of the system; the second-level node represents the gearbox system-level fault, and the node has physical entity attributes and fault attributes; the third-level node represents the component-level fault mode. The connection between the nodes in this layer represents the mutual influence relationship between the fault modes, such as the failure or damage of the box 11 may cause the failure of the gear transmission system 12; the fourth-level node represents the potential failure cause of the equipment, and the connection between the nodes in this layer represents the correlation between the failure causes, where the direction of the arrow indicates the tracing path of the failure cause, such as the damage of the shaft and bearing of the gear transmission system 48 may be caused by the fracture of the box connection bolt 46; in addition, according to the constructed multi-level fault decoupling model of offshore wind turbines, it can be seen that there are multiple tracing paths that cause the failure of the system, such as 0→2→11→46 or 0→2→12→47 are all fault tracing paths. The same fault may also cause system abnormality through multiple transmission paths. For example, the failure of gears and ring gears can have different impacts on the system through the transmission paths of 0→2→12→47 or 0→2→11→46→47.

[0063] Step S3, traversing the central nodes and bottom nodes of the fault decoupling multi-level network model in sequence according to the depth-first search algorithm to obtain a set of fault propagation paths of the fault decoupling multi-level network model.

[0064] In this step, the adjacency matrix of the fault decoupling multi-level network model is calculated, and all propagation paths of the fault decoupling multi-level network model in the fault propagation process are obtained according to the depth-first search algorithm and the adjacency matrix, and all propagation paths that meet the preset path conditions are integrated into a fault propagation path set.

[0065] In this embodiment, it is necessary to improve the path search algorithm according to the characteristics of the propagation path of the fault decoupled multi-level network model, and traverse all possible fault propagation paths based on the central node and all underlying nodes (component layers). The main idea is to use the depth-first search idea to find all possible propagation paths in the network. Among them, the depth-first search algorithm needs to pay attention to the need to change all edges connected to the starting point to start from the starting point and cannot return to the directed edge, so as to avoid passing the starting point multiple times; adopt a recursive algorithm of deep search, and define the global stack to record the search path; make judgments during the search to avoid jumping back and forth between two nodes; select all underlying nodes as the end points of the path for traversal.

[0066] Get all the propagation paths in the fault propagation process. All paths meet the following conditions: Figure 3 The requirements for propagation paths in the fault tracing model are as follows. When the model is built, the path set is fixed. It will only change when new nodes or connections need to be added or nodes and related connections need to be deleted in the model. Through path traversal, the problem of the end point of tracing is solved and unreasonable paths are removed.

[0067] Step S4, based on the reliability characteristics and topological characteristics of all nodes and edges between nodes in the fault decoupling multi-level network model, obtain the node propagation strength and edge propagation strength, and calculate the propagation strength of each propagation path in the fault propagation path set according to the path propagation strength function, node propagation strength and edge propagation strength.

[0068] In this embodiment, the calculation is as follows Figure 4 The node out-degree shown as the reliability feature, topological feature and node propagation strength of the node can be expressed as:

[0069]

[0070] Where I represents the cumulative distribution function, represents the probability density distribution, S i represents the topological characteristics of node i, d i represents the out-degree of node i, d jrepresents the out-degree of node j, n represents the total number of nodes in the fault decoupling multi-level network model, u i represents the propagation strength of node i, h i represents the reliability characteristics of node i, S i Represents the topological characteristics of node i.

[0071] The expression of edge propagation strength is:

[0072]

[0073] Among them, S ij represents the topological features of the edge between node i and node j, b ij represents the number of edges between nodes i and j, w ij represents the propagation strength of the edge between node i and node j, P ij is the reliability feature of the edge between node i and node j, W ij represents the propagation strength of the edge between node i and node j in the layer, represents the failure frequency of lower-layer node j caused by upper-layer node i, Represents the failure frequency of lower-level node i.

[0074] The expression of the path propagation strength function is:

[0075] p(l ij ) be =W ij

[0076]

[0077] p(l ij )=Πp(l ij ) in ×Πp(l ij ) be

[0078] Among them, p(l ij ) be represents the inter-layer path propagation strength, W ij represents the inter-layer edge propagation strength between node i and node j, u i represents the propagation strength of node i in the path within the layer, l ij represents the propagation characteristics between node i and node j in the intra-layer path, n represents the total number of nodes in the fault decoupling multi-level network model, p(l ij ) in represents the intra-layer path propagation strength, p(l ij ) represents the path propagation strength.

[0079] According to the definition of the fault decoupled multi-layer network model, the model has different intra-layer and inter-layer connection relationships. Based on this feature, the path fault propagation strength is calculated separately for this feature. When calculating the intra-layer propagation strength, it is equivalent to treating the propagation path of each layer node as a node. Then each path is composed of nodes representing the propagation within each layer and inter-layer edges, so that each path has the same number of nodes and edges. Therefore, this calculation method eliminates the influence of path length on path propagation strength.

[0080] Step S5, based on the node influence value corresponding to the wind power equipment status monitoring variable and the path node attribute update function, the path node attribute update value is calculated, and the path index of each propagation path is obtained according to the path node attribute update value and the path index function.

[0081] In this step, the node influence value of each node in the fault decoupling multi-level network model is calculated according to the wind power equipment status monitoring variables and the node influence relationship table; based on the node influence value and the path node attribute update function, the path node attribute update value corresponding to the node influence value is calculated; based on the path node attribute update value and the path update function, the path update value corresponding to the path node attribute update value is obtained; based on the path update value and the path indicator function, the path indicator corresponding to the path node attribute update value is obtained.

[0082] The expression of the path indicator function is:

[0083]

[0084] RI=p(l ij )×Rs

[0085] Among them, P update Indicates the updated value of the path node attribute of the propagation path root based on the wind power equipment status monitoring variable. represents the node impact value affected by the wind power equipment status monitoring variable on the propagation path root, s represents the number of nodes affected by the wind power equipment status monitoring variable on the propagation path root, Rs represents the path attribute update value of the propagation path root, m represents the number of path node attribute update values ​​under different fault location conditions, It represents the impact value of wind power equipment fault type on wind power equipment status monitoring variables, and RI represents the path index.

[0086] Step S6: Select a propagation path that meets a preset accuracy and a preset confidence in the fault propagation path set as the fault propagation path, and sort the fault propagation paths according to a preset path indicator sequence to determine the fault source.

[0087] In this step, the accuracy and confidence requirements for the fault propagation path are determined according to the actual needs and application scenarios of fault diagnosis. Generally speaking, higher accuracy and confidence will be more conducive to finding the real fault source, but it may also filter out potential valuable information. It is necessary to find a balance between these two indicators and determine reasonable preset values. According to the path propagation strength function, node propagation strength and edge propagation strength, the propagation strength of each fault propagation path is calculated. Combined with the path node attribute update value and the path indicator function, the accuracy and confidence indicators of each propagation path are obtained. All the calculated propagation paths are sorted according to the accuracy and confidence indicators, and the propagation paths that meet the preset accuracy and preset confidence requirements are selected as the fault propagation path set. If no path meets both preset indicators, the requirements can be appropriately relaxed and the higher path can be selected. According to the preset path indicator function, the selected fault propagation paths are sorted. Common path indicators include propagation strength, fault propagation time, fault propagation cost, etc. According to the sorted fault propagation path set, the top-ranked path is selected as the most likely fault propagation path. By tracing back along the path, the root cause of the fault can be determined. If there are multiple similar propagation paths, the characteristics of each path can be comprehensively considered to obtain a more reliable fault source judgment.

[0088] In this embodiment, the higher the path index is, the greater the possibility that the path is a fault propagation path. Since component abnormality may be caused by its own degradation or input abnormality, there are two situations for fault location:

[0089] The bottom node on the path is the fault source, and the calculation formula is:

[0090]

[0091] Among them, n root is the fault source, l is the fault propagation path, is the bottom node, i=1,2;

[0092] The path has a bottom-level node connected to the fault source, which causes a problem with the bottom-level node input. The node itself has no fault. The calculation formula is:

[0093]

[0094] Among them, n root is the fault source, l is the fault propagation path, is the bottom node at the end of the path; through investigation, it is determined that Figure 5 The final fault source of the wind power equipment fault decoupling multi-level network model is shown.

[0095] In this step, if the bottom node of the fault propagation path corresponding to the maximum path indicator shows a propagation state, the fault is a sequential fault; if there are two or more fault propagation paths corresponding to the maximum path indicator, the fault is a concurrent fault; if there are two or more fault propagation paths corresponding to the maximum path indicator, and the high-level node propagation paths of the fault propagation paths are the same, the fault is a high-order fault.

[0096] It can be understood that for complex faults, there are the following three situations in the fault location process: when in the path selection index calculation result, the maximum path index result exists in the path and its underlying nodes propagate, it is considered that a sequential fault has occurred; when in the path selection index calculation result, there are two or more paths in the path of the same magnitude as the maximum path index result, it is considered that a concurrent fault has occurred with the underlying nodes of the path as faults; when in the path selection index calculation result, there are two or more paths in the path of the same magnitude as the maximum path index result, and their high-level node propagation paths are the same, it is considered that a high-order fault has occurred.

[0097] By systematically collecting the status monitoring variables, fault types, functional structures and coupling relationships of wind power equipment, a comprehensive understanding of the comprehensive status of wind power equipment can be formed, which helps to improve the accuracy and timeliness of fault analysis. The fault decoupling multi-level network model can clearly display each node and their relationships, improve the visualization of the fault propagation path, facilitate tracing the source of the fault, reduce the complexity of fault analysis, and thus improve the accuracy of fault source location. At the same time, the fault propagation paths are sorted based on the path indicator function, which can more intuitively determine which fault propagation paths are more influential, thereby significantly improving the efficiency and accuracy of fault diagnosis.

[0098] Based on the above method, the embodiment of the present application discloses a wind power equipment fault tracing system based on a fault decoupling multi-level model, referring to Figure 6 The wind power equipment fault tracing system 1 includes an information collection module 11, a path calculation module 12, an index calculation module 13 and a fault location module 14, wherein:

[0099] The information collection module 11 is used to collect wind power equipment fault analysis information, wherein the wind power equipment fault analysis information includes wind power equipment state monitoring variables, wind power equipment fault types, wind power equipment functional structures and wind power equipment fault coupling relationships;

[0100] The path operation module 12 is used to construct a fault decoupling multi-level network model based on wind power equipment status monitoring variables, wind power equipment fault types, wind power equipment functional structures, and wind power equipment fault coupling relationships, and sequentially traverse the central nodes and bottom nodes of the fault decoupling multi-level network model according to a depth-first search algorithm to obtain a fault propagation path set of the fault decoupling multi-level network model;

[0101] The index calculation module 13 is used to obtain the node propagation strength and the edge propagation strength based on the reliability characteristics and topological characteristics of all nodes and the edges between nodes in the fault decoupling multi-level network model, and calculate the propagation strength of each propagation path in the fault propagation path set according to the path propagation strength function, the node propagation strength and the edge propagation strength, calculate the path node attribute update value based on the node influence value corresponding to the wind power equipment status monitoring variable and the path node attribute update function, and obtain the path index of each propagation path according to the path node attribute update value and the path index function;

[0102] The fault location module 14 is used to select a propagation path that meets a preset accuracy and a preset confidence in the fault propagation path set as the fault propagation path, and sort the fault propagation paths according to a preset path indicator sequence to determine the fault source.

[0103] In one example, the path operation module 12 is used to calculate the adjacency matrix of the fault decoupling multi-level network model, and obtain all propagation paths of the fault decoupling multi-level network model during the fault propagation process according to the depth-first search algorithm and the adjacency matrix, and integrate all propagation paths that meet the preset path conditions into a fault propagation path set.

[0104] In one example, the expression for node propagation strength is:

[0105]

[0106]

[0107] Where I represents the cumulative distribution function, represents the probability density distribution, S i represents the topological characteristics of node i, d i represents the out-degree of node i, d j represents the out-degree of node j, n represents the total number of nodes in the fault decoupling multi-level network model, u i represents the propagation strength of node i, h i represents the reliability characteristics of node i, S i Represents the topological characteristics of node i.

[0108] In one example, the expression for edge propagation strength is:

[0109]

[0110] Among them, S ij represents the topological features of the edge between node i and node j, b ij represents the number of edges between nodes i and j, w ijrepresents the propagation strength of the edge between node i and node j, P ij is the reliability feature of the edge between node i and node j, W ij represents the propagation strength of the edge between node i and node j in the layer, represents the failure frequency of lower-layer node j caused by upper-layer node i, Represents the failure frequency of lower-level node i.

[0111] In one example, the indicator calculation module 13 is used to calculate the node influence value of each node in the fault decoupling multi-level network model based on the wind power equipment status monitoring variables and the node influence relationship table; based on the node influence value and the path node attribute update function, calculate the path node attribute update value corresponding to the node influence value; based on the path node attribute update value and the path update function, obtain the path update value corresponding to the path node attribute update value; based on the path update value and the path indicator function, obtain the path indicator corresponding to the path node attribute update value.

[0112] In one example, the expression of the path propagation strength function is:

[0113] p(l ij ) be =W ij

[0114]

[0115] p(l ij )=Πp(l ij ) in ×Πp(l ij ) be

[0116] Among them, p(l ij ) be represents the inter-layer path propagation strength, W ij represents the inter-layer edge propagation strength between node i and node j, u i represents the propagation strength of node i in the path within the layer, l ij represents the propagation characteristics between node i and node j in the intra-layer path, n represents the total number of nodes in the fault decoupling multi-level network model, p(l ij ) in represents the intra-layer path propagation strength, p(l ij ) represents the path propagation strength.

[0117] In an example, the expression of the path indicator function is:

[0118]

[0119] RI=p(lij )×Rs

[0120] Among them, P update Indicates the updated value of the path node attribute of the propagation path root based on the wind power equipment status monitoring variable. represents the node impact value affected by the wind power equipment status monitoring variable on the propagation path root, s represents the number of nodes affected by the wind power equipment status monitoring variable on the propagation path root, Rs represents the path attribute update value of the propagation path root, m represents the number of path node attribute update values ​​under different fault location conditions, It represents the impact value of wind power equipment fault type on wind power equipment status monitoring variables, and RI represents the path index.

[0121] In one example, the method further includes:

[0122] If the bottom node of the fault propagation path corresponding to the maximum path index shows a propagation state, the fault is a sequential fault;

[0123] If there are two or more fault propagation paths corresponding to the maximum path index, the fault is a concurrent fault;

[0124] If there are two or more fault propagation paths corresponding to the maximum path index, and the high-level node propagation paths of the fault propagation paths are the same, the fault is a high-order fault.

[0125] See also Figure 7 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 7 As shown, the electronic device 2 may include: at least one processor 21 , at least one network interface 24 , a user interface 23 , a memory 25 , and at least one communication bus 22 .

[0126] The communication bus 22 is used to realize the connection and communication between these components.

[0127] The user interface 23 may include a display screen (Display) and a camera (Camera), and the optional user interface 23 may also include a standard wired interface and a wireless interface.

[0128] The network interface 24 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0129] Among them, the processor 21 may include one or more processing cores. The processor 21 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 25, and calling data stored in the memory 25. Optionally, the processor 21 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 21 can integrate one or more combinations of a central processing unit (Central Processing Unit, CPU), a graphics processor (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 21, and it can be implemented separately through a chip.

[0130] Among them, the memory 25 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 25 includes a non-transitory computer-readable storage medium. The memory 25 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 25 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 25 may also be optionally at least one storage device located away from the aforementioned processor 21. As Figure 7 As shown, the memory 25 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program of a wind power equipment fault tracing method based on a fault decoupling multi-level model.

[0131] exist Figure 7In the electronic device 2 shown, the user interface 23 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 21 can be used to call an application program stored in the memory 25 for a wind power equipment fault tracing method based on a fault decoupling multi-level model. When executed by one or more processors, the electronic device executes one or more methods in the above-mentioned embodiments.

[0132] A computer-readable storage medium stores instructions, which, when executed by one or more processors, enable the computer to execute one or more methods in the above-mentioned embodiments.

[0133] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0134] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0135] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0136] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0137] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0138] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0139] The above are only exemplary embodiments of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and practice, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any variation, use or adaptive change of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary techniques in the technical field that are not recorded in the present disclosure.

[0140] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A wind power equipment fault tracing method based on a fault decoupling multi-level model, characterized in that: The method comprises: Collecting wind power equipment fault analysis information, wherein the wind power equipment fault analysis information includes wind power equipment state monitoring variables, wind power equipment fault types, wind power equipment functional structures, and wind power equipment fault coupling relationships; Based on the wind power equipment status monitoring variables, the wind power equipment fault type, the wind power equipment functional structure and the wind power equipment fault coupling relationship, a fault decoupling multi-level network model is constructed; According to a depth-first search algorithm, the central nodes and bottom-level nodes of the fault decoupling multi-level network model are sequentially traversed to obtain a set of fault propagation paths of the fault decoupling multi-level network model; Based on the reliability characteristics and topological characteristics of all nodes and edges between nodes in the fault decoupling multi-level network model, the node propagation strength and the edge propagation strength are obtained, and the propagation strength of each propagation path in the fault propagation path set is calculated according to the path propagation strength function, the node propagation strength and the edge propagation strength; Based on the node influence value corresponding to the wind power equipment status monitoring variable and the path node attribute update function, the path node attribute update value is calculated, and according to the path node attribute update value and the path indicator function, the path indicator of each propagation path is obtained; A propagation path in the fault propagation path set that meets a preset accuracy and a preset confidence is selected as the fault propagation path, and the fault propagation paths are sorted according to a preset path indicator sequence to determine the fault source.

2. The method according to claim 1, characterized in that The acquiring of the fault propagation path set of the fault decoupling multi-level network model specifically includes: The adjacency matrix of the fault decoupling multi-level network model is calculated, and all propagation paths of the fault decoupling multi-level network model during the fault propagation process are obtained according to the depth-first search algorithm and the adjacency matrix, and all propagation paths that meet the preset path conditions are integrated into a fault propagation path set.

3. The method according to claim 1, characterized in that The expression of the node propagation strength is: Where I represents the cumulative distribution function, represents the probability density distribution, S i represents the topological characteristics of node i, d i represents the out-degree of node i, d j represents the out-degree of node j, n represents the total number of nodes in the fault decoupling multi-level network model, u i represents the propagation strength of node i, h i represents the reliability characteristics of node i, S i Represents the topological characteristics of node i.

4. The method according to claim 1, characterized in that The expression of the edge propagation strength is: Among them, S ij represents the topological features of the edge between node i and node j, b ij represents the number of edges between nodes i and j, w ij represents the propagation strength of the edge between node i and node j, P ij is the reliability feature of the edge between node i and node j, W ij represents the propagation strength of the edge between node i and node j in the layer, It represents the frequency of failure of lower-level nodes caused by upper-level node i. Represents the failure frequency of lower-level node i.

5. The method according to claim 1, characterized in that The obtaining of the path index of each propagation path specifically includes: Calculating the node impact value of each node in the fault decoupling multi-level network model according to the wind power equipment status monitoring variables and the node impact relationship table; Based on the node influence value and the path node attribute update function, calculating the path node attribute update value corresponding to the node influence value; Based on the path node attribute update value and the path update function, obtaining a path update value corresponding to the path node attribute update value; Based on the path update value and the path indicator function, a path indicator corresponding to the path node attribute update value is obtained.

6. The method according to claim 1, characterized in that The expression of the path propagation intensity function is: p(l ij ) be =W ij p(l ij )=∏p(l ij ) in ×∏p(l ij ) be Among them, p(l ij ) be represents the inter-layer path propagation strength, W ij represents the inter-layer edge propagation strength between node i and node j, u i represents the propagation strength of node i in the path within the layer, l ij represents the propagation characteristics between node i and node j in the intra-layer path, n represents the total number of nodes in the fault decoupling multi-level network model, p(l ij ) in represents the intra-layer path propagation strength, p(l ij ) represents the path propagation strength.

7. The method according to claim 6, characterized in that Method, the expression of the path indicator function is: RI=p(l ij )×Rs Among them, P update represents the path node attribute update value of the propagation path root based on the wind power equipment status monitoring variable, represents the node impact value on the propagation path root affected by the wind power equipment status monitoring variable, s represents the number of nodes on the propagation path root affected by the wind power equipment status monitoring variable, Rs represents the path attribute update value of the propagation path root, m represents the number of path node attribute update values ​​under different fault location conditions, It represents the impact value of the wind power equipment fault type on the wind power equipment state monitoring variable, and RI represents the path index.

8. The method according to claim 1, characterized in that The method further comprises: If the bottom node of the fault propagation path corresponding to the maximum path index shows a propagation state, the fault is a sequential fault; If there are two or more fault propagation paths corresponding to the maximum path index, the fault is a concurrent fault; If there are two or more fault propagation paths corresponding to the maximum path index, and the high-level node propagation paths of the fault propagation paths are the same, the fault is a high-order fault.

9. A wind power equipment fault tracing system based on a fault decoupling multi-level model, characterized in that: The wind power equipment fault tracing system (1) comprises an information collection module (11), a path calculation module (12), an index calculation module (13) and a fault location module (14), wherein: The information collection module (11) is used to collect wind power equipment fault analysis information, wherein the wind power equipment fault analysis information includes wind power equipment state monitoring variables, wind power equipment fault types, wind power equipment functional structures and wind power equipment fault coupling relationships; The path operation module (12) is used to construct a fault decoupling multi-level network model based on the wind power equipment state monitoring variables, the wind power equipment fault type, the wind power equipment functional structure and the wind power equipment fault coupling relationship, and sequentially traverse the central node and the bottom node of the fault decoupling multi-level network model according to the depth-first search algorithm to obtain the fault propagation path set of the fault decoupling multi-level network model; The index calculation module (13) is used to obtain the node propagation strength and the edge propagation strength based on the reliability characteristics and topological characteristics of all nodes and the edges between nodes in the fault decoupling multi-level network model, and calculate the propagation strength of each propagation path in the fault propagation path set according to the path propagation strength function, the node propagation strength and the edge propagation strength, calculate the path node attribute update value based on the node influence value corresponding to the wind power equipment status monitoring variable and the path node attribute update function, and obtain the path index of each propagation path according to the path node attribute update value and the path index function; The fault location module (14) is used to select a propagation path that meets a preset accuracy and a preset confidence level from the fault propagation path set as a fault propagation path, and to sort the fault propagation paths according to a preset path indicator sequence to determine the fault source.

10. An electronic device, characterized in that: The electronic device (2) comprises a processor (21), a memory (25), a user interface (23) and a network interface (24), wherein the memory (25) is used to store instructions, the user interface (23) and the network interface (24) are used to communicate with other devices, and the processor (21) is used to execute the instructions stored in the memory (25) so that the electronic device (2) executes the method according to any one of claims 1 to 8.

Images