A method and device for analyzing faults of power supply and maintenance equipment

Abstract

The application provides a method and device for analyzing faults of industrial power supply maintenance equipment. The method provided by the application comprises the following steps: determining historical faults of the industrial power supply maintenance equipment; screening root nodes of fault trees from the historical faults; determining associated components and external conditions of faults for each root node of the fault trees; taking each associated object in the associated components and the external conditions as a fault tree child node under the root node for each root node of the fault trees, and constructing a fault tree of the industrial power supply maintenance equipment, wherein a state of the associated object is taken as a state value of the fault tree child node; calculating an importance weight of each part according to a working principle of the industrial power supply maintenance equipment; calculating a fault probability of each root node of the fault tree based on the importance weight, and predicting a fault occurrence situation of the industrial power supply maintenance equipment. The method realizes comprehensive construction of the fault tree and accurate prediction of the fault occurrence.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of fault analysis, in particular to a fault analysis method and device for work-electricity-supply maintenance equipment. BACKGROUND

[0002] Large track maintenance machines (such as tamping cars, screen cleaning cars, etc.) are the core equipment for railway line maintenance, and their running state directly affects the safety of railway transportation. The current traditional operation and maintenance mode has the following problems:

[0003] Inefficient equipment management: relying on paper records and manual records, equipment historical data is scattered and difficult to manage uniformly.

[0004] Fault diagnosis method lags behind: lacking real-time monitoring means, fault discovery relies on manual inspection, which may delay the repair opportunity.

[0005] Insufficient fault prediction accuracy: the prediction of faults is mainly based on human experience, and the data sources for prediction are short-term and from the same equipment. The prediction is based on the overall device and estimates the macro work situation.

[0006] However, the fault of work-electricity-supply maintenance equipment is a part with high complexity and serious coupling of component faults. There is a lack of high-precision means for predicting the fault in the prior art, and it is difficult to achieve scientific and targeted maintenance. SUMMARY

[0007] The first aspect of the present application provides a fault analysis method for work-electricity-supply maintenance equipment, the method comprising:

[0008] determining the historical faults of the work-electricity-supply maintenance equipment;

[0009] selecting root nodes of fault trees from the historical faults, wherein the historical faults corresponding to each root node are independent of each other;

[0010] for each root node of the fault tree, determining the associated components and external conditions of the fault, wherein the associated components are components of the work-electricity-supply maintenance equipment, and the external conditions are external conditions for the work of the work-electricity-supply maintenance equipment;

[0011] for each root node of the fault tree, taking each associated object in the associated components and external conditions as a fault tree child node under the root node, constructing a fault tree of the work-electricity-supply maintenance equipment, and taking the state of the associated object as a state value of the fault tree child node;

[0012] calculating the importance weight of each part according to the working principle of the work-electricity-supply maintenance equipment, wherein the associated components are composed of multiple parts;

[0013] Calculate the failure probability of each root node of the fault tree based on the importance weight, and predict the failure occurrence situation of the industrial power supply maintenance equipment.

[0014] The second aspect of the application provides an industrial power supply maintenance equipment failure analysis device, the device comprises:

[0015] The extraction module is configured to determine the historical failures of the industrial power supply maintenance equipment.

[0016] The screening module is configured to screen the root nodes of the fault tree from the historical failures, wherein the historical failures corresponding to each root node are independent of each other.

[0017] The search module is configured to determine the associated components and external conditions of the failure for each root node of the fault tree, wherein the associated components are components of the industrial power supply maintenance equipment, and the external conditions are external conditions for the operation of the industrial power supply maintenance equipment.

[0018] The construction module is configured to, for each root node of the fault tree, take each associated object in the associated components and external conditions as a fault tree child node under the root node, and construct a fault tree of the industrial power supply maintenance equipment, wherein the state of the associated object is taken as a state value of the fault tree child node.

[0019] The evaluation module is configured to calculate the importance weight of each part according to the working principle of the industrial power supply maintenance equipment, wherein the associated components are composed of a plurality of parts.

[0020] The prediction module is configured to calculate the failure probability of each root node of the fault tree based on the importance weight, and predict the failure occurrence situation of the industrial power supply maintenance equipment.

[0021] The industrial power supply maintenance equipment failure analysis method and device provided by the application decouples the failure of the complex and highly coupled industrial power supply maintenance equipment based on the fault tree which integrates fault phenomena and fault causes, establishes a systematic fault occurrence cause analysis, directly locates the fault from the macroscopic fault to the fault of the bottommost part, and then narrows down the focus of the fault to the component itself. In the calculation of the probability, the probability of the top-level failure occurrence can be deduced through the bottom-level probability, and the accurate prediction of the failure is realized. At the same time, when constructing the fault tree, the extension of the two dimensions of the time and the device type of the fault data source expands the source of the fault data, and thus the accuracy of the failure location and prediction is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1 The flowchart of the industrial power supply maintenance equipment failure analysis method provided by the first embodiment of the application;

[0023] Figure 2 The fault tree established by the method provided by the first embodiment of the application is shown.

[0024] Figure 3 A structural schematic diagram of a fault analysis device of a work-electricity-supply maintenance equipment provided in Embodiment Two of the present application is provided. DETAILED DESCRIPTION

[0025] The exemplary embodiments will be described in detail herein with reference to the attached drawings. In the following description, unless otherwise indicated, like numbers in the attached drawings refer to the same or similar elements. The following exemplary embodiments described in the following description are not meant to be limiting of the present application.

[0026] The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used in the present application, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0027] It is to be understood that the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. It is to be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0028] The following specific embodiments are given to introduce the technical solutions of the present application in detail.

[0029] Figure 1 A flow chart of a fault analysis method of a work-electricity-supply maintenance equipment provided in Embodiment One of the present application is provided. Please refer to Figure 1 The method provided in the present embodiment can include:

[0030] S1: determining a historical fault of the work-electricity-supply maintenance equipment.

[0031] For large road maintenance machines, a large number of components are included, and fault diagnosis thereof is a comprehensive problem involving multiple disciplines and coupled analysis of multiple components. The life cycle assessment thereof is also computationally intensive and information is complex. The work-electricity-supply maintenance equipment referred to in the present application generally refers to large road maintenance machines, such as tamping vehicles, etc. The historical fault is a fault of the same function equipment occurring in the use process. Taking a tamping vehicle as an example, there are many models and products of different enterprises, but as long as the function is tamping ballast, the core components used and the damage mechanism to the components are consistent.

[0032] Therefore, as an optional embodiment, the determining the historical faults of the power supply and repair equipment comprises: determining a work content of the power supply and repair equipment to be analyzed; determining a reference equipment with the same work content; extracting initial historical faults of the reference equipment and the power supply and repair equipment to be analyzed in processing the work content; and sorting the initial historical faults, screening partial initial historical faults, and obtaining the historical faults. Specifically, the work content is a road maintenance work completed by the power supply and repair equipment to be analyzed, such as a tamping vehicle, and the reference equipment comprises machines of the same type, such as tamping vehicles of different models and produced by different enterprises, and also comprises machines of other types, as long as they can complete the same work content in the same way. Compared with the prior art of only obtaining historical data in a period of time, the method provided by the application expands the source of historical fault data from two dimensions of time and equipment type, and improves the comprehensiveness and reliability of fault data. From the time dimension, as long as the work content is the same in a period of time, the historical fault information thereof is extracted; from the equipment type dimension, as long as the device uses the same principle to complete the same function, the historical fault information thereof is extracted. Further, the sorting of the initial historical faults, the screening of partial initial historical faults, and the obtaining of the historical faults comprise: calculating a comprehensive evaluation value of each initial historical fault according to a frequency of occurrence of the initial historical fault and a severity level of a fault consequence, the comprehensive evaluation value being used to evaluate an influence degree of the initial historical fault on the device to complete the work content after the fault occurs. Each initial historical fault is sorted based on the comprehensive evaluation value, and N initial historical faults with a high ranking are selected as the historical faults, N being a positive integer, and the value of N being related to the work content.

[0033] S2: selecting root nodes of a fault tree from the historical faults, wherein the historical faults corresponding to each root node are independent of each other.

[0034] The historical faults include original faults and secondary faults, the original faults refer to faults independently generated by the work and power supply maintenance equipment in the process of completing the work content, and are not affected by other faults, and the secondary faults refer to associated faults affected by the original faults. The root node corresponds to the original fault in the historical fault, the identifier of the root node is a fault name, for example, insufficient power, too high temperature, etc., and the value of the root node is a content corresponding to the fault, for example, the actual power value is A, and the standard power is B; for example, the actual temperature value is A, and the temperature safety value is B. Specifically, the root node of the fault tree is selected from the historical faults, including: taking each fault as a graph node, calculating the association relationship between each graph node, and constructing a fault graph; and selecting an independent graph node corresponding to the original fault from the fault graph, and taking the fault corresponding to the independent graph node as the root node. First, each fault is taken as a graph node, the fault description content is semantically segmented to obtain a fault-associated component name and a fault content; the component names corresponding to each graph node are compared to determine a graph node pair with overlapping components, the component overlap includes complete overlap and partial overlap, for each graph node pair, the fault association degree is calculated according to the semantic similarity of the fault content corresponding to the component overlap, and the fault association degree is taken as the value of the edge to connect the two graph nodes in the graph node pair, for example, for two faults A and B, A includes fault components (a, b, c), and B includes fault components (c, d, e), at this time, there is component overlap between A and B, forming a graph node pair <A, B>, the overlapping component c in the graph node pair is calculated, and the semantic similarity of the fault content corresponding to the component c is calculated, for example, the fault content of the component c corresponding to the fault A is temperature too high, and the fault content of the component c corresponding to the fault B is too low speed, at this time, the semantic similarity is 0, and therefore, the fault association degree between the faults A and B is 0.

[0035] Further, as an optional embodiment, the historical faults at least further include concurrent faults, the concurrent faults refer to faults that are completely same as the components and fault contents of any target fault in the independent fault or the secondary fault and occur at the same time as the any target fault. The concurrent faults and the target faults are same in generation conditions and time, and therefore, in the fault tree, the concurrent faults and the target faults share a node position.

[0036] S3: For each fault tree root node, determine the associated components and external conditions of the fault, wherein the associated components are components of the work and power supply maintenance equipment, and the external conditions are external conditions of work of the work and power supply maintenance equipment.

[0037] The first layer of the fault tree is the type and content of the fault. In the layers below the first layer, the content of the fault tree is the location and / or condition of the fault. Specifically, the associated component refers to the component of the work and power supply maintenance equipment itself. The component is composed of parts, which is an integral module capable of achieving an independent function. The part is the smallest hardware unit of the work and power supply maintenance equipment, such as a screw or a nut. The external condition is the condition of the working environment of the work and power supply maintenance equipment, such as the temperature of the working space. It can also include the work content, that is, the external condition is other conditions that affect the performance of the work and power supply maintenance equipment, which are not internal structures of the work and power supply maintenance equipment.

[0038] As an optional embodiment, for each root node of the fault tree, determining the associated component and the external condition of the fault comprises: establishing a model of the work and power supply maintenance equipment, dividing the component unit of the model of the work and power supply maintenance equipment according to the work content, and the component unit divided for different work contents is different for the same work and power supply maintenance equipment; determining the fault part corresponding to the root node for each root node of the fault tree, the fault part being one or more; locating the associated component based on the fault part, wherein one fault part can correspond to one or more fault components, for example, a part (air conditioner) fails, at this time, the fault component includes not only the fan cooling component for cooling, but also the circulating component for promoting internal air flow; determining the candidate external condition based on the work content, and determining the external condition from the candidate external condition based on the fault part corresponding to the root node, wherein the external condition is the candidate external condition that affects the working state of the fault part.

[0039] S4: For each root node of the fault tree, each associated object in the associated component and the external condition is taken as a fault tree sub-node under the root node, and a fault tree of the work and power supply maintenance equipment is constructed, and the state of the associated object is taken as the state value of the fault tree sub-node.

[0040] The failure is a phenomenon, and the associated object is the cause corresponding to the failure. For example, the associated component is a diesel exhaust pipe, and the fault content is poor exhaust. Then the associated object can include multiple objects of the exhaust pipe, as shown in Table 1-9. The multiple objects can include the shape of the exhaust pipe, the muffler of the exhaust pipe, the exhaust passage of the exhaust pipe, etc. Different objects have different fault contents, and different object faults can all cause the associated step to fail.

[0041] Table 1 Diesel Engine Failure

[0042]

[0043] Table 2 Diesel Engine Power Insufficient Reason Analysis

[0044]

[0045] Table 1 Diesel engine speed instability cause analysis

[0046]

[0047] Table 2 Diesel engine oil temperature too high cause analysis

[0048]

[0049] Table 3 Diesel engine water temperature too high cause analysis

[0050]

[0051]

[0052] Table 4 Diesel engine exhaust gas temperature too high cause analysis

[0053]

[0054] Table 5 Diesel engine oil pressure too low cause analysis

[0055]

[0056] Table 6 Diesel engine intake and exhaust pressure abnormality cause analysis

[0057]

[0058] Table 7 Diesel engine cylinder pressure too low cause analysis

[0059]

[0060] Specifically, in the fault tree of the industrial power supply maintenance equipment, the first layer node is the name of the fault, from the first layer node downwards, the nodes of other layers are associated objects related to the fault, and the value of the node is the fault description content of the associated object. The fault tree of the industrial power supply maintenance equipment is constructed, including: establishing each target node of each layer from top to bottom and from left to right, for a target node K(i,j) to be established, wherein i is the ith layer and j is the jth node, determining the associated object corresponding to the target node to be established according to the upper layer node of the target node to be established, determining the fault content of the target node to be established according to the fault content of the upper layer node, and completing the construction of the target node to be established. The associated object is an object whose influence degree on the fault content of the upper layer node is greater than a threshold value, and the associated object is multiple. In principle, if the target node to be established is a root node, that is, the upper layer node is a component, the fault content corresponding to the component is obtained, various possible situations for generating the fault content of the component are analyzed, and the object whose influence degree is greater than the threshold value is determined from the possible situations. If the upper layer node is a first object, the fault content corresponding to the first object is obtained, various possible situations for generating the fault of the first object are analyzed, and the object whose influence degree is greater than the threshold value is determined from the possible situations, as a child node of the first object. The fault tree established by Table 1-9 is shown in Figure 2

[0061] The part is the smallest hardware unit of the industrial power supply maintenance equipment, the component is a complete part unit that constitutes a complete function of the industrial power supply maintenance equipment, and the object is a component part of the component, and the description granularity is greater than or equal to the part and less than the component. For example, the part is a pipe, a cover, etc., the component is an exhaust pipe, and the object is an exhaust pipe, an exhaust silencer, etc.

[0062] S5: According to the working principle of the industrial power supply maintenance equipment, the importance weight of each part is calculated, and the associated component is composed of multiple parts.

[0063] ​Specifically, the working principle is a working principle for completing the work content, and the importance weight of each part is calculated according to the working principle of the power supply and repair equipment, including: determining the working principle of the power supply and repair equipment according to the work content; determining the participation degree of each part in the power supply and repair equipment when the power supply and repair equipment completes the work content according to the working principle; determining the contribution degree of each part to the structural stability according to the structural characteristics of the power supply and repair equipment; and obtaining the importance weight of each part by comprehensively considering the participation degree and the contribution degree. Different working principles correspond to different working contents, and different parts of the power supply and repair equipment participate in different working contents. Specifically, the participation degree is determined by the ratio of the time length of the part participating in the work content to the total time length of the power supply and repair equipment completing the work content; the contribution degree is determined by the percentage of the power supply and repair equipment failure after the part failure, and the sum of the two is the importance weight of the part.

[0064] S6: calculating the failure probability of each root node of the fault tree based on the importance weight, and predicting the failure occurrence situation of the power supply and repair equipment.

[0065] The part can constitute an object or a component, and the nodes in the fault tree are components in the first layer and objects in other layers. Therefore, the weight value of each node can be calculated when the weight of the part (i.e., the bottom layer) node is known. As an optional embodiment, the calculation of the failure probability of each root node of the fault tree based on the importance weight includes: calculating the node importance weight of each node in the fault tree based on the importance weight of the part, which represents the contribution degree of the node to the failure represented by the corresponding root node; determining the minimum cut set of the top layer node corresponding to the failure occurrence from the bottom layer node upwards; calculating the failure occurrence probability of the top layer node corresponding to the minimum cut set according to the node failure content occurrence probability of the minimum cut set; comparing the failure occurrence probability of each top layer node in the fault tree, and determining the failure situation of the power supply and repair equipment according to the order from large to small of the failure occurrence probability value. Wherein, the value is the largest, which means the most likely failure.

[0066] Further, after predicting the failure occurrence situation of the power supply and repair equipment, the method further includes: correcting the prediction result of the failure occurrence situation according to the real-time working state of the power supply and repair equipment; predicting the predicted failure after the current time based on the corrected failure occurrence situation; the predicted failure is the failure that will occur after the current time; and predicting the real-time remaining life of the power supply and repair equipment according to the predicted failure.

[0067] Specifically, in order to find the minimal cut set that causes the top event to occur, the fault tree needs to be analyzed in detail. By finding the potential failure causes of the system, the system is optimized to improve reliability. The result of qualitative analysis is usually to find the minimal cut set, which can be used to guide fault identification, standardize personnel operation and develop maintenance plans.

[0068] A cut set refers to the occurrence of the top event when all events in the set occur. The minimal cut set refers to the occurrence of the top event when any event in the cut set does not occur. These concepts play an important guiding role in fault tree analysis.

[0069] For the fault tree model that has been constructed, let X1, X2, …, X n be all the bottom events of the fault tree. If there is a subset C of the set {X1, X2, …, X n} such that when all elements in C are 1, there is: φ(X1, X2, …, Xn) = 1, then the set C is a cut set of the fault tree. The elements in the set can only be bottom events of the fault tree, and the number of elements is at most n.

[0070] Similarly, if there is a subset E of the set X1, X2, …, X n such that when all elements in E are 1, there is: Φ(X1, X2, …, X n ) = 1 and for any proper subset such that when all elements in E j are 1 and the states of other bottom events are 0, there is: φ(X1, X2, …, Xn) ≠ 1, then the set E is a MCS of the fault tree.

[0071] In calculating the fault occurrence probability of the minimal cut set,

[0072]

[0073] Taking the first term of the above formula as an approximate calculation, we have:

[0074]

[0075] In order to further reduce the error and improve the calculation accuracy, the second term of the inclusion-exclusion principle formula can be considered, and the probability of the occurrence of the top event is calculated according to the following formula.

[0076]

[0077] Corresponding to the foregoing embodiment of the fault analysis method of the industrial and electrical supply maintenance equipment, the application also provides an embodiment of a fault analysis device of the industrial and electrical supply maintenance equipment.

[0078] Figure 3The structure of the fault analysis device of the power supply maintenance equipment is shown in the embodiment two of the application. Please refer to Figure 3 The device provided in the embodiment comprises:

[0079] The extraction module is configured to determine historical faults of the power supply maintenance equipment.

[0080] The screening module is configured to screen root nodes of fault trees from the historical faults, wherein the historical faults corresponding to each root node are independent of each other.

[0081] The search module is configured to determine, for each root node of the fault tree, associated components and external conditions of the fault, wherein the associated components are components of the power supply maintenance equipment, and the external conditions are external conditions of the power supply maintenance equipment.

[0082] The construction module is configured to, for each root node of the fault tree, construct a fault tree of the power supply maintenance equipment by taking each associated object in the associated components and the external conditions as a sub-node of the fault tree under the root node, and taking a state of the associated object as a state value of the sub-node.

[0083] The evaluation module is configured to calculate an importance weight of each part according to a working principle of the power supply maintenance equipment, wherein the associated components are composed of a plurality of parts.

[0084] The prediction module is configured to calculate a fault probability of each root node of the fault tree based on the importance weight, and predict a fault occurrence situation of the power supply maintenance equipment.

[0085] The device of the embodiment can be used to execute Figure 1 The steps of the method embodiment are similar to the implementation principle and process, and thus will not be described here.

[0086] The implementation process of the functions and roles of each unit in the device is specifically described in the implementation process of the corresponding steps in the above method, and thus will not be described here.

[0087] For the device embodiment, since it basically corresponds to the method embodiment, the related parts can be referred to the part of the method embodiment. The device embodiment described above is only schematic, and the units shown as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or distributed on multiple network units. According to actual needs, some or all of the modules can be selected to achieve the purpose of the application. Those skilled in the art can understand and implement without creative labor.

[0088] The above only is the preferred embodiment of the present application, and is not used to limit the present application, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for fault analysis of power supply maintenance equipment, characterized in that, The method includes: Identify the historical faults of the aforementioned power supply maintenance equipment; The root nodes of the fault tree are selected from the historical faults, wherein the historical faults corresponding to each root node are independent of each other. For each fault tree root node, determine the associated components and external conditions of the fault, wherein the associated components are the components of the power supply maintenance equipment, and the external conditions are the external conditions under which the power supply maintenance equipment operates. For each fault tree root node, each associated object in the associated components and external conditions is taken as a fault tree child node under the root node to construct the fault tree of the power supply maintenance equipment, and the state of the associated object is taken as the state value of the fault tree child node. The importance weight of each part is calculated based on the working principle of the power supply maintenance equipment. The associated component is composed of multiple parts. Based on the importance weights, the failure probability of each root node in the fault tree is calculated, and the failure trend of the power supply maintenance equipment is predicted.

2. The method according to claim 1, characterized in that, The determination of historical faults of the power supply maintenance equipment includes: Determine the work content of the power supply maintenance equipment to be analyzed; Identify reference equipment that performs the same tasks; Extract the initial historical faults of the reference equipment and the power supply maintenance equipment to be analyzed when handling the work content; The initial historical faults are sorted, and local initial historical faults are filtered to obtain the historical faults.

3. The method according to claim 1, characterized in that, The historical faults include at least primary faults and secondary faults, and the step of filtering the root node of the fault tree from the historical faults includes: Using each fault as a node in the graph, the relationships between the nodes are calculated to construct a fault graph. Select independent graph nodes corresponding to the original faults from the fault graph, and take the faults corresponding to the independent graph nodes as the root nodes.

4. The method according to claim 1, characterized in that, For each root node of the fault tree, the associated components and external conditions of the fault are determined, including: Establish the aforementioned power supply maintenance equipment model; The power supply maintenance equipment model is divided into component units according to the work content described above. For each root node of the fault tree, determine the faulty part corresponding to the root node; Locate the associated component based on the faulty part; Candidate external conditions are determined based on the aforementioned work content; The external conditions are determined from the candidate external conditions based on the faulty part corresponding to the root node.

5. The method according to claim 1, characterized in that, For each fault tree root node, each associated object among the associated components and external conditions is taken as a fault tree child node under the root node to construct the fault tree of the power supply maintenance equipment, including: Each target node in each layer is established from top to bottom and from left to right. For each target node to be established, the associated object corresponding to the target node is determined based on the upper-level node of the target node to be established. Based on the fault content of the upper-level node, determine the fault content of the target node to be established, and complete the construction of the target node to be established.

6. The method according to claim 1, characterized in that, The calculation of the importance weight of each component based on the working principle of the power supply maintenance equipment includes: The working principle of the power supply maintenance equipment is determined based on the work content described above. Based on the working principle, determine the degree of participation of each component in the power supply maintenance equipment when the power supply maintenance equipment completes the work content. The contribution of each component to the structural stability is determined based on the structural characteristics of the power supply maintenance equipment. The importance weight of each component is obtained by combining the degree of participation and the degree of contribution.

7. The method according to claim 6, characterized in that, The calculation of the failure probability of each root node of the fault tree based on the importance weight includes: The degree of participation is determined by the ratio of the duration of the part's participation in the work content to the total duration of the electrical and power supply maintenance equipment completing the work content; The contribution is determined by the percentage of failures in the power supply maintenance equipment after the component failure, and the sum of the two is the importance weight of the component.

8. The method according to claim 1, characterized in that, The calculation of the failure probability of each root node of the fault tree based on the importance weight includes: The importance weight of each node in the fault tree is calculated based on the importance weight of the component. Traverse from the bottom node upwards to determine the minimum cut set where the fault occurs at the top node; The probability of failure of the top-level node corresponding to the minimum cut set is calculated based on the probability of failure of the node content of the minimum cut set. By comparing the failure probabilities of each top-level node in the fault tree, the failure status of the power supply maintenance equipment is determined according to the order of failure probability values ​​from largest to smallest.

9. The method according to claim 1, characterized in that, After predicting the failure status of the power supply maintenance equipment, the method further includes: The prediction results of the fault occurrence situation are corrected based on the real-time working status of the power supply maintenance equipment. Based on the corrected fault occurrence situation, predict the fault at the current moment; The predicted fault is a fault that is predicted to occur after the current moment; The real-time remaining lifespan of the power supply maintenance equipment is predicted based on the predicted fault.

10. A fault analysis device for power supply maintenance equipment, characterized in that, The device includes: The extraction module is used to determine the historical faults of the power supply maintenance equipment; The filtering module is used to filter the root nodes of the fault tree from the historical faults, wherein the historical faults corresponding to each root node are independent of each other. The search module is used to determine the associated components and external conditions of the fault for each fault tree root node, wherein the associated components are the components of the power supply maintenance equipment, and the external conditions are the external conditions under which the power supply maintenance equipment operates. The construction module is used to construct the fault tree of the power supply maintenance equipment for each fault tree root node, taking each associated object in the associated components and external conditions as a fault tree child node under the root node, and the state of the associated object as the state value of the fault tree child node. The evaluation module is used to calculate the importance weight of each part based on the working principle of the power supply maintenance equipment. The associated component is composed of multiple parts. The prediction module is used to calculate the failure probability of each root node of the fault tree based on the importance weight, and to predict the failure trend of the power supply maintenance equipment.

Images