Fault diagnosis method, device, computer equipment and storage medium for operating system

Abstract

The present application relates to a fault diagnosis method, device, computer equipment and storage medium for a running system. The method comprises: obtaining fault parameters of a faulty node where a fault occurs, wherein the faulty node is one of a plurality of running nodes; performing fault diagnosis on each sub-node of the faulty node according to a preset diagnosis rule and the fault parameters, and obtaining a fault diagnosis result of each sub-node, wherein the fault diagnosis result is used to characterize the probability of each sub-node failing. The method can improve the efficiency of fault diagnosis.

Description

Technical Field

[0001] The present application relates to the technical field of fault diagnosis, and in particular to a method, apparatus, computer equipment and storage medium for fault diagnosis of an operating system. Background Art

[0002] In the production workshop of the cigarette factory, constant temperature and humidity are the basic requirements for ensuring process quality. The process temperature and humidity requirements are: temperature 26±2℃, humidity 63±5%RH. Therefore, an air conditioning system is needed to ensure the basic requirements of process quality. During the operation of the air conditioning system, one of the operation nodes will fail. After the operation node fails, it is necessary to manually diagnose the failure of each sub-node of the faulty operation node to locate the specific cause.

[0003] However, the efficiency of fault diagnosis by manually diagnosing the faults of the sub-nodes of the faulty running node is low. Summary of the invention

[0004] Based on this, it is necessary to provide a fault diagnosis method, device, computer equipment and storage medium for an operating system that can improve the fault diagnosis efficiency in response to the above technical problems.

[0005] In a first aspect, the present application provides a fault diagnosis method for an operating system, wherein the operating system includes a plurality of operating nodes, and the method includes:

[0006] Obtaining fault parameters of a faulty node where a fault occurs, wherein the faulty node is one of the multiple running nodes;

[0007] Fault diagnosis is performed on each sub-node of the faulty node according to preset diagnosis rules and the fault parameters to obtain a fault diagnosis result of each sub-node, wherein the fault diagnosis result is used to characterize the probability of failure of each sub-node.

[0008] In one embodiment, there are multiple preset diagnostic rules, and the fault diagnosis of each sub-node of the faulty node according to the preset diagnostic rules and the fault parameters includes:

[0009] According to the diagnosis sequence of the plurality of preset diagnosis rules, the fault diagnosis is performed on each sub-node in turn according to each preset diagnosis rule and the fault parameters, until one of the preset diagnosis rules successfully diagnoses the fault of each sub-node.

[0010] In one embodiment, the plurality of preset diagnostic rules include matching diagnostic rules, fuzzy diagnostic rules, and fusion diagnostic rules based on information fusion, and the diagnosis sequence of the plurality of preset diagnostic rules is followed, and each sub-node is sequentially diagnosed according to each preset diagnostic rule and the fault parameters until one of the preset diagnostic rules successfully diagnoses the fault of each sub-node, including:

[0011] Performing fault diagnosis on each sub-node according to the matching diagnosis rule and the fault parameter;

[0012] In the case where the matching diagnosis rule is successfully diagnosed, outputting the fault diagnosis result obtained by performing the fault diagnosis according to the matching diagnosis rule;

[0013] In the case where the matching diagnosis rule fault diagnosis fails, performing fault diagnosis on each sub-node according to the fuzzy diagnosis rule and the fault parameter;

[0014] In the case where the fuzzy diagnosis rule is successfully diagnosed, outputting the fault diagnosis result obtained by performing the fault diagnosis according to the fuzzy diagnosis rule;

[0015] In the case where the fuzzy diagnosis rule fails to diagnose, performing fault diagnosis on each sub-node according to the fusion diagnosis rule and the fault parameter;

[0016] When the diagnosis by the fusion diagnosis rule is successful, a fault diagnosis result obtained by performing fault diagnosis by the fusion diagnosis rule is output.

[0017] In one embodiment, the performing fault diagnosis on each sub-node according to the matching diagnosis rule and the fault parameter includes:

[0018] Acquire a fault event set matching the fault parameter, the fault event set including a plurality of fault events corresponding to when the fault node fails, each fault event representing a faulty sub-node in each sub-node;

[0019] Determine the number of times each sub-node fails according to the set of failure events;

[0020] The probability of each sub-node failure is determined based on the number of times each sub-node fails.

[0021] In one embodiment, the performing fault diagnosis on each sub-node according to the fuzzy diagnosis rule and the fault parameter includes:

[0022] Performing fuzzy processing on the fault parameters to obtain the first fault membership degree of each sub-node;

[0023] The fault diagnosis result of each sub-node is determined according to the first fault membership degree.

[0024] In one embodiment, there are multiple fault parameters, and the performing fault diagnosis on each sub-node according to the fusion diagnosis rule and the fault parameters includes:

[0025] Perform fuzzy processing on each fault parameter to obtain the first fault membership degree of each sub-node corresponding to each fault parameter;

[0026] The first fault membership of each sub-node corresponding to each fault parameter is merged to obtain a second fault membership;

[0027] The fault diagnosis result of each sub-node is determined according to the second fault membership degree.

[0028] In a second aspect, the present application provides a fault diagnosis device for an operation system, wherein the operation system includes a plurality of operation nodes, and the device includes:

[0029] A parameter acquisition module, used to acquire fault parameters of a faulty node where a fault occurs, wherein the faulty node is one of the multiple running nodes;

[0030] The fault diagnosis module is used to perform fault diagnosis on each sub-node of the fault node according to preset diagnosis rules and the fault parameters to obtain a fault diagnosis result of each sub-node, wherein the fault diagnosis result is used to characterize the probability of failure of each sub-node.

[0031] In a third aspect, the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0032] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0033] In a fifth aspect, the present application provides a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0034] The above-mentioned fault diagnosis method, device, computer equipment and storage medium of the operating system, the fault diagnosis method of the operating system includes: obtaining the fault parameters of the faulty node where the fault occurs, the faulty node is one of multiple operating nodes; performing fault diagnosis on each sub-node of the faulty node according to preset diagnostic rules and the fault parameters to obtain the fault diagnosis results of each sub-node, the fault diagnosis results are used to characterize the probability of each sub-node failing. Since the fault parameters of the faulty node and the preset diagnostic rules can be used to automatically diagnose each sub-node of the faulty node, the probability of each sub-node failing can be obtained. Therefore, the operation and maintenance personnel can quickly confirm whether each sub-node has failed based on the probability of each sub-node failing, thereby solving the technical problem of low diagnostic efficiency caused by manually diagnosing the fault of the sub-node of the operating node, and achieving the technical effect of improving the fault diagnosis efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A schematic diagram of a flow chart of a method for diagnosing a fault of an operating system in an embodiment;

[0036] Figure 2 A detailed flow chart of performing fault diagnosis on each sub-node according to multiple preset rules in an embodiment;

[0037] Figure 3 is a schematic diagram of the structure of a fault diagnosis device for an operating system in an embodiment;

[0038] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0040] refer to Figure 1 , Figure 1 FIG. 1 is a flow chart of a method for diagnosing a fault of an operating system in an embodiment. Figure 1 As shown, a fault diagnosis method for a running system is provided. The fault diagnosis method of this embodiment is used to diagnose the fault of the running system. The running system includes multiple running nodes. This embodiment is illustrated by applying the method to a computer device. It can be understood that the method can also be applied to a server, and can also be applied to a system including a computer device and a server, and is implemented through the interaction between the computer device and the server. In this embodiment, the method steps 110 to 120.

[0041] Step 110: Obtain fault parameters of a faulty node where a fault occurs, where the faulty node is one of the multiple running nodes.

[0042] Among them, the fault node refers to the operating node where the fault occurs among the multiple operating nodes of the operating system. The operating node refers to the node that works in the operating system. Optionally, the operating system can be an air-conditioning system. Taking the operating system as an air-conditioning system as an example, the operating nodes include but are not limited to air processing nodes, air delivery nodes, air distribution nodes, etc. In this embodiment, what is obtained may be the fault parameters when the operating node fails. The fault parameters generally refer to key fault parameters, which are used to characterize whether a fault occurs. For example, the current temperature, the current air flow, etc. Optionally, the fault parameters of this embodiment can be obtained by collecting sensors.

[0043] Step 120: perform fault diagnosis on each sub-node of the faulty node according to preset diagnosis rules and the fault parameters to obtain a fault diagnosis result of each sub-node, wherein the fault diagnosis result is used to characterize the probability of failure of each sub-node.

[0044] Wherein, the preset diagnosis rule refers to the rule for performing fault diagnosis on each sub-node of the faulty node. Optionally, the preset diagnosis rule in this embodiment may be one or more. Wherein, the sub-node refers to one of the branches of the running node. In this embodiment, the sub-node refers to the sub-node of the faulty node. For example, if the faulty node is an air handling node, the sub-node may be a compressor, etc. In this step, fault diagnosis is performed on each sub-node of the faulty node according to the preset diagnosis rule and the fault parameter, so as to determine the probability of failure of each sub-node.

[0045] The technical solution of this embodiment can automatically diagnose the faults of the sub-nodes of the faulty node through the fault parameters of the faulty node and the preset diagnosis rules, and can obtain the probability of failure of each sub-node. The operation and maintenance personnel can then quickly confirm the faults of each sub-node based on the probability of failure of each sub-node, thus solving the technical problem of low diagnostic efficiency caused by manual diagnosis of the failures of the sub-nodes of the operating node, and achieving the technical effect of improving the efficiency of fault diagnosis.

[0046] In a possible implementation manner, there are multiple preset diagnosis rules, and fault diagnosis is performed on each sub-node of the faulty node according to the preset diagnosis rules and the fault parameters, including:

[0047] According to the diagnosis sequence of the plurality of preset diagnosis rules, the fault diagnosis is performed on each sub-node in turn according to each preset diagnosis rule and the fault parameters, until one of the preset diagnosis rules successfully diagnoses the fault of each sub-node.

[0048] In this embodiment, there are multiple preset diagnostic rules, and each sub-node is diagnosed for faults using one preset diagnostic rule and fault parameters each time until one of the preset diagnostic rules successfully diagnoses the fault of each sub-node, and then the diagnosis of other preset diagnostic rules is stopped.

[0049] It should be noted that the diagnostic order of the plurality of preset diagnostic rules is related to the diagnostic accuracy among the plurality of preset diagnostic rules. Specifically, the higher the diagnostic accuracy, the higher the diagnostic order.

[0050] It can be understood that this embodiment uses multiple preset diagnostic rules to perform fault diagnosis on each sub-node of the faulty node. The higher the diagnostic accuracy, the higher the diagnostic order. Under the premise of ensuring normal diagnosis results, the diagnostic accuracy is higher.

[0051] refer to Figure 2 , Figure 2 FIG. 1 is a detailed flow chart of performing fault diagnosis on each sub-node according to multiple preset rules in an embodiment. In this embodiment, multiple preset rules including matching diagnosis rules, fuzzy diagnosis rules and fusion diagnosis rules based on information fusion are used as examples for explanation. Figure 2 As shown, according to the diagnosis order of multiple preset diagnostic rules, each sub-node is diagnosed according to each preset diagnostic rule and the fault parameter in turn, until one of the preset diagnostic rules successfully diagnoses the fault of each sub-node, including:

[0052] Step 210: Perform fault diagnosis on each sub-node according to the matching diagnosis rule and the fault parameters.

[0053] Step 220: Determine whether the diagnosis is successful based on the matching diagnosis rule.

[0054] In this step, if the diagnosis is successful, step 230 is executed; if the diagnosis fails, step 240 is executed.

[0055] Step 230: output the fault diagnosis result obtained by performing fault diagnosis based on the matching diagnosis rule.

[0056] In this step, when the matching diagnosis rule is successfully diagnosed, the fault diagnosis result obtained by performing the fault diagnosis according to the matching diagnosis rule is output.

[0057] Step 240: Perform fault diagnosis on each sub-node according to the fuzzy diagnosis rule and the fault parameter.

[0058] In this step, when the fault diagnosis by matching the diagnosis rule fails, the fault diagnosis is performed on each sub-node according to the fuzzy diagnosis rule and the fault parameter.

[0059] Step 250: Determine whether the fuzzy diagnosis rule is successful.

[0060] In this step, if the diagnosis is successful, step 260 is executed; if the diagnosis fails, step 270 is executed.

[0061] Step 260: Output the fault diagnosis result obtained by performing fault diagnosis using the fuzzy diagnosis rule.

[0062] In this step, when the fuzzy diagnosis rule is successfully diagnosed, the fault diagnosis result obtained by performing the fault diagnosis according to the fuzzy diagnosis rule is output.

[0063] Step 270: Perform fault diagnosis on each sub-node according to the fusion diagnosis rule and the fault parameters.

[0064] In this step, when the fuzzy diagnosis rule fails to diagnose, fault diagnosis is performed on each sub-node according to the fusion diagnosis rule and the fault parameter.

[0065] Step 280: Determine whether the diagnosis is successful based on the fusion diagnosis rule.

[0066] In this step, if the diagnosis is successful, step 290 is executed.

[0067] Step 290: Output the fault diagnosis result obtained by performing fault diagnosis based on the fusion diagnosis rule.

[0068] In this step, when the diagnosis by the fusion diagnosis rule is successful, the fault diagnosis result obtained by performing fault diagnosis by the fusion diagnosis rule is output.

[0069] In this embodiment, if a fault diagnosis result can be obtained, it can be considered that the diagnosis is successful.

[0070] The technical solution of this embodiment is to diagnose by matching diagnostic rules first. If the matching diagnostic rules fail, diagnosis is performed by fuzzy diagnostic rules. If the fuzzy diagnostic rules fail, diagnosis is performed by fusion diagnostic rules. Diagnosis by multiple preset diagnostic rules can ensure that the fault diagnosis results of each sub-node can be diagnosed.

[0071] It should be noted that if the matching diagnosis rules, fuzzy diagnosis rules and fusion diagnosis rules based on information fusion all fail to diagnose, it is necessary to re-establish the preset diagnosis rules of the faulty node so as to perform fault diagnosis on each sub-node of the faulty node through the newly established preset diagnosis rules.

[0072] It is understandable that fault diagnosis may also be performed using only one of the matching diagnosis rules, the fuzzy diagnosis rules, and the fusion diagnosis rules based on information fusion.

[0073] The following embodiments describe how to perform diagnosis according to preset diagnosis rules based on any of the above embodiments.

[0074] In a possible implementation manner, the performing fault diagnosis on each sub-node according to the matching diagnosis rule and the fault parameter includes:

[0075] Acquire a fault event set matching the fault parameter, the fault event set including a plurality of fault events corresponding to when the fault node fails, each fault event representing a faulty sub-node in each sub-node;

[0076] Determine the number of times each sub-node fails according to the set of failure events;

[0077] The probability of each sub-node failure is determined based on the number of times each sub-node fails.

[0078] Among them, the fault event refers to a real event in which a fault has occurred, and the fault event can be obtained through simulation. The fault event of this embodiment is a fault event corresponding to when a fault node has failed. Specifically, this embodiment pre-establishes a set of fault events that match each parameter interval, and then determines a set of fault events that match the fault parameter according to the parameter interval in which the fault parameter is located.

[0079] In this embodiment, since the fault event set includes multiple fault events corresponding to the fault node failure, and each fault event records the faulty sub-nodes in each sub-node when the fault node fails, the number of times each sub-node fails can be determined based on the fault time set, and the probability of each sub-node failure can be determined based on the number of failures.

[0080] It should be noted that the higher the number of failures in each sub-node, the higher the probability of failure. Optionally, the probability of failure of each sub-node can be calculated by calculating the ratio of the number of failures of a certain sub-node to the total number of failures of all sub-nodes in the combination of the failure probability event.

[0081] The technical solution of this embodiment determines the fault diagnosis result of each sub-node through a set of fault events. Since it reflects the actual situation when the fault node fails, the obtained fault diagnosis result is more accurate.

[0082] In a possible implementation manner, the performing fault diagnosis on each sub-node according to the fuzzy diagnosis rule and the fault parameter includes:

[0083] Performing fuzzy processing on the fault parameters to obtain the first fault membership degree of each sub-node;

[0084] The fault diagnosis result of each sub-node is determined according to the first fault membership degree.

[0085] Among them, fault membership refers to the membership that characterizes the fault. The first fault membership refers to the fault membership obtained by fuzzy processing the operation process. If for any element x in the domain (scope of research) U, there is a number A(x)∈[0,1] corresponding to it, then A is called a fuzzy set on U, and A(x) is called the membership of x to A. When x changes in U, A(x) is a function, called the membership function of A. The closer the membership A(x) is to 1, the higher the degree to which x belongs to A, and the closer A(x) is to 0, the lower the degree to which x belongs to A. The membership function A(x) with a value in the interval (0,1) is used to characterize the degree to which x belongs to A. The membership belongs to the concept of fuzzy evaluation function: fuzzy comprehensive evaluation is a very effective multi-factor decision-making method for making a comprehensive evaluation of things affected by multiple factors. Its characteristic is that the evaluation result is not absolutely affirmative or negative, but is expressed as a fuzzy set. In this implementation manner, after the first fault membership of each sub-node is obtained, the fault diagnosis result of each sub-node can be determined according to the second fault membership.

[0086] It should be noted that in this embodiment, when there are multiple fault parameters, one of the fault parameters is fuzzy processed to obtain the first fault membership of each sub-node. If one of the fault parameters cannot be diagnosed after fuzzy processing, another fault parameter is fuzzy processed until all fault parameters are fuzzy processed and still cannot be diagnosed, then diagnosis is performed through fusion diagnosis rules.

[0087] In a possible implementation, the fault parameters can be fuzzy processed by a fuzzy algorithm. Optionally, the fuzzy algorithm includes but is not limited to normal distribution, triangular distribution, trapezoidal distribution, ascending half normal distribution, descending half normal distribution, Cauchy distribution and rectangular distribution. Taking the expression of normal distribution as an example, the expression is:

[0088] μ(x)=exp[-k(xa)], k>0.

[0089] Taking the expression of triangular distribution as an example, its expression is:

[0090]

[0091] Among them, a is the parent node parameter corresponding to a certain fault type, and b and c are the limit deviations of the parameters.

[0092] Let A be the set of possible decisions of the fault diagnosis system, such as the set of fault types of each child node; B is the set of parent node fault parameters (i.e. sensor test data, the same below). The element μji in the relationship matrix R between A and B represents the possibility of inferring the decision i (the i-th child node fault) from the parameter j of the parent node, X represents the credibility of each fault parameter of the parent node, and Y obtained by fuzzy transformation is the possibility of each child node fault after integration. Specifically, assuming that there are m sensors testing the parent node (i.e., there are m fault parameters), and there are n child nodes, then:

[0093] A={y1 / child node 1, y2 / child node 2,…, yn / child node n}

[0094] B = {x1 / parameter 1, x2 / parameter 2, ..., xm / parameter m}

[0095] The judgment of the fault parameter on each possible decision is expressed by the membership function defined on A. Let the judgment result of the parent node parameter j on each child node be: [μj1 / child node 1, μj2 / child node 2, …, μjn / child node n] where 0≤μji≤1

[0096] That is, the probability of the failure of subnode i is considered to be μji, recorded as a vector (μj1, μj2, …, μjn), and the m parameters constitute the A×B relationship matrix:

[0097]

[0098] Among them, the relationship matrix A×B can be regarded as the first fault membership. The credibility of each parameter judgment is represented by the membership X={x1 / parameter 1, x2 / parameter 2, ..., xm / parameter m} on B, then Y=X·R is used for fuzzy transformation to obtain the comprehensive diagnosis result Y={μ(x1),μ(x2), ...,μ(xn)}, which is the set of comprehensive fault possibilities of each sub-node.

[0099] In a possible implementation manner, there are multiple fault parameters, and the performing fault diagnosis on each sub-node according to the fusion diagnosis rule and the fault parameters includes:

[0100] Perform fuzzy processing on each fault parameter to obtain the first fault membership degree of each sub-node corresponding to each fault parameter;

[0101] The first fault membership of each sub-node corresponding to each fault parameter is merged to obtain a second fault membership;

[0102] The fault diagnosis result of each sub-node is determined according to the second fault membership degree.

[0103] The second fault membership refers to the fault membership obtained by fusing the first fault memberships of each sub-node corresponding to each fault parameter, and the second fault membership can be considered as the fused membership. In this embodiment, each fault parameter is first fuzzy processed to obtain the first fault membership corresponding to each sub-node, and the first fault memberships are fused to obtain the second fault membership, so that the fault diagnosis result of each sub-node is determined by the second fault membership.

[0104] In a possible implementation, the first fault membership of each sub-node corresponding to each fault parameter may be fused through a fusion algorithm. Optionally, the fusion algorithm includes but is not limited to a fuzzy information fusion algorithm, an information fusion algorithm based on DS evidence theory, and a neural network information fusion algorithm.

[0105] Specifically, the neural network information fusion algorithm mainly combines fuzzy sets with BP networks to form a fuzzy neural network classifier, which combines fuzzy concepts in each layer of the neural network, and its input and output are membership values ​​with semantic properties. During fault diagnosis, the first fault membership value of each sub-node is obtained by using each fault parameter as the input of the BP network, and the second fault membership value after fusion is output.

[0106] It should be noted that among multiple fusion algorithms, the BP algorithm has a higher fault recognition rate when the samples are complete. However, in some cases, fault samples are difficult to obtain and the BP fusion fault diagnosis algorithm cannot be used. At this time, fuzzy fusion or information fusion fault diagnosis algorithms based on DS evidence theory can be applied. They do not require fault samples. The fuzzy fusion algorithm is simple and has a small amount of calculation. The DS fusion algorithm is relatively complex, but the diagnostic accuracy is high. You can choose according to different situations.

[0107] In this embodiment, the fusion algorithm used for fusion is not limited in this embodiment.

[0108] In a possible implementation, the fault diagnosis result may also be displayed in a visual form, or information may be sent to inform the operation and maintenance personnel so that the operation and maintenance personnel can confirm the fault in a timely manner.

[0109] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0110] Based on the same inventive concept, the embodiment of the present application also provides a fault diagnosis device for an operating system for implementing the fault diagnosis method for an operating system involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of the fault diagnosis device for one or more operating systems provided below can refer to the limitations of the fault diagnosis method for an operating system above, and will not be repeated here.

[0111] refer to Figure 3 , Figure 3 FIG. 1 is a schematic diagram of a fault diagnosis device for a running system in an embodiment. Figure 3 As shown, a fault diagnosis device for a running system is provided, comprising: a parameter acquisition module 310 and a fault diagnosis module 320, wherein:

[0112] The parameter acquisition module 310 is used to acquire the fault parameters of the faulty node where the fault occurs, wherein the faulty node is one of the multiple running nodes;

[0113] The fault diagnosis module 320 is used to perform fault diagnosis on each sub-node of the faulty node according to preset diagnosis rules and the fault parameters to obtain a fault diagnosis result of each sub-node, and the fault diagnosis result is used to characterize the probability of failure of each sub-node.

[0114] In one embodiment, there are multiple preset diagnostic rules, and the fault diagnosis module 320 is specifically used to perform fault diagnosis on each sub-node in accordance with the diagnostic order of the multiple preset diagnostic rules, in turn according to each preset diagnostic rule and the fault parameters, until one of the preset diagnostic rules successfully diagnoses the fault of each sub-node.

[0115] In one embodiment, the plurality of preset diagnostic rules include matching diagnostic rules, fuzzy diagnostic rules and fusion diagnostic rules based on information fusion, and the fault diagnosis module 320 includes:

[0116] A first fault diagnosis unit is used to perform fault diagnosis on each sub-node according to the matching diagnosis rule and the fault parameter; if the matching diagnosis rule is successfully diagnosed, output the fault diagnosis result obtained by performing the fault diagnosis according to the matching diagnosis rule;

[0117] A second fault diagnosis unit is used to perform fault diagnosis on each sub-node according to the fuzzy diagnosis rule and the fault parameter when the fault diagnosis of the matching diagnosis rule fails; and output the fault diagnosis result obtained by performing the fault diagnosis according to the fuzzy diagnosis rule when the diagnosis of the fuzzy diagnosis rule succeeds;

[0118] The third fault diagnosis unit is used to perform fault diagnosis on each sub-node according to the fusion diagnosis rule and the fault parameter when the diagnosis by the fuzzy diagnosis rule fails; and output the fault diagnosis result obtained by the fault diagnosis by the fusion diagnosis rule when the diagnosis by the fusion diagnosis rule succeeds.

[0119] In one of the embodiments, the first fault diagnosis unit is specifically used to obtain a set of fault events that match the fault parameters, the set of fault events including multiple fault events corresponding to the fault node, each fault event representing a faulty sub-node in each sub-node; determining the number of times each sub-node fails based on the set of fault events; and determining the probability of each sub-node failing based on the number of times each sub-node fails.

[0120] In one of the embodiments, the second fault diagnosis unit is specifically configured to perform fuzzy processing on the fault parameter to obtain a first fault membership of each sub-node; and determine a fault diagnosis result of each sub-node according to the first fault membership.

[0121] In one of the embodiments, there are multiple fault parameters, and the third fault diagnosis unit is specifically used to perform fuzzy processing on each fault parameter to obtain a first fault membership of each sub-node corresponding to each fault parameter; fuse the first fault membership of each sub-node corresponding to each fault parameter to obtain a second fault membership; and determine the fault diagnosis result of each sub-node according to the second fault membership.

[0122] Each module in the fault diagnosis device of the above-mentioned operating system can be implemented in whole or in part by software, hardware and a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module above.

[0123] refer to Figure 4 , Figure 4FIG. 1 is an internal structure diagram of a computer device in an embodiment. In one embodiment, a computer device is provided. The computer device may be a terminal. The internal structure diagram thereof may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a fault diagnosis method for an operating system is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0124] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0125] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps of the method of any of the above embodiments when executing the computer program.

[0126] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method of any of the above embodiments are implemented.

[0127] In one embodiment, a computer program product is provided, including a computer program, which implements the steps of the method of any of the above embodiments when executed by a processor.

[0128] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0129] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0130] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for diagnosing a fault in a running system, characterized in that: The operation system includes a plurality of operation nodes, and the method includes: Acquire multiple fault parameters of a faulty node where a fault occurs, wherein the faulty node is one of multiple running nodes, and the fault parameters are key parameters that characterize whether a fault occurs; Performing fault diagnosis on each sub-node according to the matching diagnosis rule and the fault parameters; In the case where the matching diagnosis rule is successfully diagnosed, outputting the fault diagnosis result obtained by performing the fault diagnosis according to the matching diagnosis rule; In the case where the matching diagnosis rule fault diagnosis fails, one of the fault parameters is fuzzy processed to obtain the first fault membership of each child node, wherein the first fault membership is an A×B relationship matrix, wherein A is a set of fault types of each child node, B is a fault parameter of the parent node, and the relationship matrix contains multiple elements μji, wherein the element μji represents the possibility of inferring the fault of the i-th child node from the fault parameter j of the parent node; the fault diagnosis result of each child node is determined according to the first fault membership, wherein the product of the credibility of each fault parameter of the parent node and the relationship matrix is ​​used as the set of the comprehensive fault possibilities of each child node; if the diagnosis result cannot be diagnosed, another fault parameter is fuzzy processed until all fault parameters are fuzzy processed and the diagnosis result cannot be diagnosed; In the case where the fuzzy diagnosis rule is successful, outputting the fault diagnosis result obtained by performing the fault diagnosis according to the fuzzy diagnosis rule; In the case that the fuzzy diagnosis rule fails to diagnose, each fault parameter is fuzzy processed to obtain the first fault membership of each sub-node corresponding to each fault parameter, and the first fault membership of each sub-node corresponding to each fault parameter is merged to obtain the second fault membership, and the fault diagnosis result of each sub-node is determined according to the second fault membership; When the diagnosis by the fusion diagnosis rule is successful, the fault diagnosis result obtained by the fusion diagnosis rule for fault diagnosis is output, and the fault diagnosis result is used to characterize the probability of failure of each sub-node.

2. The method according to claim 1, characterized in that The preset diagnostic rule has a diagnostic accuracy. The higher the diagnostic accuracy of the preset diagnostic rule is, the higher the diagnostic order of the preset diagnostic rule is.

3. The method according to claim 1, characterized in that: The method further comprises: If the matching diagnosis rule, the fuzzy diagnosis rule and the fusion diagnosis rule based on information fusion all fail to diagnose, the preset diagnosis rule of the faulty node is re-established to perform fault diagnosis on each sub-node of the faulty node through the newly established preset diagnosis rule.

4. The method according to claim 1, characterized in that The performing fault diagnosis on each sub-node according to the matching diagnosis rule and the fault parameter includes: Acquire a fault event set matching the fault parameter, wherein the fault event set includes a plurality of fault events corresponding to the fault node when the fault occurs, and each fault event represents a faulty sub-node in each sub-node where the fault occurs; Determine the number of times each sub-node fails according to the set of failure events; The probability of each sub-node failure is determined based on the number of times each sub-node fails.

5. The method according to claim 1, characterized in that The membership function defined on A is used to represent the judgment of the fault parameters on each possible decision.

6. The method according to claim 1, characterized in that The method further comprises: The fault diagnosis result is displayed in a visual form or a message is sent to the operation and maintenance personnel so that the operation and maintenance personnel can confirm the fault in time.

7. A fault diagnosis device for a running system, characterized in that: The operation system includes a plurality of operation nodes, and the device includes: A parameter acquisition module, used to acquire multiple fault parameters of a faulty node where a fault occurs, wherein the faulty node is one of multiple running nodes, and the fault parameters are key parameters that characterize whether a fault occurs; A fault diagnosis module is used to perform fault diagnosis on each child node according to the matching diagnosis rule and the fault parameter; if the matching diagnosis rule diagnosis is successful, the fault diagnosis result obtained by the matching diagnosis rule is output; if the matching diagnosis rule fault diagnosis fails, one of the fault parameters is fuzzy processed to obtain the first fault membership of each child node, wherein the first fault membership is an A×B relationship matrix, wherein A is a set of fault types of each child node, B is a fault parameter of the parent node, and the relationship matrix contains multiple elements μji, wherein the element μji represents the possibility of inferring the fault of the i-th child node from the fault parameter j of the parent node; the fault diagnosis result of each child node is determined according to the first fault membership, wherein the product of the credibility of each fault parameter of the parent node and the relationship matrix is ​​used as the comprehensive A set of possible faults of each sub-node; if the diagnosis result cannot be diagnosed, another fault parameter is fuzzy processed until all fault parameters are fuzzy processed and the diagnosis result cannot be diagnosed; in the case of successful diagnosis by the fuzzy diagnosis rule, the fault diagnosis result obtained by the fuzzy diagnosis rule for fault diagnosis is output; in the case of failed diagnosis by the fuzzy diagnosis rule, each fault parameter is fuzzy processed to obtain the first fault membership of each sub-node corresponding to each fault parameter, and the first fault membership of each sub-node corresponding to each fault parameter is fused to obtain the second fault membership, and the fault diagnosis result of each sub-node is determined according to the second fault membership; in the case of successful diagnosis by the fusion diagnosis rule, the fault diagnosis result obtained by the fusion diagnosis rule for fault diagnosis is output, and the fault diagnosis result is used to characterize the probability of failure of each sub-node.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images