Equipment fault analysis method based on equipment function and hardware performance coupling mechanism

Abstract

The embodiment of the invention provides an equipment fault analysis method and device based on an equipment function and hardware performance coupling mechanism and a storage medium, and the method comprises the steps: carrying out the structure analysis and function analysis of target equipment, obtaining a feature description, and determining a coupling relation unit of the target equipment according to the feature description; an FRAM model is established according to the upstream and downstream relation of the coupling relation unit and is used for determining the coupling relation between the function of the target equipment and the hardware performance; according to an analytic hierarchy process, determining the unit variability of the coupling relation unit from two dimensions of hardware performance degradation and function output precision; determining the coupling loss degree of the coupling relation unit according to the unit variability, the structure entropy and the frequency entropy; and evaluating the fault risk of the target equipment according to the coupling loss degree. According to the method, effective fault risk assessment of the equipment is realized.

Description

Technical Field

[0001] The present invention relates to the field of equipment failure analysis methods, and in particular to an equipment failure analysis method based on a coupling mechanism between equipment function and hardware performance. Background Art

[0002] Studying the failure modes of equipment, diagnosing the causes of equipment malfunction, and quantifying the risks of equipment hardware performance degradation to equipment functions are all of great significance to improving equipment reliability. Hardware materials and structural connections will continue to deteriorate over time, and hardware structural performance will decline accordingly, followed by hardware failures, which will eventually lead to system malfunctions. With the continuous development of manufacturing equipment, equipment systems have become increasingly complex, and there is a coupled variation relationship between equipment functions and hardware performance, and there is an emergent nature between failures.

[0003] Existing fault analysis tools mainly include fault tree analysis and failure mode and effect analysis. These fault analysis methods mainly use hardware analysis or functional analysis, which are out of touch with actual work and have low practicality. Summary of the invention

[0004] The purpose of the embodiment of the present invention is to provide a device failure analysis method based on a device function and hardware performance coupling mechanism, which method implements effective failure risk assessment for the device.

[0005] In order to achieve the above object, an embodiment of the present invention provides a device failure analysis method based on a device function and hardware performance coupling mechanism, the method comprising:

[0006] Performing structural analysis and functional analysis on the target device to obtain a feature description, and determining a coupling relationship unit of the target device according to the feature description;

[0007] Establishing a FRAM model according to the upstream and downstream relationship of the coupling relationship unit, so as to determine the coupling relationship between the function and the hardware performance of the target device;

[0008] According to the hierarchical analysis method, the unit variability of the coupling relationship unit is determined from two dimensions: hardware performance degradation and function output accuracy;

[0009] Determining the coupling loss degree of the coupling relationship unit according to the unit variability, structural entropy and frequency entropy;

[0010] The failure risk of the target device is evaluated according to the coupling loss degree.

[0011] Optionally, the feature description includes input description, output description, premise description, resource description, time description and control description;

[0012] The input is described as something or a condition that initiates the coupling relationship unit;

[0013] The output is described as the output processing result of the operation of the coupling relationship unit;

[0014] The premise description is a necessary condition for the operation of the coupling relationship unit;

[0015] The resource description is the material or information required or consumed during the operation of the coupling relationship unit;

[0016] The time description is a time constraint for the operation of the coupling relationship units;

[0017] The control description is a method of monitoring and controlling the operation process of the coupling relationship unit.

[0018] Optionally, establishing a FRAM model according to the upstream and downstream relationship of the coupling relationship unit includes:

[0019] Determine the functional hexagon of the coupling relationship unit according to the feature description;

[0020] The functional hexagon connects the upstream unit and the downstream unit, and the output of the upstream unit is used as the feature description of the downstream unit;

[0021] A FRAM model is established based on the functional hexagons and their connected upstream and downstream units.

[0022] Optionally, the unit variability A of the coupling relationship unit i ,include:

[0023]

[0024] in, Score the degradation change, t∈{1,2,3,4},

[0025] Score the accuracy change, [∈{1,2,3},

[0026] is the relative weight of the degradation dimension,

[0027] is the relative weight of the precision dimension,

[0028] i is the i-th coupling relationship unit.

[0029] Optionally, the coupling loss degree of the coupling relationship unit is determined according to the unit variability, structural entropy and frequency entropy;

[0030]

[0031] B i =ECi A i

[0032] Among them, EC i is the entropy center, is the structural entropy, is the frequency entropy, i is the i-th coupling relationship unit,

[0033] ξ1 is the first weight coefficient, ξ2 is the second weight coefficient,

[0034] B i is the coupling loss, A i Unit variability.

[0035] Optionally, the structural entropy for:

[0036]

[0037] The frequency entropy for:

[0038]

[0039] Where M is the number of first-order neighbor nodes of the coupling relationship unit,

[0040] DC j is the degree of the jth node, DC k is the degree of the kth node, z ij is the influence of coupling relationship unit i on coupling relationship unit j, z ik is the influence of coupling relationship unit i on coupling relationship unit k.

[0041] Optionally, the method further includes:

[0042] The degradation and precision discrete probabilities of the coupling relationship units in the FRAM model are corrected by using a hierarchical analysis method to determine the output changes of the coupling relationship units.

[0043] On the other hand, the present invention also proposes a device failure analysis device based on a device function and hardware performance coupling mechanism, the device comprising:

[0044] A first processing module, configured to perform structural analysis and functional analysis on a target device to obtain a feature description, and determine a coupling relationship unit of the target device according to the feature description;

[0045] A second processing module, used for establishing a FRAM model according to the upstream and downstream relationship of the coupling relationship unit, and used for determining the coupling relationship between the function and the hardware performance of the target device;

[0046] A third processing module is used to determine the unit variability of the coupling relationship unit from two dimensions of hardware performance degradation and function output accuracy according to the hierarchical analysis method;

[0047] A fourth processing module, used for determining the coupling loss degree of the coupling relationship unit according to the unit variability, structural entropy and frequency entropy;

[0048] A fifth processing module is used to evaluate the failure risk of the target device according to the coupling loss degree.

[0049] Optionally, establishing a FRAM model according to the upstream and downstream relationship of the coupling relationship unit includes:

[0050] Determine the functional hexagon of the coupling relationship unit according to the feature description;

[0051] The functional hexagon connects the upstream unit and the downstream unit, and the output of the upstream unit is used as the feature description of the downstream unit;

[0052] A FRAM model is established based on the functional hexagons and their connected upstream and downstream units.

[0053] Optionally, the unit variability A of the coupling relationship unit i ,include:

[0054]

[0055] in, Score the degradation change, t∈{1,2,3,4},

[0056] Score the accuracy change, p∈{1,2,3},

[0057] is the relative weight of the degradation dimension,

[0058] is the relative weight of the precision dimension,

[0059] i is the i-th coupling relationship unit.

[0060] Optionally, the coupling loss degree of the coupling relationship unit is determined according to the unit variability, structural entropy and frequency entropy;

[0061]

[0062] B i =EC i A i

[0063] Among them, EC i is the entropy center, is the structural entropy, is the frequency entropy, i is the i-th coupling relationship unit,

[0064] ξ1 is the first weight coefficient, ξ2 is the second weight coefficient,

[0065] B i is the coupling loss, A i Unit variability.

[0066] On the other hand, the present invention also proposes a machine-readable storage medium, which stores instructions, which, when executed by a processor, configure the processor to execute the above-mentioned device failure analysis method based on the coupling mechanism of device function and hardware performance.

[0067] The device failure analysis method based on the coupling mechanism of device function and hardware performance of the present invention includes: performing structural analysis and functional analysis on the target device to obtain a feature description, determining the coupling relationship unit of the target device according to the feature description; establishing a FRAM model according to the upstream and downstream relationship of the coupling relationship unit, which is used to determine the coupling relationship between the function of the target device and the hardware performance; determining the unit variability of the coupling relationship unit from the two dimensions of hardware performance degradation and function output accuracy according to the hierarchical analysis method; determining the coupling loss degree of the coupling relationship unit according to the unit variability, structural entropy and frequency entropy; and evaluating the failure risk of the target device according to the coupling loss degree. The method takes the FRAM framework as the core, considers the degradability of the device system, analyzes the coupling variation relationship between the device function and the hardware performance, establishes a relationship model between the device function and the hardware performance, calculates the coupling loss degree based on the information entropy, combines the structural entropy and the frequency entropy, and quantifies the impact of hardware performance degradation on the device function. The method realizes effective failure risk assessment of different devices.

[0068] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0070] Figure 1 It is a flow chart of a device failure analysis method based on a device function and hardware performance coupling mechanism of the present invention;

[0071] Figure 2 It is a schematic diagram of the hexagonal characteristics of the coupling relationship unit of the present invention;

[0072] Figure 3 is a schematic diagram of a flow chart of Embodiment 2 of the present invention;

[0073] Figure 4 is a schematic diagram of coupling relationship unit change probability in embodiment 2 of the present invention;

[0074] Figure 5 is a schematic diagram of a coupling relationship model between equipment functions and hardware performance of a steam turbine according to an embodiment of the present invention;

[0075] Figure 6 It is a schematic diagram of a device failure analysis apparatus based on a device function and hardware performance coupling mechanism of the present invention.

[0076] Description of Reference Numerals

[0077] 100-Equipment failure analysis device based on the coupling mechanism of device function and hardware performance;

[0078] 200-first processing module;

[0079] 300-second processing module;

[0080] 400-third processing module;

[0081] 500-fourth processing module;

[0082] 600-Fifth processing module. DETAILED DESCRIPTION

[0083] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0084] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. In the embodiments of this application, some existing solutions in the industry such as certain software, components, and models may be mentioned, which should be considered as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0085] Embodiment 1

[0086] Figure 1 FIG. 1 is a flow chart of a device failure analysis method based on a device function and hardware performance coupling mechanism of the present invention. Figure 1 As shown, a method for assessing equipment failure risk of the present invention includes:

[0087] Step S101 is to perform structural analysis and functional analysis on a target device to obtain a feature description, and determine a coupling relationship unit of the target device according to the feature description.

[0088] Specifically, the feature description includes input description, output description, premise description, resource description, time description and control description; the input description is the thing or condition that starts the coupling relationship unit; the output description is the output processing result of the coupling relationship unit; the premise description is the necessary condition for the operation of the coupling relationship unit; the resource description is the material or information required or consumed during the operation of the coupling relationship unit; the time description is the time sequence constraint of the operation of the coupling relationship unit; and the control description is the monitoring and control method of the operation process of the coupling relationship unit.

[0089] According to a specific implementation method, the target device is subjected to structural and functional analysis to determine all functions and supporting structures required for the system operation, analyze the structural and functional relationships between the various levels of the device, describe the specific process of the normal operation of the system, and identify the coupling relationship unit. On this basis, the coupling relationship unit is characterized from six aspects: input I, output O, premise P, resource R, time T, and control C (i.e., input description, output description, premise description, resource description, time description, and control description). Among them, input I represents the thing or condition that starts the coupling relationship unit; output O represents the output processing result of the operation of the coupling relationship unit; premise P represents the necessary conditions for the operation of the coupling relationship unit, but cannot directly start the unit; resource R represents the materials or information required or consumed during the operation of the coupling relationship unit; time T represents the relevant time sequence constraints of the operation of the coupling relationship unit; control C represents the monitoring and control means of the operation process of the coupling relationship unit.

[0090] Step S102 is to establish a FRAM model according to the upstream and downstream relationship of the coupling relationship unit, so as to determine the coupling relationship between the function and the hardware performance of the target device. The FRAM is a functional resonance analysis method.

[0091] The coupling relationship unit is the basis of the FRAM framework. The structural relationship and functional relationship of the target device give in detail the transfer relationship of each level of the device structure to complete the given function. The hardware structure and system function of the device are defined as coupling relationship units, and the set of coupling relationship units is defined as F = {f1, f2, ..., f n}(F is the set of coupling relationship units, f i is the coupling relationship unit, and n is the number of hardware and device functions).

[0092] According to a specific implementation, establishing a FRAM model according to the upstream and downstream relationship of the coupling relationship unit includes: determining a functional hexagon of the coupling relationship unit according to the feature description; the functional hexagon connects an upstream unit and a downstream unit, and the output of the upstream unit serves as a feature description of the downstream unit; and establishing a FRAM model according to the functional hexagon and the upstream unit and downstream unit connected thereto.

[0093] Based on the identification and description of the coupling relationship units, the FRAM method is used to consider the upstream and downstream relationships of the coupling relationship units, establish a FRAM framework, express the potential coupling relationship between the coupling relationship units, and complete the establishment of the coupling relationship between the device function and the hardware performance.

[0094] Specifically, Figure 2 As shown, the coupling relationship unit uses a hexagonal graphical form to represent the six characteristics of the unit (capital letters are used to represent the corresponding functional unit characteristics). After the unit identification and description are completed, the FRAM framework is established to represent the potential coupling relationship between the units. For any two units f i and f j The coupling relationship between them is defined as l ij , and define the coupling set as L = {l ij |1≤i≤n, 1≤j≤n}, where L is the set of coupling relationships between units, l ij For unit f i and f j The FRAM framework is based on the premise that each unit represents the hexagonal image. The output of the upstream unit can be used as the input, resource, control, premise or time feature description of the downstream unit, and connect them. Assuming that unit i and unit j are directly connected by an edge, then l ij =1, otherwise l ij =0. After that, the connection relationship between all units is constructed, and the relationship model between the device function and the hardware performance based on FRAM is established. In the subsequent analysis process, the potential or actual coupling mode between the units is determined by the specific description of the unit characteristics. The established device function and hardware performance coupling relationship model can be expressed as:

[0095]

[0096] Among them, f i Represented as a coupling relationship unit, l ij Represented as any two units f i and f j The coupling relationship between ij Representation unit f i Leading to unit f jThe weight of the failure.

[0097] Step S103 is to determine the unit variability of the coupling relationship unit from two dimensions of hardware performance degradation and function output accuracy according to the hierarchical analysis method.

[0098] According to a specific implementation, the unit variability A of the coupling relationship unit i ,include:

[0099]

[0100] in, Score the degradation change, t∈{1,2,3,4}, Score the change in accuracy ( The coupling relationship unit f i Deterioration change score, The coupling relationship unit f i Output accuracy change score), p∈{1,2,3}, is the relative weight of the degradation dimension, is the relative weight of the precision dimension, and i is the i-th coupling relationship unit.

[0101] Specifically, during the operation of the device, considering factors such as hardware performance degradation and functional stability, the present invention quantitatively describes the coupling relationship unit from the two aspects of time and accuracy, and uses the Analytic Hierarchy Process (AHP) to correct the discrete probability of changes in time and accuracy of each coupling relationship unit.

[0102] The FRAM framework identifies and describes the output changes of the unit from the perspectives of time and accuracy, including premature, timely, late, and non-occurrence in terms of time, and accurate, acceptable, and inaccurate in terms of accuracy. During the operation of the equipment, the degradation of the hardware structure is a gradual process, including the intact quality state, the tolerable state, the affected state, and the fault state, which can correspond to the change description of the coupling relationship unit in the time dimension. The coupling relationship unit f i Deterioration change scoring Indicates that t∈{1,2,3,4} represents good quality, tolerable, affected and faulty. Coupling relationship unit f i Output accuracy change Indicates that p∈{1,2,3} represents exact, acceptable, and inexact.

[0103] In order to give full play to the role of FRAM in equipment fault analysis and evaluation, make the fault analysis results more in line with the actual operation of the equipment, and improve the pertinence and accuracy of equipment fault analysis and identification, the present invention adopts the Analytic Hierarchy Process (AHP) to correct the discrete probability of changes in degradation and accuracy of each FTAM unit, and characterize the possibility of different output changes in coupling relationship units. First, the importance of different factors is compared and assigned in the form of a judgment matrix. The scaling method of the judgment matrix is ​​shown in Table 1. Then calculate the relative weight, multiply each row element of the judgment matrix one by one, and calculate the nth root of the multiplication result according to the matrix order to obtain the corresponding eigenvector value. The eigenvector value of the degradation change dimension is expressed as

[0104]

[0105] Among them, a tj is the element in the tth row and jth column in the judgment matrix.

[0106] Table 1: Judgment matrix scale table

[0107] Scale value Scale value definition (comparison of two factors) 1 Both are equally important 3 The former is slightly more important than the latter 5 The former is obviously more important than the latter 7 The former is more important than the latter 9 The former is extremely more important than the latter 2，4，6，8 The middle value of the above adjacent scale values

[0108] Then the obtained eigenvector values ​​are normalized to obtain the relative weights of each change factor, expressed as:

[0109]

[0110] Finally, the variability A of the coupling relationship unit is calculated i , expressed as:

[0111]

[0112] in, is the relative weight of the degradation dimension, is the relative weight of the precision dimension. i The coupling relationship unit f i variability.

[0113] Step S104 is to determine the coupling loss degree of the coupling relationship unit according to the unit variability, structural entropy and frequency entropy.

[0114] According to a specific implementation manner, the coupling loss degree of the coupling relationship unit is determined according to the unit variability, structural entropy and frequency entropy;

[0115]

[0116] B i =EC iA i

[0117] Among them, EC i is the entropy center, is the structural entropy, is the frequency entropy, i is the i-th coupling relationship unit, ξ1 is the first weight coefficient, ξ2 is the second weight coefficient, B i is the coupling loss, A i Unit variability.

[0118] Specifically, the structural entropy for:

[0119]

[0120] The frequency entropy for:

[0121]

[0122] Where M is the number of first-order neighbor nodes of the coupling relationship unit,

[0123] DC j is the degree of the jth node, DC k is the degree of the kth node, z ij is the influence of coupling relationship unit i on coupling relationship unit j, z ik is the influence of coupling relationship unit i on coupling relationship unit k.

[0124] According to a specific implementation method, the present invention defines the degree of the coupling relationship unit, based on information entropy, evaluates the degree of the coupling relationship unit in the relationship model between device function and hardware performance from two dimensions of structural entropy and frequency entropy, quantitatively describes the units that may have coupling effects in functional changes, and calculates the coupling loss degree of the coupling relationship unit. Based on the upstream and downstream relationship of the coupling relationship unit, the degree of the node is defined as DC i :

[0125]

[0126] Among them, l ij Represents the coupling relationship unit f i With coupling relationship unit f j If the upstream coupling relationship unit is connected to the unit to be analyzed by a direct relationship, then l ij is 1, otherwise l ij is 0.

[0127] According to the topological characteristics of the network, structural entropy is used Evaluate a given coupling relationship unit f iThe influence or intensity of the position in the FRAM network on other coupling relationship units or the entire network is expressed as:

[0128]

[0129] Where M is the coupling relationship unit f i The number of first-order neighbor nodes.

[0130] Using the weight information contained in the coupling relationship units, the probability Z is used to represent the weight of the fault cause leading to the occurrence of the fault mode, and Z = {z ij |1≤i≤n,1≤j≤n} is used to represent the set of weights, indicating the influence of one coupling relationship unit on another coupling relationship unit. This paper adopts frequency entropy EC i f Describes the possible effectiveness of the propagation of a given coupling relationship unit. That is, the larger the weight, the greater the probability of mutual influence between coupling relationship units, expressed as:

[0131]

[0132] Furthermore, the coupling relationship unit f i The entropy center is set to EC i , which can be expressed as:

[0133]

[0134] Among them, ξ1 and ξ2 are the weight coefficients of the equation, and ξ1+ξ2=1 (ξ1 is the first weight coefficient, ξ2 is the second weight coefficient, and according to experience, ξ1 and ξ2 are set to 0.4 and 0.6). Under the conditions of this specific parameter set, the entropy-based centrality is better than the degree-based centrality and the path-based centrality.

[0135] Finally, the coupling relationship unit f i Entropy Center EC i and coupling relationship unit f i Unit variability A i , calculate the coupling relationship unit f i The coupling loss B i , quantifying the relationship between device functionality and hardware performance:

[0136]

[0137] in, The coupling relationship unit f i The structural entropy of The coupling relationship unit f i The frequency entropy of .

[0138] Step S105 is to evaluate the failure risk of the target device according to the coupling loss degree.

[0139] By quantifying the changes in each unit during the operation of the equipment and the transmission and coupling of changes between units, the possibility of unit coupling impact during the operation of the equipment is analyzed, the equipment hardware structure or fault propagation link that is prone to unit coupling impact is identified and determined, and effective preventive measures are proposed.

[0140] The present invention establishes a relationship model between device functions and hardware performance, and uses FRAM as a framework to quantify the variability of coupling relationship units and the coupling loss of coupling relationship units, thereby completing the device failure analysis work including potential fault identification and risk quantification. In addition, the present invention takes into account the deterioration of the device system, analyzes the coupling variation relationship between device functions and hardware performance, and establishes a relationship model between device functions and hardware performance. Starting from information entropy, the coupling loss degree is calculated in combination with structural entropy and frequency entropy, and the impact of hardware performance degradation on device functions is quantified. The present invention has a certain degree of openness and practicality in practical applications, and is also applicable to the fault analysis entropy of different devices.

[0141] Embodiment 2

[0142] This embodiment is aimed at a certain steam turbine equipment, focuses on the typical functions and hardware structures of the steam turbine body system, water delivery system and lubricating oil system of the steam turbine equipment, and performs fault analysis, as shown in Table 2.

[0143] Table 2: Failure analysis

[0144]

[0145] like Figure 3 As shown, for this embodiment, the present invention performs the following steps to evaluate the fault:

[0146] Step 1: Identify and describe the coupling relationship units, conduct structural and functional analysis on the steam turbine equipment, and according to Table 2 above, determine that the function of the steam turbine body system is to convert the thermal energy of steam into mechanical energy, the function of the water supply system is to remove water accumulation, prevent water shock, and protect the blades, and the function of the lubricating oil system is lubrication, cooling, and cleaning. The typical hardware structure of the steam turbine body is the rotor, radial bearing, thrust bearing, bearing, and cylinder. The typical hardware structure of the water supply system is the manual drain valve and the air-controlled drain valve. The typical hardware structure of the lubrication system is the main oil tank, oil filter, and oil cooler. Define the coupling relationship units f1-f 13 They represent the turbine body, water delivery system, lubrication system and typical hardware structures respectively. On this basis, each coupling relationship unit is characterized from six aspects: input I, output O, premise P, resource R, time T and control C (such as Figure 4 shown).

[0147] Step 2: Establish a relationship model between device functions and hardware performance: Figure 5 As shown, based on the identification and description of coupling relationship units, the FRAM method is used to consider the upstream and downstream relationships of the coupling relationship units, and a FRAM model is established to represent the potential coupling correlation between the coupling relationship units, thereby completing the establishment of the relationship between device functions and hardware performance.

[0148] Step 3: Quantitative analysis of the variability of the coupling relationship unit: During the operation of the equipment, the coupling relationship unit is quantitatively described from the aspects of time and precision, taking into account factors such as hardware performance degradation and functional stability. The analytic hierarchy process is used to correct the discrete probability of each coupling relationship unit changing in terms of time and precision. Considering that the hardware structure will deteriorate over time and the hardware performance will decrease accordingly, the probability of change in the time dimension of the coupling relationship unit is evaluated from the four stages of quality integrity, tolerance, impact and failure. The probability of change of the coupling relationship unit is shown in Table 3. The variability of the coupling relationship unit is obtained by combining the formulas f4 and f4. 11 The high degree of variability indicates that attention should be paid to the hardware performance changes of the rotor and the oil tank. When the system operates normally, the hardware structure corresponding to the above-mentioned coupling relationship unit is prone to failure, resulting in abnormal equipment function.

[0149] Table 3: Coupling relationship units

[0150]

[0151] Table 4: Coupling relationship unit variability

[0152] Coupling relationship unit f1 f2 f3 f4 f5 f6 f7 Mutability 2.9625 2.9022 2.9464 3.5337 3.0462 3.0501 3.1963 Coupling relationship unit f8 f9 f10 f11 f12 f13 Variability 3.0475 3.0712 3.0434 3.4886 3.1273 3.1372

[0153] Table 5: Coupling relationship unit loss

[0154]

[0155]

[0156] Step 4: Quantitative analysis of coupling loss of coupling relationship units: Based on information entropy, the structural entropy and frequency entropy of each coupling relationship unit are calculated to quantitatively describe the units that may be affected by coupling in functional changes, and the coupling loss of coupling relationship units is calculated. As shown in Tables 3-5, the coupling relationship units f4 and f 11 The coupling loss degree of the above units is much greater than that of other coupling relationship units, which means that the hardware structure corresponding to the above units is prone to coupling failure during the operation of the equipment, which has a great impact on the operation of the equipment and is prone to cause the function transmission link to break, affecting the function of the equipment.

[0157] Step 5: Analyze the risk of equipment failure: According to the quantitative transmission and coupling of the changes of each unit and the changes between units during the operation of the equipment, it is found that the coupling relationship unit f4 and the coupling relationship unit f 11 Coupling is very likely to occur. The rotor is prone to bending failure, which will cause the turbine bearing to vibrate with greater intensity. In the early stage, the radial seal gap of the turbine will be worn out, and the unit economy will be reduced; further development will cause the bearing to be dislodged and damaged, the shaft and blades to crack or even break, causing damage to the blades and partitions, bending of the shaft and other serious accidents; eventually, the turbine vibration will be as large as the tripping value, causing the turbine to function abnormally. The inspection frequency of the rotor and the accuracy of online monitoring should be improved, and preventive measures should be proposed to reduce the impact of hardware performance degradation on equipment functions. The main oil tank is prone to oil leakage, and then the lubricating oil cannot be stored, and the normal oil level of the main oil tank cannot be guaranteed, triggering a low oil level alarm. In severe cases, it causes bearing wear, oil failure and burning of bearings, causing abnormal functions of the turbine. The monitoring frequency of the main oil tank oil level should be increased, and preventive measures should be proposed in time to reduce the impact of hardware performance degradation on equipment functions.

[0158] According to the above method, on-site staff can comprehensively analyze the equipment failure and accurately locate the hardware failure cause that causes the equipment malfunction. According to the quantitative analysis results given by the method, appropriate measures can be selected to take preventive measures for possible equipment malfunction to ensure that the equipment operates under safe and stable conditions.

[0159] Embodiment 3

[0160] like Figure 6 As shown, the present invention also proposes a device failure analysis device 100 based on the device function and hardware performance coupling mechanism, the device comprising: a first processing module 200, used to perform structural analysis and functional analysis on the target device to obtain a feature description, and determine the coupling relationship unit of the target device according to the feature description; a second processing module 300, used to establish a FRAM model according to the upstream and downstream relationship of the coupling relationship unit, and used to determine the coupling relationship between the function and the hardware performance of the target device; a third processing module 400, used to determine the unit variability of the coupling relationship unit from two dimensions of hardware performance degradation and functional output accuracy according to the hierarchical analysis method; a fourth processing module 500, used to determine the coupling loss degree of the coupling relationship unit according to the unit variability, structural entropy and frequency entropy; a fifth processing module 600, used to evaluate the failure risk of the target device according to the coupling loss degree.

[0161] Specifically, the establishing of the FRAM model according to the upstream and downstream relationship of the coupling relationship unit includes: determining a functional hexagon of the coupling relationship unit according to the feature description; the functional hexagon connects an upstream unit and a downstream unit, and the output of the upstream unit serves as a feature description of the downstream unit; and establishing the FRAM model according to the functional hexagon and the upstream unit and downstream unit connected thereto.

[0162] The unit variability A of the coupling relationship unit i ,include:

[0163]

[0164] in, Score the degradation change, t∈{1,2,3,4}, Score the accuracy change, p∈{1,2,3}, is the relative weight of the degradation dimension, is the relative weight of the precision dimension, and i is the i-th coupling relationship unit.

[0165] Determining the coupling loss degree of the coupling relationship unit according to the unit variability, structural entropy and frequency entropy;

[0166]

[0167] B i =EC i A i

[0168] Among them, EC i is the entropy center, is the structural entropy, is the frequency entropy, i is the i-th coupling relationship unit, ξ1 is the first weight coefficient, ξ2 is the second weight coefficient, B i is the coupling loss, A i Unit variability.

[0169] The device takes the FRAM framework as the core, considers the degradation of the equipment system, analyzes the coupling variation relationship between equipment function and hardware performance, establishes a relationship model between equipment function and hardware performance, and calculates the coupling loss degree based on information entropy, combining structural entropy and frequency entropy, and quantifies the impact of hardware performance degradation on equipment function. This method realizes effective fault risk assessment of different equipment.

[0170] The device failure analysis method based on the coupling mechanism of device function and hardware performance of the present invention includes: performing structural analysis and functional analysis on the target device to obtain a feature description, determining the coupling relationship unit of the target device according to the feature description; establishing a FRAM model according to the upstream and downstream relationship of the coupling relationship unit, which is used to determine the coupling relationship between the function of the target device and the hardware performance; determining the unit variability of the coupling relationship unit from the two dimensions of hardware performance degradation and function output accuracy according to the hierarchical analysis method; determining the coupling loss degree of the coupling relationship unit according to the unit variability, structural entropy and frequency entropy; and evaluating the failure risk of the target device according to the coupling loss degree. The method takes the FRAM framework as the core, considers the degradability of the device system, analyzes the coupling variation relationship between the device function and the hardware performance, establishes a relationship model between the device function and the hardware performance, calculates the coupling loss degree based on the information entropy, combines the structural entropy and the frequency entropy, and quantifies the impact of hardware performance degradation on the device function. The method realizes effective failure risk assessment of different devices.

[0171] On the other hand, an embodiment of the present invention provides a storage medium on which a program is stored. When the program is executed by a processor, the device failure analysis method based on the device function and hardware performance coupling mechanism is implemented.

[0172] An embodiment of the present invention provides a processor, which is used to run a program, wherein the device failure analysis method based on the device function and hardware performance coupling mechanism is executed when the program is running.

[0173] The embodiment of the present invention provides a device, the device includes a processor, a memory and a program stored in the memory and can be run on the processor, and the processor implements the following steps when executing the program: structural analysis and functional analysis of the target device are performed to obtain a feature description, and the coupling relationship unit of the target device is determined according to the feature description; a FRAM model is established according to the upstream and downstream relationship of the coupling relationship unit to determine the coupling relationship between the function and the hardware performance of the target device; according to the hierarchical analysis method, the unit variability of the coupling relationship unit is determined from the two dimensions of hardware performance degradation and function output accuracy; the coupling loss degree of the coupling relationship unit is determined according to the unit variability, structural entropy and frequency entropy; and the failure risk of the target device is evaluated according to the coupling loss degree. The device in this article can be a server, PC, PAD, mobile phone, etc.

[0174] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that is initialized with the following method steps: performing structural analysis and functional analysis on a target device to obtain a feature description, and determining a coupling relationship unit of the target device based on the feature description; establishing a FRAM model based on the upstream and downstream relationship of the coupling relationship unit to determine the coupling relationship between the function and hardware performance of the target device; determining the unit variability of the coupling relationship unit from two dimensions of hardware performance degradation and functional output accuracy according to the hierarchical analysis method; determining the coupling loss degree of the coupling relationship unit based on the unit variability, structural entropy and frequency entropy; and evaluating the failure risk of the target device based on the coupling loss degree.

[0175] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0176] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0177] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0178] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0179] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0180] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0181] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0182] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0183] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A device failure analysis method based on the coupling mechanism of device function and hardware performance, characterized in that: The method includes: Performing structural analysis and functional analysis on the target device to obtain a feature description, and determining a coupling relationship unit of the target device according to the feature description; Establishing a FRAM model according to the upstream and downstream relationship of the coupling relationship unit, so as to determine the coupling relationship between the function and the hardware performance of the target device; According to the hierarchical analysis method, the unit variability of the coupling relationship unit is determined from two dimensions: hardware performance degradation and function output accuracy; Determining the coupling loss degree of the coupling relationship unit according to the unit variability, structural entropy and frequency entropy; The failure risk of the target device is evaluated according to the coupling loss degree.

2. The method according to claim 1, characterized in that The feature description includes input description, output description, premise description, resource description, time description and control description; The input is described as something or a condition that initiates the coupling relationship unit; The output is described as the output processing result of the operation of the coupling relationship unit; The premise description is a necessary condition for the operation of the coupling relationship unit; The resource description is the material or information required or consumed during the operation of the coupling relationship unit; The time description is a time constraint for the operation of the coupling relationship units; The control description is a method of monitoring and controlling the operation process of the coupling relationship unit.

3. The method according to claim 1, characterized in that The establishing of the FRAM model according to the upstream and downstream relationship of the coupling relationship unit includes: Determine the functional hexagon of the coupling relationship unit according to the feature description; The functional hexagon connects the upstream unit and the downstream unit, and the output of the upstream unit is used as the feature description of the downstream unit; A FRAM model is established based on the functional hexagons and their connected upstream and downstream units.

4. The method according to claim 1, characterized in that: Unit variability A of the coupling relationship unit i ,include: in, Score the degradation change, t∈{1,2,3,4}, Score the accuracy change, [∈{1,2,3}, is the relative weight of the degradation dimension, is the relative weight of the precision dimension, i is the i-th coupling relationship unit.

5. The method according to claim 1, characterized in that Determining the coupling loss degree of the coupling relationship unit according to the unit variability, structural entropy and frequency entropy; B i =EC i A i Among them, EC i is the entropy center, is the structural entropy, is the frequency entropy, i is the i-th coupling relationship unit, ξ1 is the first weight coefficient, ξ2 is the second weight coefficient, B i is the coupling loss, A i Unit variability.

6. The method according to claim 5, characterized in that The structural entropy for: The frequency entropy for: Where M is the number of first-order neighbor nodes of the coupling relationship unit, DC j is the degree of the jth node, DC k is the degree of the kth node, z ij is the influence of coupling relationship unit i on coupling relationship unit j, z ik is the influence of coupling relationship unit i on coupling relationship unit k.

7. The method according to claim 1, characterized in that The method further includes: The degradation and precision discrete probabilities of the coupling relationship units in the FRAM model are corrected by using a hierarchical analysis method to determine the output changes of the coupling relationship units.

8. A device failure analysis device based on the coupling mechanism of device function and hardware performance, characterized in that: The device includes: A first processing module, configured to perform structural analysis and functional analysis on a target device to obtain a feature description, and determine a coupling relationship unit of the target device according to the feature description; A second processing module, used for establishing a FRAM model according to the upstream and downstream relationship of the coupling relationship unit, and used for determining the coupling relationship between the function and the hardware performance of the target device; A third processing module is used to determine the unit variability of the coupling relationship unit from two dimensions of hardware performance degradation and function output accuracy according to the hierarchical analysis method; A fourth processing module, used for determining the coupling loss degree of the coupling relationship unit according to the unit variability, structural entropy and frequency entropy; A fifth processing module is used to evaluate the failure risk of the target device according to the coupling loss degree.

9. The device according to claim 8, characterized in that The establishing of the FRAM model according to the upstream and downstream relationship of the coupling relationship unit includes: Determine the functional hexagon of the coupling relationship unit according to the feature description; The functional hexagon connects the upstream unit and the downstream unit, and the output of the upstream unit is used as the feature description of the downstream unit; A FRAM model is established based on the functional hexagons and their connected upstream and downstream units.

10. The device according to claim 8, characterized in that Unit variability A of the coupling relationship unit i ,include: in, Score the degradation change, t∈{1,2,3,4}, Score the accuracy change, p∈{1,2,3}, is the relative weight of the degradation dimension, is the relative weight of the precision dimension, i is the i-th coupling relationship unit.

11. The device according to claim 8, characterized in that Determining the coupling loss degree of the coupling relationship unit according to the unit variability, structural entropy and frequency entropy; B i =EC i A i Among them, EC i is the entropy center, is the structural entropy, is the frequency entropy, i is the i-th coupling relationship unit, ξ1 is the first weight coefficient, ξ2 is the second weight coefficient, B i is the coupling loss, A i Unit variability.

12. A machine-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor is configured to execute the device failure analysis method based on the device function and hardware performance coupling mechanism described in any one of claims 1 to 7.

Images