FL-AHP-based system-level equipment health state assessment method, apparatus and device, and medium

Abstract

The invention discloses an FL-AHP-based system-level equipment health state assessment method, device and equipment and a medium, and relates to the field of equipment health state assessment, and the method comprises the steps: dividing system-level equipment into a plurality of levels; quantitatively calculating the health index of each evaluation index based on the monitoring parameter of each evaluation index; the FL-AHP algorithm is adopted to correct the preset weight of each level; calculating the health index of the system-level equipment according to the hierarchy based on the health index of each evaluation index and the corrected weight; and evaluating the health state of the system-level equipment according to the health index of the system-level equipment. According to the invention, the accuracy of equipment health state evaluation can be improved, and support is provided for system-level equipment maintenance guarantee.

Description

TECHNICAL FIELD

[0001] The application relates to the field of equipment health state evaluation, in particular to a system-level equipment health state evaluation method and device based on FL-AHP, equipment and medium. BACKGROUND

[0002] With a large number of high-tech equipment being deployed in the army, the equipment maintenance and support task is becoming more and more heavy. Based on the state maintenance, the traditional time and distance maintenance is gradually replaced by the state maintenance, which becomes the mainstream idea of equipment maintenance and support, because the state maintenance can solve the problem of long maintenance period of new equipment. The equipment health state evaluation and fault prediction are the keys to realize the state maintenance, so in order to ensure the normal operation of the equipment and improve the maintenance efficiency of the equipment, the equipment health state evaluation gradually becomes a research hotspot.

[0003] The health state of equipment refers to the ability of the equipment to maintain a certain level of reliability and maintainability and stably and continuously complete the predetermined function within a specified time and under specified conditions. The equipment health state evaluation is an important function of the Prognostics and Health Management (PHM) system, and correct evaluation of the health state of the equipment can not only provide a basis for fault prediction and maintenance decision of the equipment, but also provide technical support for accurate maintenance of the equipment. The equipment health degree analysis is a key link to ensure the long-term stable operation of the equipment. Through monitoring and evaluating the running state of the equipment, the fault can be prevented, the downtime can be reduced, and the service life of the equipment can be prolonged. This analysis usually involves data collection, state monitoring, fault diagnosis and predictive maintenance strategy making. It is of great significance to improve production efficiency, reduce maintenance cost and ensure personnel safety.

[0004] The analytic hierarchy process (AHP) is an evaluation method combining qualitative analysis and quantitative analysis, which is proposed by Saaty in the early 1970s. The complex system is defined as an ordered structure with progressive hierarchical relationship, the different evaluation indexes are set in the same level, the authoritative experts are invited to score and construct the judgment matrix, then the consistency of the constructed matrix is checked, and the column vector summation method is used to obtain the weight of each evaluation index, so that the subjective factors are reduced, and the evaluation result is more objective and scientific. However, due to the different professional backgrounds and research directions of the experts, the judgment matrix constructed by the experts inevitably has subjectivity, so that the evaluation of the overall system health state inevitably has errors. SUMMARY

[0005] The application aims to provide a system-level equipment health state evaluation method and device based on FL-AHP, equipment and medium, which can improve the accuracy of the equipment health state evaluation and provide support for the system-level equipment maintenance and support.

[0006] To achieve the above object, the application provides the following scheme.

[0007] In a first aspect, the application provides a system-level equipment health state evaluation method based on FL-AHP, comprising:

[0008] dividing the system-level equipment into multiple levels; the levels include a component level, a subsystem level and a system level; the component level includes multiple evaluation indexes;

[0009] quantitatively calculating health indexes of the evaluation indexes based on monitoring parameters of the evaluation indexes;

[0010] correcting weights of the levels preset in advance by using an FL-AHP algorithm; the weights include weights of the evaluation indexes, weights of the components and weights of the subsystems;

[0011] calculating health indexes of the system-level equipment according to the levels based on the health indexes of the evaluation indexes and the corrected weights;

[0012] evaluating a health state of the system-level equipment according to the health indexes of the system-level equipment.

[0013] In a second aspect, the application provides a system-level equipment health state evaluation device based on FL-AHP, comprising:

[0014] a level division module, configured to divide the system-level equipment into multiple levels; the levels include a component level, a subsystem level and a system level; the component level includes multiple evaluation indexes;

[0015] an evaluation index health index calculation module, configured to quantitatively calculate health indexes of the evaluation indexes based on monitoring parameters of the evaluation indexes;

[0016] a weight correction module, configured to correct weights of the levels preset in advance by using an FL-AHP algorithm; the weights include weights of the evaluation indexes, weights of the components and weights of the subsystems;

[0017] a system-level equipment health index calculation module, configured to calculate health indexes of the system-level equipment according to the levels based on the health indexes of the evaluation indexes and the corrected weights;

[0018] a health state evaluation module, configured to evaluate a health state of the system-level equipment according to the health indexes of the system-level equipment.

[0019] In a third aspect, the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the FL-AHP-based system-level equipment health state evaluation method.

[0020] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the FL-AHP-based system-level equipment health state evaluation method.

[0021] According to the specific embodiments provided in the present application, the present application has the following technical effects:

[0022] The present application provides a FL-AHP-based system-level equipment health state evaluation method, device, equipment and medium, by splitting the overall system-level equipment by level, and using FL-AHP (Fuzzy-Lagrange Analytic Hierarchy Process) to correct the weights of each level set in advance, so as to solve the problem of inevitable subjectivity in the constructed judgment matrix due to the different professional backgrounds and research directions of each expert in the prior art, and make the final system-level equipment state evaluation result more accurate. BRIEF DESCRIPTION OF DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0024] Figure 1 The flowchart of the FL-AHP-based system-level equipment health state evaluation method provided by an embodiment of the present application is shown in the figure.

[0025] Figure 2 The hierarchical division diagram for system-level equipment is shown in the figure.

[0026] Figure 3 The structural diagram of a computer device provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0027] With reference to the accompanying drawings, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative effort belong to the scope of the present application.

[0028] The overall performance prediction of system-level equipment can grasp the operation state of the complex system-level equipment as a whole, understand the development trend of the system-level equipment failure in time, and perform preventive maintenance at the moment when the failure may occur, thereby providing a basis for system-level equipment maintenance decision. At present, the failure prediction is mainly for the key core components of the system-level equipment, and the performance decline trend of the system-level equipment is less studied. In view of this, the health state evaluation and failure prediction of the system-level equipment are researched, and a health state evaluation and failure prediction system of the system-level equipment is developed, so as to provide support for the maintenance support of the system-level equipment.

[0029] In order to make the above objectives, characteristics and advantages of the present application more obvious and easy to understand, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0030] In one exemplary embodiment, as shown in Figure 1 a FL-AHP-based health state evaluation method of system-level equipment is provided, which is executed by a computer device, specifically, can be executed by a terminal or a server, or can be executed by a terminal and a server together. In the embodiments of the present application, the method is taken as an example applied to a server, and includes the following steps S1 to S5. Wherein:

[0031] S1: dividing the system-level equipment into multiple levels; the levels include a component level, a subsystem level and a system level; the component level includes multiple evaluation indexes.

[0032] In a specific embodiment, an unmanned cluster system for a maritime search and rescue task is taken as a research object, as shown in Figure 2 which is composed of an unmanned aerial vehicle subsystem, an unmanned boat subsystem and an unmanned underwater vehicle subsystem. Wherein: the unmanned aerial vehicle subsystem includes a flight platform, a radar system and a communication system; the unmanned boat subsystem includes an autonomous control system, an optical / electronic camera, a communication system; and the unmanned underwater vehicle subsystem includes an underwater propulsion system, a sonar system and a navigation system. The component level is regarded as level 1, the subsystem level is regarded as level 2, and the system level is regarded as the target level.

[0033] Each component in the component layer includes a plurality of evaluation indexes. For example, the flight platform includes seven evaluation indexes, i.e., maximum take-off weight Z1, maximum flight distance Z2, flight speed Z3, flight height Z4, flight time Z5, wind resistance Z6, and hovering accuracy Z7.

[0034] According to the importance of the subsystems, components and evaluation indexes of the system-level equipment, each level has different weights, and the sum of the weights of the levels is 1.

[0035] S2: quantitatively calculate the health index of each evaluation index based on the monitoring parameters of each evaluation index.

[0036] There are three cases for the monitoring judgment threshold of the monitoring parameters of each evaluation index:

[0037] ① the case of upper and lower boundary threshold constraints [x min ,x max ].

[0038] ② the case of upper boundary threshold constraints [x0,x max ].

[0039] ③ the case of lower boundary threshold constraints [x min ,x1].

[0040] If the monitoring parameter is outside the boundary threshold constraint, it is considered that there is a fault. Wherein, x min , x max are the lower boundary and the upper boundary of the monitoring parameter when declaring a fault, and x0 and x1 are the expected values of the monitoring parameter when the system is normally running.

[0041] For the above three cases, different health index calculation methods are proposed, as follows.

[0042] For case ①, generally, the power function evaluation algorithm is:

[0043]

[0044] For case ②, the power function evaluation algorithm is:

[0045]

[0046] For case ③, the power function evaluation algorithm is:

[0047]

[0048] Wherein, H scbHealth index of the bth evaluation index of the cth component of the st subsystem, x is a monitoring parameter of the evaluation index, μ is a median of the upper and lower boundaries of the monitoring parameter, δ is half of the allowable deviation of the monitoring parameter, the size of re reflects the relationship between the monitoring parameter and the system health status, re = 1 indicates that a linear evaluation algorithm is adopted.

[0049] S3: adopting the FL-AHP algorithm to correct the weights of each level preset, and the weights include the weights of each evaluation index, the weights of each component and the weights of each subsystem.

[0050] In order to fully express the fuzziness and subjectivity in the expert judgment process and the consistency optimization between multi-source judgment results, on the basis of the traditional AHP, the present application combines fuzzy logic and Lagrange optimization, and proposes a fuzzy-Lagrange analytic hierarchy process (Fuzzy-Lagrange Analytic Hierarchy Process, FL-AHP) for weight correction and fusion. The FL-AHP algorithm includes four stages of fuzzy judgment modeling, fuzzy weight calculation, de-fuzzification conversion and Lagrange weighted optimization. Taking the weight of the evaluation index as an example, the specific process of the FL-AHP algorithm is as follows:

[0051] S31: constructing a fuzzy judgment matrix.

[0052] Supposing that the evaluation indexes are C = {C1, C2,..., Cn}, all the evaluation indexes are compared by p experts respectively. The expert judgment is expressed by triangular fuzzy numbers (Triangular Fuzzy Number, TFN), and is defined as follows: n

[0053]

[0054] Among them:

[0055] The minimum possible scale value of the kth expert for the evaluation index i relative to the evaluation index j;

[0056] The most possible scale value of the kth expert for the evaluation index i relative to the evaluation index j;

[0057] The maximum possible scale value of the kth expert for the evaluation index i relative to the evaluation index j.

[0058] Meanwhile, the reciprocal symmetry condition is met:

[0059]

[0060] The fuzzy judgment matrix of the kth expert is constructed as follows: ​

[0061]

[0062] The correspondence between the commonly used judgment semantics and the triangular fuzzy numbers in the standard fuzzy scale system is shown in Table 1.

[0063] Table 1

[0064] Scale Triangular fuzzy number (TFN) Meaning 1 (1,1,1) Evaluation index i is equally important compared to evaluation index j 3 (2,3,4) Evaluation index i is slightly more important than evaluation index j 5 (4,5,6) Evaluation index i is significantly more important than evaluation index j 7 (6,7,8) Evaluation index i is strongly more important than evaluation index j 9 (8,9,9) Evaluation index i is extremely more important than evaluation index j

[0065] If the judgment semantics falls in the middle value (such as "between slightly and obviously"), the fuzzy number can be constructed using interpolation means, for example, (3, 4, 5).

[0066] S32: The fuzzy judgment matrix is processed using the fuzzy geometric mean method to obtain the fuzzy weight.

[0067] In the fuzzy AHP, the fuzzy geometric mean method is used to process the fuzzy judgment matrix. This method can preserve the characteristics of the fuzzy numbers and realize the fuzzy fidelity transmission in the weight calculation process.

[0068] Let the fuzzy judgment matrix of the kth expert be Then, the fuzzy geometric mean value of each evaluation index i is calculated by row:

[0069]

[0070] wherein:

[0071] are the lower limit, the median, and the upper limit of the triangular fuzzy number , respectively.

[0072] The geometric mean operation is to maintain the proportion consistency of the pair-wise comparison matrix, which meets the principle of "multiplicative transitivity" in the AHP theory.

[0073] The obtained in the previous step is normalized to obtain the normalized fuzzy weight:

[0074]

[0075] The denominators of the normalization are respectively combined with the upper and lower values of other fuzzy numbers to maintain the envelope of the fuzzy range; the final weight of each evaluation index is still a triangular fuzzy number; the normalization ensures that the sum of the fuzzy weights of each evaluation index is 1 in the "fuzzy sense".

[0076] For each expert k, the fuzzy weight is output:

[0077]

[0078] S33: Defuzzification is performed on the fuzzy weight using a defuzzification algorithm to obtain a clear weight.

[0079] The fuzzy weight calculated in S32 is converted into a clear weight. Although the fuzzy weight can express the uncertainty of the judgment, subsequent operations such as weight fusion and optimal combination need to be performed in the real number domain, so a defuzzification algorithm must be introduced to convert the fuzzy number.

[0080] Each fuzzy weight is a triangular fuzzy number:

[0081]

[0082] wherein: is the lowest possible weight value; is the most possible weight value; is the highest possible weight value.

[0083] To map the triangular fuzzy number to a single real value, the commonly used methods include: center method (Center of Gravity), maximum membership principle method (Max Membership Principle), right end method, and left end method (Right / Left Endpoint).

[0084] In this application, the center method (also known as the center of gravity method, center of gravity average method) is used for defuzzification.

[0085] For each fuzzy weight its corresponding clear value is:

[0086]

[0087] After calculation, the clear weight vector of the expert k can be obtained:

[0088]

[0089] Each element is a standard real number, satisfying the positive number property and the relative comparison property.

[0090] To ensure that the weight sum is 1, the result can be normalized:

[0091]

[0092] This processing can be determined according to the situation. If the fuzzy weight has been fully normalized in step S32, this step can be omitted. After completing this step, the clear weight set of all experts is obtained:

[0093] {w (1) ,w(2) ..., w (m)}

[0094] Each weight w (k) has a dimension of n.

[0095] S34: The clear weight is optimized by using the Lagrange multiplier method to obtain the modified weight.

[0096] The clear weight provided by multiple experts in the previous step is fused into a final unified weight for subsequent evaluation modeling of the entire system. Since there are certain differences in the importance of each evaluation index by different experts, direct averaging may cause deviation or loss of overall consistency. Therefore, the Lagrange multiplier method is introduced in this step to obtain a combined weight that is "most representative and has the smallest deviation" for all expert judgments by constructing a weighted least deviation optimization model. Assume: n: the number of evaluation indexes; p: the number of experts; the clear weight of the kth expert: The optimal combined weight to be solved: w = [w1, w2,..., wn] n ] T .

[0097] It is desired that the mean square distance of w and all w (k) is the smallest, while satisfying:

[0098] Define the objective function as the sum of the deviations of each expert's weight and the combination:

[0099]

[0100] Introduce the Lagrange multiplier λ to construct the Lagrange function:

[0101]

[0102] Take the partial derivative of each w i and set it to zero:

[0103]

[0104] Take the partial derivative of λ to get the constraint condition:

[0105]

[0106] Organize it into a linear equation system:

[0107]

[0108] Solve λ by simultaneously solving all i = 1,...,n and the constraint condition Σw i = 1, and then obtain the final wi .

[0109] The final output is the unified weight:

[0110] w final = [w1, w2, …, w n ] T .

[0111] w final , which is the corrected weight.

[0112] S4: Calculate the health index of the system-level equipment based on the health index of each evaluation index and the corrected weight. Specifically, it includes: calculating the health index of each component in the component layer based on the health index of each evaluation index and the corrected weight of each evaluation index; calculating the health index of each subsystem in the subsystem layer based on the health index of each component and the corrected weight of each component; calculating the health index of the system layer based on the health index of each subsystem and the corrected weight of each subsystem, and obtaining the health index of the system-level equipment.

[0113] Assuming that the health index of the bth evaluation index of the cth component of the st subsystem is H scb , and the weight is ω scb , then the health index of the cth component is:

[0114]

[0115] The health index of the st subsystem is:

[0116]

[0117] Finally, the health index of the system-level equipment is:

[0118]

[0119] That is, the health index of the system-level equipment is:

[0120]

[0121] The health index of each evaluation index of the flight platform and the health index of the flight platform calculated by the above method are shown in Tables 2-3.

[0122] Table 2

[0123]

[0124] Table 3

[0125]

[0126]

[0127] According to the health index of each component and the weight of each component, the health index of the system is calculated step by step, as shown in Table 4 below.

[0128] Table 4

[0129]

[0130] S5: According to the health index of the system-level equipment, the health status of the system-level equipment is evaluated.

[0131] Due to the influence of factors including but not limited to the aging of the equipment itself, environmental factors, etc., the health status of the equipment system and related equipment will become more and more deteriorated. In the process of daily use, the system is difficult to achieve the most ideal state, but also not deteriorated to the worst expected state, and generally will be in an "intermediate state", which is quantified according to the degree of deviation from the expected state in this application, and the health index H(t) with the scoring concept is used to represent the state of the system. The health index is specified as 0-100, when H(t) is 100, it indicates that the system is in the expected state; H(t) is between 60 and 100, which indicates that the system currently has defects in performance, but can still be used; H(t) is less than 60, which indicates that the system cannot complete its functions and is difficult to continue to work, and is in a failure state. In other words, the higher H(t) represents the more "healthy" system, which can better complete its own work and has higher fault tolerance when dealing with harsh environments. Table 5 shows the correspondence between the health state classification and the health index.

[0132] Table 5

[0133] Serial number Health index H(t) Health status definition 1 80～100 Healthy 2 70～80 Sub-healthy 3 60～70 Approaching failure 4 <60 Failure

[0134] According to Table 5, it can be concluded that the unmanned cluster system for maritime search and rescue tasks is still in a healthy state, but needs to be maintained at all times to delay the time of entering the sub-health state as much as possible.

[0135] The present application integrates the parameters and performance requirements of multiple subsystems to predict the overall performance of the system level, rather than focusing on a single component. This method makes the overall performance of the equipment in actual operation be fully reflected. It can comprehensively consider the synergistic effect between each subsystem, thereby improving the accuracy and reliability of the prediction. Moreover, the FL-AHP algorithm is used to correct the weights of each level set in advance, so that the final system-level equipment state evaluation result is more accurate.

[0136] Based on the same inventive concept, the embodiments of the present application also provide a FL-AHP-based system-level equipment health state evaluation device. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme described in the above method, so the specific limitations in one or more FL-AHP-based system-level equipment health state evaluation device embodiments provided below can refer to the limitations of the FL-AHP-based system-level equipment health state evaluation method described above, and will not be repeated here.

[0137] In an exemplary embodiment, a FL-AHP-based system-level equipment health state evaluation device is provided, comprising:

[0138] a hierarchical division module configured to divide the system-level equipment into multiple hierarchies; the hierarchies include a component hierarchy, a subsystem hierarchy, and a system hierarchy; the component hierarchy includes multiple evaluation indexes.

[0139] an evaluation index health index calculation module configured to quantitatively calculate the health index of each evaluation index based on the monitoring parameters of each evaluation index.

[0140] a weight correction module configured to correct the pre-set weights of each hierarchy by using the FL-AHP algorithm; the weights include the weights of each evaluation index, the weights of each component, and the weights of each subsystem.

[0141] a system-level equipment health index calculation module configured to calculate the health index of the system-level equipment based on the health index of each evaluation index and the corrected weights according to the hierarchy.

[0142] a health state evaluation module configured to evaluate the health state of the system-level equipment according to the health index of the system-level equipment.

[0143] In an exemplary embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps in the above method embodiments when executing the computer program. The computer device can be a server or a terminal, and its internal structure diagram can be as follows: Figure 3As shown in the figure. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capability. 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, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data to be processed. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement a system-level equipment health state evaluation method based on FL-AHP.

[0144] Those skilled in the art can understand that, Figure 3 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement. In one exemplary embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps in each of the above method embodiments.

[0145] In one exemplary embodiment, a computer readable storage medium is provided, storing a computer program, which is executed by a processor to implement the steps in each of the above method embodiments.

[0146] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0147] 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. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, databases or other media 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 storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric 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 but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0148] The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a blockchain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0149] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described, but as long as the combinations of the technical features do not exist, they should be considered as the scope of the present application.

[0150] The principles and implementation modes of the present application are described by applying specific examples in the present application. The above-mentioned embodiments are only used to help understand the method and its core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range will be changed. In conclusion, the content of the present application should not be understood as a limitation.

Claims

1. A system-level equipment health status assessment method based on FL-AHP, characterized in that, include: The system-level equipment is divided into multiple levels; these levels include the component level, the subsystem level, and the system level; the component level includes multiple evaluation indicators. The health index of each assessment indicator is quantitatively calculated based on the monitoring parameters of each assessment indicator. The FL-AHP algorithm is used to correct the pre-set weights of each level; the weights include the weights of each evaluation index, the weights of each component, and the weights of each subsystem. The health index of system-level equipment is calculated hierarchically based on the health index of each evaluation indicator and the adjusted weights. The health status of system-level equipment is assessed based on the health index of the system-level equipment.

2. The system-level equipment health status assessment method based on FL-AHP according to claim 1, characterized in that, The health index of each assessment indicator is quantitatively calculated based on the monitoring parameters of each assessment indicator, specifically including: When the monitoring parameters of each evaluation indicator have upper and lower boundary threshold constraints, the formula is used. Calculate the health index for each assessment indicator; When the monitoring parameters of each evaluation indicator have upper boundary threshold constraints, the formula is used. Calculate the health index for each assessment indicator; When the monitoring parameters of each evaluation indicator have lower boundary threshold constraints, the formula is used. Calculate the health index for each assessment indicator; Among them, H scb Let x be the health index of the b-th evaluation indicator of the c-th component of the s-th subsystem, μ be the median of the upper and lower boundaries of the monitoring indicator, and δ be half of the allowable deviation of the monitoring indicator. min x max These are the lower and upper boundaries of the monitoring parameter when a fault is reported, respectively. x0 and x1 are the expected values ​​of the monitoring parameter when the system-level equipment is running normally, respectively. The magnitude of re reflects the relationship between the monitoring parameter and the health status of the system-level equipment.

3. The system-level equipment health status assessment method based on FL-AHP according to claim 1, characterized in that, The FL-AHP algorithm is used to correct the pre-defined weights of each level, specifically including: Construct a fuzzy judgment matrix; The fuzzy judgment matrix is ​​processed using the fuzzy geometric average method to obtain the fuzzy weights; The blurred weights are deblurred using a deblurring algorithm to obtain clear weights; The Lagrange multiplier method is used to optimize the weights of the clear weights, resulting in the corrected weights.

4. The system-level equipment health status assessment method based on FL-AHP according to claim 1, characterized in that, The system-level equipment health index is calculated hierarchically based on the health index of each evaluation indicator and the adjusted weights, specifically including: The health index of each component in the component layer is calculated based on the health index of each evaluation indicator and the adjusted weight of each evaluation indicator. The health index of each subsystem in the subsystem layer is calculated based on the health index of each component and the corrected weight of each component. The system-level health index is calculated based on the health index of each subsystem and the corrected weights of each subsystem, thus obtaining the health index of the system-level equipment.

5. The system-level equipment health status assessment method based on FL-AHP according to claim 4, characterized in that, Using formula Calculate the health index of each component; where H sc H represents the health index of the c-th component of the s-th subsystem. scb ω is the health index of the b-th evaluation indicator of the c-th component of the s-th subsystem. scb The weight is the adjusted weight of the b-th evaluation index for the c-th component of the s-th subsystem.

6. The system-level equipment health status assessment method based on FL-AHP according to claim 4, characterized in that, Using formula Calculate the health index of each subsystem; where H s H is the health index of the s-th subsystem. sc Let ω be the health index of the c-th component of the s-th subsystem. sc The corrected weights are those of the c-th component of the s-th subsystem.

7. The system-level equipment health status assessment method based on FL-AHP according to claim 6, characterized in that, Using formula Calculate the health index of each component; where H is the health index of the system-level equipment. s Let ω be the health index of the s-th subsystem. s The weights are the corrected weights for the s-th subsystem.

8. A system-level equipment health status assessment device based on FL-AHP, characterized in that, include: The hierarchy module is used to divide system-level equipment into multiple levels; The hierarchy includes a component layer, a subsystem layer, and a system layer; the component layer includes multiple evaluation metrics. The health index calculation module for assessment indicators is used to quantitatively calculate the health index of each assessment indicator based on the monitoring parameters of each assessment indicator. The weight correction module is used to correct the pre-set weights of each level using the FL-AHP algorithm; the weights include the weights of each evaluation index, the weights of each component, and the weights of each subsystem. The system-level equipment health index calculation module is used to calculate the system-level equipment health index by level based on the health index of each evaluation indicator and the corrected weights. The health status assessment module is used to assess the health status of system-level equipment based on the system-level equipment's health index.

9. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the FL-AHP-based system-level equipment health status assessment method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the FL-AHP-based system-level equipment health status assessment method as described in any one of claims 1-7.

Images