Electro-hydraulic servo mechanism health state evaluation method and device based on aperiodic data, computer readable storage medium and product

The non-periodic data of the electro-hydraulic servo mechanism is periodically processed through the M-H algorithm and the BRB method. Combined with expert knowledge, a health assessment model is constructed, which solves the problems of insufficient data and uncertainty in the health status evaluation of the electro-hydraulic servo mechanism. Improved assessment accuracy and stability.

CN118897964APending Publication Date: 2024-11-05ROCKET FORCE UNIV OF ENG
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410939253.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-15
Publication Date
2024-11-05

AI Technical Summary

Technical Problem

Due to the test cost limitations and task cycle differences, the health status detection data of electro-hydraulic servo mechanisms have small data volume and non-periodic problems, resulting in a decrease in the accuracy of health status assessment, affecting equipment reliability and maintenance strategies.

Method used

The Metropolis-Hastings algorithm (M-H algorithm) is used to obtain periodic data from non-periodic data, and combine the confidence rule base (BRB) method and expert knowledge to build a health assessment model, and use analytical evidence inference algorithm Evaluate.

Benefits of technology

By periodically processing non-periodic data, the accuracy of the health status evaluation of electro-hydraulic servo mechanisms is improved, data noise and uncertainty are reduced, and the evaluation effect is optimized.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118897964A_ABST
    Figure CN118897964A_ABST
Patent Text Reader

Abstract

The invention discloses an electro-hydraulic servo mechanism health state evaluation method and device based on non-periodic data, a computer readable storage medium and a product, and relates to the technical field of electro-hydraulic servo mechanism health state evaluation.The method comprises the steps that periodic data are obtained through an M-H algorithm based on historical detection data of electro-hydraulic servo mechanisms of the same batch; calculating a matching degree between the periodic data and a rule in a BRB model; calculating an activation weight based on the matching degree; based on the rule activation weight, fusing rules in a BRB model by adopting an analytic evidence reasoning algorithm to obtain a health assessment model; and evaluating the health state of the electro-hydraulic servo mechanism by adopting the health evaluation model. According to the invention, the limitation caused by limited test data and time interval uncertainty can be solved, so that the accuracy of health state evaluation of the electro-hydraulic servo mechanism is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of health status assessment of an electro-hydraulic servo mechanism, and in particular to a health status assessment method, device, computer-readable storage medium and product of an electro-hydraulic servo mechanism based on non-periodic data. Background Art

[0002] The electro-hydraulic servo mechanism is an indispensable key device in the spacecraft system. Its main task is to convert the control signal into the deflection angle of the spacecraft engine nozzle under the control of the flight control computer, so as to adjust the attitude of the spacecraft. The stability of the flight attitude is directly related to the flight safety of the spacecraft. Therefore, it is extremely important to evaluate the health status of the electro-hydraulic servo mechanism.

[0003] The purpose of evaluating the health status of the electro-hydraulic servo mechanism is to comprehensively evaluate the overall performance and status of the system by combining historical information and real-time test data. Effective evaluation can not only reveal the potential risks of the system, but also provide strong support for low-cost fault diagnosis and preventive maintenance.

[0004] However, in practical applications, due to the limitation of testing cost, the health status detection data of electro-hydraulic servo mechanisms often have the problems of small data volume and lack of continuity. In addition, due to the difference in task cycles, the test data may also be non-periodic, and it is impossible to obtain periodic and continuous health status data of electro-hydraulic servo mechanisms. Over time, the accumulation of evaluation errors may lead to a decrease or inadequacy in the evaluation accuracy of equipment health status and potential problems, which in turn has a negative impact on the reliability, performance and maintenance strategy of the equipment. Summary of the invention

[0005] The purpose of the present invention is to provide a method, device, computer-readable storage medium and product for evaluating the health status of an electro-hydraulic servo mechanism based on non-periodic data, so as to solve the limitations caused by limited test data and uncertainty in time intervals, thereby improving the accuracy of health status evaluation of the electro-hydraulic servo mechanism.

[0006] To achieve the above object, the present invention provides the following solutions:

[0007] A method for evaluating the health status of an electro-hydraulic servo mechanism based on non-periodic data, comprising:

[0008] Based on the historical detection data of the same batch of electro-hydraulic servo mechanisms, the MH algorithm is used to obtain periodic data; the historical detection data is non-periodic data, and the historical detection data includes test data of each feature of the electro-hydraulic servo mechanism;

[0009] Calculating the matching degree between the periodic data and the rules in the BRB model;

[0010] Calculating an activation weight based on the matching degree;

[0011] Based on the rule activation weights, the rules in the BRB model are integrated using an analytical evidence reasoning algorithm to obtain a health assessment model;

[0012] The health assessment model is used to assess the health status of the electro-hydraulic servo mechanism.

[0013] To achieve the above object, the present invention also provides the following solution:

[0014] A computer device comprises: 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 steps of the above-mentioned method for evaluating the health status of an electro-hydraulic servo mechanism based on non-periodic data.

[0015] To achieve the above object, the present invention also provides the following solution:

[0016] A computer-readable storage medium stores a computer program, which implements the steps of the above method when executed by a processor.

[0017] To achieve the above object, the present invention also provides the following solution:

[0018] A computer program product comprises a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for evaluating the health status of an electro-hydraulic servo mechanism based on non-periodic data.

[0019] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0020] The present invention firstly performs periodic processing on non-periodic test data to make up for the limitations brought by limited test data and uncertainty of time intervals, and then constructs a health assessment model based on periodic data through the Belief Rule Base (BRB) method in combination with expert knowledge, thereby improving the accuracy of health status assessment of the electro-hydraulic servo mechanism. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0022] Figure 1 A flow chart of a method for evaluating the health status of an electro-hydraulic servo mechanism based on non-periodic data provided by the present invention;

[0023] Figure 2 This is a schematic diagram of the comparison of the test data of the electro-hydraulic servo mechanism before and after periodization;

[0024] Figure 3 Schematic diagram of the health status assessment results of the electro-hydraulic servo mechanism. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] The technical solution of the present invention is: first, for non-periodic test data that can reflect the health status of the electro-hydraulic servo mechanism, a Markov Monte Carlo method in statistics and statistical physics of the Metropolis-Hastings algorithm (MH) is used to extract a random sample sequence from a probability distribution when it is difficult to directly sample, and the missing values ​​are interpolated with the most likely values ​​to obtain periodic data while retaining the original data. Then, a health assessment model is constructed based on periodic data by combining expert knowledge through the Belief Rule Base (BRB) method.

[0027] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0028] Embodiment 1

[0029] This embodiment provides a method for evaluating the health status of an electro-hydraulic servo mechanism based on non-periodic data. Figure 1 As shown, the method includes:

[0030] S1: Based on the historical detection data of the same batch of electro-hydraulic servo mechanisms, the MH algorithm is used to obtain periodic data; the historical detection data is non-periodic data, and the historical detection data includes test data of each feature of the electro-hydraulic servo mechanism.

[0031] S2: Calculate the matching degree between the periodic data and the rules in the BRB model.

[0032] S3: Calculate activation weight based on the matching degree.

[0033] S4: Based on the rule activation weights, the rules in the BRB model are integrated using an analytical evidence reasoning algorithm to obtain a health assessment model.

[0034] S5: Using the health assessment model to assess the health status of the electro-hydraulic servo mechanism.

[0035] Furthermore, step S1 specifically includes:

[0036] When evaluating the health status of an electro-hydraulic servo mechanism, equally spaced test data is more advantageous due to its continuity and stability of sampling frequency. This continuity and stability helps to reduce data noise and uncertainty, improve the stability and accuracy of the evaluation, and thus establish a more accurate model and optimize the evaluation effect. Therefore, in order to more accurately evaluate the health status of the equipment, it is necessary to consider periodizing the non-periodic test data to make up for the limitations brought about by limited test data and uncertainty in time intervals.

[0037] In practical applications, equipment is usually in a state of long-term storage. And different equipment in the same batch has problems such as different task cycles and unequal test time intervals. This leads to the problem of non-periodicity in the detection data of the electro-hydraulic servo mechanism. However, when performing health assessment, equally spaced periodic detection data has better continuity and stability, which helps to reduce data noise and uncertainty. Therefore, in order to better perform health assessment, this embodiment periodizes the non-periodic test data of this device by combining the historical detection data of other equipment in the same batch.

[0038] The historical inspection data of the same batch of equipment is used as the sample set, and the MH algorithm is used to obtain the interpolation samples that periodize the data by Monte Carlo sampling method. In order to verify that the interpolated data can converge to the original data model, the estimated potential scale reduction factor (EPSR) method is used to determine whether the sample converges to the probability distribution of the original data.

[0039] (1) Obtain samples for periodic interpolation of data

[0040] 1) Set the test data of each feature of the electro-hydraulic servo mechanism and establish the following Markov chain [x (0) ,x (1) ,x (2) ,…]. As time t changes, a sufficiently long Markov chain is generated and then obeys the stationary distribution π(x), where x is a sample randomly sampled from the Markov chain.

[0041] 2) Set the recommended distribution to g(x * ,x (t) ), which means that the state is determined by x (t) Transition to state x *The probability of the proposed distribution is determined subjectively by people based on the characteristics of the data distribution.

[0042] 3) According to the stationary distribution π(x), the calculation formula of the acceptance probability is as follows:

[0043]

[0044] Among them, π(x * ) is the sampling value x * Obeying the stationary distribution, π(x (t) ) is the sampling value x (t) Obeys a stationary distribution. g(x (t) ,x * ) is the sampling value from x (t) Transfer to x * The probability of g(x * ,x (t) ) is the sampling value from x * Transfer to x (t) probability.

[0045] 4) Generate a random number u′ that obeys the average distribution, u′~U(0,1) Let x (t+1) for:

[0046]

[0047] 5) In the case where the electro-hydraulic servo mechanism has I feature, assume that steps 2)-4) are repeated C times to obtain C random samples, and each random sample is inserted into the initial Markov chain of each feature, and each feature generates C Markov chains. ic The new chain generated after inserting the sample into the original Markov chain of the i-th feature, the new chain y ic There are S samples x ics ,i=1,…,I; c=1,…,C; s=1,…,S,x ics represents the sth sample of the cth Markov chain in the ith feature. Using the EPSR algorithm, determine the acceptance of sample x ics After that, the model converges. The judgment process is as follows.

[0048] (2) Determine sample convergence

[0049] 1) Calculate the mean within the chain and the inter-chain mean

[0050]

[0051]

[0052] 2) Calculate the variance B within each chain and the variance W between chains:

[0053]

[0054]

[0055] 3) Posterior variance Make an estimate:

[0056]

[0057] 4) Calculate EPSR value

[0058]

[0059] when When it is close to 1, the target is approximately converged. isc Take the mean value and interpolate it into the original data set. Repeat steps 1)-2) until the original data is periodized.

[0060] Furthermore, step S2 specifically includes:

[0061] In the BRB model, the types of input information are mainly divided into two categories: qualitative knowledge and quantitative data. These different types of input information need to be unified into the following structure:

[0062]

[0063] in, is the matching degree of M inputs for the kth rule. Represents input x i Reference value of the input attribute for the kth rule.

[0064] Qualitative knowledge mainly refers to information accumulated through experience, subjective decision-making, and symbolic description. It can usually be given directly by experts.

[0065] For quantitative data, rule-based or utility-based transformation methods can be used, namely:

[0066] S(x i )={(A i,j ,α i,j ),i=1,2,...,M; j=1,2,...,J} (10)

[0067] Among them, S(·) is the conversion function, {(A 1,1 ,α 1,1 ),...,(A M,J ,α M,J )} represents the transformed confidence distribution. A i,jFor input x i The jth reference level, α i,j For input x i The matching degree of the jth reference level, J is the number of reference levels. The following rules are established by experts to make reference level A i,j With reference value γ i,j Establish a corresponding relationship between:

[0068] γ i,j means A i,j ,i=1,2,…,M; j=1,2,…,J (11)

[0069] The matching degree is calculated as follows:

[0070]

[0071] in, represents the matching degree between the test data of the i-th feature in the periodic data and the h-th rule in the BRB model, x i represents the attribute input, i.e. the test data of the i-th feature, γ ik represents the attribute reference value of the kth rule, γ i(k+1) is the attribute reference value of the k+1th rule.

[0072] Furthermore, step S3 specifically includes:

[0073] Obtain matching degree The ER algorithm is then used to fuse the rules. When the system has input, some rules of the BRB rule base are activated. The weight calculation method of the activated rules is:

[0074]

[0075] Among them, ω k represents the activation weight of the kth rule, θ k is the weight of the kth rule, θ h is the weight of the h-th rule, δ i is the attribute weight of the test data of the i-th feature, is the relative attribute weight of the test data of the i-th feature, The matching degree between the test data of the i-th feature in the periodic data and the k-th rule in the BRB model, is the matching degree between the test data of the i-th feature in the periodic data and the h-th rule in the BRB model, 0≤ω k ≤1, k=1…h, H is the total number of rules, and M is the number of characteristics of the electro-hydraulic servo mechanism.

[0076] Furthermore, step S4 specifically includes:

[0077] The expression of ER parsing algorithm is:

[0078]

[0079]

[0080] Among them, N is the number of evaluation levels, β n represents the confidence level of the health assessment model output assessment level n, and β n,k is the confidence of rule k relative to the evaluation level n, and μ is an intermediate parameter.

[0081] The expression of the health assessment model is:

[0082] S(x i )={(n,β n )},n=1,2,...N (16)

[0083] Among them, S(x i ) represents the health assessment model, x i is the test data of the i-th feature, n represents the evaluation level, β n Represents the confidence level of the evaluation level n. The final output is converted into expected utility:

[0084]

[0085] Among them, u n represents the utility of the evaluation level n, Represents the expected outcome of the health assessment model.

[0086] The following is an introduction to the health status assessment method of the electro-hydraulic servo mechanism based on non-periodic data provided by this embodiment through an example application.

[0087] The loop width, zero position deviation, maximum swing angle and relative error reflect the health status of the electro-hydraulic servo mechanism. According to the actual situation, 68 sets of test data were collected, which had the problems of small sample size and unequal sampling intervals. Since the minimum sampling interval in the original data is one month, the data is interpolated as periodic detection data with an interval of one month.

[0088] Step 1: Periodize the original non-periodic data

[0089] Through the MH algorithm and EPSR method, the original 68 groups of test data are interpolated into 100 groups of equal-periodic data. The interpolation effect is as follows: Figure 2 shown.

[0090] Depend on Figure 2It can be seen that by comparing the interpolated periodic data with the original non-periodic data, the periodic data are consistent with the changing trend of the original data. The statistical method t-test is used to compare the similarity of the two sets of data under different indicators, and the results are shown in Table 1.

[0091] Table 1 Difference analysis

[0092]

[0093] Take the loop width test data as an example. A t-test was performed between the two groups of data before and after interpolation, and the results were h = 0 and p = 0.9635. According to the conventional practice in statistics, in general, when p>0.05, the null hypothesis cannot be rejected, that is, there is no statistically significant difference between the two groups of data.

[0094] Step 3: Build an evaluation model

[0095] The reference levels of the health status of the electro-hydraulic servo mechanism are "healthy", "sub-healthy" and "unhealthy". The confidence rule base is used to combine the test data with expert knowledge, and the reference values ​​are given by experts, as shown in Table 2:

[0096] Table 2 Reference levels and reference values

[0097]

[0098] Combined with expert knowledge, corresponding rules are formed according to the above indicators and reference levels. Through evidence reasoning, the health assessment model obtains the output results as follows Figure 3 As shown. Figure 3 It can be seen that the evaluation results obtained by the health assessment model are consistent with the actual health status of the electro-hydraulic servo mechanism, which verifies the feasibility of the model.

[0099] Embodiment 2

[0100] A computer device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the computer program to implement the steps of the method for evaluating the health status of an electro-hydraulic servo mechanism based on non-periodic data in the first embodiment.

[0101] Embodiment 3

[0102] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for evaluating the health status of an electro-hydraulic servo mechanism based on non-periodic data in the first embodiment.

[0103] Embodiment 4

[0104] A computer program product includes a computer program, which, when executed by a processor, implements the steps of the method for evaluating the health status of an electro-hydraulic servo mechanism based on non-periodic data in the first embodiment.

[0105] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided by the present invention may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited thereto. The processor involved in each embodiment provided by the present invention may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, etc., but are not limited thereto.

[0106] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0107] This article uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only used to help understand the method and core ideas of the present invention. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for evaluating the health status of an electro-hydraulic servo mechanism based on non-periodic data, characterized in that: include: Based on the historical test data of the same batch of electro-hydraulic servo mechanisms, the MH algorithm is used to obtain the cycle data; The historical detection data is non-periodic data, and the historical detection data includes test data of each feature of the electro-hydraulic servo mechanism; Calculating the matching degree between the periodic data and the rules in the BRB model; Calculating an activation weight based on the matching degree; Based on the rule activation weights, the rules in the BRB model are integrated using an analytical evidence reasoning algorithm to obtain a health assessment model; The health assessment model is used to assess the health status of the electro-hydraulic servo mechanism.

2. The method for evaluating the health status of an electro-hydraulic servo mechanism based on non-periodic data according to claim 1, characterized in that: Based on the historical detection data of the same batch of equipment, the MH algorithm is used to obtain periodic data, including: The test data of each characteristic of the electro-hydraulic servo mechanism is sorted in time to establish a Markov chain; Calculating the acceptance probability of the random sample based on the stationary distribution and the proposed distribution of the random sample in the Markov chain; Generate random numbers that obey average distribution based on the acceptance probability calculation to obtain multiple new random samples; Insert each new random sample into the Markov chain of each feature to obtain periodic data.

3. The method for evaluating the health status of an electro-hydraulic servo mechanism based on non-periodic data according to claim 1, characterized in that: The calculation formula of the acceptance probability is: Among them, α(x (t) ,x * ) is the sampling value from x (t) Transfer to x * The acceptance probability, π(x * ) is the sampling value x * Obeying the stationary distribution, π(x (t) ) is the sampling value x (t) Obeying the stationary distribution, g(x (t) ,x * ) is the sampling value from x (t) Transfer to x * The probability of g(x * ,x (t) ) is the sampling value from x * Transfer to x (t) The probability of , t is the time of the test data.

4. The method for evaluating the health status of an electro-hydraulic servo mechanism based on non-periodic data according to claim 1, characterized in that: After acquiring non-periodic data, it also includes: The method of estimating potential size reduction factors is used to judge the convergence of the periodic data.

5. The method for evaluating the health status of an electro-hydraulic servo mechanism based on non-periodic data according to claim 1, characterized in that: The calculation formula of the matching degree is: in, is the matching degree between the test data of the i-th feature in the periodic data and the h-th rule in the BRB model, x i is the test data of the i-th feature, γ ik is the attribute reference value of the kth rule, γ i(k+1) is the attribute reference value of the k+1th rule.

6. The method for evaluating the health status of an electro-hydraulic servo mechanism based on non-periodic data according to claim 1, characterized in that: The calculation formula of the activation weight is: Among them, ω k represents the activation weight of the kth rule, θ k is the weight of the kth rule, θ h is the weight of the h-th rule, δ i is the attribute weight of the test data of the i-th feature, is the relative attribute weight of the test data of the i-th feature, The matching degree between the test data of the i-th feature in the periodic data and the k-th rule in the BRB model, is the matching degree between the test data of the i-th feature in the periodic data and the h-th rule in the BRB model, 0≤ω k ≤1, k=1…H, H is the total number of rules, and M is the number of characteristics of the electro-hydraulic servo mechanism.

7. The method for evaluating the health status of an electro-hydraulic servo mechanism based on non-periodic data according to claim 6, characterized in that: The expression of the analytical evidence reasoning algorithm is: Among them, N is the number of evaluation levels, β n represents the confidence level of the health assessment model output assessment level n, β n,k is the confidence of rule k relative to the evaluation level n, μ is an intermediate parameter; The expression of the health assessment model is: S(x i )={(n,β n )},n=1,2,…N Among them, S(x i ) represents the health assessment model, x i is the test data of the i-th feature, n represents the evaluation level, β n Represents the confidence level of the evaluation level n.

8. 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 steps of the method for evaluating the health status of an electro-hydraulic servo mechanism based on non-periodic data as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method for evaluating the health status of an electro-hydraulic servo mechanism based on non-periodic data as described in any one of claims 1 to 7 are implemented.