CN112381380B - System health detection method and device for spacecraft - Google Patents
System health detection method and device for spacecraft Download PDFInfo
- Publication number
- CN112381380B CN112381380B CN202011254719.XA CN202011254719A CN112381380B CN 112381380 B CN112381380 B CN 112381380B CN 202011254719 A CN202011254719 A CN 202011254719A CN 112381380 B CN112381380 B CN 112381380B
- Authority
- CN
- China
- Prior art keywords
- health
- state
- health data
- determining
- distribution
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000036541 health Effects 0.000 title claims abstract description 252
- 238000001514 detection method Methods 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 claims abstract description 57
- 238000009826 distribution Methods 0.000 claims description 81
- 239000011159 matrix material Substances 0.000 claims description 32
- 239000013598 vector Substances 0.000 claims description 30
- 230000000750 progressive effect Effects 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 230000002068 genetic effect Effects 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims description 5
- 230000006870 function Effects 0.000 description 45
- 230000003862 health status Effects 0.000 description 19
- 238000004891 communication Methods 0.000 description 14
- 238000011156 evaluation Methods 0.000 description 11
- 230000015556 catabolic process Effects 0.000 description 7
- 238000006731 degradation reaction Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 239000011521 glass Substances 0.000 description 5
- 239000012634 fragment Substances 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 235000019800 disodium phosphate Nutrition 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000010187 selection method Methods 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 238000012935 Averaging Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000009347 mechanical transmission Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004549 pulsed laser deposition Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Biophysics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Physiology (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Genetics & Genomics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a method and a device for detecting system health of a spacecraft. The method comprises the following steps: acquiring first health data of various health states of the parts in the target system; determining second health data of the part by using the first weights configured for the various health states and the first health data of the various health states; determining third health data of a target system by using second weights configured for the parts and the second health data of the parts, wherein the target system is a system used by a spacecraft; a health state of the plurality of states that matches the third health data is determined. The application can finish the system-level health state detection from the bottom layer parameters to the parts, is more comprehensive, has more accurate detection results, and can be widely applied to various systems of the spacecraft.
Description
Technical Field
The application relates to the technical field of spacecrafts, in particular to a method and a device for detecting system health of a spacecraft.
Background
With the continuous development of the aerospace technology, the spacecraft composition system is more and more complex. In order to ensure that the spacecraft can keep safe and stable operation in the operation process, the health state of the spacecraft needs to be monitored in real time, and the technical problem to be solved in the aerospace field is urgent, namely, how to comprehensively and accurately analyze the health state of each system, each component and even each parameter of the spacecraft facing to a huge and complex spacecraft system.
At present, in the related art, a specific health state detection scheme can be formulated only for a specific system, and the detection result of the health state is inaccurate due to complex system, multiple components and parameter interleaving.
In view of the above problems, no effective solution has been proposed at present.
Disclosure of Invention
The application provides a method and a device for detecting the system health of a spacecraft, which are used for solving the technical problem of lack of a more comprehensive and more accurate method for detecting the health state of the spacecraft.
According to an aspect provided by the present embodiment, the present application provides a method for detecting system health of a spacecraft, including: acquiring first health data of various health states of the parts in the target system; determining second health data of the part by using the first weights configured for the various health states and the first health data of the various health states; determining third health data of a target system by using second weights configured for the parts and the second health data of the parts, wherein the target system is a system used by a spacecraft; a health state of the plurality of states that matches the third health data is determined.
Optionally, the obtaining the first health data of each type of health state in the plurality of types of health states of the components in the target system includes: determining a target time period for detecting the current health state according to a preset starting time and a preset ending time; acquiring state parameters of various health states in a target time period, and acquiring history parameters of various health states in a history synchronization period, wherein the history synchronization period is each period of target time period of a spacecraft using target system which does not comprise the current detection time period; calculating a first distribution of state parameters of various health states and a second distribution of history parameters of various health states by using a nuclear density estimation mode; determining a plurality of canonical values of the difference between a first distribution of state parameters for each type of state of health and a second distribution of historical parameters for the corresponding same type of state of health; the first health data is determined based on the third weights and the respective canonical values that match the plurality of canonical values.
Optionally, calculating the first distribution of the state parameters of each type of health state and the second distribution of the history parameters of each type of health state using the method of nuclear density estimation includes: taking the horizontal axis as time and the vertical axis as the numerical value of the state parameter, and generating a first histogram of the state parameter; moving the Gaussian kernel function between each point of the first histogram to fit a first probability density curve of the state parameter; adjusting the window width of the Gaussian kernel function until the accuracy of kernel density estimation reaches an optimal value, and taking a first probability density curve as the first distribution; and generating a second histogram of the history parameter with the horizontal axis as time and the vertical axis as a numerical value of the history parameter; moving the Gaussian kernel function between points of the second histogram to fit a second probability density curve of the history parameter; and (3) adjusting the window width of the Gaussian kernel function until the accuracy of the kernel density estimation reaches an optimal value, and taking a second probability density curve as a second distribution.
Optionally, the method further comprises adjusting the window width of the gaussian kernel as follows: determining an integral square error of the state parameter and/or the history parameter, wherein the integral square error takes the window width as a parameter; calculating the expectation of the integral square error to obtain an integral average error; carrying out Taylor series expansion on the integral average error to obtain a progressive mean square error; the adjustment of the window width is stopped in case the window width minimizes the value of the progressive mean square error.
Optionally, determining a plurality of canonical values of the difference between the first distribution of the state parameters of each type of state of health and the second distribution of the history parameters of the respective same type of state of health comprises: determining a plurality of KL-divergence values between the first distribution and each of the second distributions, the KL-divergence values being indicative of a difference between the first distribution and each of the second distributions; discretizing the plurality of KL divergence values, and taking the logarithm of the plurality of the discrete KL divergence values to obtain a plurality of standard values.
Optionally, determining the first health data according to the third weights and the respective canonical values that match the plurality of canonical values comprises: and taking the sum of products of the standard values and the corresponding third weights as first health data, wherein the generation time of the history parameters of the standard values is obtained, and the third weights matched with the standard values are larger as the generation time is closer to the current detection time period.
Optionally, determining the second health data of the part using the first weights configured for each type of health state and the first health data of each type of health state includes: the sum of the products of the plurality of first health data and the corresponding first weights is taken as second health data.
Optionally, determining the third health data of the target system using the second weights configured for the respective components and the second health data of the respective components includes: and taking the sum of products of the plurality of second health data and the corresponding second weights as third health data.
Optionally, before determining the third health data of the target system using the second weights configured for the respective components and the second health data of the respective components, the method further comprises determining the second weights as follows: constructing a pair comparison matrix of the parts by utilizing the interaction relation between every two parts; calculating weight vectors of the pair comparison matrixes; and calculating an optimal weight vector of the weight vector by using a genetic algorithm, wherein the weight value in the optimal weight vector is used as a second weight.
According to another aspect provided by the present embodiment, the present application provides a system health detection device of a spacecraft, including: the index level detection module is used for acquiring first health data of various health states in various health states of the parts in the target system; the component level detection module is used for determining second health data of the component by using the first weights configured for various health states and the first health data of various health states; the system-level detection module is used for determining third health data of a target system by using second weights configured for all parts and second health data of all parts, wherein the target system is a system used by a spacecraft; and the health state judging module is used for determining the health state matched with the third health data in the plurality of states.
According to another aspect of the embodiments of the present application, there is provided an electronic device including a memory, a processor, a communication interface, and a communication bus, where the memory stores a computer program executable on the processor, the memory, the processor, and the processor communicate through the communication bus and the communication interface, and the processor executes the computer program to implement the method.
According to another aspect provided by the present embodiment, the present application also provides a computer readable medium having a non-volatile program code executable by a processor, the program code causing the processor to perform the above-described method.
Compared with the related art, the technical scheme provided by the embodiment of the application has the following advantages:
The technical scheme of the application is that first health data of various health states in various health states of parts in a target system are obtained; determining second health data of the part by using the first weights configured for the various health states and the first health data of the various health states; determining third health data of a target system by using second weights configured for the parts and the second health data of the parts, wherein the target system is a system used by a spacecraft; a health state of the plurality of states that matches the third health data is determined. The application can finish the system-level health state detection from the bottom layer parameters to the parts, is more comprehensive, has more accurate detection results, and can be widely applied to various systems of the spacecraft.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described, and it will be apparent to those skilled in the art that other drawings can be obtained according to these drawings without inventive effort.
FIG. 1 is a schematic diagram of a hardware environment of an alternative method for detecting system health of a spacecraft according to an embodiment of the application;
FIG. 2 is a flowchart of an alternative method for detecting system health of a spacecraft according to an embodiment of the application;
FIG. 3 is a flowchart of an alternative first health data determination method according to an embodiment of the present application;
FIG. 4 is a flowchart of an alternative first distribution determination method according to an embodiment of the present application;
FIG. 5 is a flowchart of an alternative second distribution determination method according to an embodiment of the present application;
FIG. 6 is a flowchart of an alternative window width adjustment method according to an embodiment of the present application;
FIG. 7 is a flowchart of an alternative KL divergence determination method provided according to an embodiment of the application;
FIG. 8 is a flowchart of an alternative second weight determination method according to an embodiment of the present application;
FIG. 9 is a block diagram of an alternative spacecraft system health detection device, provided in accordance with an embodiment of the present application;
fig. 10 is a schematic structural diagram of an alternative electronic device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In the following description, suffixes such as "module", "component", or "unit" for representing elements are used only for facilitating the description of the present application, and are not of specific significance per se. Thus, "module" and "component" may be used in combination.
First, partial terms or terminology appearing in the course of describing the embodiments of the application are applicable to the following explanation:
Nuclear density estimation
Let x 1,x2,...,xn be the mutually independent samples extracted from the population subject to the density function f. K () is a symmetric probability density kernel function of the bounded support. h is the window width, then the core density of f (x) at the interior point x is estimated as:
the performance is related to the kernel function K () and window width h, where the impact of window width is critical, and when window width is large, the above formula works with more x i related to x, making/> The estimate of (2) is more stable, the variance fluctuation is smaller, but because the window width is larger, more f (x i) is considered, so that the estimated deviation/>Larger. Conversely, when the window width is smaller, the estimated deviation is smaller, but the data is also smaller, so that the fluctuation variance of f (x) is larger.
In summary, selecting an appropriate window width in the estimation of the density function f (x) is one of the most important issues in the specific calculation. In addition, the relatively sparse appearance of the samples due to the low density at the boundary points also affects f (x) at the boundary pointsThis gives rise to the idea of estimating the time-varying window width by a function, thus making the corresponding deviation smaller.
Paired comparison matrix
Assuming that the weight of a glass fragment is 1, breaking into n small pieces, each block has weights of B1, B2 and B3The matrix of the weight ratios of each patch is:
Letting the matrix
An observation of matrix a reveals that the elements in the matrix have the following properties:
Akk＝1，k＝1，2，3，...，n；
The matrix a constructed in the above manner is called a positive-negative matrix, and if a ik×Akj＝Aij in the matrix a, a is called a uniform matrix. The identity matrix has the following properties:
A T is also a uniform matrix; matrix rows are proportional, rank (a) =1; the maximum special root of the matrix is lambda=n, and the rest n-1 characteristic roots are 0; any row (column) of the matrix is a feature vector corresponding to the feature root n. The matrix A of glass fragments is a uniform matrix and is also a positive and negative matrix. If the eigenvalue of matrix a is expressed by λ and the eigenvector of matrix a is expressed by x, the relationship between the eigenvalue and eigenvector of matrix a is ax=λx. Wherein the maximum feature root is n, the feature vector x= (B 1,B2,B3,...,Bn)T, after normalization of the feature vector x, there is Wherein B i is the weight of the factor in total, i.e. the ith glass fragment in total weight of glass.
The glass fragment example is just a special case, and because of the complexity of the actual problem or the difference of the own properties among things, the things do not have strict comparability, so the importance degree is described by the language in abstract sense, for example, the language of equal importance, a little importance, a more importance, a far importance and the like expresses the importance degree of a certain thing compared with another thing. The importance degree is attached to numbers 1,3, 5, 7, 9 and the like, and the matrix is a 1-9 scale matrix, for example, a pair judgment matrix A is formed:
Wherein the method comprises the steps of Representing a i and a k are equally important;
representing a i slightly more important than a k;
Representing that A i is more important than A k;
representing a i more important than a k;
Indicating that a i is far more important than a k.
Such asThe meanings expressed by 1/3, 1/5, 1/7 and 1/9 are the exact opposite of the above, e.g. subdivided,/>2, 4, 6, 8 Respectively, the importance of which is between 1, 3, 5, 7, 9.
In order to solve the problems mentioned in the background art, according to an aspect of the embodiments of the present application, an embodiment of a system health detection method of a spacecraft is provided.
Alternatively, in the embodiment of the present application, the above-mentioned method for detecting system health of a spacecraft may be applied to a hardware environment formed by the terminal 101 and the server 103 as shown in fig. 1. As shown in fig. 1, the server 103 is connected to the terminal 101 through a network, which may be used to provide services to the terminal or a client installed on the terminal, and a database 105 may be provided on the server or independent of the server, for providing data storage services to the server 103, where the network includes, but is not limited to: a wide area network, metropolitan area network, or local area network, and terminal 101 includes, but is not limited to, a PC, a cell phone, a tablet computer, etc.
The method for detecting the system health of the spacecraft in the embodiment of the application can be executed by the server 103, or can be executed by the server 103 and the terminal 101 together, as shown in fig. 2, the method can include the following steps:
Step S202, obtaining first health data of various health states in various health states of components in a target system.
The system health detection method of the spacecraft in the embodiment of the application can be applied to technical scenes of detecting the system health state of each typical system of the spacecraft such as a space shuttle and a rocket. The above-mentioned typical system can be a system for ensuring the operation of the spacecraft, such as a thermal control system, for monitoring and controlling the heat and temperature of the spacecraft, where the thermal control system is composed of multiple parts, such as a hydraulic part, an electric control part, and a mechanical transmission part, and each part further includes multiple core parameters, so that the health status of each parameter can be evaluated. That is, the first health data may be health status scores of various specific indexes of the basic components in the system, for example, the health status score of a certain component may be scored, if the temperature is within the set temperature threshold range, the component temperature is normal, and the health status score is higher, otherwise, if the temperature is not within the set temperature threshold range, the deviation degree is greater, and the health status score of the index is lower. In the embodiment of the application, the health status scores of various specific indexes of the basic parts can be obtained based on a statistical or threshold method.
Step S204, determining second health data of the parts by using the first weights configured for the health states and the first health data of the health states.
In the embodiment of the application, after the health status evaluation is performed on each index of the basic component, the integral of the component can be comprehensively evaluated by combining the first weights respectively set for each index of the basic component, and the integral health status score of the component can be obtained by taking the sum of products of a plurality of first health data and corresponding first weights as the second health data. The first weight may be obtained through experiments, or may be specified empirically by an expert.
In step S206, third health data of the target system is determined by using the second weights configured for the respective components and the second health data of the respective components, where the target system is a system used by the spacecraft.
In the embodiment of the application, as well, after each component of the system to be evaluated is subjected to health status evaluation to obtain the integral health status score of each component, the integral of the system to be evaluated can be comprehensively evaluated by combining the second weights respectively set for each component, and the sum of the products of the second health data and the corresponding second weights is used as the third health data to obtain the integral health status score of the system.
Step S208, determining a health status of the plurality of statuses that matches the third health data.
In the embodiment of the application, after the system-level health state score is obtained, the current health state of the system can be intuitively determined through the system-level health state score.
By adopting the technical scheme of the application, the system-level health state detection can be completed from each parameter (index) of the bottom part to the last part, the detection can be more comprehensively and accurately carried out, and the method can be widely applied to each system of a spacecraft.
The following describes in detail a method of statistically acquiring the individual index-level health status scores of the base parts.
Optionally, as shown in fig. 3, acquiring the first health data of each of the plurality of health states of the component in the target system may include:
step S302, determining a target time period for detecting the health state currently according to a preset starting time and a preset ending time;
Step S304, acquiring state parameters of various health states in a target time period, and acquiring history parameters of various health states in a history synchronization period, wherein the history synchronization period is each period of target time period of a spacecraft use target system which does not comprise the current detection time period;
step S306, calculating a first distribution of state parameters of various health states and a second distribution of history parameters of various health states by using a nuclear density estimation mode;
Step S308, determining a plurality of standard values of the difference between the first distribution of the state parameters of each type of health state and the second distribution of the history parameters of the corresponding same type of health state;
Step S310, determining the first health data according to the third weight matched with the plurality of standard values and each standard value.
In the embodiment of the present application, the time period between the start time and the end time is a target time period for detecting the health status of the system, for example, from one month to one month in the current year is used as the target time period for the health detection of the system, and then the status parameters of each index, such as the temperature, the pressure, the moment, the magnetic field strength, and the like, in the target time period (i.e., from one month to one month in the current year) can be obtained. Meanwhile, index state parameters of all other years except the current year can be obtained as history parameters of various health states in the history synchronization after the spacecraft is put into use.
In the embodiment of the application, the statistics-based acquisition of the health status scores of the index levels of the basic parts can be specifically implemented by adopting a nuclear density estimation mode, calculating a first distribution D n+1 obeyed by data acquired in a target time period to be detected, and calculating a second distribution obeyed by data collected in the past year synchronization, wherein the distributions are represented by D 1,D2,...,Dn. Next, a measure of the difference between D n+1 and D 1,D2,...,Dn is needed, i.e. a plurality of canonical values of the difference between a first distribution of state parameters for each type of health state and a second distribution of history parameters for the corresponding same type of health state is determined. The above-mentioned standard value is a difference metric value between the first distribution and the second distribution. And taking the sum of products of the standard values and the corresponding third weights as first health data, wherein the generation time of the historical parameters of the standard values is obtained, and the third weights matched with the standard values are larger as the generation time is closer to the current detection time period.
In the embodiment of the application, the kernel density estimation needs to be performed by selecting a proper kernel function. The kernel function plays a smooth role in the kernel density estimation, i.e., eliminates the random factor of the disturbance, so that the resulting curve better reflects the actual link between the variables. Common kernel functions are Box kernel functions, epanechnikov kernel functions and gaussian kernel functions. Outside the limited range, the values of the Box kernel function and the Epanechnikov kernel function are both zero, while the value of the Gaussian kernel function is non-zero in any region, but outside the limited range, its function value is very small. Experiments prove that if enough training samples can be collected, no matter what type of kernel function is actually adopted, a reliable estimation result converged on the density function can be obtained in theory, that is, under the condition that the sample capacity is large enough, the selection of the kernel function is not critical to the estimation of the overall density. Thus, any available kernel function may be used at will. The Gaussian kernel is most widely used since it works very well, and preferably the present application can use the Gaussian kernel for kernel density estimation.
Optionally, as shown in fig. 4 and fig. 5, calculating the first distribution of the state parameters of each type of health state and the second distribution of the history parameters of each type of health state by using the method of the kernel density estimation may further include:
step S402, taking the horizontal axis as time and the vertical axis as the numerical value of the state parameter, and generating a first histogram of the state parameter;
Step S404, moving the Gaussian kernel function between each point of the first histogram to fit a first probability density curve of the state parameter;
and step S406, adjusting the window width of the Gaussian kernel function until the first probability density curve is used as the first distribution under the condition that the accuracy of the kernel density estimation reaches an optimal value.
In the embodiment of the application, the data acquired in the target time period can be expressed in the form of a histogram to obtain a first histogram, and then the kernel density estimation is carried out on the data by adopting a Gaussian kernel function so as to fit a first probability density curve corresponding to the data. And adjusting the window width of the Gaussian kernel function until the accuracy of the kernel density estimation reaches an optimal value, and taking a first probability density curve as the first distribution.
Step S502, taking the horizontal axis as time and the vertical axis as the numerical value of the history parameter, and generating a second histogram of the history parameter;
step S504, moving the Gaussian kernel function between each point of the second histogram to fit a second probability density curve of the history parameter;
And S506, adjusting the window width of the Gaussian kernel function until the second probability density curve is used as a second distribution under the condition that the accuracy of the kernel density estimation reaches an optimal value.
In the embodiment of the application, the data of the period corresponding to the past year can be expressed in the form of a histogram to obtain a second histogram, and then the kernel density estimation is carried out on the data by adopting a Gaussian kernel function so as to fit a second probability density curve corresponding to the data. And adjusting the window width of the Gaussian kernel function until the accuracy of the kernel density estimation reaches an optimal value, and taking a second probability density curve as the second distribution.
Optionally, as shown in fig. 6, the method further includes adjusting the window width of the gaussian kernel as follows:
Step S602, determining an integral square error of a state parameter and/or a history parameter, wherein the integral square error takes a window width as a parameter;
step S604, calculating the expectation of the integral square error to obtain an integral average error;
Step S606, carrying out Taylor series expansion on the integral average error to obtain a progressive mean square error;
in step S608, when the window width minimizes the value of the progressive mean square error, the adjustment of the window width is stopped.
In the embodiment of the application, the window width is an important parameter for controlling the estimation precision of the nuclear density. Too small a window width results in a function with zero function values for points other than the data points. Therefore, too small a window width would make it an meaningless estimate that noise generated by random error terms is not excluded. While too large a window width gives an excessively smooth curve, close to a straight line, the estimation at this time is not significant at all.
To evaluate the properties of the density estimator, letFor the estimation of f over the whole support area, an integral square error is introduced:
If one wants to discuss the general nature of the estimator, it is reasonable to average ISE (h) over all possible samples. The integrated average error is:
MISE(h)＝E{ISE(h)}
Where the desire is with respect to the distribution f. Thus MISE (h) can be seen as the average of the overall measure of error ISE (h) with respect to sample density. Again by the desirability and interchangeability of integration,
Wherein,
Both MISE and ISE can be used to study the criteria for selecting the h value.
The expression MISE (h) indicates that the choice of window width is a compromise between bias and variance.
In practice, only a string of values for h needs to be tried, and then a suitable one is chosen.
In the embodiment of the application, the following window width selection method can be adopted:
one measure of a given function g is defined:
R(g)＝∫g2(z)dz
By performing Taylor-series expansion on each item in MISE (h), the following can be obtained:
Wherein,
Known as progressive mean square error. The optimal window width can be obtained by minimum value of the above equation about h.
Optionally, as shown in fig. 7, determining a plurality of canonical values of the difference between the first distribution of the state parameters of each type of health state and the second distribution of the history parameters of the corresponding same type of health state includes:
Step S702, determining a plurality of KL divergence values between the first distribution and each of the second distributions, the KL divergence values being used to represent differences between the first distribution and each of the second distributions;
step S704, discretizing the plurality of KL divergence values, and taking the logarithm of the discretized plurality of KL divergence values to obtain a plurality of standard values.
In the embodiment of the present application, the plurality of standard values for determining the difference between the first distribution of the state parameters of each type of health state and the second distribution of the history parameters of the corresponding same type of health state are the differences between the first distribution D n+1 and the second distribution D 1,D2,...,Dn to which the data collected in the same year period obey, and the above standard values (difference measurement values) may be measured by using KL divergence:
Distance(p，q)＝[KL(p，q)+KL(q，p)]/2
Where p is the first distribution and q is the respective second distribution, so that the KL divergence can be used here to measure the distance of the two distributions.
The difference between the different distributions was measured before, yielding a series of KL divergence values, which were noted as KL 1,KL2,...,KLn(KLn being close to the time period to be evaluated). These difference metrics are then normalized. The distribution of the KL divergence values is sparse. For this feature of the data, KL 1,KL2,...,KLn may be logarithmized, and when a final evaluation is made on a parameter, a method may be adopted to weight these difference metric values, that is, the closer to the difference metric value of the time period to be evaluated, the greater the weight obtained, and the weighted sum of the respective KL divergence and the weight is taken as the respective index-level health status score of the basic component:
E＝k1×log K L1+k2×log K L2+...+kn×log K Ln(k1＜k2＜...＜kn).
alternatively, the individual index level health scores for the base part may also be obtained based on a threshold. Some indexes can adopt a threshold judgment mode, and firstly, judgment of whether the indexes are qualified or not is given. Further statistical methods are used to give a specific quantization level for the index. The evaluation result is given for the adopted trend evaluation method with long-term change trend. The parameters of the basic components have smooth fluctuation, frequent fluctuation and long-term degradation in the running process of the system.
For the fluctuation stable parameters, firstly, judging according to engineering threshold values, determining the health state range of the parameters for preliminary evaluation, if the fluctuation of the parameters deviates from the expected fluctuation range, calculating the average relative error of the parameters in the evaluation period, normalizing the relative error, and then determining the final health state score of the parameters.
For the fluctuation frequent parameter, firstly, judging according to an engineering threshold value, determining the health state range of the parameter for preliminary evaluation, performing offset calculation by utilizing the corresponding distribution of the parameter in the history synchronization and the distribution of the parameter in the current health state evaluation period, determining the offset, and determining the final health state score of the parameter after normalizing the offset.
For the long-term degradation parameters, firstly, judging according to engineering threshold values, determining the health state range of the parameters for preliminary evaluation, calculating the total degradation level and degradation rate in the evaluation period for the degradation occurrence part, weighting and normalizing the total degradation level and degradation rate, and determining the final health state score of the parameters.
Optionally, before determining the third health data of the target system using the second weights configured for the respective components and the second health data of the respective components, as shown in fig. 8, the method further includes determining the second weights as follows:
Step S802, constructing a pair comparison matrix of a plurality of parts by utilizing interaction relations among the parts;
step S804, calculating weight vectors of the pair comparison matrix;
step S806, calculating an optimal weight vector of the weight vectors by using the genetic algorithm, wherein the weight value in the optimal weight vector is used as the second weight.
In the embodiment of the application, a hierarchical analysis method is adopted to determine the weight of each component in the system based on the importance degree of each component in the system to the system. The analytic hierarchy process analyzes and determines the importance of various factors by decomposing the problems, judges the scheme and comprehensively obtains the conclusion. In the hierarchical analysis, if each factor of the upper layer dominates or is affected by all factors of the lower layer, the hierarchical structure is called a complete hierarchical structure, otherwise, the hierarchical structure is called an incomplete hierarchical structure. The mathematical expression is constructed into a judgment matrix, and the weights of the factors are calculated, so that the obtained numerical value represents the advantages and disadvantages of the decision scheme, and a scientific basis is provided for final decision.
In the embodiment of the application, the pair comparison matrix is constructed to obtain the influence degree of each component on the system, and the weight vector is further calculated on the pair comparison matrix so as to score the subsequent comprehensive health state. The weight vector may be calculated by an averaging method, a feature root method, a least square method, or the like, and the feature root method may be preferably employed in the present application.
In the embodiment of the application, the optimal weight vector of the weight vector can be calculated by adopting a genetic algorithm. The optimal weight vector is the minimum value of the objective function, so that global random search can be adopted in programming, and the variables are randomly selected to meet the requirementsThe objective function is minF (D):
And (3) adopting real number coding to randomly generate a group of groups, substituting the groups into an objective function to calculate the fitness, and sequencing. And then, copying the group according to a sorting selection method, intersecting and mutating according to a preset probability, generating a next generation group, and then continuing to calculate the fitness. When inheritance is carried out for a plurality of generations, the corresponding individual is output after meeting the termination criterion, namely an optimal weight vector w, and each weight value in the optimal weight vector is used as a second weight corresponding to each component.
The technical scheme of the application is that first health data of various health states in various health states of parts in a target system are obtained; determining second health data of the part by using the first weights configured for the various health states and the first health data of the various health states; determining third health data of a target system by using second weights configured for the parts and the second health data of the parts, wherein the target system is a system used by a spacecraft; a health state of the plurality of states that matches the third health data is determined. The application can finish the system-level health state detection from the bottom layer parameters to the parts, is more comprehensive, has more accurate detection results, and can be widely applied to various systems of the spacecraft.
According to still another aspect of the embodiment of the present application, as shown in fig. 9, there is provided a system health detection apparatus of a spacecraft, including: the index level detection module 901 is configured to obtain first health data of various health states in various health states of components in the target system; the component level detection module 903 is configured to determine second health data of the component by using the first weights configured for each health state and the first health data of each health state; a system level detection module 905, configured to determine third health data of a target system by using the second weights configured for each component and the second health data of each component, where the target system is a system used by a spacecraft; a health status discrimination module 907 is configured to determine a health status of the plurality of status that matches the third health data.
It should be noted that, the index level detection module 901 in this embodiment may be used to perform step S202 in the embodiment of the present application, the component level detection module 903 in this embodiment may be used to perform step S204 in the embodiment of the present application, the system level detection module 905 in this embodiment may be used to perform step S206 in the embodiment of the present application, and the health status discrimination module 907 in this embodiment may be used to perform step S208 in the embodiment of the present application.
It should be noted that the above modules are the same as examples and application scenarios implemented by the corresponding steps, but are not limited to what is disclosed in the above embodiments. It should be noted that the above modules may be implemented in software or hardware as a part of the apparatus in the hardware environment shown in fig. 1.
Optionally, the system health detection device of the spacecraft further comprises: the detection time determining module is used for determining a target time period for detecting the current health state according to a preset starting time and a preset ending time; the parameter acquisition module is used for acquiring state parameters of various health states in a target time period and acquiring history parameters of various health states in a history synchronization period, wherein the history synchronization period is each period of target time period of a spacecraft use target system which does not comprise the current detection time period; the probability distribution calculation module is used for calculating the first distribution of the state parameters of various health states and the second distribution of the history parameters of various health states by using a nuclear density estimation mode; a canonical value calculation module for determining a plurality of canonical values of the differences between a first distribution of state parameters for each type of health state and a second distribution of historical parameters for the corresponding same type of health state; and the parameter index level health detection module is used for determining the first health data according to the third weight matched with the plurality of standard values and each standard value.
Optionally, the probability distribution calculation module is further configured to: taking the horizontal axis as time and the vertical axis as the numerical value of the state parameter, and generating a first histogram of the state parameter; moving the Gaussian kernel function between each point of the first histogram to fit a first probability density curve of the state parameter; adjusting the window width of the Gaussian kernel function until the accuracy of kernel density estimation reaches an optimal value, and taking a first probability density curve as the first distribution; and generating a second histogram of the history parameter with the horizontal axis as time and the vertical axis as a numerical value of the history parameter; moving the Gaussian kernel function between points of the second histogram to fit a second probability density curve of the history parameter; and (3) adjusting the window width of the Gaussian kernel function until the accuracy of the kernel density estimation reaches an optimal value, and taking a second probability density curve as a second distribution.
Optionally, the system health detection device of the spacecraft further comprises: the window width adjusting module is used for determining an integral square error of the state parameter and/or the history parameter, and the integral square error takes the window width as a parameter; calculating the expectation of the integral square error to obtain an integral average error; carrying out Taylor series expansion on the integral average error to obtain a progressive mean square error; the adjustment of the window width is stopped in case the window width minimizes the value of the progressive mean square error.
Optionally, the specification value calculation module is further configured to: determining a plurality of KL-divergence values between the first distribution and each of the second distributions, the KL-divergence values being indicative of a difference between the first distribution and each of the second distributions; discretizing the plurality of KL divergence values, and taking the logarithm of the plurality of the discrete KL divergence values to obtain a plurality of standard values.
Optionally, the parameter index level health detection module is further configured to: and taking the sum of products of the standard values and the corresponding third weights as first health data, wherein the generation time of the history parameters of the standard values is obtained, and the third weights matched with the standard values are larger as the generation time is closer to the current detection time period.
Optionally, the component level detection module is further configured to: the sum of the products of the plurality of first health data and the corresponding first weights is taken as second health data.
Optionally, the system level detection module is further configured to: and taking the sum of products of the plurality of second health data and the corresponding second weights as third health data.
Optionally, the system health detection device of the spacecraft further comprises: the second weight determining module is used for constructing a pair comparison matrix of the parts by utilizing the interaction relation between the parts; calculating weight vectors of the pair comparison matrixes; and calculating an optimal weight vector of the weight vector by using a genetic algorithm, wherein the weight value in the optimal weight vector is used as a second weight.
According to another aspect of the embodiments of the present application, as shown in fig. 10, the present application provides an electronic device, including a memory 1001, a processor 1003, a communication interface 1005, and a communication bus 1007, where the memory 1001 stores a computer program executable on the processor 1003, and the memory 1001, the processor 1003 communicates with the communication bus 1007 through the communication interface 1005, and the processor 1003 implements the steps of the method when executing the computer program.
The memory and the processor in the computer device communicate with the communication interface through a communication bus. The communication bus may be a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, or the like. The communication bus may be classified as an address bus, a data bus, a control bus, or the like.
The memory may include random access memory (Random Access Memory, RAM) or may include non-volatile memory (non-volatile memory), such as at least one disk memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, abbreviated as CPU), a network processor (Network Processor, abbreviated as NP), etc.; but may also be a digital signal processor (DIGITAL SIGNAL Processing, DSP), application Specific Integrated Circuit (ASIC), field-Programmable gate array (FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components.
There is also provided, in accordance with yet another aspect of embodiments of the present application, a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the steps of any of the embodiments described above.
Optionally, in an embodiment of the present application, the computer readable medium is arranged to store program code for the processor to:
Acquiring first health data of various health states of the parts in the target system;
Determining second health data of the part by using the first weights configured for the various health states and the first health data of the various health states;
Determining third health data of a target system by using second weights configured for the parts and the second health data of the parts, wherein the target system is a system used by a spacecraft;
A health state of the plurality of states that matches the third health data is determined.
Alternatively, specific examples in this embodiment may refer to examples described in the foregoing embodiments, and this embodiment is not described herein.
When the embodiment of the application is specifically implemented, the above embodiments can be referred to, and the application has corresponding technical effects.
It is to be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For a hardware implementation, the Processing units may be implemented within one or more Application SPECIFIC INTEGRATED Circuits (ASICs), digital signal processors (DIGITAL SIGNAL Processing, DSPs), digital signal Processing devices (DSP DEVICE, DSPD), programmable logic devices (Programmable Logic Device, PLDs), field-Programmable gate arrays (Field-Programmable GATE ARRAY, FPGA), general purpose processors, controllers, micro-controllers, microprocessors, other electronic units for performing the functions described herein, or a combination thereof.
For a software implementation, the techniques described herein may be implemented by means of units that perform the functions described herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be additional divisions when actually implemented, for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the embodiments of the present application may be embodied in essence or a part contributing to the prior art or a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, etc. It should be noted that in this document, relational terms such as "first" and "second" and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
The foregoing is only a specific embodiment of the application to enable those skilled in the art to understand or practice the application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (6)
1. A method for detecting system health of a spacecraft, comprising:
The method for acquiring the first health data of various health states in the various health states of the parts in the target system comprises the following steps: determining a target time period for detecting the current health state according to a preset starting time and a preset ending time; acquiring state parameters of various health states in the target time period, and acquiring history parameters of various health states in a history synchronization, wherein the history synchronization is the target time period of the spacecraft using the target system without the current detection time period; calculating a first distribution of the state parameters of each type of the health state and a second distribution of the history parameters of each type of the health state by using a nuclear density estimation mode; determining a plurality of canonical values of differences between the first distribution of the state parameters for each type of the state of health and the second distribution of the history parameters for the respective same type of the state of health; determining the first health data according to a third weight matched with a plurality of the specification values and each specification value;
Determining second health data for the component using first weights configured for the respective types of health states and the first health data for the respective types of health states, comprising: taking as the second health data the sum of the products of a plurality of the first health data and the corresponding first weights, the first weights being set in advance according to experimental results or in advance according to expert knowledge;
Determining third health data of the target system using second weights configured for each of the components and the second health data of each of the components, comprising: taking the sum of the products of a plurality of the second health data and the corresponding second weights as the third health data, wherein the target system is a system used by the spacecraft;
determining a health state of the plurality of states that matches the third health data;
The method further includes determining the second weight as follows: constructing a pair comparison matrix of a plurality of parts by utilizing the interaction relation between every two parts; calculating weight vectors of the pair of comparison matrixes; and calculating an optimal weight vector of the weight vectors by using a genetic algorithm, wherein the weight value in the optimal weight vector is used as the second weight.
2. The method of claim 1, wherein calculating a first distribution of the state parameters for each type of the state of health and a second distribution of the history parameters for each type of the state of health using a nuclear density estimation comprises:
taking the horizontal axis as time and the vertical axis as the numerical value of the state parameter, and generating a first histogram of the state parameter;
Moving a Gaussian kernel function between points of the first histogram to fit a first probability density curve of the state parameter;
adjusting the window width of the Gaussian kernel function until the accuracy of kernel density estimation reaches an optimal value, and taking the first probability density curve as the first distribution;
And
Taking the horizontal axis as time and the vertical axis as the numerical value of the history parameter, and generating a second histogram of the history parameter;
Moving the Gaussian kernel function between points of the second histogram to fit a second probability density curve of the history parameter;
And adjusting the window width of the Gaussian kernel function until the accuracy of kernel density estimation reaches an optimal value, and taking the second probability density curve as the second distribution.
3. The method of claim 2, further comprising adjusting the window width of the gaussian kernel as follows:
determining an integral square error of the state parameter and/or the history parameter, wherein the integral square error takes the window width as a parameter;
calculating the expectation of the integral square error to obtain an integral average error;
Carrying out Taylor series expansion on the integral average error to obtain a progressive mean square error;
and stopping the adjustment of the window width when the window width minimizes the value of the progressive mean square error.
4. The method of claim 1, wherein determining a plurality of canonical values of differences between the first distribution of the state parameters for each type of the state of health and the second distribution of the history parameters for the respective same type of the state of health comprises:
determining a plurality of KL-divergence values between the first distribution and each of the second distributions, wherein the KL-divergence values are used to represent differences between the first distribution and each of the second distributions;
discretizing a plurality of KL divergence values, and taking the logarithm of the discretized KL divergence values to obtain a plurality of standard values.
5. The method of claim 4, wherein determining the first health data based on a third weight that matches a plurality of the canonical values and each of the canonical values comprises:
And taking the sum of products of the standard values and the corresponding third weights as the first health data, wherein the generation time of the history parameters of the standard values is obtained, and the third weights matched with the standard values are larger as the generation time is closer to the current detection time period.
6. A system health detection device for a spacecraft, comprising:
The index level detection module is used for acquiring first health data of various health states in various health states of parts in a target system, and comprises the following steps: determining a target time period for detecting the current health state according to a preset starting time and a preset ending time; acquiring state parameters of various health states in the target time period, and acquiring history parameters of various health states in a history synchronization, wherein the history synchronization is the target time period of the spacecraft using the target system without the current detection time period; calculating a first distribution of the state parameters of each type of the health state and a second distribution of the history parameters of each type of the health state by using a nuclear density estimation mode; determining a plurality of canonical values of differences between the first distribution of the state parameters for each type of the state of health and the second distribution of the history parameters for the respective same type of the state of health; determining the first health data according to a third weight matched with a plurality of the specification values and each specification value;
A component level detection module, configured to determine second health data of the component using first weights configured for each type of the health states and the first health data of each type of the health states, including: taking as the second health data the sum of the products of a plurality of the first health data and the corresponding first weights, the first weights being set in advance according to experimental results or in advance according to expert knowledge;
a system level detection module for determining third health data of the target system using second weights configured for each of the components and the second health data of each of the components, comprising: taking the sum of the products of a plurality of the second health data and the corresponding second weights as the third health data, wherein the target system is a system used by the spacecraft;
The health state judging module is used for determining the health state matched with the third health data in the plurality of states;
The second weight determining module is specifically configured to: constructing a pair comparison matrix of a plurality of parts by utilizing the interaction relation between every two parts; calculating weight vectors of the pair of comparison matrixes; and calculating an optimal weight vector of the weight vectors by using a genetic algorithm, wherein the weight value in the optimal weight vector is used as the second weight.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011254719.XA CN112381380B (en) | 2020-11-11 | 2020-11-11 | System health detection method and device for spacecraft |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011254719.XA CN112381380B (en) | 2020-11-11 | 2020-11-11 | System health detection method and device for spacecraft |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112381380A CN112381380A (en) | 2021-02-19 |
| CN112381380B true CN112381380B (en) | 2024-05-21 |
Family
ID=74582642
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011254719.XA Active CN112381380B (en) | 2020-11-11 | 2020-11-11 | System health detection method and device for spacecraft |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112381380B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116307943A (en) * | 2023-05-18 | 2023-06-23 | 山东通维信息工程有限公司 | Highway electromechanical system health index evaluation method based on analytic hierarchy process |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106777997A (en) * | 2016-04-18 | 2017-05-31 | 中国西安卫星测控中心 | A kind of heath state of spacecraft appraisal procedure |
| CN110210161A (en) * | 2019-06-12 | 2019-09-06 | 中国神华能源股份有限公司 | Appraisal procedure, device and the storage medium of rail vehicle health status |
| CN110222437A (en) * | 2019-06-12 | 2019-09-10 | 中国神华能源股份有限公司 | Appraisal procedure, device and the storage medium of train car team health status |
| CN110795510A (en) * | 2019-10-22 | 2020-02-14 | 北京空间技术研制试验中心 | Spacecraft system health state evaluation method based on high-dimensional data association mining |
| CN111401795A (en) * | 2020-04-26 | 2020-07-10 | 新智数字科技有限公司 | Method and device for evaluating health state of equipment, readable medium and electronic equipment |
| CN111812427A (en) * | 2020-05-29 | 2020-10-23 | 中电普瑞电力工程有限公司 | Health state assessment method and system for power electronic device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105976074A (en) * | 2015-10-21 | 2016-09-28 | 乐卡汽车智能科技（北京）有限公司 | Vehicle health parameter generation and presentation method and device |
| TWI669617B (en) * | 2018-10-12 | 2019-08-21 | 財團法人工業技術研究院 | Health monitor method for an equipment and system thereof |
-
2020
- 2020-11-11 CN CN202011254719.XA patent/CN112381380B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106777997A (en) * | 2016-04-18 | 2017-05-31 | 中国西安卫星测控中心 | A kind of heath state of spacecraft appraisal procedure |
| CN110210161A (en) * | 2019-06-12 | 2019-09-06 | 中国神华能源股份有限公司 | Appraisal procedure, device and the storage medium of rail vehicle health status |
| CN110222437A (en) * | 2019-06-12 | 2019-09-10 | 中国神华能源股份有限公司 | Appraisal procedure, device and the storage medium of train car team health status |
| CN110795510A (en) * | 2019-10-22 | 2020-02-14 | 北京空间技术研制试验中心 | Spacecraft system health state evaluation method based on high-dimensional data association mining |
| CN111401795A (en) * | 2020-04-26 | 2020-07-10 | 新智数字科技有限公司 | Method and device for evaluating health state of equipment, readable medium and electronic equipment |
| CN111812427A (en) * | 2020-05-29 | 2020-10-23 | 中电普瑞电力工程有限公司 | Health state assessment method and system for power electronic device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112381380A (en) | 2021-02-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112731159B (en) | Method for pre-judging and positioning battery faults of battery compartment of energy storage power station | |
| CN105975443B (en) | Network anomalous behaviors detection method and system based on Lasso | |
| CN112327191B (en) | Battery diving probability evaluation method based on geometric feature fusion decision | |
| CN113255848B (en) | Water turbine cavitation sound signal identification method based on big data learning | |
| CN112633421A (en) | Method and device for detecting abnormal electricity utilization behavior of user | |
| CN109784528A (en) | Water quality prediction method and device based on time series and support vector regression | |
| CN112101554A (en) | Anomaly detection method and device, equipment and computer-readable storage medium | |
| US20220382229A1 (en) | Machining condition searching device and machining condition searching method | |
| CN113409166A (en) | XGboost model-based method and device for detecting abnormal electricity consumption behavior of user | |
| CN112381380B (en) | System health detection method and device for spacecraft | |
| CN112307536A (en) | Dam seepage parameter inversion method | |
| CN114003900A (en) | Network intrusion detection method, device and system for secondary system of transformer substation | |
| CN113537693A (en) | Personnel risk level obtaining method, terminal and storage device | |
| CN117629122A (en) | Dam displacement monitoring and early warning method and system | |
| CN117171702A (en) | Multi-mode power grid fault detection method and system based on deep learning | |
| CN111898664B (en) | Bridge modal parameter automatic identification method based on Block-Bootstrap and multi-stage clustering | |
| CN113052256B (en) | Wind direction clustering method and device and electronic equipment | |
| Chen et al. | Uncertain random accelerated degradation modelling and statistical analysis with aleatory and epistemic uncertainties from multiple dimensions | |
| CN111026661A (en) | Method and system for comprehensively testing usability of software | |
| CN117057236B (en) | Optical fiber temperature measuring point evaluation system based on laser | |
| KR20200145347A (en) | Method and apparatus for predicting stock price based on case-by-company event identification and multi-category emotional analysis | |
| CN117367751B (en) | Performance detection method and device for ultra-pulse thulium-doped laser | |
| Bingjie et al. | An improved similarity-based prognostics method for remaining useful life estimation of aero-engine | |
| Lu et al. | Dynamic weight-based accelerated test modeling for fault degradation and lifetime analysis | |
| CN117992726A (en) | Multi-stage early warning method, device, equipment and medium for rotary machine |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information |
Inventor after: Wang Xinfeng Inventor after: Hu Weigang Inventor after: He Xiaoqiong Inventor after: Sun Jian Inventor after: Fang Hongzheng Inventor after: Luo Kai Inventor after: Fan Huanzhen Inventor after: Li Rui Inventor after: Wang Xiaodong Inventor after: Yang Hao Inventor after: Liu Yong Inventor before: Wang Xinfeng Inventor before: Yang Hao Inventor before: Liu Yong Inventor before: Hu Weigang Inventor before: He Xiaoqiong Inventor before: Sun Jian Inventor before: Fang Hongzheng Inventor before: Luo Kai Inventor before: Miao Xuewen Inventor before: Zhang Jun Inventor before: Fan Huanzhen Inventor before: Li Rui Inventor before: Wang Xiaodong |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |