CN110163403A - Tactical missile failure prediction method based on gray theory - Google Patents
Tactical missile failure prediction method based on gray theory Download PDFInfo
- Publication number
- CN110163403A CN110163403A CN201810370400.XA CN201810370400A CN110163403A CN 110163403 A CN110163403 A CN 110163403A CN 201810370400 A CN201810370400 A CN 201810370400A CN 110163403 A CN110163403 A CN 110163403A
- Authority
- CN
- China
- Prior art keywords
- health factor
- health
- time
- group
- test data
- 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.)
- Pending
Links
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to tactical missile failure predication technical field more particularly to a kind of tactical missile failure prediction methods based on gray theory.This method comprises: the historical test data based on tactical missile establishes health factor group;Prediction time slot is determined based on the historical test data of the health factor in the health factor group;Based on the prediction time slot to there are the health factor data sequence of shortage of data progress Data Whitenings to operate to obtain corresponding clear figure in the health factor group;Historical test data and the clear figure based on the health factor in the health factor group determine that with the time be the Grey Theory Forecast model referred to;The time that each health factor breaks down in the health factor group is determined based on the Grey Theory Forecast model.Tactics failure predication can be effectively solved the problems, such as a result, realize and tactics Missile Fault is predicted.
Description
Technical field
The present invention relates to tactical missile failure predication technical field more particularly to a kind of tactical missiles based on gray theory
Failure prediction method.
Background technique
Tactical missile after the states such as storage, detection and breakdown maintenance after a period of time, internal material performance
Variation will lead to storage reliability decline, eventually leads to guided missile state and occurs slowly to degenerate.Since guided missile individual is experienced
The difference of the factors such as environmental stress, service condition, maintenance and repair situation, the speed that state is degenerated also difference.In view of war
Art guided missile collects machinery, chemical industry, hydraulic, starting, electronics, electrical, infrared and optics dress as a kind of typical complex Hi-Tech equipment
It is placed in one, has the characteristics that small in size, structure is complicated, system relationship is strong, with high content of technology, reliability requirement is high, therefore
Its health status can not be developed and establish accurate mathematical model.Meanwhile actually ensureing in utilization, tactical missile has again
" long-term storage, first use " feature, equipment Test ensure that data are rare, can not predict war using traditional statistical analysis technique
The decline of art missile performance and time of failure.
Summary of the invention
It is an object of the invention to overcome the shortage of prior art, a kind of tactical missile failure based on gray theory is provided
Prediction technique is able to solve above-mentioned the problems of the prior art.
Technical solution of the invention: a kind of tactical missile failure prediction method based on gray theory, this method packet
It includes:
Historical test data based on tactical missile establishes health factor group;
Prediction time slot is determined based on the historical test data of the health factor in the health factor group;
Based on the prediction time slot, in the health factor group, there are the progress of the health factor data sequence of shortage of data
Data Whitening operates to obtain corresponding clear figure;
Historical test data and the clear figure based on the health factor in the health factor group, which were determined with the time, is
The Grey Theory Forecast model of reference;
The time that each health factor breaks down in the health factor group is determined based on the Grey Theory Forecast model.
The historical test data for being preferably based on tactical missile establishes health factor group and includes:
The historical test data of the tactical missile is pre-processed to obtain tactical missile historical test data sequence;
Health factor alternative collection is obtained based on the tactical missile historical test data sequence;
Trend analysis is carried out to the health factor in the health factor alternative collection;
Using the health factor of one group of one-dimensional Long-term change trend as the parameter basis of building health factor group;
The historical test data of the health factor of one group of one-dimensional Long-term change trend is classified according to affiliated missile subsystem
To construct the statistic for embodying corresponding missile subsystem performance change;
The Long-term change trend feature of each subsystem is obtained in the variation of the statistic of different time using each subsystem, and
According to the corresponding failure threshold of the health factor of the Long-term change trend feature of each subsystem and one group of one-dimensional Long-term change trend
Value determines the corresponding failure threshold of statistic of each subsystem, to obtain the health factor group.
It is preferably based on the tactical missile historical test data sequence and obtains health factor alternative collection and include:
Selection and guided missile health status strong correlation from the numerical value shape parameter of the tactical missile historical test data sequence
Parameter obtain the health factor alternative collection.
Preferably in carrying out trend analysis to the health factor in the health factor alternative collection includes:
On time according to the corresponding all historical test data indices of the health factor in the health factor alternative collection
Between sequentially draw carry out trend analysis.
It is preferably based on the Grey Theory Forecast model and determines that each health factor breaks down in the health factor group
Time include:
The prediction result of at least one following predetermined time slot of each health factor is obtained based on the Grey Theory Forecast model;
Prediction result and corresponding failure threshold based on each health factor determine each health in the health factor group
The time that the factor breaks down.
The prediction result and corresponding failure threshold for being preferably based on each health factor determine in the health factor group
The time that each health factor breaks down includes:
The prediction result corresponding time for being greater than corresponding failure threshold in the prediction result of each health factor is determined
The time broken down for the health factor.
Preferably, this method further include:
Based on the time that each health factor in the health factor group breaks down determine that tactical missile breaks down when
Between.
Be preferably based on the time that each health factor breaks down in the health factor group determine tactical missile occur therefore
The time of barrier includes:
Time earliest in time that each health factor breaks down is determined as the time that tactical missile breaks down.
Through the above technical solutions, can be based on the health in the health factor group established by tactical missile test data
The historical data of the factor determines prediction time slot, can be to there are shortage of data in the health factor group based on the prediction time slot
Health factor data sequence carry out Data Whitening operate to obtain corresponding clear figure, the historical data based on the health factor
It can determine that with the time be the Grey Theory Forecast model referred to the clear figure, and then can be pre- based on the gray theory
Survey the time that model determines that each health factor breaks down in the health factor group.It is pre- that tactics failure can effectively be solved as a result,
The problem of survey is realized and is predicted tactics Missile Fault, to provide decision support for Missile Equipment preventative maintenance, in turn
Improve equipment availability and safeguard level.
Detailed description of the invention
Included attached drawing is used to provide to be further understood from the embodiment of the present invention, and which constitute one of specification
Point, for illustrating the embodiment of the present invention, and come together to illustrate the principle of the present invention with verbal description.It should be evident that below
Attached drawing in description is only some embodiments of the present invention, for those of ordinary skill in the art, is not paying creation
Property labour under the premise of, be also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of process of the tactical missile failure prediction method based on gray theory provided in an embodiment of the present invention
Figure;
Fig. 2 is a kind of flow chart for the method for establishing health factor group provided in an embodiment of the present invention.
Specific embodiment
Specific embodiments of the present invention are described in detail below in conjunction with attached drawing.In the following description, for solution
Purpose and not restrictive is released, elaborates detail, to help to be apparent from the present invention.However, to those skilled in the art
It is readily apparent that the present invention can also be practiced in the other embodiments departing from these details for member.
It should be noted that only showing in the accompanying drawings in order to avoid having obscured the present invention because of unnecessary details
Gone out with closely related device structure and/or processing step according to the solution of the present invention, and be omitted with relationship of the present invention not
Big other details.
Fig. 1 is a kind of process of the tactical missile failure prediction method based on gray theory provided in an embodiment of the present invention
Figure.
As shown in Figure 1, a kind of tactical missile failure prediction method based on gray theory provided in an embodiment of the present invention can
To include:
S100, the historical test data based on tactical missile establish health factor group;
S102 determines prediction time slot based on the historical test data of the health factor in the health factor group, that is, determines
The time interval of historical test data divides;
For example, prediction time slot can be determined according to the time of measuring interval of historical test data.
S104, based on the prediction time slot to there are the health factor data sequences of shortage of data in the health factor group
Data Whitening is carried out to operate to obtain corresponding clear figure;
S106, historical test data based on the health factor in the health factor group and the clear figure determine with when
Between for reference Grey Theory Forecast model;
S108 determines that each health factor in the health factor group breaks down based on the Grey Theory Forecast model
Time.
Through the above technical solutions, can be based on the health in the health factor group established by tactical missile test data
The historical data of the factor determines prediction time slot, can be to there are shortage of data in the health factor group based on the prediction time slot
Health factor data sequence carry out Data Whitening operate to obtain corresponding clear figure, the historical data based on the health factor
It can determine that with the time be the Grey Theory Forecast model referred to the clear figure, and then can be pre- based on the gray theory
Survey the time that model determines that each health factor breaks down in the health factor group.It is pre- that tactics failure can effectively be solved as a result,
The problem of survey is (that is, the status data solved in the tactical missile use process with " long-term storage, first use " is poor
Weary problem), it realizes and tactics Missile Fault is predicted, to provide decision support for Missile Equipment preventative maintenance, in turn
Improve equipment availability and safeguard level.
In other words, method of the present invention is pre- with the time based on equipping (tactical missile) historical test data
Reference is surveyed, with GM (1,1) model (that is, Grey Theory Forecast model) for prediction model, realizes the failure predication to tactical missile.
Wherein, the historical test data of tactical missile is the primary information resource for reflecting the variation of tactical missile health status.
Health factor group (Health Index Group, HIG) is the series of parameters combination for being able to reflect equipment general health,
It is with the storage and use of equipment, and each parameter is with rising or downward trend.
Fig. 2 is a kind of flow chart for the method for establishing health factor group provided in an embodiment of the present invention.
As shown in Fig. 2, S100 shown in Fig. 1 health factor group is established based on the historical test data of tactical missile can be with
Include:
S1002 pre-processes the historical test data of the tactical missile to obtain tactical missile historical test data
Sequence;
S1004 obtains health factor alternative collection based on the tactical missile historical test data sequence;
S1006 carries out trend analysis to the health factor in the health factor alternative collection;
S1008, using the health factor of one group of one-dimensional Long-term change trend (that is, monotonic increase or successively decrease) as building health factor
The parameter basis of group;
S1010, by the historical test data of the health factor of one group of one-dimensional Long-term change trend according to affiliated missile subsystem into
Row classification is to construct the statistic for embodying corresponding missile subsystem performance change;
For example, the historical test data of the corresponding health factor of each subsystem can be integrated to obtain corresponding point
The statistic of system.Wherein, the statistic of each subsystem can change over time.
S1012, the variation using each subsystem in the statistic of different time obtain the Long-term change trend of each subsystem
Feature (for example, increaseing or decreasing), and according to the Long-term change trend feature of each subsystem and one group of one-dimensional Long-term change trend
The corresponding failure threshold of health factor determines the corresponding failure threshold of the statistic of each subsystem, to obtain the health
Factor group (for example, it is available include M parameters tactical missile health factor group (x1,x2,…,xM))。
It is, building health factor group's can find multiple one-dimensional sequences from the test data of its different time,
The sequence with a certain change curve with temporal characteristics variable present it is certain rise or fall trend, thus can use its table
Levy the health status variation of tactical missile.Also, in view of tactical missile is during utilization, equipment is before use, long-term place
In stored condition, and tactical missile is as typical complex electronic system, external environment and permanent unused device when can be because of storage
The reasons such as part aging cause the biggish performance degradation of tactical missile, so being in the present invention with reference to constructing tactics with time quantum
Guided missile health factor.
Wherein, it is pre-processed by the historical test data to tactical missile, can be converted into numerical value shape parameter
Digital quantity type data carry out secondary treatment, convert numerical value shape parameter for it.
According to an embodiment of the present invention, health is obtained based on the tactical missile historical test data sequence in S1004
Factor alternative collection may include:
Selection and guided missile health status strong correlation from the numerical value shape parameter of the tactical missile historical test data sequence
Parameter obtain the health factor alternative collection.
It is, filtering out numeric type test parameter, selection and equipment health status in each test parameter of tactical missile
The parameter item of strong correlation obtains equipment health factor alternative collection.
According to an embodiment of the present invention, trend is carried out to the health factor in the health factor alternative collection in S1006
Analysis may include:
On time according to the corresponding all historical test data indices of the health factor in the health factor alternative collection
Between sequentially draw carry out trend analysis.
Thus, it is possible to according to the available trend analysis result of data variation in the figure drawn (for example, the list of parameter
Adjust incremental or monotone decreasing trend).
According to an embodiment of the present invention, the health factor group is determined based on the Grey Theory Forecast model in S108
In time for breaking down of each health factor may include:
The prediction result of at least one following predetermined time slot of each health factor is obtained based on the Grey Theory Forecast model
(that is, the predicted value of each health factor in future time);
Prediction result and corresponding failure threshold (the corresponding failure threshold of each health factor based on each health factor
Value) determine the time that each health factor breaks down in the health factor group.
According to an embodiment of the present invention, the prediction result based on each health factor and corresponding failure threshold determine institute
Stating the time that each health factor breaks down in health factor group may include:
Corresponding failure threshold (the corresponding failure threshold of each health factor will be greater than in the prediction result of each health factor
Value) the prediction result corresponding time be determined as the time that the health factor breaks down.
For example, firstly, the historical test data based on health factor, can determine reasonable prediction time slot, namely
Determine that the time interval of historical test data divides;After prediction time slot determines, for there are data in health factor group's sequence
The part of missing can carry out the operation of health factor data sequence Data Whitening.
Since tactical missile is the trend development constantly degenerated to performance, health factor is also presented monotone increasing and adds deduct
The data of small trend, missing are an Interval Gray Number, and the both ends in section are respectively its two adjacent time slot health factor data.Mirror
Lack in the value distributed intelligence of health factor, therefore the albefaction of health factor ash data can be obtained using mean value whitening approach
Value, specific whitening approach are as follows.
Assuming that the original data sequence (that is, to carry out the data sequence of albefaction) of health factor are as follows:
X(0)=(x(0)(1),x(0)(2),…,x(0)(n))。 (1)
Wherein k-th of data is a grey number(x(0)(k)) (k ≠ 1 and k ≠ n), the adjacent two data difference of its in sequence
For x(0)(k+1) and x(0)(k-1), then known to(x(0)(k)) clear figure[4]Are as follows:
Then enable α=1/2 that can obtain x(0)(k) mean value clear figure are as follows:
When there is adjacent multiple grey numbers, using the above process successively by each grey number albefaction.
By in health factor sequence it is all ash numbers carry out albefactions after, further according to GM (1,1) model prediction basic principle into
Row failure predication:
Remember X(1)For X(0)One-accumulate formation sequence:
X(1)=(x(1)(1),x(1)(2),…,x(1)(n))。 (4)
Wherein,
By accumulation process, compared to original series X(0), X(1)The consistent level of formation sequence is increased, and random journey
Degree is weakened, and the influence of noise in data is reduced.
Utilize formation sequence X(1)Construct GM (1,1) model mean value form albinism differential equation:
Wherein, parameter a is known as development coefficient, the developing state of reaction sequence, and b is known as model cooperation index, reflects data
Between transformation relation.Parameter a, b are solved using least square method:
Wherein Y, B are respectively as follows:
Y=[x0(2),x0(3),…,x0(n)]T。 (10)
It solves the differential equation (6), prediction model can be obtained:
Regressive reduction is made to formula (10) again, health factor original data series X can be obtained(0)Grey forecasting model are as follows:
Failure predication can be carried out to tactical missile according to each health factor predicted value and failure threshold according to above formula.With
For the health factor of monotonic increase, it is assumed that health factor x failure threshold is Tx, and thrashing in m-th time slot then solves not
Equation equation group:
According to above formula, it can determine the time slot position that each parameter of tactical missile breaks down, obtain prediction result.
According to an embodiment of the present invention, this method can also include:
Based on the time that each health factor in the health factor group breaks down determine that tactical missile breaks down when
Between.
Wherein, the time broken down based on each health factor in the health factor group determines that tactical missile breaks down
Time may include:
Time earliest in time that each health factor breaks down is determined as the time that tactical missile breaks down.
For example, tactical missile each health factor out-of-service time, i.e., the time that each parameter breaks down, under are obtained
Formula (14) is stated to merge each health factor failure predication result, tactical missile failure predication can be obtained as a result, according to
Prediction result, it is proposed that targetedly equipment repair suggestion.
The tactical missile failure prediction method of the present invention based on gray theory is described below with reference to example.
Specifically, by taking certain tactical missile as an example, the tactical missile is in T0It delivers in year into labour, is equipping time two groups of surveys of generation
Data are tried, remove T later0+ 4 years outer, generates one group of test data every year.By taking the equipment as an example, in T0+ 7 beginning of the years application present invention
The method carries out failure predication.
The type tactical missile historical test data includes T0-T0+ 6 times amounted to 7 groups of test datas, wherein T0It tests within+2 years
In data, key equipment A test data has two packets, wherein the first packet test data is imperfect, it only include first few items test item knot
Fruit, and intermediate a certain data test result is overproof, it is confirmed to work as time unreliable link of test cable plug, therefore lead to this
Test failure patches again by cable plug, and after checking again for exact p-value state, key equipment A test passes.By
It is imperfect in the first packet test data, and include error items, while working as the unreliable connection of cable in time test may be test
As a result noise is introduced, therefore the packet test data is done into delete processing as singular value;Meanwhile according to the record in test data
Data convert the index that part can be converted into numeric type data, such as by test item: the qualified or not signal of resistance (number
Amount, is converted into corresponding resistivity measurements);Further, since T0Year generates two groups of test datas, it is contemplated that test interval twice
It is smaller, therefore processing is averaged to test result, synthesis obtains T0The equipment Test data in year.
Tactical missile historical test data is carried out, it can be seen that include many tests in tactical missile historical test data
Unit and project, projects and unit testing result are comprehensive, available tactical missile historical test data sequence.Then,
Principle is constructed according to equipment health factor, digital quantity parameter in test data is rejected, while screening and equipment performance strong correlation
Quality test item (for example, inertial navigation position error, steering engine controls error etc.), to obtain equipment health factor alternative collection;It
After can test numbers by simple statistical method, such as by the corresponding all history of the health factor in health factor alternative collection
According to indices in chronological order described point draw etc., complete the trend analysis of historical test data;By trend analysis, Ke Yixuan
Take out parameter basis of one group of parameter (health factor) with one-dimensional Long-term change trend as building health factor;Based on the group list
The historical test data for tieing up the parameter of Long-term change trend is classified according to affiliated missile subsystem to construct and embody corresponding guided missile point
The statistic of system performance variation, for example, some projects are carried out comprehensive (carry out the control error of four steering engines of level-one comprehensive
Close, taking the maximum fan rudder face control error of error change is that level-one steering engine controls error assessment value), while being using each point
System obtains the Long-term change trend feature of each subsystem in the variation of the statistic of different time, and according to the trend of each subsystem
The corresponding failure threshold of health factor of variation characteristic and one group of one-dimensional Long-term change trend determines the system of each subsystem
Measure corresponding failure threshold, so as to obtain include 4 parameters equipment health factor group (x1,x2,x3,x4),
In the corresponding failure threshold of each health factor may refer to the following table 1 (table 1 indicate each in the health factor group of tactical missile to be predicted
The corresponding failure threshold of health factor), referring to the following table 2, (table 2 indicates the health factor of tactical missile to be predicted to historical test data
The corresponding historical test data of each health factor in group).
The corresponding failure threshold of each health factor in the health factor group of the tactical missile to be predicted of table 1
Wherein, those skilled in the art can predefine the health factor group of tactical missile to be predicted according to the actual situation
In the corresponding failure threshold of each health factor, the present invention is defined not to this.
The corresponding historical test data of each health factor in the health factor group of the tactical missile to be predicted of table 2
The corresponding historical test data of each health factor, can be easy in health factor group based on aforementioned tactical missile
Ground determines that prediction time slot is 1 year;After prediction time slot determines, for T in health factor sequence0The portion of+4 years health datas missing
Point, health factor data sequence data mean value whitening operation can be carried out using formula (1)-(3), to obtain type equipment T0+4
The test data clear figure in year, (table 3 indicates the health factor T of tactical missile to be predicted as shown in table 30+ 4 annual data albefactions
Value).
The health factor T of the tactical missile to be predicted of table 30+ 4 annual data clear figures
Data based on table 2 and table 3 can obtain the grey forecasting model of each health factor using formula (1)~(9),
And realize the prediction developed to each health factor of tactical missile, this makes it possible to obtain the prediction results of each factor the five-year, such as table 4
It is shown that (table 4 indicates the prediction result of each health factor in the health factor group of tactical missile to be predicted, and wherein runic indicates that this is strong
Kang Yinzi prediction result is more than corresponding failure threshold).
The prediction result of each health factor in the health factor group of the tactical missile to be predicted of table 4
According to the predicted value of health factor each in health factor group and formula (13), the failure to tactical missile may be implemented
Prediction, obtains the time slot position that each health factor breaks down, and (table 5 indicates each health of tactical missile to be predicted as shown in table 5
Factor fault time prediction result).
Each health factor fault time prediction result of the tactical missile to be predicted of table 5
According to prediction result shown in formula (14) and table 5, each health factor prediction result of the tactical missile is melted
It closes, it is that the equipment may be in T that prediction result, which can be obtained,0It breaks down within+9 years, overproof index is x3.And based on the pre- of the equipment
It surveys as a result, the index development of equipment can be paid close attention to, and fitting in order to which related guarantee mechanism is in the guarantee maintenance in later period
When time carry out preventative maintenance.
As above it describes for a kind of embodiment and/or the feature that shows can be in a manner of same or similar at one or more
It is used in a number of other embodiments, and/or combines or substitute the feature in other embodiments with the feature in other embodiments
It uses.
It should be emphasized that term "comprises/comprising" refers to the presence of feature, one integral piece, step or component when using herein, but simultaneously
It is not excluded for the presence or additional of one or more other features, one integral piece, step, component or combinations thereof.
The method more than present invention can be by hardware realization, can also be by combination of hardware software realization.The present invention relates to this
The computer-readable program of sample can be such that the logical block realizes described above when the program is performed by logical block
Device or component parts, or the logical block is made to realize various method or steps described above.The invention further relates to for depositing
Store up the storage medium of procedure above, such as hard disk, disk, CD, DVD, flash memory.
The many features and advantage of these embodiments are clear according to the detailed description, therefore appended claims are intended to
Cover all these feature and advantage of these embodiments fallen into its true spirit and range.Further, since this field
Technical staff is readily apparent that many modifications and changes, therefore is not meant to for the embodiment of the present invention to be limited to illustrated and description essence
Really structurally and operationally, but all suitable modifications and the equivalent fallen within the scope of its can be covered.
Unspecified part of the present invention is known to the skilled person technology.
Claims (8)
1. a kind of tactical missile failure prediction method based on gray theory, which is characterized in that this method comprises:
Historical test data based on tactical missile establishes health factor group;
Prediction time slot is determined based on the historical test data of the health factor in the health factor group;
Based on the prediction time slot to there are the health factor data sequences of shortage of data to carry out data in the health factor group
Whitening operation obtains corresponding clear figure;
Historical test data and the clear figure based on the health factor in the health factor group determine that with the time be reference
Grey Theory Forecast model;
The time that each health factor breaks down in the health factor group is determined based on the Grey Theory Forecast model.
2. the method according to claim 1, wherein historical test data based on tactical missile establish health because
Subgroup includes:
The historical test data of the tactical missile is pre-processed to obtain tactical missile historical test data sequence;
Health factor alternative collection is obtained based on the tactical missile historical test data sequence;
Trend analysis is carried out to the health factor in the health factor alternative collection;
Using the health factor of one group of one-dimensional Long-term change trend as the parameter basis of building health factor group;
The historical test data of the health factor of one group of one-dimensional Long-term change trend is classified according to affiliated missile subsystem with structure
Build the statistic for embodying corresponding missile subsystem performance change;
The Long-term change trend feature of each subsystem is obtained in the variation of the statistic of different time using each subsystem, and according to
The Long-term change trend feature of each subsystem and the corresponding failure threshold of health factor of one group of one-dimensional Long-term change trend are true
The corresponding failure threshold of statistic of fixed each subsystem, to obtain the health factor group.
3. according to the method described in claim 2, it is characterized in that, being obtained based on the tactical missile historical test data sequence
Health factor alternative collection includes:
The ginseng with guided missile health status strong correlation is selected from the numerical value shape parameter of the tactical missile historical test data sequence
Number obtains the health factor alternative collection.
4. according to the method described in claim 2, it is characterized in that, being carried out to the health factor in the health factor alternative collection
Trend analysis includes:
It is temporally suitable according to the corresponding all historical test data indices of the health factor in the health factor alternative collection
Sequence, which is drawn, carries out trend analysis.
5. the method according to claim 1, wherein determining the health based on the Grey Theory Forecast model
The time that each health factor breaks down in factor group includes:
The prediction result of at least one following predetermined time slot of each health factor is obtained based on the Grey Theory Forecast model;
Prediction result and corresponding failure threshold based on each health factor determine each health factor in the health factor group
The time broken down.
6. according to the method described in claim 5, it is characterized in that, prediction result and corresponding mistake based on each health factor
Effect threshold value time for determining that each health factor breaks down in the health factor group includes:
The prediction result corresponding time for being greater than corresponding failure threshold in the prediction result of each health factor is determined as this
The time that health factor breaks down.
7. method according to claim 1 to 6, which is characterized in that this method further include:
The time that tactical missile breaks down is determined based on the time that each health factor in the health factor group breaks down.
8. the method according to the description of claim 7 is characterized in that event occurs based on health factor each in the health factor group
The time that the time of barrier determines that tactical missile breaks down includes:
Time earliest in time that each health factor breaks down is determined as the time that tactical missile breaks down.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810370400.XA CN110163403A (en) | 2018-04-24 | 2018-04-24 | Tactical missile failure prediction method based on gray theory |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810370400.XA CN110163403A (en) | 2018-04-24 | 2018-04-24 | Tactical missile failure prediction method based on gray theory |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110163403A true CN110163403A (en) | 2019-08-23 |
Family
ID=67644794
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810370400.XA Pending CN110163403A (en) | 2018-04-24 | 2018-04-24 | Tactical missile failure prediction method based on gray theory |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110163403A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114860496A (en) * | 2022-05-25 | 2022-08-05 | 苏州浪潮智能科技有限公司 | Cluster fault duration prediction method, device, equipment and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030014692A1 (en) * | 2001-03-08 | 2003-01-16 | California Institute Of Technology | Exception analysis for multimissions |
CN102208028A (en) * | 2011-05-31 | 2011-10-05 | 北京航空航天大学 | Fault predicting and diagnosing method suitable for dynamic complex system |
CN104461771A (en) * | 2014-11-03 | 2015-03-25 | 北京百度网讯科技有限公司 | Data backup processing method and device |
CN104596767A (en) * | 2015-01-13 | 2015-05-06 | 北京工业大学 | Method for diagnosing and predicating rolling bearing based on grey support vector machine |
CN105974225A (en) * | 2016-04-28 | 2016-09-28 | 上海机电工程研究所 | Fault diagnosis system based on distributed detection data and fault diagnosis method thereof |
-
2018
- 2018-04-24 CN CN201810370400.XA patent/CN110163403A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030014692A1 (en) * | 2001-03-08 | 2003-01-16 | California Institute Of Technology | Exception analysis for multimissions |
CN102208028A (en) * | 2011-05-31 | 2011-10-05 | 北京航空航天大学 | Fault predicting and diagnosing method suitable for dynamic complex system |
CN104461771A (en) * | 2014-11-03 | 2015-03-25 | 北京百度网讯科技有限公司 | Data backup processing method and device |
CN104596767A (en) * | 2015-01-13 | 2015-05-06 | 北京工业大学 | Method for diagnosing and predicating rolling bearing based on grey support vector machine |
CN105974225A (en) * | 2016-04-28 | 2016-09-28 | 上海机电工程研究所 | Fault diagnosis system based on distributed detection data and fault diagnosis method thereof |
Non-Patent Citations (1)
Title |
---|
李小力 等: "改进的灰色预测模型在导弹中的应用", 《计算机仿真》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114860496A (en) * | 2022-05-25 | 2022-08-05 | 苏州浪潮智能科技有限公司 | Cluster fault duration prediction method, device, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Thöns | On the value of monitoring information for the structural integrity and risk management | |
CN114323644B (en) | Gear box fault diagnosis and signal acquisition method and device and electronic equipment | |
CN110807257A (en) | Method for predicting residual life of aircraft engine | |
Shi et al. | Rolling bearing initial fault detection using long short-term memory recurrent network | |
CN109376401B (en) | Self-adaptive multi-source information optimization and fusion mechanical residual life prediction method | |
EP2384971B1 (en) | Method of determining a maneuver performed by an aircraft | |
CN108375474B (en) | A kind of aero-engine transition state critical performance parameters prediction technique | |
CN113298297B (en) | Wind power output power prediction method based on isolated forest and WGAN network | |
WO2015052408A1 (en) | Monitoring of an aircraft engine to anticipate maintenance operations | |
CN109886328B (en) | Electric vehicle charging facility fault prediction method and system | |
CN115809405A (en) | Fan main shaft gear box temperature anomaly detection method based on multi-feature fusion | |
FR3095424A1 (en) | System and method for monitoring an aircraft engine | |
CN114330101A (en) | Slope earthquake slip prediction method and system based on artificial neural network | |
CN114330517A (en) | Neural network-based aircraft engine sensor fault self-diagnosis method | |
CN111337244A (en) | Method and device for monitoring and diagnosing faults of input shaft of fan gearbox | |
CN105408828B (en) | To being used to detecting the method that the reference point of engine abnormity estimated and the data handling system for implementing this method on curve | |
CN114330120B (en) | 24-Hour PM prediction based on deep neural network2.5Concentration method | |
CN110163403A (en) | Tactical missile failure prediction method based on gray theory | |
Wang et al. | Evaluating weather influences on transmission line failure rate based on scarce fault records via a bi‐layer clustering technique | |
FR2957170A1 (en) | Equipment monitoring system designing tool for engine of aircraft, involves processing unit evaluating quantification of monitoring system based on quality value of result corresponding to output quality value associated with output module | |
CN110889186B (en) | Consistency test method for degradation data of accelerated storage and natural storage of ash correlation analysis | |
CN110895624B (en) | Method for testing consistency of degraded data of accelerated storage and natural storage based on maximum entropy spectrum estimation | |
CN116127354A (en) | High-voltage cable partial discharge fault positioning method and system based on deep learning | |
CN113744888B (en) | Regional epidemic trend prediction and early warning method and system | |
CN113157992B (en) | Fan sensor data reconstruction method and device and computer readable storage medium |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190823 |