CN107944090A - Gas turbine engine systems performance prediction method based on critical component failure model - Google Patents
Gas turbine engine systems performance prediction method based on critical component failure model Download PDFInfo
- Publication number
- CN107944090A CN107944090A CN201711048187.2A CN201711048187A CN107944090A CN 107944090 A CN107944090 A CN 107944090A CN 201711048187 A CN201711048187 A CN 201711048187A CN 107944090 A CN107944090 A CN 107944090A
- Authority
- CN
- China
- Prior art keywords
- gas turbine
- turbine engine
- critical component
- engine systems
- component
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Control Of Turbines (AREA)
Abstract
The present invention relates to a kind of gas turbine engine systems performance prediction method based on critical component failure model, gas turbine engine systems are layered;The weighing factor that component to system are carried out using analytic hierarchy process (AHP) is analyzed;Obtain the reliability variation tendency of critical component;According to the reliability analysis of critical component as a result, using the weight coefficient between the component and system obtained in step analysis, the reliability variation tendency of whole gas turbine engine systems is calculated.The present invention is by being layered gas turbine engine systems, construct weights influence matrix, establish from component to the foreseeable basis of system progressive, carry out the prediction of critical component performance degradation trend using life cycle management data, each critical component and system are associated quantification treatment, realizes and the performance change trend in whole system future is obtained by the degraded performance prediction result of critical component.
Description
Technical field
The present invention relates to field of electromechanical technology, more particularly to a kind of gas turbine engine systems based on critical component failure model
Performance prediction method.
Background technology
Since gas turbine engine systems are complicated, regime mode change is various, and each component intercouples influence, therefore combustion gas
Expander system often frees failure, while as one of main propulsion system in naval vessel, gas turbine engine systems, which break down, not only can
Cause naval vessel to be forced to suspend, influence efficiency of navigation, and very high maintenance cost can be brought, or even trigger security incident.Therefore
For Vessel personnel system performance prediction techniques research for reduce rate of breakdown, ensure naval vessel normal/cruise ten
Divide important.
Traditional performance prediction method passes through least square method, gray model etc. usually using some component as research object
Data variation trend is fitted, but the slight change of underlying component performance is sometimes in systematic parameter it is difficult to or can not be direct
Reflection is caught, cause that component degradation trend is serious and system monitoring parameter not less than fault threshold phenomenon.
Least square method is divided into linear trend and nonlinear trend according to historical data, establishes the mathematical model of hypothesis and leads to
The variation tendency of historical data is crossed to determine model parameter, but least square method can not meet high-precision requirement, it is necessary to which priori is known
Know.
Gray model is considered as observation data sequence the grey colo(u)r specification changed over time, new by cumulative or inverse accumulated generating
Sequence, progressively makes grey colo(u)r specification albefaction, is predicted so as to establish Differential Equation Model.Gray model presence cannot do long-term forecast
The problem of.
The content of the invention
In view of above-mentioned analysis, the present invention is intended to provide a kind of gas turbine engine systems based on critical component failure model
Energy Forecasting Methodology, is associated quantification treatment by each critical component and system, realizes the performance prediction knot by critical component
Fruit obtains the performance change trend in whole system future.
The purpose of the present invention is mainly achieved through the following technical solutions:
A kind of gas turbine engine systems performance prediction method based on critical component failure model, comprises the following steps:
Step S1, three layers of decomposition carry out gas turbine engine systems based on gas turbine engine systems 26S Proteasome Structure and Function feature, will fires
Gas turbine system resolves into three subsystem, key equipment and critical component levels;
Step S2, by the combing to gas turbine engine systems 26S Proteasome Structure and Function from top to bottom, carried out using analytic hierarchy process (AHP)
The weighing factor of component to system is analyzed, and obtains the weight coefficient between component and system;
Step S3, performance degradation trend prediction is carried out to the critical components of gas turbine engine systems, obtain critical component can
By spending variation tendency;
Step S4, according to the reliability variation tendency of critical component, using the component obtained in step analysis and system it
Between weight coefficient, calculate the reliability variation tendencies of whole gas turbine engine systems.
Further, three layers of decomposition in the step S1, first layer divide gas turbine engine systems from functional perspective
For dynamical system, transmission system and control system three subsystems;Each subsystem is carried out refinement and decomposes key setting by the second layer
Standby level, key equipment refer to the equipment to play a key effect to each subsystem normal operation;In last foundation ship actual motion
Common fault type, trouble unit, then key equipment level is refine to critical component level.
Further, the analytic hierarchy process (AHP) in the step S2 comprises the following steps:
Step S201, each factor that gas turbine engine systems break down is determined;The factor is to combine gas turbine expert
System and scene are actually determined;
Step S202, each factor is grouped to form mutually disjoint level according to the difference of attribute, the element pair of last layer
Next layer of adjacent element is all or dominating role is played in part, and the top-down successively dominance relation of level is pressed in formation;
Step S203, after recursive hierarchy structure is established, the membership of element between levels is determined, with comparing two-by-two
Multilevel iudge matrix A two-by-two is established compared with method:A=(aij)n×nTo determine the weight of each factor, the n represents the rank of judgment matrix
Number;
Step S204, according to the weight calculation of each layer factorWherein, n represents the exponent number of judgment matrix,
λmaxFor the maximum eigenvalue of judgment matrix;
Step S205, CI is judged, if no more than 0.1, carries out step S206;If greater than 0.1, step is jumped back to
Rapid S202, redefines the hierarchical structure of each factor;
Step S206, by calculating the weights influence coefficient of target between layers, and finally determine that component arrives system
Weight coefficient.
Further, the gas turbine engine systems critical component performance degradation trend in the step S3 is with SVM prediction moulds
Type is analyzed and predicted, and is comprised the following steps:
Step S301, the termination threshold value of critical component is set;
Step S302, critical component degraded data is trained and predicted using SVM prediction models;
Step S303, the feature degenerated curve of the critical component of prediction is normalized;
Step S304, the form parameter m and scale parameter η with the Weibull distribution of feature degenerated curve fitting are determined;
Step S305, the form parameter m and scale parameter η are brought into formula
Obtain the prediction data of critical component life-cycle reliability.
Further, the SVM training detailed process is as follows:
(1) in the vibration signal of life cycle management, time extraction characteristic signal x at equal intervalsi(N), characteristic signal is formed
Sequence { x1(N),x2(N),…,xm(N)};Wherein m is the characteristic signal number after time segmentation at equal intervals;
(2) characteristic quantity including RMS and kurtosis of the sequence of calculation, using it as performance degradation characteristic quantity, formative
Can degenerative character amount sequence { Dp,…,Dm, 0 < p < m;
(3) performance degenerative character amount sequence { D is passed throughp,…,DmTraining Support Vector Machines SVM models;
(4) prediction to unknown data is realized using trained support vector machines model.
Further, the characteristic signal can reflect critical component failure spy including bearing vibration signal
Sign, influences the signal of critical component reliability.
Further, using the critical component life-cycle performance degradation trend forecasting method, to bearing, main shaft, impeller,
Blade, air exhauster, cylinder, fuel nozzle, igniter, connection combustion pipe, bypass mechanism, torque tube, turbine touch mouth, gear, belt, change
Fast device, controlling switch and control component, the reliability variation tendency of 17 kinds of gas turbine engine systems critical components are predicted, obtain
To the prediction data of the gas turbine engine systems critical component life-cycle reliability.
Further, Weibull distribution degradation ratio curve matching is carried out to data after normalization, according to Weibull distribution
Expression formulaDetermine to meet the form parameter m and scale parameter η under the degenerated form.
Further, the termination threshold value of the critical component is according to the species including the critical component, model, building ring
Factor including border is specifically set.
Further, the reliability variation tendency formula of the whole gas turbine engine systemsRepresent,
Wherein n is component count, and R (i) is each components reliability, σiFor the corresponding weight of each component.
The present invention has the beneficial effect that:
1) the top-down hierarchical structure of gas turbine engine systems is divided, have studied with analytic hierarchy process (AHP) between each layer
Influence relation, is characterized in the form of weight coefficient, has finally been constructed by the weight shadow of bottom critical component to top layer system
Matrix is rung, has been established from component to the foreseeable basis of system progressive.
2) prediction of critical component performance degradation trend, structure have been carried out using existing rolling bearing life cycle management data
SVM prediction model is made, obtained prediction result has higher matching degree with primitive curve.
3) bearing performance prediction data is converted into bearing degradation rate curve by Weibull distribution, is met this and moves back
Relevant parameter under change form, and obtained the reliability of bearing with the parameter.
4) gas turbine engine systems have been obtained not using analytic hierarchy process (AHP) by each critical component reliability calculating result of bottom
The reliability variation tendency come, thus reflects the situation of change of gas turbine engine systems performance degradation trend.
Brief description of the drawings
Attached drawing is only used for showing the purpose of specific embodiment, and is not considered as limitation of the present invention, in whole attached drawing
In, identical reference symbol represents identical component.
Fig. 1 is gas turbine engine systems overall performance decline trend method flow diagram;
Fig. 2 is the gas turbine engine systems level hierarchical structure according to gas turbine engine systems 26S Proteasome Structure and Function analysis result structure
Figure;
Fig. 3 is step analysis flow chart;
Fig. 4 is to reflect the performance trend flow chart of gas turbine engine systems by the performance trend prediction except axis;
Fig. 5 is the partial data result to be trained and predict using SVM;
Fig. 6 is the partial data result to be trained and predict using SVM;
Fig. 7 is the degradation ratio curve of fitting Weibull distribution;
Fig. 8 is the reliability change trend curve of bearing;
Fig. 9 is the reliability change trend curve of complete machine.
Embodiment
The preferred embodiment of the present invention is specifically described below in conjunction with the accompanying drawings, wherein, attached drawing forms the application part, and
It is used to explain the principle of the present invention together with embodiments of the present invention.
The specific embodiment of the present invention, discloses a kind of gas turbine engine systems based on critical component failure model
Energy Forecasting Methodology, the method predict gas turbine engine systems entirety using gas turbine engine systems critical component performance degradation trend
Performance degradation trend, as shown in Figure 1, comprising the following steps:
Step S1, three layers of decomposition carry out gas turbine engine systems based on gas turbine engine systems 26S Proteasome Structure and Function feature, will fires
Gas turbine system resolves into three subsystem, key equipment and critical component levels
Since gas turbine engine systems huge structure is complicated, the present invention is according to marine gas turbine system structure and work(
Can analysis result, gas turbine engine systems are carried out with three layers of decomposition, as shown in Fig. 2, first layer from functional perspective by combustion gas wheel
Machine system is divided into dynamical system, transmission system and control system three subsystems;Each subsystem is carried out refinement decomposition by the second layer
To key equipment level, the key equipment refers to the equipment to play a key effect to each subsystem normal operation, for example, dynamical system
The key equipment of system includes low-pressure compressor, high-pressure compressor, combustion chamber, low pressure turbine and high pressure turbine;The pass of transmission system
Button apparatus includes gear, belt and gearbox, and the key equipment of control system includes controlling switch and control component;Again finally
Key equipment level is refine to critical component level, foundation is fault type common in ship actual motion, trouble unit progress
Division, for example, for dynamical system refinement critical component include main shaft, impeller, blade, air exhauster, cylinder, fuel nozzle,
Igniter, connection combustion pipe, bypass mechanism, torque tube and turbine touch mouth.This dividing mode meets system-equipment-component level
Thought is associated, and partition process makes division result more have scientific and accuracy using typical fault in engineering as reference.
Step S2, by the combing to gas turbine engine systems 26S Proteasome Structure and Function from top to bottom, carried out using analytic hierarchy process (AHP)
The weighing factor of component to system is analyzed, and obtains the weight coefficient between component and system
Judgment matrix of each layer relative to last layer is actually obtained by expert system and scene first, then in single standard
The relative weighting of each element is then calculated down.
As shown in figure 3, step analysis comprises the following steps:
Step S201, each factor that gas turbine engine systems break down is determined;
The gas turbine engine systems failure problems of labyrinth are decomposed into its part or factor, each is because being called usually
For element.With reference to each factor of the actual definite gas turbine engine systems failure problems of gas turbine expert system and scene.
Step S202, the hierarchical structure of each factor is determined;
Each factor is grouped to form mutually disjoint level according to the difference of attribute, the element of last layer is to adjacent next
Layer element is all or dominating role is played in part, and the top-down successively dominance relation of level, i.e. Recurison order hierarchy are pressed in formation.
Step S203, each layer factor is compared in pairs;
After recursive hierarchy structure is established, determine the membership of element between levels, established with tournament method
Multilevel iudge matrix A two-by-two:A=(aij)n×nTo determine the weight of each factor, the n represents the exponent number of judgment matrix.
The judgment matrix has following property:aij> 0;aii=1, i, j=1 ..., n.
The A is positive reciprocal matrix, when the element of A has transitivity, i.e. aij·ajk=aik, k=1 ..., n are set up
When, then A is referred to as consistency matrix;When exporting element sequencing weight by judgment matrix, consistency matrix is significant.
Step S204, according to the weight calculation CI of each layer factor;
After each element weight order is obtained, consistency check is carried out, coincident indicator CI is:
Wherein, n represents the exponent number of judgment matrix, λmaxFor the maximum eigenvalue of judgment matrix.
Step S205, CI is judged, if no more than 0.1, carries out step 206;If greater than 0.1, step is jumped back to
Rapid 202, redefine the hierarchical structure of each factor.
Step S206, by calculating the weights influence coefficient of target between layers, and finally determine that component arrives system
Weight coefficient.
Step S3, performance degradation trend prediction is carried out to the critical components of gas turbine engine systems, obtain critical component can
By spending variation tendency
The characteristic parameter of gas turbine engine systems critical feature data is analyzed and predicted with SVM prediction models,
Obtain going out degradation ratio curve using Weibull Distribution after prediction data, the relevant parameter being met under the degenerated form,
And obtain the reliability variation tendency of critical component, i.e. critical component performance degradation trend with the parameter.
By taking bearing as an example, the described pre- flow gauge of gas turbine engine systems critical component such as Fig. 4, detailed step is as follows:
Step S301, the termination threshold value of bearing is set.The setting of threshold value is according to the species, model, building ring of critical component
The factors such as border are specifically set.For the effective Value Data of bearing, we assume here that the life end point of bearing is the bearing
RMS value reach 0.725, therefore, set the threshold value of RMS as 0.725.
Step S302, bearing degradation data are trained and predicted using SVM prediction models;
Existing bearing data are predicted by the threshold value of setting, until data reach the threshold value of setting.The present invention
Bearing data are trained and predicted using SVM prediction models, SVM training detailed process is as follows:
(1) in the vibration signal of life cycle management, time extraction vibration signal x at equal intervalsi(N), vibration signal is formed
Sequence { x1(N),x2(N),…,xm(N)};Wherein m is the vibration signal number after time segmentation at equal intervals;
(2) characteristic quantities such as RMS and the kurtosis of the sequence are calculated, are moved back it as performance degradation characteristic quantity, forming properties
Change characteristic quantity sequence { Dp,…,Dm, 0 < p < m;
(3) performance degenerative character amount sequence { D is passed throughp,…,DmTraining Support Vector Machines SVM models;
(4) bearing features degenerated curve is predicted to realize using trained support vector machines model, obtained
Reach the prediction data of given threshold.
Fig. 5 and Fig. 6 is the partial data result to be trained and predict using SVM.From figure it can be found that pair
It is higher in the precision of prediction of bearing features parameter, can preferably it be approached in the estimation range of 20 steps with original degenerated curve.
Step S303, the bearing features degenerated curve of prediction is normalized;
After the prediction data of given threshold must be reached using SVM prediction algorithms, it is necessary to the data that prediction obtains into
Row normalized, normalized are to allow prediction data to be represented with the same order of magnitude, and change procedure is brighter
It is aobvious.
Step S304, the form parameter m and scale parameter η with the Weibull distribution of feature degenerated curve fitting are determined;
According to the expression formula of Weibull distributionDetermine to meet under the degenerated form
Form parameter m and scale parameter η.As shown in fig. 7, be the Weibull distribution degradation ratio curve after data fitting after normalization,
The form parameter m and scale parameter η for meeting the degenerated form are obtained from this curve.
Step S305, bearing reliability trend determines;The form parameter m and scale parameter η that will meet under the degenerated form
Bring formula intoObtain the prediction data of bearing life-cycle reliability.As shown in figure 8,
For by the parameter determined by Weibull distribution degradation ratio matched curve obtain under the working environment, the reliability of the bearing
Change trend curve.In curve, bearing reliability before breaking down is declined with the change rate of a very little, when event occurs in bearing
After barrier, reliability declines rapidly, and when rapid rise occurs for the characteristic value of bearing, reliability also reaches a very low value.
According to above-mentioned bearing life-cycle performance degradation trend forecasting method, to main shaft, impeller, blade, air exhauster, cylinder,
Fuel nozzle, igniter, connection combustion pipe, bypass mechanism, torque tube, turbine touch mouth, gear, belt, speed changer, controlling switch and control
Component processed, the reliability variation tendency of 16 kinds of gas turbine engine systems critical components are predicted, and obtain the gas turbine system
The prediction data for critical component life-cycle reliability of uniting.
Step S4, according to the reliability variation tendency of critical component, using the component obtained in step analysis and system it
Between weight coefficient, calculate the reliability variation tendencies of whole gas turbine engine systems
According to formulaCalculate the reliability R of whole gas turbine engine systemsrVariation tendency, wherein n are
Component count, R (i) are each components reliability, σiFor the corresponding weight of each component.
The results are shown in Figure 9.As can be seen from Figure 9 the reliability of complete machine is following is presented downward trend, that is, illustrates combustion gas
The performance of expander system gradually fails with the time.
It will be understood by those skilled in the art that realizing all or part of flow of above-described embodiment method, meter can be passed through
Calculation machine program instructs relevant hardware to complete, and the program can be stored in computer-readable recording medium.Wherein, institute
Computer-readable recording medium is stated as disk, CD, read-only memory or random access memory etc..
The foregoing is only a preferred embodiment of the present invention, but protection scope of the present invention be not limited thereto,
Any one skilled in the art the invention discloses technical scope in, the change or replacement that can readily occur in,
It should be covered by the protection scope of the present invention.
Claims (10)
1. a kind of gas turbine engine systems performance prediction method based on critical component failure model, it is characterised in that including following
Step:
Step S1, three layers of decomposition carry out gas turbine engine systems based on gas turbine engine systems 26S Proteasome Structure and Function feature, by combustion gas wheel
Machine system decomposition is into three subsystem, key equipment and critical component levels;
Step S2, by the combing to gas turbine engine systems 26S Proteasome Structure and Function from top to bottom, analytic hierarchy process (AHP) is utilized to carry out component
Weighing factor to system is analyzed, and obtains the weight coefficient between component and system;
Step S3, performance degradation trend prediction is carried out to the critical component of gas turbine engine systems, obtains the reliability of critical component
Variation tendency;
Step S4, according to the reliability variation tendency of critical component, using between the component and system obtained in step analysis
Weight coefficient, calculates the reliability variation tendency of whole gas turbine engine systems.
2. Forecasting Methodology according to claim 1, it is characterised in that three layers in step S1 decomposition, first layer from
Functional perspective sets out is divided into dynamical system, transmission system and control system three subsystems by gas turbine engine systems;The second layer will
Each subsystem carries out refinement and decomposes key equipment level, and key equipment refers to what is played a key effect to each subsystem normal operation
Equipment;Common fault type, trouble unit in last foundation ship actual motion, then key equipment level is refine to crucial portion
Part level.
3. Forecasting Methodology according to claim 1, it is characterised in that the analytic hierarchy process (AHP) in the step S2 includes following
Step:
Step S201, each factor that gas turbine engine systems break down is determined;The factor is to combine gas turbine expert system
It is actually determined with scene;
Step S202, each factor is grouped to form mutually disjoint level according to the difference of attribute, the element of last layer is to adjacent
Next layer of element it is all or dominating role is played in part, the top-down successively dominance relation of level is pressed in formation;
Step S203, after recursive hierarchy structure is established, the membership of element between levels is determined, with tournament method
Establish multilevel iudge matrix A two-by-two:A=(aij)n×nTo determine the weight of each factor, the n represents the exponent number of judgment matrix;
Step S204, according to the weight calculation of each layer factorWherein, n represents the exponent number of judgment matrix, λmax
For the maximum eigenvalue of judgment matrix;
Step S205, CI is judged, if no more than 0.1, carries out step S206;If greater than 0.1, step is jumped back to
S202, redefines the hierarchical structure of each factor;
Step S206, by calculating the weights influence coefficient of target between layers, and finally determine component to the weight of system
Coefficient.
4. Forecasting Methodology according to claim 1, it is characterised in that the gas turbine engine systems key portion in the step S3
Part performance degradation trend is analyzed and predicted with SVM prediction models, is comprised the following steps:
Step S301, the termination threshold value of critical component is set;
Step S302, critical component degraded data is trained and predicted using SVM prediction models;
Step S303, the feature degenerated curve of the critical component of prediction is normalized;
Step S304, the form parameter m and scale parameter η with the Weibull distribution of feature degenerated curve fitting are determined;
Step S305, the form parameter m and scale parameter η are brought into formulaObtain
The prediction data of critical component life-cycle reliability.
5. Forecasting Methodology according to claim 4, it is characterised in that
The SVM training detailed process is as follows:
(1) in the vibration signal of life cycle management, time extraction characteristic signal x at equal intervalsi(N), characteristic signal sequence is formed
{x1(N),x2(N),…,xm(N)};Wherein m is the characteristic signal number after time segmentation at equal intervals;
(2) characteristic quantity including RMS and kurtosis of the sequence of calculation, is moved back it as performance degradation characteristic quantity, forming properties
Change characteristic quantity sequence { Dp,…,Dm, 0 < p < m;
(3) performance degenerative character amount sequence { D is passed throughp,…,DmTraining Support Vector Machines SVM models;
(4) prediction to unknown data is realized using trained support vector machines model.
6. Forecasting Methodology according to claim 5, it is characterised in that the characteristic signal is to include bearing vibration signal to exist
Interior, it can reflect critical component fault signature, influence the signal of critical component reliability.
7. Forecasting Methodology according to claim 4, it is characterised in that become using the critical component life-cycle performance degradation
Gesture Forecasting Methodology, to bearing, main shaft, impeller, blade, air exhauster, cylinder, fuel nozzle, igniter, connection combustion pipe, bypass mechanism,
Torque tube, turbine touch mouth, gear, belt, speed changer, controlling switch and control component, 17 kinds of gas turbine engine systems key portions
The reliability variation tendency of part is predicted, and obtains the prediction number of the gas turbine engine systems critical component life-cycle reliability
According to.
8. Forecasting Methodology according to claim 4, it is characterised in that Weibull distribution degeneration is carried out to data after normalization
Rate curve matching, according to the expression formula of Weibull distributionDetermine to meet the degenerated form
Under form parameter m and scale parameter η.
9. according to any Forecasting Methodologies of claim 4-8, it is characterised in that the termination threshold value of the critical component according to
Factor including the species, model, working environment of the critical component is specifically set.
10. Forecasting Methodology according to claim 1, it is characterised in that the reliability of the whole gas turbine engine systems becomes
Change trend formulaRepresent, wherein n is component count, and R (i) is each components reliability, σiCorresponded to for each component
Weight.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711048187.2A CN107944090B (en) | 2017-10-31 | 2017-10-31 | Gas turbine system performance prediction method based on key component failure model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711048187.2A CN107944090B (en) | 2017-10-31 | 2017-10-31 | Gas turbine system performance prediction method based on key component failure model |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107944090A true CN107944090A (en) | 2018-04-20 |
CN107944090B CN107944090B (en) | 2021-11-02 |
Family
ID=61936749
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711048187.2A Active CN107944090B (en) | 2017-10-31 | 2017-10-31 | Gas turbine system performance prediction method based on key component failure model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107944090B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109710983A (en) * | 2018-12-04 | 2019-05-03 | 北京大学 | A kind of cylinder of diesel engine hierarchical fault diagnosis method based on Key Performance Indicator |
CN109856483A (en) * | 2019-01-30 | 2019-06-07 | 中国电子产品可靠性与环境试验研究所((工业和信息化部电子第五研究所)(中国赛宝实验室)) | The Primary Component reliability estimation method and device of MMC power module |
CN110765406A (en) * | 2019-10-21 | 2020-02-07 | 长沙理工大学 | Multi-response information fusion method for inversion identification analysis |
CN112197973A (en) * | 2020-08-17 | 2021-01-08 | 中国船舶重工集团公司第七0四研究所 | Diesel generating set health diagnosis method |
CN112330034A (en) * | 2020-11-10 | 2021-02-05 | 深圳市汇拓新邦科技有限公司 | Fault prediction method and system |
CN113158352A (en) * | 2020-11-25 | 2021-07-23 | 长江勘测规划设计研究有限责任公司 | Method for evaluating remaining service life of water turbine generator set based on key components |
CN113435228A (en) * | 2020-03-23 | 2021-09-24 | 中韩(武汉)石油化工有限公司 | Motor bearing service life prediction and analysis method based on vibration signal modeling |
CN113534779A (en) * | 2021-09-09 | 2021-10-22 | 北汽福田汽车股份有限公司 | Vehicle integrated controller performance prediction method, device, medium, and electronic apparatus |
CN115879913A (en) * | 2023-02-13 | 2023-03-31 | 成都秦川物联网科技股份有限公司 | Intelligent gas pipe network maintenance material prediction method, internet of things system and medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103218752A (en) * | 2013-03-13 | 2013-07-24 | 云南电力试验研究院(集团)有限公司电力研究院 | Current and short-term reliability assessment method of high-voltage transformer |
US20140129152A1 (en) * | 2012-08-29 | 2014-05-08 | Michael Beer | Methods, Systems and Devices Comprising Support Vector Machine for Regulatory Sequence Features |
CN103902706A (en) * | 2014-03-31 | 2014-07-02 | 东华大学 | Method for classifying and predicting big data on basis of SVM (support vector machine) |
CN104239694A (en) * | 2014-08-28 | 2014-12-24 | 北京交通大学 | Fault prediction and condition-based repair method of urban rail train bogie |
CN104462718A (en) * | 2014-12-25 | 2015-03-25 | 国家电网公司 | Method for evaluating economic operation year range of transformer substation |
CN104834994A (en) * | 2015-04-17 | 2015-08-12 | 国家电网公司 | Small sample relay protection reliability parameter estimation method based on SVM (Support Vector Machine) |
-
2017
- 2017-10-31 CN CN201711048187.2A patent/CN107944090B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140129152A1 (en) * | 2012-08-29 | 2014-05-08 | Michael Beer | Methods, Systems and Devices Comprising Support Vector Machine for Regulatory Sequence Features |
CN103218752A (en) * | 2013-03-13 | 2013-07-24 | 云南电力试验研究院(集团)有限公司电力研究院 | Current and short-term reliability assessment method of high-voltage transformer |
CN103902706A (en) * | 2014-03-31 | 2014-07-02 | 东华大学 | Method for classifying and predicting big data on basis of SVM (support vector machine) |
CN104239694A (en) * | 2014-08-28 | 2014-12-24 | 北京交通大学 | Fault prediction and condition-based repair method of urban rail train bogie |
CN104462718A (en) * | 2014-12-25 | 2015-03-25 | 国家电网公司 | Method for evaluating economic operation year range of transformer substation |
CN104834994A (en) * | 2015-04-17 | 2015-08-12 | 国家电网公司 | Small sample relay protection reliability parameter estimation method based on SVM (Support Vector Machine) |
Non-Patent Citations (4)
Title |
---|
XINFENG BAO等: "Water Region Detection Supporting Ship Identification in Port Surveillance", 《INTERNATIONAL CONFERENCE ON ADVANCED CONCEPTS FOR INTELLIGENT VISION SYSTEMS》 * |
简宪华等: "基于支持向量机的舰船柴油机分层故障诊断", 《计算机与现代化》 * |
邱伯华等: "知识经济与CPS在船舶工业中的应用实践", 《信息技术与标准化》 * |
魏巍等: "基于支持向量机的船舶柴油机层次故障诊断的研究", 《南通航运职业技术学院学报》 * |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109710983B (en) * | 2018-12-04 | 2020-11-27 | 北京大学 | Diesel engine cylinder layered fault diagnosis method based on key performance indexes |
CN109710983A (en) * | 2018-12-04 | 2019-05-03 | 北京大学 | A kind of cylinder of diesel engine hierarchical fault diagnosis method based on Key Performance Indicator |
CN109856483B (en) * | 2019-01-30 | 2022-01-11 | 中国电子产品可靠性与环境试验研究所((工业和信息化部电子第五研究所)(中国赛宝实验室)) | Reliability evaluation method and device for key device of MMC power module |
CN109856483A (en) * | 2019-01-30 | 2019-06-07 | 中国电子产品可靠性与环境试验研究所((工业和信息化部电子第五研究所)(中国赛宝实验室)) | The Primary Component reliability estimation method and device of MMC power module |
CN110765406A (en) * | 2019-10-21 | 2020-02-07 | 长沙理工大学 | Multi-response information fusion method for inversion identification analysis |
CN113435228A (en) * | 2020-03-23 | 2021-09-24 | 中韩(武汉)石油化工有限公司 | Motor bearing service life prediction and analysis method based on vibration signal modeling |
CN112197973A (en) * | 2020-08-17 | 2021-01-08 | 中国船舶重工集团公司第七0四研究所 | Diesel generating set health diagnosis method |
CN112197973B (en) * | 2020-08-17 | 2022-06-28 | 中国船舶重工集团公司第七0四研究所 | Diesel generating set health diagnosis method |
CN112330034A (en) * | 2020-11-10 | 2021-02-05 | 深圳市汇拓新邦科技有限公司 | Fault prediction method and system |
CN113158352A (en) * | 2020-11-25 | 2021-07-23 | 长江勘测规划设计研究有限责任公司 | Method for evaluating remaining service life of water turbine generator set based on key components |
CN113534779B (en) * | 2021-09-09 | 2022-01-04 | 北汽福田汽车股份有限公司 | Vehicle integrated controller performance prediction method, device, medium, and electronic apparatus |
CN113534779A (en) * | 2021-09-09 | 2021-10-22 | 北汽福田汽车股份有限公司 | Vehicle integrated controller performance prediction method, device, medium, and electronic apparatus |
CN115879913A (en) * | 2023-02-13 | 2023-03-31 | 成都秦川物联网科技股份有限公司 | Intelligent gas pipe network maintenance material prediction method, internet of things system and medium |
CN115879913B (en) * | 2023-02-13 | 2023-05-05 | 成都秦川物联网科技股份有限公司 | Intelligent gas pipe network maintenance material prediction method, internet of things system and medium |
US11966885B2 (en) | 2023-02-13 | 2024-04-23 | Chengdu Qinchuan Iot Technology Co., Ltd. | Methods and Internet of Things (IoT) systems for predicting maintenance materials of smart gas pipeline networks |
Also Published As
Publication number | Publication date |
---|---|
CN107944090B (en) | 2021-11-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107944090A (en) | Gas turbine engine systems performance prediction method based on critical component failure model | |
CN106444703B (en) | Dynamic equipment running status fuzzy evaluation and prediction technique based on fault mode probability of happening | |
Byington et al. | Prognostic enhancements to diagnostic systems for improved condition-based maintenance [military aircraft] | |
CN107111311B (en) | Gas turbine sensor fault detection using sparse coding methods | |
Pillai et al. | A hybrid approach for fusing physics and data for failure prediction | |
CN107104978A (en) | A kind of network risks method for early warning based on deep learning | |
Huang et al. | Improved trajectory similarity-based approach for turbofan engine prognostics | |
CN102999038A (en) | Diagnostic device for power generating equipment, and diagnostic method for power generating equipment | |
CN114396321B (en) | Multi-dimensional service life monitoring method of nuclear turbine | |
Vatani et al. | Health monitoring and degradation prognostics in gas turbine engines using dynamic neural networks | |
CN114880925A (en) | Equipment life prediction method based on time convolution network and multi-layer self-attention | |
CN109740727A (en) | A kind of hydraulic turbine shaft state monitoring method neural network based and system | |
Simon et al. | Analytic confusion matrix bounds for fault detection and isolation using a sum-of-squared-residuals approach | |
CN115600739A (en) | Boiler superheater and reheater oxide skin prediction method and system | |
CN112417700A (en) | Fault diagnosis system of EH oil station based on state evaluation | |
Zhang et al. | Water droplet erosion life prediction method for steam turbine blade materials based on image recognition and machine learning | |
Li | Diagnostics of power setting sensor fault of gas turbine engines using genetic algorithm | |
Chen et al. | A time-series turbofan engine successive fault diagnosis under both steady-state and dynamic conditions | |
Wang et al. | Shock-loading-based reliability modeling with dependent degradation processes and random shocks | |
Lamoureux et al. | An approach to the health monitoring of a pumping unit in an aircraft engine fuel system | |
Ning et al. | A feature selection algorithm based on variable correlation and time correlation for predicting remaining useful life of equipment using rnn | |
Jain et al. | Prediction of remaining useful life of an aircraft engine under unknown initial wear | |
Zhao et al. | Research on an adaptive threshold setting method for aero-engine fault detection based on KDE-EWMA | |
CN109840563B (en) | Fan fault diagnosis method based on three-dimensional membership function fuzzy logic system | |
CN109614722B (en) | Modeling method for scroll engine full-state parameters based on fuzzy logic |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |