CN109670243B - Service life prediction method based on Leeberg space model - Google Patents
Service life prediction method based on Leeberg space model Download PDFInfo
- Publication number
- CN109670243B CN109670243B CN201811563196.XA CN201811563196A CN109670243B CN 109670243 B CN109670243 B CN 109670243B CN 201811563196 A CN201811563196 A CN 201811563196A CN 109670243 B CN109670243 B CN 109670243B
- Authority
- CN
- China
- Prior art keywords
- leeberg
- state
- time
- value
- running time
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- 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
- 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"
-
- 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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/04—Ageing analysis or optimisation against ageing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention belongs to the technical field related to bearing fault diagnosis and prediction, and discloses a service life prediction method based on a Leeberg space model, which comprises the following steps: (1) acquiring state data of equipment to be tested in real time; (2) setting Leeberg intervals according to the state data, further dividing the obtained health index into a series of Leeberg states, and then constructing a Leeberg space model; (3) initializing parameters of a particle filter algorithm, and performing cycle recursion on the obtained running time corresponding to the Leeberg state by adopting the particle filter algorithm to obtain an estimated value of the running time corresponding to the current Leeberg state; (4) and based on the obtained estimated value, predicting the running time corresponding to the next Leeberg state by adopting a particle filter algorithm, and further calculating the residual life of the equipment to be measured. The invention improves the calculation efficiency and accuracy, and has better flexibility and stronger applicability.
Description
Technical Field
The invention belongs to the technical field related to bearing fault diagnosis and prediction, and particularly relates to a service life prediction method based on a Leeberg space model.
Background
In recent years, failure prediction and health management technologies have received increasing attention, especially for safety-critical devices such as power plants, nuclear power plants, aerospace devices, and drones. These devices are often complex and, in case of failure, not only cause huge economic losses, but also threaten the life safety of people. The fault diagnosis and prediction technology can carry out quantitative analysis on the current fault degree of the equipment by analyzing and processing the real-time data, and simultaneously accurately and effectively predict the future development condition.
Although the existing fault diagnosis and prediction technology also has good performance, in engineering practice, with the increasing number of sensors and the complexity of algorithms, the application of fault diagnosis and prediction is mainly limited by the shortage of computing power. Especially in distributed applications, the diagnostic prediction algorithm behaves more significantly when deployed on an embedded computing system. Accordingly, there is a need in the art to develop a life prediction method based on a lebbeck space model that can improve efficiency.
Disclosure of Invention
Aiming at the defects or improvement requirements in the prior art, the invention provides a service life prediction method based on a Leeberg space model, which is researched and designed based on the characteristics of the existing fault diagnosis and prediction, and can improve the efficiency. The service life prediction method combines modern advanced intelligent technology and state monitoring technology, and improves accuracy and calculation efficiency. The service life prediction method can be used for monitoring the state by using real-time data under the condition of no shutdown, can also be used for effectively predicting the development condition of faults, and has strong applicability and high flexibility.
In order to achieve the above object, the present invention provides a life prediction method based on a lebesger space model, which comprises the following steps:
(1) acquiring state data of equipment to be tested in real time, and further obtaining a corresponding health index by adopting a health index formula;
(2) setting a Leeberg interval according to the state data, and dividing the obtained health index into a series of Leeberg states according to the Leeberg interval; meanwhile, constructing a Leeberg space model based on the health index and the relationship between the Leeberg state and the corresponding collected running time, wherein the Leeberg space model takes the Leeberg state as input to calculate the running time corresponding to the output Leeberg state;
(3) initializing parameters of a particle filter algorithm, and performing cycle recursion on the obtained running time corresponding to the Leeberg state by adopting the particle filter algorithm to obtain an estimated value of the running time corresponding to the current Leeberg state;
(4) and based on the obtained estimated value, predicting the running time corresponding to the next Leeberg state by adopting a particle filter algorithm, and further calculating the residual life of the equipment to be measured.
Further, the Lenberg space model adopts a transfer equation and an observation equation to express the running time distribution of the fault in each state.
Further, the transfer equation is:
t(Lk+1)=f(t(Lk),ωt(Lk)) (1)
in the formula, t (L)k) In the Leibe lattice stateLkA corresponding run time; omegat(Lk) Is in a Lenberg state LkDisturbance of time-of-flight time transfer, which is used for describing uncertainty in the fault development process; t (L)k+1) Is in a Lenberg state Lk+1The corresponding running time.
Further, the observation equation is:
t(Lk)m=t(Lk)+vt(Lk) (2)
in the formula, t (L)k) Is in a Lenberg state LkA corresponding run time; t (L)k)mFor the Leeberg state L obtained by measurement meanskA corresponding run time; v. oft(Lk) Is the noise that the process has.
Further, the initialized parameters of the particle filter algorithm include an error initial limit value, a first run time value and an initial weight value.
Further, the state data of the equipment to be measured is collected in real time to serve as an observation value, and the observation value is in the Leeberg state L0A small range [ L ] around0-,L0+]And then, acquiring and recording corresponding running time, and continuously acquiring until the observed value is less than L0Stopping after n times the value of D/2, averaging the running time of all records as the first running time value t0。
Further, corresponding to the Leeberg state L0Obtaining N Gaussian-obeyed distributions and dividing by t0Run-time particle set as a meanWherein N is 500; and setting the initial weight of the particles to be 1/N.
Further, the obtaining of the estimation value comprises the following steps:
(21) according to the Lenberg state LkCorresponding run-time particle setsRun with le BesseEquation of transfer t (L) betweenk+1)=f(t(Lk),ωt(Lk) Generate N Leiberg states Lk+1Lower corresponding run-time particle set;
(22) The health index obtained in the collection is lower than Lk-after n times the value of D/2, starting to acquire the health index continuously, if the value of the health index is in the next Leeberg state L0A small range of [ L ]k-,Lk+]And recording the corresponding running time, and continuing to collect the state observation value until the state observation value is less than Lk+1Stopping after n times of value of D/2, taking the mean value of all recorded running times as Leeberg state Lk+1Corresponding measured running time;
(23) Inputting each runtime particle generated in step (21) to calculate and measure runtimeThe difference between them, then according to the measured running timeThe uncertainty of each runtime particle is used to find the weight value of each runtime particle;
(24) calculating the sum of the weight values of all the operation time particles, and performing renormalization on the weight of each operation time particle;
(25) reserving the operation time particles with the weight values larger than q according to the weight value, wherein q is initially set according to the actual situation;
(26) and calculating the average value of all the running time particles corresponding to the same Leiberg state after resampling to be used as the estimated running time of the Leiberg state.
Further, the step (4) comprises the following steps:
(41) according to LebeiTrellis state LkCorresponding run-time particle setsUsing the transfer equation t (L) for the Leeberg runtimek+1)=f(t(Lk),ωt(Lk) Generate N Leiberg states Lk+1Lower corresponding run-time particle setWherein ω istRepresenting the uncertainty present during the transfer;
(42) and (4) circularly executing the step (41) until the Leeberg state reaches the set fault threshold value, circularly stopping, and calculating the residual service life of the equipment to be tested according to the obtained running time particle set.
In general, compared with the prior art, the service life prediction method based on the lebbeck space model provided by the invention mainly has the following beneficial effects:
1. the service life prediction method executes the filtering algorithm according to the state axis, has very good calculation efficiency and better accuracy, and is very suitable for distributed application.
2. The service life prediction method is based on a Leeberg space model which is constructed based on the health index and the relation between the Leeberg state and the corresponding collected running time, the integration level is high, the automation degree is good, the flexibility is high, and the calculation efficiency is improved.
3. The particle filter algorithm is combined with the Leeberg space model, so that the calculation speed is increased, the cost is reduced, and powerful data support is provided for the life prediction research of equipment.
4. The service life prediction method is simple, easy to implement and beneficial to popularization and application.
Drawings
Fig. 1 is a schematic flow chart of a life prediction method based on a lebesger space model according to the present invention.
Fig. 2 a and b are schematic diagrams comparing results obtained by using the conventional state space-based life prediction method and the lebbeck space model-based life prediction method in fig. 1, respectively.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Referring to fig. 1 and fig. 2, the life prediction method based on the lebbeck space model provided by the present invention includes the following steps:
the method comprises the steps of firstly, acquiring state data of equipment to be tested in real time, and then obtaining a corresponding health index by adopting a health index formula.
Specifically, an online monitoring system is adopted to acquire real-time state data of equipment to be tested, and a corresponding health index is obtained according to a health index formula.
Setting a Leeberg interval according to the state data, and dividing the obtained health index into a series of Leeberg states according to the Leeberg interval; and meanwhile, constructing a Leeberg space model based on the health index and the relationship between the Leeberg state and the corresponding collected running time, wherein the Leeberg space model takes the Leeberg state as input to calculate and output the running time corresponding to the Leeberg state.
Specifically, a statistical method is applied to set a Leibe interval D according to the collected state data, and the health index is divided into a series of Leibe states according to the Leibe interval; and constructing a Leeberg space model aiming at the relationship between the Leeberg states and the corresponding running time thereof and the health index, wherein the Leeberg space model adopts the transfer equation and the observation equation to express the running time distribution of the fault in each state. The transfer equation and the observation equation both take the Leeberg state as input and take the running time corresponding to the Leeberg state as output.
The transfer equation is:
t(Lk+1)=f(r(Lk),ωt(Lk)) (1)
the observation equation is:
t(Lk)m=t(Lk)+vt(Lk) (2)
in the formula, t (L)k) Is in a Lenberg state LkA corresponding run time; t (L)k+1) Is in a Lenberg state Lk+1A corresponding run time; omegat(Lk) Is in a Lenberg state LkDisturbance of time-of-flight time transfer, which is used for describing uncertainty in the fault development process; t (L)k)mFor the Leeberg state L obtained by measurement meanskA corresponding run time; v. oft(Lk) Is the noise that the process has.
In this embodiment, ω in the equationt(Lk)、Vt(Lk) Value of and Legeberg state LkThe functional relation is determined according to a large number of actual fault development examples; d, n,Selecting the value according to a series of fault examples by using a statistical method; in obtaining the Leiberg state LkCorresponding measured running timeThen, all can be in a small range [ Lk-,Lk+]Recording the running time in the system, and then selecting the state observation value which is closest to the Leeberg state LkAs the measured running time.
And step three, initializing parameters of the particle filter algorithm, and performing cyclic recursion on the obtained running time corresponding to the Leeberg state by adopting the particle filter algorithm to obtain an estimated value of the running time corresponding to the current Leeberg state.
Specifically, the initialization setting of the parameters of the particle filtering algorithm comprises the following steps:
(1) setting an error initial limit value: when the fault does not occur, the real-time health index value is basically stable, the fluctuation is small, the health index continuously decreases along with the continuous development of the fault, and the particle filter algorithm starts to run after the health index is lower than the set error initial limit value.
(2) Acquiring state data of the equipment to be measured in real time as an observed value, wherein the observed value is in a Leeberg state L0A small range [ L ] around0-,L0+]And then, acquiring and recording corresponding running time, and continuously acquiring until the observed value is less than L0Stopping after n times the value of D/2, averaging the running time of all records as the first running time value t0。
(3) Corresponding to the Leiberg state L0Obtaining N Gaussian-obeyed distributions and using the first running time value t0Run-time particle set as a meanWherein N is 500; and setting the initial weight of the particles to be 1/N.
Wherein the obtaining of the estimated value comprises the following steps:
(21) according to the Lenberg state LkCorresponding run-time particle setsUsing the transfer equation t (L) for the Leeberg runtimek+1)=f(t(Lk),ωt(Lk) Generate N Leiberg states Lk+1Lower corresponding run-time particle set。
(22) The health index obtained in the collection is lower than Lk-after n times the value of D/2, starting to acquire the health index continuously if the value is in the next Leeberg state L0A small range of [ L ]k-,Lk+]And recording the corresponding running time, and continuing to collect the state observation value until the state observation value is less than Lk+1Stopping after n times of value of D/2, taking the mean value of all recorded running times as Leeberg state Lk+1Corresponding measured running time。
(23) Inputting each runtime particle generated in step (21) to calculate and measure runtimeThe difference between them, then according to the measured running timeThe uncertainty of each runtime particle is evaluated to determine a weight value.
(24) The sum of the weight values of all the runtime particles is calculated and the weight of each runtime particle is renormalized.
(25) And (3) adopting a resampling technology, namely reserving the runtime particles with weight values larger than q according to the weight value, wherein q is initially set according to the actual situation.
(26) And calculating the average value of all the running time particles corresponding to the same Leiberg state after resampling to be used as the estimated running time of the Leiberg state.
And fourthly, based on the obtained estimated value, predicting the running time corresponding to the next Leeberg state by adopting a particle filter algorithm, and further calculating the residual life of the equipment to be measured.
Specifically, the method specifically comprises the following steps:
(41) according to the Lenberg state LkCorresponding run-time particle setsUsing the transfer equation t (L) for the Leeberg runtimek+1)=f(t(Lk),ωt(Lk) Generate N Leiberg states Lk+1Lower corresponding run-time particle setWherein ω istRepresenting the uncertainty present in the transfer process.
(42) And (4) circularly executing the step (41) until the Leeberg state reaches the set fault threshold value, circularly stopping, and calculating the residual service life of the equipment to be tested according to the obtained running time particle set.
The service life prediction method based on the Leeberg space model quantitatively divides health indexes, constructs a transfer equation and an observation equation of Leeberg running time by taking Leeberg states as input and taking running time corresponding to the Leeberg states as output, performs cyclic recursion on the running time of each Leeberg state by adopting a particle filter algorithm to perform optimized estimation on running time distribution corresponding to each Leeberg state, acquires the running time distribution corresponding to a set limit value and calculates the remaining service life. The service life prediction method greatly improves the calculation efficiency and the prediction accuracy, and has good flexibility and strong applicability.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (9)
1. A service life prediction method based on a Leeberg space model is characterized by comprising the following steps:
(1) acquiring state data of equipment to be tested in real time, and further obtaining a corresponding health index by adopting a health index formula;
(2) setting a Leeberg interval according to the state data, and dividing the obtained health index into a series of Leeberg states according to the Leeberg interval; meanwhile, constructing a Leeberg space model based on the health index and the relationship between the Leeberg state and the corresponding collected running time, wherein the Leeberg space model takes the Leeberg state as input to calculate the running time corresponding to the output Leeberg state;
(3) initializing parameters of a particle filter algorithm, and performing cycle recursion on the obtained running time corresponding to the Leeberg state by adopting the particle filter algorithm to obtain an estimated value of the running time corresponding to the current Leeberg state;
(4) and based on the obtained estimated value, predicting the running time corresponding to the next Leeberg state by adopting a particle filter algorithm, and further calculating the residual life of the equipment to be measured.
2. The method of claim 1, wherein the life prediction method based on the Leeberg space model comprises: the Lenberg space model adopts a transfer equation and an observation equation to express the running time distribution of the fault in each state.
3. The method of claim 2, wherein the life prediction method based on the Leeberg space model comprises: the transfer equation is:
t(Lk+1)=f(t(Lk),ωt(Lk)) (1)
in the formula, t (L)k) Is in a Lenberg state LkA corresponding run time; omegat(Lk) Is in a Lenberg state LkDisturbance of time-of-flight time transfer, which is used for describing uncertainty in the fault development process; t (L)k+1) Is in a Lenberg state Lk+1The corresponding running time.
4. The method of claim 2, wherein the life prediction method based on the Leeberg space model comprises: the observation equation is:
t(Lk)m=t(Lk)+vt(Lk) (2)
in the formula, t (L)k) Is in a Lenberg state LkA corresponding run time; t (L)k)mFor the Leeberg state L obtained by measurement meanskA corresponding measurement run time; v. oft(Lk) Is the noise that the process has.
5. The method of claim 1, wherein the life prediction method based on the Leeberg space model comprises: the parameters of the initialized particle filter algorithm comprise an error initial limit value, a first measurement running time value and an initial weight value.
6. The method of claim 5, wherein the life prediction method based on the Lenberg space model comprises: acquiring state data of the equipment to be measured in real time as an observed value, wherein the observed value is in a Leeberg state L0A small range [ L ] around0-,L0+]And then, acquiring and recording corresponding running time, and continuously acquiring until the observed value is less than L0Stopping after n times the value of D/2, averaging the running times recorded, as the first measured running time value t (L)0)m。
7. The method of claim 6, wherein the life prediction method based on the Leeberg space model comprises: corresponding to the Leiberg state L0Obtaining N Gaussian-obeyed distributions and dividing the N Gaussian-obeyed distributions by t (L)0)mRun-time particle set as a meanWherein N is 500; and setting the initial weight of the particles to be 1/N.
8. The method of any of claims 1-7 for life prediction based on a Lenberg space model, wherein: the acquisition of the estimated value comprises the following steps:
(21) according to the Lenberg state LkCorresponding run-time particle setsTransfer equation t (L) with Leeberg runtimek+1)=f(t(Lk),ωt(Lk) Generate N Leiberg states Lk+1Lower corresponding run-time particle set
(22) The health index obtained in the collection is lower than Lk-after n times the value of D/2, starting to acquire the health index continuously, if the value of the health index is in the next Leeberg state Lk+1A small range of [ L ]k+1-,Lk+1+]And recording the corresponding running time, and continuing to collect the state observation value until the state observation value is less than Lk+1Stopping after n times of value of D/2, taking the mean value of all recorded running times as Leeberg state Lk+1Corresponding measured running time t (L)k+1)m;
(23) Inputting each runtime particle generated in step (21) to calculate and measure a runtime t (L)k+1)mThe difference between them, then according to the measured running time t (L)k+1)mThe uncertainty of each runtime particle is used to find the weight value of each runtime particle;
(24) calculating the sum of the weight values of all the operation time particles, and performing renormalization on the weight of each operation time particle;
(25) reserving the operation time particles with the weight values larger than q according to the weight value, wherein q is initially set according to the actual situation;
(26) calculating the average value of all running time particles corresponding to the same Leeberg state after resampling as the estimated running time of the Leeberg state;
wherein, t (L)k) Is in a Lenberg state LkA corresponding run time; omegat(Lk) Is in a Lenberg state LkDisturbance of time-of-flight time transfer, which is used for describing uncertainty in the fault development process; t is t(Lk+1) Is in a Lenberg state Lk+1The corresponding running time.
9. The method of claim 1, wherein the life prediction method based on the Leeberg space model comprises: the step (4) comprises the following steps:
(41) according to the Lenberg state LkCorresponding run-time particle setsTransfer equation t (L) with Leeberg runtimek+1)=f(t(Lk),ωt(Lk) Generate N Leiberg states Lk+1Lower corresponding run-time particle setWherein ω istRepresenting the uncertainty present during the transfer;
(42) circularly executing the step (41) until the Leeberg state reaches a set fault threshold value, circularly stopping, and calculating the residual service life of the equipment to be tested according to the obtained running time particle combinations;
wherein, t (L)k) Is in a Lenberg state LkA corresponding run time; t (L)k+1) Is in a Lenberg state Lk+1The corresponding running time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811563196.XA CN109670243B (en) | 2018-12-20 | 2018-12-20 | Service life prediction method based on Leeberg space model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811563196.XA CN109670243B (en) | 2018-12-20 | 2018-12-20 | Service life prediction method based on Leeberg space model |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109670243A CN109670243A (en) | 2019-04-23 |
CN109670243B true CN109670243B (en) | 2020-11-24 |
Family
ID=66144503
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811563196.XA Active CN109670243B (en) | 2018-12-20 | 2018-12-20 | Service life prediction method based on Leeberg space model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109670243B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112068179A (en) * | 2020-08-13 | 2020-12-11 | 南昌大学 | Positron imaging method based on Leeberg sampling |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102542155A (en) * | 2011-12-05 | 2012-07-04 | 北京航空航天大学 | Particle filter residual life forecasting method based on accelerated degradation data |
CN105204341A (en) * | 2015-09-25 | 2015-12-30 | 西安石油大学 | Robust tracking control method of network control system based on switching control theory |
CN106092575A (en) * | 2016-06-01 | 2016-11-09 | 浙江工业大学 | A kind of based on Johnson conversion and the bearing failure diagnosis of particle filter algorithm and method for predicting residual useful life |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101231672A (en) * | 2008-02-02 | 2008-07-30 | 湖南大学 | Method for diagnosing soft failure of analog circuit base on modified type BP neural network |
US20090265141A1 (en) * | 2008-04-21 | 2009-10-22 | Aly Salah A | Distributed storage in wireless sensor networks |
US8594982B2 (en) * | 2011-06-09 | 2013-11-26 | Pulsar Informatics, Inc. | Systems and methods for distributed calculation of fatigue-risk prediction and optimization |
JP2013152655A (en) * | 2012-01-26 | 2013-08-08 | Hitachi Ltd | Abnormality diagnostic method and health management method for plant or facility |
CN104677632B (en) * | 2015-01-21 | 2018-04-10 | 大连理工大学 | Utilize particle filter and the Fault Diagnosis of Roller Bearings of spectrum kurtosis |
CN104792529A (en) * | 2015-04-12 | 2015-07-22 | 北京化工大学 | Rolling bearing life prediction method based on state-space model |
CN107967395A (en) * | 2017-12-11 | 2018-04-27 | 北京航空航天大学 | A kind of nonlinear time_varying system Fast Identification Method based on the expansion of beta wavelet basis functions |
-
2018
- 2018-12-20 CN CN201811563196.XA patent/CN109670243B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102542155A (en) * | 2011-12-05 | 2012-07-04 | 北京航空航天大学 | Particle filter residual life forecasting method based on accelerated degradation data |
CN105204341A (en) * | 2015-09-25 | 2015-12-30 | 西安石油大学 | Robust tracking control method of network control system based on switching control theory |
CN106092575A (en) * | 2016-06-01 | 2016-11-09 | 浙江工业大学 | A kind of based on Johnson conversion and the bearing failure diagnosis of particle filter algorithm and method for predicting residual useful life |
Also Published As
Publication number | Publication date |
---|---|
CN109670243A (en) | 2019-04-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11888316B2 (en) | Method and system of predicting electric system load based on wavelet noise reduction and EMD-ARIMA | |
CN108959778B (en) | Method for predicting residual life of aircraft engine based on consistency of degradation modes | |
CN112418277B (en) | Method, system, medium and equipment for predicting residual life of rotating machine parts | |
Ahwiadi et al. | An enhanced particle filter technology for battery system state estimation and RUL prediction | |
CN111414703B (en) | Method and device for predicting residual life of rolling bearing | |
CN108717579B (en) | Short-term wind power interval prediction method | |
CN113722985A (en) | Method and system for evaluating health state and predicting residual life of aircraft engine | |
CN111881574B (en) | Wind turbine generator set key component reliability modeling method based on distribution function optimization | |
WO2023065580A1 (en) | Fault diagnosis method and apparatus for gearbox of wind turbine generator set | |
CN103678886B (en) | A kind of satellite Bayesian network health based on ground test data determines method | |
Yao et al. | Novel lithium-ion battery state-of-health estimation method using a genetic programming model | |
CN111709350B (en) | Low-frequency oscillation modal parameter identification method and system based on FCM clustering | |
CN109670243B (en) | Service life prediction method based on Leeberg space model | |
CN104008433A (en) | Method for predicting medium-and-long-term power loads on basis of Bayes dynamic model | |
CN104268408A (en) | Energy consumption data macro-forecast method based on wavelet coefficient ARMA model | |
CN117060353A (en) | Fault diagnosis method and system for high-voltage direct-current transmission system based on feedforward neural network | |
Niu et al. | Fault diagnosis and prognosis based on deep belief network and particle filtering | |
CN115718906A (en) | Multi-energy system multi-source heterogeneous data fusion method and system | |
CN113158134B (en) | Method, device and storage medium for constructing non-invasive load identification model | |
CN113221248B (en) | Ship system equipment state parameter prediction method based on PF-GARCH model | |
CN116224950A (en) | Intelligent fault diagnosis method and system for self-organizing reconstruction of unmanned production line | |
Guifan | Fault diagnosis method of rotating machinery based on collaborative hybrid metaheuristic algorithm to optimize VMD | |
CN110083804B (en) | Wind power plant SCADA data missing intelligent repairing method based on condition distribution regression | |
Ni et al. | An adaptive state-space model for predicting remaining useful life of planetary gearbox | |
CN114201825A (en) | Method and system for evaluating equipment performance degradation state based on combination characteristics |
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 |