CN110209999A - A kind of mobile unit failure trend prediction method - Google Patents
A kind of mobile unit failure trend prediction method Download PDFInfo
- Publication number
- CN110209999A CN110209999A CN201810166699.7A CN201810166699A CN110209999A CN 110209999 A CN110209999 A CN 110209999A CN 201810166699 A CN201810166699 A CN 201810166699A CN 110209999 A CN110209999 A CN 110209999A
- Authority
- CN
- China
- Prior art keywords
- mobile unit
- sequence
- model
- autoregression model
- malfunction
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000007257 malfunction Effects 0.000 claims abstract description 30
- 238000000611 regression analysis Methods 0.000 claims abstract description 29
- 238000012360 testing method Methods 0.000 claims abstract description 11
- 230000003044 adaptive effect Effects 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 13
- 230000001419 dependent effect Effects 0.000 claims description 8
- 238000005311 autocorrelation function Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000001744 unit root test Methods 0.000 claims description 2
- 241000208340 Araliaceae Species 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 238000013528 artificial neural network Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000003455 independent Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 239000010410 layer Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000011229 interlayer Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000010338 mechanical breakdown Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Algebra (AREA)
- Evolutionary Biology (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of mobile unit failure trend prediction methods, the described method comprises the following steps: S1: the fault type and fault data that acquisition mobile unit occurs, and various probabilities of malfunction are arranged as sequence Xi;S2: whether sequence is steady in judgment step S1, if sequence is non-stationary series, which is pre-processed;S3: autoregression model identification is carried out to stable sequence, and determines autoregression model order;S4: parameter is carried out according to a preliminary estimate to autoregression model using algorithm, and model of the adaptive test to confirm the validity is carried out to autoregression model;S5: carrying out the prediction of the probability of malfunction of each fault type by determining autoregression model, and regression analysis equation is recycled to export the probability of malfunction of entire mobile unit.Train operation hidden danger can be found in advance by the prediction technique and hidden danger is discharged, to reduce the incidence of accident, ensure train safe and highly efficient operation, and then improve train operation efficiency.
Description
Technical field
The invention belongs to mobile unit safety analysis technique fields, and in particular to a kind of mobile unit failure trend prediction side
Method.
Background technique
In order to guarantee the high efficiency transport of city underground, subway manager draws high the intensity of operation to pole in busy route
Limit.However train is high-intensitive, under prolonged traffic-operating period, inevitably breaks down, influences the conevying efficiency of train
And safety.The vehicle-mounted equipment fault diagnosis of present subway and maintenance still rely on expertise, and the accuracy of diagnosis is difficult to meet
The demand of subway manager.The vehicle-mounted signal device of subway train is a kind of system of complexity, and failure is true with diversity and not
It is qualitative, and fault sample is imperfect.
It traditionally, for the fault diagnosis of subway mobile unit, is diagnosed based on neural network failure.Usual situation
Under, the step of neural network failure diagnoses, is as follows: firstly, sorting out by the detection and collection of signal and being able to reflect tested pair
As the characteristic parameter of (module device or components), such as { x1,x2,…xnInput as network;Then to the event of checked object
Barrier state is encoded.Such as failure 1, failure 2, normal three kinds of states, it is desired for encoding are as follows: failure 1 { 0,1 }, event
Hinder 2 { 1,0 }, normal { 0,0 };And then arrange set of data samples as training sample, network is trained after inputting network,
The weight between each neuron is calculated, state recognition is carried out to checked object with trained network;Finally, being divided by arranging
The means such as analysis, experiment, formula calculating, emulation, which have determined, outputs and inputs sample data, the number of layers from network, hidden layer nerve
Network model is optimized in metadata, the transmission function of each interlayer, training function, initial weight and deviation, and by pair
Than predicted value and actual value, Application of Neural Network is verified in the feasibility of mobile unit failure predication.
However, being owed when for the fluctuation in a certain range of the index under normal condition using neural network prediction effect
It is good.Therefore the development for utilizing Neural Network model predictive mechanical breakdown starts sampling and builds only when characteristic parameter obviously becomes larger
Mould just has preferable effect.And due to the various limitations of neural network, lead to itself and not applicable long-term forecast equipment fault.
Summary of the invention
To solve the above-mentioned problems, the purpose of the present invention is to provide a kind of mobile unit failure trend prediction methods, lead to
It is general to cross the failure for predicting entire subway load equipment in the following rapid lapse of time that the prediction technique can be relatively reasonable
Rate improves the efficiency and safety of subway circulation.
To achieve the above object, the present invention is achieved by following technical scheme:
A kind of mobile unit failure trend prediction method, the described method comprises the following steps:
S1: the fault type and fault data that acquisition mobile unit occurs count the fault type and calculate various events
Hinder probability, and various probabilities of malfunction are arranged as sequence Xi;
S2: whether sequence is steady in judgment step S1, if sequence is non-stationary series, which is pre-processed, and leads to
It crosses and uses difference method formula: Yi=Xi+1-XiIt is pre-processed, until unit root test result is steady;
S3: autoregression model identification is carried out to stable sequence, estimates the order of autoregression model, then be determined by calculation
Final autoregression model order;
S4: parameter is carried out according to a preliminary estimate to autoregression model using algorithm, and adaptability inspection is carried out to autoregression model
Test the model to confirm the validity;
S5: carrying out the prediction of the probability of malfunction of each fault type by determining autoregression model, recycles regression analysis
Equation exports the probability of malfunction of entire mobile unit.
Further, the autoregression model in the step S3 are as follows:Wherein, X in formulatFor t
The corresponding sequence at moment, wtFor white noise, p is the order of model, akTo need the parameter estimated.
Further, the autoregression model identification includes to sequence XiCarry out the meter of auto-correlation function and deviation―related function
It calculates, with the determination sequence XiIt is suitble to autoregression model.
Further, the determination of the autoregression model order is the minimum information criterion value by calculating each model, most
Order when small information criterion value value minimum is final mask order.
It further, is to miss priori prediction errors and back forecast to the algorithm of parameter according to a preliminary estimate in the step S4
The smallest Burg algorithm of the sum of poor mean square error.
Further, the adaptive test of the autoregression model calculates the estimation of former sequence including the use of estimation parameter
Value, and the residual sequence of estimation is calculated, residual sequence is examined if white noise, can determine whether that the autoregression model is effective.
Further, the probability of malfunction prediction in the step S5 uses sequence XtIn moment t to the observed value at t+l moment
Xt-lIt is predicted, this prediction is using t as origin, and X is used in the prediction for being l to time early periodt+lConditional expectation as Xt-l's
Predicted value.
Further, the input of regression analysis equation described in the step S5 is the probability of malfunction of each fault type.
Further, the regression analysis equation foundation the following steps are included:
S501: the probability of malfunction composition independent variable matrix of each fault type is acquired, and corresponds to and acquires entire mobile unit
Probability of malfunction group dependent variable matrix;
S502: the independent variable matrix and dependent variable matrix are substituted into regression equation model:
In, find out parameter a, bkValue, obtain regression analysis equation, and test to the correlation output and input;
S503: taking successive Regression thought to carry out model optimization to the regression analysis equation, obtains optimum regression analysis
Equation falls in the coefficient R of regression analysis equation in the range of 0.8~1.
Compared with prior art, the beneficial effects of the present invention are:
The invention discloses a kind of mobile unit failure trend prediction methods, by time series analysis, have both inputted each
The failure of fault type predicts the probability of malfunction at next moment, can accurately obtain the failure of each fault type
Probability;The probability of malfunction of entire mobile unit is from which further followed that by regression analysis equation.So that train fault discovery before compared with
Accurately to find failure, and carry out excluding to reach to scent a hidden danger in advance that hidden danger is discharged rapidly, so that the incidence of accident is reduced,
It ensures train safe and highly efficient operation, and then improves train operation efficiency.
Detailed description of the invention
Specific embodiments of the present invention will be described in further detail with reference to the accompanying drawing, in which:
Fig. 1 is the method flow diagram of the mobile unit failure trend prediction method of disclosure of the invention;
Fig. 2 is regression analysis equation Establishing process figure in the mobile unit failure trend prediction method of disclosure of the invention.
Specific embodiment
Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings, it should be understood that preferred reality described herein
Apply example only for the purpose of illustrating and explaining the present invention and is not intended to limit the present invention.
As shown in Figure 1, the invention discloses a kind of mobile unit failure trend prediction methods, it is described as can be seen from Figure 1
Method is the following steps are included: S1: the fault type and fault data that acquisition mobile unit occurs, counting statistics fault type and each
Kind probability of malfunction, and various probabilities of malfunction are arranged as sequence Xi;S2: whether sequence is steady in judgment step S1, if sequence is
Non-stationary series pre-process the sequence, by using difference method formula: Yi=Xi+1-XiIt is pre-processed, until unit
Until root inspection result is steady;S3: autoregression model identification is carried out to stable sequence, estimates the substantially rank of autoregression model
Number, then final autoregression model order is determined by detailed calculate;S4: parameter is carried out to autoregression model using algorithm
According to a preliminary estimate, and to autoregression model model of the adaptive test to confirm the validity is carried out;S5: pass through determining autoregression model
The prediction of the probability of malfunction of each fault type is carried out, regression analysis equation is recycled to export the probability of malfunction of entire mobile unit.
Wherein, present invention is generally directed to the failures of ATP mobile unit to carry out trend analysis and prediction.ATP mobile unit is train control system
Important component, can control running speed, guarantee traffic safety, it is vehicle-mounted automatic protection equipment, is operated in existing
In railway line, is interlocked with ground track circuit, transponder device, automatically control safe train operation.The vehicle acquired in step S1
It carrying equipment fault data to classify first, be predicted with will pass through AR model to the probability of malfunction of various fault types,
In judgment step S1 sequence it is whether steady in, the standard of judgement are as follows: as time went on, auto-correlation coefficient is decayed with fast speed
It is zero, can determine whether as stationary sequence, it is on the contrary then be non-stationary series.If a system is X in the response of moment tt, and only with
Its former moment it is corresponding related, and it is unrelated with the disturbance that its former moment enters system, then, this system is exactly autoregression
System, corresponding model are denoted as AR model, the autoregression model as introduced in above-mentioned steps.
Preferably, the autoregression model in the step S3 are as follows:Wherein, X in formulatWhen for t
The corresponding sequence at quarter, wtFor white noise, p is the order of model, akTo need the parameter estimated.The establishment process of autoregression model
The as process of model parameter estimation exactly selects suitable parameter to make the residual error w of autoregression modeltFor white noise sequence.
Preferably, the autoregression model identification includes to sequence XiThe calculating of auto-correlation function and deviation―related function is carried out to be somebody's turn to do to determine
Sequence is suitble to autoregression model, with the order of this described autoregression model according to a preliminary estimate.
Preferably, the determination of the autoregression model order is the minimum information criterion value by calculating each model, when most
Order when small information criterion value value minimum is final autoregression model order.Wherein, in the step S3 according to a preliminary estimate
Autoregression model there are multiple estimation orders, by minimum information criterion value can weigh estimated model complexity and this
The Optimality of models fitting data, to determine suitable autoregression model order.Preferably, at the beginning of parameter in the step S4
The algorithm of step estimation is to make the smallest Burg algorithm of the sum of priori prediction errors and posteriori prediction errors mean square error, passes through the calculation
Method obtains the parameter a in the autoregression modelk。
Preferably, the adaptive test of the autoregression model calculates estimating for former sequence including the use of the estimation parameter
Evaluation, and the residual sequence of estimation is calculated, residual sequence is examined if white noise, can determine whether that the autoregression model has
Effect.Reliable autoregression model is obtained by adaptive test, the model is enabled effectively to predict subsequent time
Probability of malfunction.Preferably, the probability of malfunction prediction in the step S5 uses sequence XtIn moment t to the observed value at t+l moment
Xt-lIt is predicted, this prediction is for using t as origin, X is used in the prediction for being l to time early periodt+lConditional expectation as Xt-l
Predicted value, to obtain the probability of malfunction of fault type.
As shown in Figure 1, the invention discloses regression analysis equation method for building up in mobile unit failure trend prediction method.
Preferably, the probability of malfunction prediction of entire mobile unit is the applied regression analysis side on the basis for establishing autoregression model
Journey is realized.The output of regression analysis equation is the probability of malfunction of entire mobile unit, is inputted as the failure of each fault type
Probability.Preferably, the foundation of the regression analysis equation is the following steps are included: S501: acquiring the probability of malfunction of each fault type
Form independent variable matrix, and the corresponding probability of malfunction group dependent variable matrix for acquiring entire mobile unit;S502: will be described from change
Moment matrix and dependent variable matrix substitute into regression equation model:In, find out parameter a, bk's
Value, obtains regression analysis equation, and test to the correlation output and input;S503: take successive Regression thought to institute
It states regression analysis equation and carries out model optimization, obtain optimum regression analysis equation, fall in the coefficient R of regression analysis equation
In the range of 0.8~1.Wherein, the method for regression analysis is varied, and the regression analysis equation established in the present invention is gradually to return
Return analytic approach, the method selects to influence that linear correlation more significantly and is between each other not present on dependent variable under certain criterion
Independent variable, the independent variable be each fault type probability of malfunction composition matrix.It is reasonable and simple and practical to establish
Regression analysis equation model.Successive Regression basic thought is to choose the initial data set comprising some independents variable first, then
Increase by the independent variable of one with dependent variable correlation maximum outside data set, then is carried out together with all independents variable in data set
It examines, it is the smallest to remove correlation from relatively inapparent variable, gradually carries out, knot when can not increase and remove variable
Beam finally therefrom finds an optimal combination.
The other structures of mobile unit failure trend prediction method of the present invention are no longer superfluous herein referring to the prior art
It states.
The above described is only a preferred embodiment of the present invention, be not intended to limit the present invention in any form, therefore
Without departing from the technical solutions of the present invention, according to the technical essence of the invention it is to the above embodiments it is any modification,
Equivalent variations and modification, all of which are still within the scope of the technical scheme of the invention.
Claims (9)
1. a kind of mobile unit failure trend prediction method, which is characterized in that the described method comprises the following steps:
S1: the fault type and fault data that acquisition mobile unit occurs count the fault type and the various failures of calculating are general
Rate, and various probabilities of malfunction are arranged as sequence Xi;
S2: whether sequence is steady in judgment step S1, if sequence is non-stationary series, which is pre-processed, by making
With difference method formula: Yi=Xi+1-XiIt is pre-processed, until unit root test result is steady;
S3: carrying out autoregression model identification to stable sequence, estimate the order of autoregression model, then is determined by calculation final
Autoregression model order;
S4: using algorithm to autoregression model carry out parameter according to a preliminary estimate, and to autoregression model carry out adaptive test with
The model confirmed the validity;
S5: carrying out the prediction of the probability of malfunction of each fault type by determining autoregression model, recycles regression analysis equation
Export the probability of malfunction of entire mobile unit.
2. mobile unit failure trend prediction method according to claim 1, which is characterized in that in the step S3 from
Regression model are as follows:Wherein, X in formulatFor the corresponding sequence of t moment, wtFor white noise, p is model
Order, akTo need the parameter estimated.
3. mobile unit failure trend prediction method according to claim 1, which is characterized in that the autoregression model is known
It does not include to sequence XiThe calculating of auto-correlation function and deviation―related function is carried out, with the determination sequence XiIt is suitble to autoregression model.
4. mobile unit failure trend prediction method according to claim 1, which is characterized in that the autoregression model rank
Several determinations is the minimum information criterion value by calculating each model, and order when minimum information criterion value value minimum is final
Model order.
5. mobile unit failure trend prediction method according to claim 1, which is characterized in that ginseng in the step S4
The algorithm of number according to a preliminary estimate is to make the smallest Burg algorithm of the sum of priori prediction errors and posteriori prediction errors mean square error.
6. mobile unit failure trend prediction method according to claim 1, which is characterized in that the autoregression model
Adaptive test calculates the estimated value of former sequence including the use of estimation parameter, and the residual sequence of estimation, residual error is calculated
Sequence is examined if white noise, can determine whether that the autoregression model is effective.
7. mobile unit failure trend prediction method according to claim 1, which is characterized in that the event in the step S5
Hinder probabilistic forecasting and uses sequence XtIn moment t to the observed value X at t+l momentt-lIt is predicted, this prediction is to be former with t
Point, the prediction for being l to time early period, uses Xt+lConditional expectation as Xt-lPredicted value.
8. mobile unit failure trend prediction method according to claim 1, which is characterized in that described in the step S5
The input of regression analysis equation is the probability of malfunction of each fault type.
9. mobile unit failure trend prediction method according to claim 1 or 8, which is characterized in that the regression analysis
The foundation of equation the following steps are included:
S501: the probability of malfunction composition independent variable matrix of each fault type, and the corresponding failure for acquiring entire mobile unit are acquired
Probability group dependent variable matrix;
S502: the independent variable matrix and dependent variable matrix are substituted into regression equation model:
In, find out parameter a, bkValue, obtain regression analysis equation, and test to the correlation output and input;
S503: taking successive Regression thought to carry out model optimization to the regression analysis equation, obtain optimum regression analysis equation,
Fall in the coefficient R of regression analysis equation in the range of 0.8~1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810166699.7A CN110209999A (en) | 2018-02-28 | 2018-02-28 | A kind of mobile unit failure trend prediction method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810166699.7A CN110209999A (en) | 2018-02-28 | 2018-02-28 | A kind of mobile unit failure trend prediction method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110209999A true CN110209999A (en) | 2019-09-06 |
Family
ID=67778682
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810166699.7A Pending CN110209999A (en) | 2018-02-28 | 2018-02-28 | A kind of mobile unit failure trend prediction method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110209999A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110765619A (en) * | 2019-10-28 | 2020-02-07 | 中国人民解放军63921部队 | Short-term multi-step prediction method for failure-free canned motor pump failure based on multi-state parameters |
CN110764065A (en) * | 2019-10-16 | 2020-02-07 | 清华大学 | Radar fault diagnosis method based on time sequence reconstruction |
CN110809280A (en) * | 2019-10-21 | 2020-02-18 | 北京锦鸿希电信息技术股份有限公司 | Detection and early warning method and device for railway wireless network quality |
CN112149877A (en) * | 2020-08-31 | 2020-12-29 | 国网江苏省电力有限公司苏州供电分公司 | Multi-source data-driven fault prediction method and system for multi-element complex urban power grid |
CN112632711A (en) * | 2021-01-06 | 2021-04-09 | 神华中海航运有限公司 | Ship fault prediction method and device, computer equipment and storage medium |
CN113219939A (en) * | 2021-04-07 | 2021-08-06 | 山东润一智能科技有限公司 | Equipment fault prediction method and system based on residual autoregression |
CN114267178A (en) * | 2021-12-30 | 2022-04-01 | 佳都科技集团股份有限公司 | Intelligent operation maintenance method and device for station |
CN115580635A (en) * | 2022-09-26 | 2023-01-06 | 广州健新科技有限责任公司 | Intelligent fault diagnosis method and system for terminal of Internet of things |
CN116643554A (en) * | 2023-06-01 | 2023-08-25 | 中国铁道科学研究院集团有限公司通信信号研究所 | Fault management method, system and equipment for ATP (adenosine triphosphate) vehicle-mounted equipment of high-speed railway |
CN117235540A (en) * | 2023-08-21 | 2023-12-15 | 江西农业大学 | Sensor dynamic information linkage analysis method based on feature matching fusion |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105158598A (en) * | 2015-08-15 | 2015-12-16 | 国家电网公司 | Fault prediction method suitable for power equipment |
CN106598029A (en) * | 2016-12-21 | 2017-04-26 | 北京交通大学 | Train control vehicle equipment reliability prediction method based on performance degeneration |
-
2018
- 2018-02-28 CN CN201810166699.7A patent/CN110209999A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105158598A (en) * | 2015-08-15 | 2015-12-16 | 国家电网公司 | Fault prediction method suitable for power equipment |
CN106598029A (en) * | 2016-12-21 | 2017-04-26 | 北京交通大学 | Train control vehicle equipment reliability prediction method based on performance degeneration |
Non-Patent Citations (1)
Title |
---|
肖飞: "基于时间序列分析和智能算法的故障预测方法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110764065A (en) * | 2019-10-16 | 2020-02-07 | 清华大学 | Radar fault diagnosis method based on time sequence reconstruction |
CN110764065B (en) * | 2019-10-16 | 2021-10-08 | 清华大学 | Radar fault diagnosis method based on time sequence reconstruction |
CN110809280A (en) * | 2019-10-21 | 2020-02-18 | 北京锦鸿希电信息技术股份有限公司 | Detection and early warning method and device for railway wireless network quality |
CN110809280B (en) * | 2019-10-21 | 2022-10-18 | 北京锦鸿希电信息技术股份有限公司 | Detection and early warning method and device for railway wireless network quality |
CN110765619A (en) * | 2019-10-28 | 2020-02-07 | 中国人民解放军63921部队 | Short-term multi-step prediction method for failure-free canned motor pump failure based on multi-state parameters |
CN110765619B (en) * | 2019-10-28 | 2023-05-30 | 中国人民解放军63921部队 | Failure-free canned motor pump fault short-term multi-step prediction method based on multi-state parameters |
CN112149877B (en) * | 2020-08-31 | 2022-07-05 | 国网江苏省电力有限公司苏州供电分公司 | Multi-source data driven fault prediction method and system for multi-element complex urban power grid |
CN112149877A (en) * | 2020-08-31 | 2020-12-29 | 国网江苏省电力有限公司苏州供电分公司 | Multi-source data-driven fault prediction method and system for multi-element complex urban power grid |
CN112632711A (en) * | 2021-01-06 | 2021-04-09 | 神华中海航运有限公司 | Ship fault prediction method and device, computer equipment and storage medium |
CN112632711B (en) * | 2021-01-06 | 2024-01-30 | 神华中海航运有限公司 | Ship fault prediction method, device, computer equipment and storage medium |
CN113219939A (en) * | 2021-04-07 | 2021-08-06 | 山东润一智能科技有限公司 | Equipment fault prediction method and system based on residual autoregression |
CN114267178A (en) * | 2021-12-30 | 2022-04-01 | 佳都科技集团股份有限公司 | Intelligent operation maintenance method and device for station |
CN114267178B (en) * | 2021-12-30 | 2023-09-26 | 佳都科技集团股份有限公司 | Intelligent operation maintenance method and device for station |
CN115580635A (en) * | 2022-09-26 | 2023-01-06 | 广州健新科技有限责任公司 | Intelligent fault diagnosis method and system for terminal of Internet of things |
CN115580635B (en) * | 2022-09-26 | 2023-06-13 | 广州健新科技有限责任公司 | Intelligent fault diagnosis method and system for Internet of things terminal |
CN116643554A (en) * | 2023-06-01 | 2023-08-25 | 中国铁道科学研究院集团有限公司通信信号研究所 | Fault management method, system and equipment for ATP (adenosine triphosphate) vehicle-mounted equipment of high-speed railway |
CN116643554B (en) * | 2023-06-01 | 2023-11-28 | 中国铁道科学研究院集团有限公司通信信号研究所 | Fault management method, system and equipment for ATP (adenosine triphosphate) vehicle-mounted equipment of high-speed railway |
CN117235540A (en) * | 2023-08-21 | 2023-12-15 | 江西农业大学 | Sensor dynamic information linkage analysis method based on feature matching fusion |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110209999A (en) | A kind of mobile unit failure trend prediction method | |
CN110262463B (en) | Rail transit platform door fault diagnosis system based on deep learning | |
CN107941537B (en) | A kind of mechanical equipment health state evaluation method | |
CN116625438B (en) | Gas pipe network safety on-line monitoring system and method thereof | |
CN104809878B (en) | Method for detecting abnormal condition of urban road traffic by utilizing GPS (Global Positioning System) data of public buses | |
CN105846780B (en) | A kind of photovoltaic module method for diagnosing faults based on decision-tree model | |
CN106528975B (en) | A kind of prognostic and health management method applied to Circuits and Systems | |
CN104778837A (en) | Multi-time scale forecasting method for road traffic running situation | |
CN201898519U (en) | Equipment maintenance early-warning device with risk control | |
CN111046583A (en) | Switch machine fault diagnosis method based on DTW algorithm and ResNet network | |
CN109655298A (en) | A kind of the failure real time early warning method and device of large span metal Roof | |
CN112132394B (en) | Power plant circulating water pump predictive state evaluation method and system | |
KR102373827B1 (en) | An Industrial Facility Operating Device Based on Standard Operation Level Evaluations and a Method for Operating It | |
CN118130984B (en) | Cable partial discharge fault real-time monitoring method based on data driving | |
CN112149750A (en) | Water supply network pipe burst identification data driving method | |
CN114757365A (en) | High-speed railway roadbed settlement prediction and early warning method based on deep learning | |
CN113657217A (en) | Concrete state recognition model based on improved BP neural network | |
CN117610971B (en) | Highway electromechanical system health index evaluation method | |
CN109034211A (en) | A kind of parking space state detection method based on machine learning | |
CN112257914A (en) | Aviation safety cause and effect prediction method based on random forest | |
CN110794254A (en) | Power distribution network fault prediction method and system based on reinforcement learning | |
CN116151561A (en) | Power system operation security situation identification method and system | |
CN115526258A (en) | Power system transient stability evaluation method based on Spearman correlation coefficient feature extraction | |
CN116506309B (en) | Vehicle-mounted ATP communication signal comprehensive monitoring system and method | |
CN118036819A (en) | Influence of environmental factors on operation of power distribution network and equipment maintenance system and method |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190906 |
|
RJ01 | Rejection of invention patent application after publication |