CN110782126A - Method for evaluating operation reliability of direct current charging pile for electric vehicle integrated by multiple failure models - Google Patents
Method for evaluating operation reliability of direct current charging pile for electric vehicle integrated by multiple failure models Download PDFInfo
- Publication number
- CN110782126A CN110782126A CN201910904810.2A CN201910904810A CN110782126A CN 110782126 A CN110782126 A CN 110782126A CN 201910904810 A CN201910904810 A CN 201910904810A CN 110782126 A CN110782126 A CN 110782126A
- Authority
- CN
- China
- Prior art keywords
- failure
- charging pile
- current charging
- direct current
- model
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- 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
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention discloses a method for evaluating the running reliability of a direct current charging pile for an electric vehicle integrated with multiple failure models, which comprises the following steps: the method comprises the steps of researching potential failure modes of the direct-current charging pile for the electric automobile, establishing corresponding candidate failure models, averagely establishing a multi-failure-model-integrated direct-current charging pile operation reliability evaluation model for the electric automobile based on a Bayesian model, determining the weight and variance of a conditional probability function of each failure model by adopting an improved finite memory quasi-Newton method, and calculating the operation reliability of the direct-current charging pile for the electric automobile. Aiming at the potential failure mode of the direct current charging pile for the electric automobile, the candidate failure models are brought into the same frame, the operation reliability analysis is carried out by using a multi-model integration technology, the limitation problem caused by single-model failure research is solved, and the accuracy of the operation reliability analysis of the direct current charging pile for the electric automobile is effectively improved.
Description
Technical Field
The invention belongs to the technical field of charging, relates to the technical field of vehicle conduction charging safety, and particularly relates to a method for evaluating the running reliability of a direct current charging pile for an electric vehicle integrated with multiple failure models.
Background
In recent years, under the support of a large amount of financial subsidies, the new energy automobile market in China shows an explosive growth situation. By 2018, the new energy automobiles in China keep 261 thousands of automobiles, and the new energy automobiles play a great role in relieving resource shortage, improving the environmental quality and improving the energy utilization efficiency. At present, new energy vehicles can be classified into three types, namely pure electric vehicles, hybrid electric vehicles and fuel cells according to power sources. The pure electric vehicle has the advantages of zero emission, high efficiency, convenience in arrangement of the whole vehicle and the like, so that the pure electric vehicle occupies a higher share in the new energy vehicle market. As is well known, the power of the pure electric vehicle is mainly derived from the electric energy stored in the high-voltage battery, and the electric energy can be introduced into an external power grid power supply to be charged in a conduction mode. The charging voltage type can be divided into alternating current slow charging and direct current fast charging. Compared with alternating current slow charging, the direct current fast charging has higher voltage level and charging current, the operation reliability of the direct current fast charging directly influences the use experience of an owner and the use frequency of a vehicle, and potential restrictions also exist on power grid scheduling. Therefore, the operation reliability of the direct current charging pile is evaluated, on one hand, the vehicle attendance rate can be guaranteed, the use experience of a vehicle owner is improved, on the other hand, a basis can be provided for formulating an equipment maintenance plan, and the organic combination of the safety, the reliability and the economy of the operation process of the direct current charging pile is realized.
The direct current charging pile for the electric automobile has multiple functions of rectification, protection, communication, output control and the like as a typical complex electric control system, the reliability of the direct current charging pile in the operation process is influenced by multiple factors, the failure mechanism is complex, and the operation reliability level of the complex electric control system is difficult to accurately describe by using a single failure model.
Disclosure of Invention
In view of the above problems, the invention aims to provide a method for evaluating the operation reliability of a direct current charging pile for an electric vehicle integrated by multiple failure models.
In order to achieve the purpose, the invention adopts the following technical scheme: a method for evaluating the operation reliability of a direct current charging pile for an electric automobile integrated with multiple failure models comprises the following steps:
step 1, acquiring a potential failure mode of the direct current charging pile for the electric automobile by combining failure records of current and past processes according to the operation characteristics of the direct current charging pile for the electric automobile;
step 2, analyzing potential failure modes of the direct current charging pile by using a multi-failure-mode analysis method, and respectively establishing a direct current charging pile operation reliability evaluation candidate model for the electric vehicle according to different failure modes;
step 3, constructing a direct current charging pile operation reliability evaluation model for the electric vehicle integrated with multiple failure models based on Bayesian model average;
step 4, establishing an evaluation error expression of the log-type likelihood function on the basis of mutually independent assumption of evaluation error space and time according to the maximum likelihood principle, and estimating and determining the weight omega of the conditional probability function of each candidate failure model by adopting an improved finite memory quasi-Newton method
iAnd variance σ
i;
And 5, calculating the running reliability of the direct current charging pile for the electric automobile.
Further, potential failure modes include: the direct current charging pile for the electric automobile has performance degradation failure, functional fault failure and sudden failure; the performance degradation failure comprises insulation aging failure, charging interface contact abrasion failure and direct current contactor adhesion failure; the functional failure comprises failure of an electronic lock of the charging gun, failure of network communication and failure of disconnection of a cable assembly.
Further, the DC charging pile operation reliability evaluation candidate model for the electric automobile comprises a performance degradation failure operation reliability evaluation model M based on Gamma (Gamma) process
1Functional fault failure operation reliability evaluation model M based on Power law (Power law) distribution
2Sudden failure operational reliability evaluation model M based on Weibull (Weibull) distribution
3。
Further, the direct current charging pile operation reliability evaluation model for the electric automobile integrated with multiple failure models is
Wherein P is
i(Ω|M
i) Is represented in model M
iConditional probability density function of lower event omega.
Further, the estimated error expression of the log-type likelihood function is
Wherein f is
istAnd representing the evaluation result of the ith member in the failure model set in space s and time t.
Further, the improved finite memory quasi-Newton method comprises the following steps:
step (1) determining an initial point x
0∈R
nAnd an initial positive definite matrix
Wherein R is
nIs a real number vector of n-dimension,
is n × n real matrix, set to 0<ε<1,k=0;
Step (2) calculating function f (x) at point x
kGradient g of
k=▽f(x
k) Judging g | |
kIf | < epsilon is satisfied, stopping if satisfied, and taking the optimal point x
*=x
kThe algorithm terminates; otherwise, jumping to the step (3);
step (3) solving equation B
kd
k+g
kGet the search direction d as 0
kIn which B is
kAn approximation matrix for the curvature information (Hessian matrix) for the function f (x);
step (4) introduces a linear search mechanism to obtain the step size α
kI.e. given a constant m
1Satisfy 0<m
1<1, order α
k>0, such that
Thereby finally determining the step value;
step (5) let x
k+1=x
k+1+α
kd
k,s
k=x
k+1-x
k,y
k=▽f(x
k+1)-▽f(x
k) Judging g | |
k+1If | < epsilon is satisfied, if so, solving to obtain x
k+1The algorithm terminates; otherwise, calculating
Wherein
Psi is the acceleration factor;
and (6) enabling k to be k +1, and jumping to the step (3).
Compared with the prior art, the invention has the following beneficial effects:
the direct-current charging function of the electric automobile is realized by respectively constructing a plurality of candidate failure models matched with the actual variation process of the operational reliability of the direct-current charging pile for the electric automobile on the basis of mutual coordination and cooperation of a plurality of modules or parts, and evaluating a Gamma (Gamma) process-based performance degradation failure operational reliability evaluation model M
1Functional fault failure operation reliability evaluation model M based on Power law (Power law) distribution
2Sudden failure operational reliability evaluation model M based on Weibull (Weibull) distribution
3The operation reliability analysis is carried out by taking multiple potential failure modes into consideration, so that the operation reliability analysis method is more consistent with the change rule of the operation reliability of the direct current charging pile for the electric automobile, and a foundation is laid for improving the accuracy of a final analysis result; the Bayesian model is used for averaging, and the direct current charging pile for the electric automobile can be operated in multiple failure modesThe method has the advantages that the integration of multiple failure models in the same frame is completed by taking the influence of the dependence into consideration, the limitation of single model analysis research is eliminated, and the accurate evaluation on the running reliability of the direct current charging pile for the electric automobile is realized; the weight and variance of the conditional probability function of each candidate failure model are estimated by adopting an improved finite memory quasi-Newton method, so that P is eliminated
i(Ω|M
i) The method has the advantages of high calculation efficiency, less required storage units and the like, further improves the convergence rate of iterative calculation by introducing an acceleration factor, and can more accurately describe the operation reliability of the complex electric control system.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without inventive efforts, wherein:
FIG. 1 is a flow chart of a method for evaluating the operation reliability of a DC charging pile for an electric vehicle integrated with multiple failure models according to the present invention;
fig. 2 is a typical failure mode of a dc charging post for an electric vehicle.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
The direct current charging pile for the electric automobile has multiple functions of rectification, protection, communication, output control and the like as a typical complex electric control system, and different component modules need to run in a mutual cooperation mode, so that the reliability of the direct current charging pile is influenced by more factors. Therefore, potential failure modes of the direct-current charging pile are researched and explored, a candidate model for evaluating the operation reliability of the direct-current charging pile is established, the operation reliability of the direct-current charging pile for the electric automobile is evaluated on average based on a Bayesian model, the reliable operation of equipment can be guaranteed, the use experience of an electric automobile owner and the use frequency of the automobile are improved, and a reference basis is provided for formulating an equipment maintenance plan. The specific implementation process can be divided into the following 5 steps, as shown in fig. 1.
Step 1, according to the operation characteristics of a direct current charging pile for an electric automobile, considering that a plurality of module parts are required to be matched with each other in a coordinated manner in order to realize a charging function, the operation modes are multiple and complex, and therefore multiple failure modes exist. More importantly, different failure modes mutually influence each other, and direct current fills electric pile operational reliability level for electric automobile is directly related to. And (3) exploring and acquiring potential failure modes of the current and past processes by combining the failure records of the current and past processes, wherein the potential failure modes mainly comprise performance degradation failure, functional failure and burst failure as shown in FIG. 2.
The performance degradation failure mainly presents asymptotic characteristics, namely the failure characteristics are gradually obvious along with the time, and the current state of the performance degradation failure can be obtained by monitoring key state parameters. Here, the performance degradation failure includes an insulation aging failure, a charging interface contact wear failure, and a dc contactor adhesion failure. The optimized key state monitoring parameters are respectively the system insulation resistance, the charging interface temperature rise and the direct current contactor breaking current Joule integral value (I)
2t)。
The functional failure mainly is that the system functional failure is caused by the failure of a certain component or module in the system, and the occurrence of the functional failure can be judged by monitoring whether a certain function of the system is lost. Here, the failure of the functional fault of the dc charging pile includes failure of an electronic lock of the charging gun, failure of network communication, and failure of disconnection of a cable assembly.
The sudden failure is caused by unexpected impact or sudden change of the working condition of the equipment, whether the sudden failure occurs or not can not be judged by monitoring key state parameters, and the sudden failure does not have any sign and presents the characteristics of contingency and randomness.
Step 2, analyzing the potential failure modes of the direct current charging pile by using a multi-failure-mode analysis method, and analyzing x
iRandom variable, x, expressed as the i-th failure mode
iHas a probability density function of f (x)
i) Then is electrically drivenThe failure probability function of the running reliability of the direct current charging pile for the automobile is as follows:
in the formula, p
iA weight factor representing the i-th failure mode, an
And (3) respectively establishing a DC charging pile operation reliability evaluation candidate model for the electric automobile according to the failure mode types in the step (1). Considering that the probability change of performance degradation failure shows a monotone rising trend, the Gamma (Gamma) process can be used to describe the accumulated damage related to time, i.e. the degradation amount in any finite time interval is composed of infinite jumps following the Gamma distribution. The amount of degradation v can be assumed
G(t) obeys the Ga (a, b) distribution, the probability density function of which can be expressed as
Wherein Γ (·) is a gamma function, a is a shape parameter that controls the frequency of the jump point arrival, and b is a scale parameter that controls the jump degree of the jump.
According to the failure characteristics of the direct current charging pile function fault for the electric automobile, a random process which accords with Power law (Power law) distribution is used for describing. Assumption of failure variable v
P(t) obeys a power-law distribution with a parameter of α, its probability density function can be expressed as
f
P(t;α,β)=βt
-α-1
Wherein β is a constant greater than 0.
Considering that the change rule of the service life of the direct current charging pile for the electric vehicle caused by the sudden failure meets Weibull (Weibull) distribution, the probability density function can be expressed as
Wherein m is a proportional parameter and n is a shape parameter.
Step 3, constructing a direct current charging pile operation reliability evaluation model for the electric vehicle integrated with multiple failure models based on Bayesian model average; the Bayes model average is a statistical post-processing method for probability prediction by utilizing a multi-mode set, and the prediction probability density distribution function of a certain variable is the weighted average of the prediction probability distribution of a single model after deviation correction, and the weight is the posterior probability of the corresponding model. Here, the direct current charging pile operation reliability evaluation model for the electric automobile with the integration of multiple failure models can be established as follows:
in the formula P
i(Ω|M
i) Is represented in model M
iConditional probability density function of lower event omega, omega
iIs a weight, i.e., a posterior probability representing that the ith model is the best model, and ω
iAre non-negative values. Assuming that the mean value of the conditional probability distribution or the simple linear function expected to be the prediction result of the original candidate model, it can be expressed as:
in the formula, c
i,d
iAre respectively a deviation correction term, f
iAs candidate model M
iThe prediction result of (2). Its variance can be expressed again as
In the formula (f)
istAnd (3) representing the prediction (evaluation) result of the ith member in the failure model set in space s and time t. The first term in the above equation represents the degree of diffusion of the prediction ensemble, and the second term represents the prediction variance within the ensemble.
Step 4, according to the maximum likelihood principle, assuming that the estimation errors are mutually independent in space and time, establishing an estimation error expression as follows:
here, the log-type likelihood function is adopted rather than the likelihood function itself, mainly from the point of convergence stability of the iterative computation. Introduction of an intermediate variable p
i(0≤ρ
iLess than or equal to 1), let
Can eliminate
Is explicitly constrained.
The weight omega of each candidate model in the model set needs to be accurately estimated due to the Bayesian model averaging
iAnd variance σ
iThe estimation of the weights and variances essentially solves the extremum problem as follows:
the extreme value problem is solved by adopting an improved finite memory quasi-Newton method, and the optimal weight and variance can be obtained. The improved finite memory quasi-Newton method mainly comprises the following steps:
step (1) determining an initial point x
0∈R
nAnd an initial positive definite matrix
Wherein R is
nIs a real number vector of n-dimension,
is n × n real matrix, set to 0<ε<1,k=0;
Step (2) calculating function f (x) at point x
kGradient g of
k=▽f(x
k) Judging g | |
kIf | < epsilon is satisfied, stopping if satisfied, and taking the optimal point x
*=x
kThe algorithm terminates; otherwise, jumping to the step (3);
step (3) solving equation B
kd
k+g
kGet the search direction d as 0
kIn which B is
kAn approximation matrix for the curvature information (Hessian matrix) for the function f (x);
step (4) introduces a linear search mechanism to obtain the step size α
kI.e. given a constant m
1Satisfy 0<m
1<1, order α
k>0, such that
Thereby finally determining the step value;
step (5) let x
k+1=x
k+1+α
kd
k,s
k=x
k+1-x
k,y
k=▽f(x
k+1)-▽f(x
k) Judging g | |
k+1If | < epsilon is satisfied, if so, solving to obtain x
k+1The algorithm terminates; otherwise, calculating
Wherein
Psi is the acceleration factor; here, the preferred value of ψ is
And (6) enabling k to be k +1, and jumping to the step (3).
And 5, calculating to obtain the running reliability of the direct current charging pile for the electric automobile.
The potential failure modes of the direct current charging pile for the electric automobile are identified, corresponding candidate failure models are respectively established, the candidate failure models are brought into the same frame by using a multi-model integration technology for reliability analysis, the accuracy of an analysis and prediction result is improved, and a theoretical basis is laid for the organic combination of the safety, the reliability and the economy of the operation process of the direct current charging pile.
While the invention has been described in terms of its preferred embodiments, it will be understood by those skilled in the art that various changes and modifications can be made without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (8)
1. A method for evaluating the operation reliability of a direct current charging pile for an electric automobile integrated with multiple failure models is characterized by comprising the following steps:
step 1, acquiring a potential failure mode of the direct current charging pile for the electric automobile by combining failure records of current and past processes according to the operation characteristics of the direct current charging pile for the electric automobile;
step 2, analyzing potential failure modes of the direct current charging pile by using a multi-failure-mode analysis method, and respectively establishing a direct current charging pile operation reliability evaluation candidate model for the electric vehicle according to different failure modes;
step 3, constructing a direct current charging pile operation reliability evaluation model for the electric vehicle integrated with multiple failure models based on Bayesian model average;
step 4, establishing an evaluation error expression of the log-type likelihood function on the basis of mutually independent assumption of evaluation error space and time according to the maximum likelihood principle, and estimating and determining the weight omega of the conditional probability function of each candidate failure model by adopting an improved finite memory quasi-Newton method
iAnd variance σ
i;
And 5, calculating the running reliability of the direct current charging pile for the electric automobile.
2. The method for evaluating the operation reliability of the direct current charging pile for the electric automobile integrated by the multiple failure models as claimed in claim 1, wherein the potential failure modes in step 1 comprise: the direct current charging pile for the electric automobile has performance degradation failure, functional failure and sudden failure.
3. The method for evaluating the operation reliability of the direct current charging pile for the electric automobile integrated by the multiple failure models as claimed in claim 2, wherein the performance degradation failure comprises insulation aging failure, charging interface contact abrasion failure and direct current contactor adhesion failure.
4. The method for evaluating the operation reliability of the direct current charging pile for the electric automobile integrated by the multiple failure models as claimed in claim 2, wherein the functional failure comprises failure of an electronic lock of a charging gun, failure of network communication and failure of disconnection of a cable assembly.
5. The method for evaluating the operational reliability of the DC charging post for the electric vehicle integrated by the multiple failure models as claimed in claim 1, wherein the DC charging post operational reliability evaluation candidate model for the electric vehicle in the step 2 comprises a Gamma (Gamma) process-based performance degradation failure operational reliability evaluation model M
1Functional fault failure operation reliability evaluation model M based on Power law (Power law) distribution
2Sudden failure operational reliability evaluation model M based on Weibull (Weibull) distribution
3。
6. The method for evaluating the operation reliability of the multi-failure-model-integrated direct-current charging pile for the electric vehicle according to claim 1, wherein the multi-failure-model-integrated direct-current charging pile operation reliability evaluation model for the electric vehicle in the step 3 is
Wherein P is
i(Ω|M
i) Is represented in model M
iConditional probability density function of lower event omega.
7. The method for evaluating the operation reliability of the direct current charging pile for the electric vehicle integrated by the multiple failure models as claimed in claim 1, wherein the evaluation error expression of the log type likelihood function in the step 4 is
Wherein f is
istAnd representing the evaluation result of the ith member in the failure model set in space s and time t.
8. The method for evaluating the operational reliability of the direct current charging pile for the electric automobile integrated by the multiple failure models as claimed in claim 1, wherein the improved finite memory quasi-Newton method in step 4 comprises the following steps:
step (1) determining an initial point x
0∈R
nAnd an initial positive definite matrix
Wherein R is
nIs a real number vector of n-dimension,
is n × n real matrix, set to 0<ε<1,k=0;
Step (2) calculating function f (x) at point x
kGradient g of
k=▽f(x
k) Judging g | |
kIf | < epsilon is satisfied, stopping if satisfied, and taking the optimal point x
*=x
kThe algorithm terminates; otherwise, jumping to the step (3);
step (3) solving equation B
kd
k+g
kGet the search direction d as 0
kIn which B is
kAn approximation matrix for the curvature information (Hessian matrix) for the function f (x);
step (4) introduces a linear search mechanism to obtain the step size α
kI.e. given a constant m
1Satisfy 0<m
1<1, order α
k>0, such that
Thereby finally determining the step value;
step (5) let x
k+1=x
k+1+α
kd
k,s
k=x
k+1-x
k,y
k=▽f(x
k+1)-▽f(x
k) Judging g | |
k+1If | < epsilon is satisfied, if so, solving to obtain x
k+1The algorithm terminates; otherwise, calculating
Wherein
Psi is the acceleration factor;
and (6) enabling k to be k +1, and jumping to the step (3).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910904810.2A CN110782126B (en) | 2019-09-24 | 2019-09-24 | DC charging pile operation reliability evaluation method for electric automobile |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910904810.2A CN110782126B (en) | 2019-09-24 | 2019-09-24 | DC charging pile operation reliability evaluation method for electric automobile |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110782126A true CN110782126A (en) | 2020-02-11 |
CN110782126B CN110782126B (en) | 2023-07-21 |
Family
ID=69383746
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910904810.2A Active CN110782126B (en) | 2019-09-24 | 2019-09-24 | DC charging pile operation reliability evaluation method for electric automobile |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110782126B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111391694A (en) * | 2020-02-29 | 2020-07-10 | 国网江苏省电力有限公司苏州供电分公司 | Multi-level rapid data monitoring method and system for operation and maintenance of charging station |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103778295A (en) * | 2014-01-26 | 2014-05-07 | 南京航空航天大学 | Method for evaluating operating reliability of multi-model integrated aero-engine under multiple failure modes |
US20160196236A1 (en) * | 2015-01-07 | 2016-07-07 | Umm Al-Qura University | Method for estimating and predicting parameters of exponentiated weibull model |
CN107832921A (en) * | 2017-10-19 | 2018-03-23 | 南京邮电大学 | A kind of charging electric vehicle integrated safe evaluation method based on Evaluation formula |
-
2019
- 2019-09-24 CN CN201910904810.2A patent/CN110782126B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103778295A (en) * | 2014-01-26 | 2014-05-07 | 南京航空航天大学 | Method for evaluating operating reliability of multi-model integrated aero-engine under multiple failure modes |
US20160196236A1 (en) * | 2015-01-07 | 2016-07-07 | Umm Al-Qura University | Method for estimating and predicting parameters of exponentiated weibull model |
CN107832921A (en) * | 2017-10-19 | 2018-03-23 | 南京邮电大学 | A kind of charging electric vehicle integrated safe evaluation method based on Evaluation formula |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111391694A (en) * | 2020-02-29 | 2020-07-10 | 国网江苏省电力有限公司苏州供电分公司 | Multi-level rapid data monitoring method and system for operation and maintenance of charging station |
CN111391694B (en) * | 2020-02-29 | 2023-08-11 | 国网江苏省电力有限公司苏州供电分公司 | Multi-level rapid data monitoring method and system for operation and maintenance of charging station |
Also Published As
Publication number | Publication date |
---|---|
CN110782126B (en) | 2023-07-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhou et al. | A robust prognostic indicator for renewable energy technologies: A novel error correction grey prediction model | |
Liu et al. | PEMFC residual life prediction using sparse autoencoder-based deep neural network | |
Caliwag et al. | Hybrid VARMA and LSTM method for lithium-ion battery state-of-charge and output voltage forecasting in electric motorcycle applications | |
Yu et al. | OCV-SOC-temperature relationship construction and state of charge estimation for a series–parallel lithium-ion battery pack | |
CN114372417A (en) | Electric vehicle battery health state and remaining life evaluation method based on charging network | |
CN110266031B (en) | Energy storage grid-connected charging and discharging capacity control method and device, server and storage medium | |
CN112884270B (en) | Multi-scene power distribution network planning method and system considering uncertainty factors | |
US20220099743A1 (en) | Method and Apparatus for Operating a System for Providing Predicted States of Health of Electrical Energy Stores for a Device Using Machine Learning Methods | |
CN113125987A (en) | Novel hybrid lithium ion battery health state prediction method | |
Wang et al. | Health diagnosis for lithium-ion battery by combining partial incremental capacity and deep belief network during insufficient discharge profile | |
Wu et al. | Hydrogen energy storage system for demand forecast error mitigation and voltage stabilization in a fast-charging station | |
Zhao et al. | The li-ion battery state of charge prediction of electric vehicle using deep neural network | |
CN116151114A (en) | Method and system for predicting service life of fuel cell under meta-universe based on hybrid framework | |
CN116298936A (en) | Intelligent lithium ion battery health state prediction method in incomplete voltage range | |
CN113791351B (en) | Lithium battery life prediction method based on transfer learning and difference probability distribution | |
CN110782126B (en) | DC charging pile operation reliability evaluation method for electric automobile | |
Zhou et al. | A light-weight feature extractor for lithium-ion battery health prognosis | |
Fletcher et al. | Comparison of fuel consumption and fuel cell degradation using an optimised controller | |
CN116774045A (en) | Lithium battery health state prediction method based on HHO-SVR | |
CN116819372A (en) | Method for calculating health state of energy storage battery by neural network | |
CN114859231B (en) | Battery remaining life prediction method based on wiener process and extreme learning machine | |
Gao et al. | A novel indirect health indicator extraction based on charging data for lithium-ion batteries remaining useful life prognostics | |
CN112736894A (en) | Two-stage unit combination modeling method considering randomness of wind power and electric automobile | |
Wei et al. | Two-phase early prediction method for remaining useful life of lithium-ion batteries based on a neural network and Gaussian process regression | |
Wang et al. | A reinforcement learning‐based energy management strategy for a battery–ultracapacitor electric vehicle considering temperature effects |
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 |