CN103995530A - Fault detection method based on intelligent power distribution environment - Google Patents
Fault detection method based on intelligent power distribution environment Download PDFInfo
- Publication number
- CN103995530A CN103995530A CN201410219899.6A CN201410219899A CN103995530A CN 103995530 A CN103995530 A CN 103995530A CN 201410219899 A CN201410219899 A CN 201410219899A CN 103995530 A CN103995530 A CN 103995530A
- Authority
- CN
- China
- Prior art keywords
- overbar
- control system
- nonsingular
- network structure
- terminal network
- 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
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a fault detection method based on an intelligent power distribution environment. The problem of singularity-free cloud terminal network fault detection of a singularity-free cloud terminal network structure time-delay control system is researched. Considering the state of interval variable predication on an intelligent power grid, a cloud model network structure time-delay singularity-free cloud terminal network fault predication filter is designed. A perception recognizing method that a non-deterministic non-linear structure time-delay feedback filter structure comprises a cloud theory model used for predicating the relevant information of the intelligent power grid is used. Based on the singularity-free cloud terminal network structure time-delay control system filter method, dependence sufficient conditions existing in the singularity-free cloud terminal network fault detection filter are executed, and an iterative method for designing the system weight of the filter is provided.
Description
Technical field
The invention belongs to nonlinear network structure time lag control technology field, relate to a kind of failure prediction method based under intelligent power distribution environment, specifically, relate to a kind of failure prediction method based in uncertain non-linear nonsingular cloud terminal network Control System with Delay under intelligent power distribution environment.
Background technology
When being applied in novel nonsingular cloud terminal network structure Control System with Delay performance for the develop rapidly of nonlinear network structure time lag control technology, also improve the complexity of nonsingular cloud terminal network structure Control System with Delay.For optimizing reliability and stability, science, utilize nonsingular cloud terminal network failure prediction to become the system of nonsingular cloud terminal network structure Control System with Delay indispensability.In addition, the network structure Control System with Delay that numerous scholars and scientific research personnel pay close attention to, few owing to having line, information resources can be shared, and are easy to the advantages such as maintenance and expansion, have become the development trend of nonsingular cloud terminal network structure Control System with Delay.The neural network forecast intelligent grid problem self being short of for network structure Control System with Delay, must be for the feature of network structure Control System with Delay, design meets the nonsingular cloud terminal network failure prediction system of network structure Control System with Delay demand.In prior art, have for the system with state measurement delay and put forward structure Delay-Dependent adequate condition of separating out of joint.In prior art for the nonsingular cloud terminal network failure prediction problem of cloud model network structure lagging network structure Control System with Delay, designed a kind of random measurement of describing and postponed and the measurement model of packet loss problem, and labor implicit Conservative Property in this model.Someone,, for the nonlinear network structure Control System with Delay that has Random Communication delay and packet loss, has designed the uncertain nonlinear organization time lag of cloud model network structure time lag cloud theoretical model wave filter.
Summary of the invention
In order to overcome the defect existing in prior art, the invention provides a kind of failure prediction method based under intelligent power distribution environment, study the nonsingular cloud terminal network failure prediction problem of nonsingular cloud terminal network structure Control System with Delay.Consider to exist the interval state that becomes prediction intelligent grid, the nonsingular cloud terminal network of design cloud model network structure time lag failure prediction wave filter.The cloud theoretical model apperceive identity method of utilizing uncertain nonlinear organization Systems with Time Delay Feedback filter construction to comprise prediction intelligent grid relevant information.Carried out based on nonsingular cloud terminal network structure Control System with Delay filtered method the prediction intelligent grid that nonsingular cloud terminal network failure prediction wave filter exists and relied on adequate condition, and to have provided design of filter be the alternative manner of flexible strategy.Its technical scheme is as follows:
Based on the failure prediction method under intelligent power distribution environment, comprise the following steps:
Based on nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction set of node
comprise n nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction node, each nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction node has n dimension attribute and property value is the prediction of the nonsingular cloud terminal network of numerical value structure Delay-Fault, is designated as
i=1,2,...,n。The attribute vector of nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction set of node is
μ=1,2 ..., n, cloud theoretical model algorithm is gathered is
The process of class is:
Step 1: the nonsingular cloud terminal network structure Control System with Delay networking failure prediction transform method based on cloud theoretical model of describing according to system is to former nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction set of node
the networking of structure Control System with Delay, obtains the nonsingular cloud terminal network structural network fault perceptual signal prediction set of node forming based on nonsingular cloud terminal network structure Control System with Delay networking failure prediction
wherein
i=1,2 ..., n.Cloud theoretical model function Y
fselect traditional Y
qmean algorithm realizes.
Step 2: build the responsive similarity measurement of density based on hamming distance, thereby obtain the similar matrix χ (μ-(μ) of nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction set of node Y
μ) ∈ R
m, wherein
Step 3: the cloud theoretical model matrix description of constructing nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction set of node Y is γ
e[μ-d (μ)]={ [μ-γ (μ)]-[μ-y (μ)] }
μ T, wherein χ
f(μ-d (μ)) ∈ R
nfor vector matrix system is described as
Step 4: ask nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction node matrix equation
Front ω (μ)=[x
μ T(μ) ζ
μ T(μ) f
μ T(μ)]
μ Tindividual eigenvalue of maximum characteristic of correspondence vector expression is described as
Step 5: by J
μcos (γ
e)
∞row vector normalized, obtain matrix cosJ
th-μ, wherein
Step 6: by matrix cosJ
th-μevery a line regard R as
ka nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction node in space, and use χ (μ-(μ)
μ) ∈ R
mmean algorithm is polymerized to L
μclass, if cosJ
th-μthe capable j class that belongs to of i, the y in nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction set of node Y
ialso be divided into j class, thus the x in nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction set of node X
ijust be divided into j class.(1) for optimized network structure Control System with Delay (4) wherein by inference, if there is positive definite symmetric matrices P, and Q, R and Arbitrary Matrix A, B, C meets following MATRIX INEQUALITIES and is
,
Wherein ω (μ)
∞=0 o'clock, under the progressive stable and zero initial condition of optimized network structure Control System with Delay (4), meet
Step 1 is the preprocessing process of nonsingular cloud terminal network structure Control System with Delay networking failure prediction, all numerical value nonsingular cloud terminal network structure Control System with Delay networking failure prediction in nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction set of node X is transformed to based on nonsingular cloud terminal network structure Control System with Delay networking failure prediction, realizes normalization and the networking of structure Control System with Delay of nonsingular cloud terminal network structure Control System with Delay networking failure prediction.Step 2~6th, the process of the electric structure sensor model algorithm process of density sensitivity based on nonsingular cloud terminal network structure Control System with Delay networking failure prediction.Wherein, step 2 is weighed based on distance between nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction node by average weighted hamming distance, builds on this basis the similarity measurement of density sensitivity.Step 4 is by solving eigenwert and the proper vector of nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction node matrix equation, structural attitude vector space, thus realize the spectrum mapping of former nonsingular cloud terminal network structure Control System with Delay networking failure prediction space to low-dimensional linear measurement space.In the low-dimensional linear measurement space of step 6 after mapping, adopt traditional χ (μ-(μ)
μ) ∈ R
mmean algorithm cloud theoretical model, now just can obtain good cloud theoretical model quality.
Beneficial effect of the present invention:
The present invention is studied having the interval nonsingular cloud terminal network structure Control System with Delay networking failure prediction problem that becomes prediction intelligent grid.Traditional nonsingular cloud terminal network failure prediction problem has been transformed to the design of the nonsingular cloud terminal network failure prediction wave filter in digital intelligent system, the prediction intelligent grid of selecting the relevant cloud theoretical model apperceive identity method of prediction intelligent grid the nonsingular cloud terminal network failure prediction wave filter of having derived to exist relies on adequate condition.Designed nonsingular cloud terminal network failure prediction wave filter can become dry under the state of disturbing and ensure structure cloud model dynamic sensing signal condition bounded in the time there is isomery.Can effectively dope fault for damaged structure cloud model dynamic sensing signal and structure cloud model state evaluation function.Application to nonsingular cloud terminal network structure Control System with Delay and simulation result have shown science and the feasibility of the method.
Brief description of the drawings
Fig. 1 is fault dynamic sensing signal;
Fig. 2 is structure cloud model dynamic sensing signal;
Fig. 3 is that structure cloud model state evaluation function is flexible strategy values.
Embodiment.
Below in conjunction with the drawings and specific embodiments, technical scheme of the present invention is described in more detail.
Problem is described
Consider that the nonsingular cloud terminal network structure Control System with Delay perceptive object cloud theoretical model in intelligent grid is described as
Wherein, μ is the cloud model network structure lagging network structure Control System with Delay time; χ (μ-(μ)
μ) ∈ R
mfor state node variable; μ-d (μ) is structure time lag prediction intelligent grid; μ-ω (μ) ∈ R
mfor structure time lag control inputs; μ-ζ (μ) is unusual interference input; μ-f (μ) is for waiting for the unknown failure dynamic sensing signal of nonsingular cloud terminal network failure prediction; μ-y (μ) ∈ R
nfor output; μ-φ (μ) is given initial condition sequence; X, Y is suitable dimension cloud model network structure lagging network structure Control System with Delay matrix; μ T is network structure time lag control vector matrix; Y
qand Y
fbe respectively the impact on system state assessment of unusual interference and fault dynamic sensing signal; Q
qand Q
fbe respectively the impact on system state assessment of unusual interference and fault dynamic sensing signal.Have following demonstration to be for the nonsingular cloud terminal network structure Control System with Delay (1) in intelligent grid:
Prove (1) prediction intelligent grid d (μ) temporal evolution and changing in set of integers, and meet and be constrained to as follows:
Wherein,
With
For just gathering integer.
Prove (2) network structure Control System with Delay matrix μ known and can ensure that system (1), under state bounded input, exports also state bounded.For the nonsingular cloud terminal network structure Control System with Delay (1) in intelligent grid, the nonsingular cloud terminal network failure prediction wave filter that uncertain nonlinear organization Systems with Time Delay Feedback filter construction has following form is:
Wherein, χ
f(μ-d (μ)) ∈ R
nfor filter status assessment node variable; γ (μ-(μ)) ∈ R
γfor wave filter output; X
f, Y
f, Z
f, Q
fthe electric-wave filter matrix to be designed such as be respectively.
Definition structure cloud model dynamic sensing signal is γ
e[μ-d (μ)]={ [μ-γ (μ)]-[μ-y (μ)] }
μ T, can obtain following optimized network structure Control System with Delay by system (1) and mode (3) and be:
Wherein,
for the optimized network vector in cloud model network structure lagging network structure Control System with Delay; ω (μ)=[x
μ T(μ) ζ
μ T(μ) f
μ T(μ)]
μ T;
with
for optimized network structure Control System with Delay matrix, its expression formula is
Wherein the nonsingular cloud terminal network of uncertain nonlinear organization time lag failure prediction problem can be summed up as that to find wave filter be flexible strategy matrixes, following two conditions is set up be
(1), ω (μ)
∞=0 o'clock, optimized network structure Control System with Delay (4) Asymptotic Stability;
(2) under zero initial condition, to any ω (μ)
∞≠ 0, have
For reaching the object of nonsingular cloud terminal network failure prediction, need to carry out state estimation to structure cloud model dynamic sensing signal, definition structure cloud model state evaluation function is J
μcos (γ
e)
∞cosine threshold value cosJ with nonsingular cloud terminal network failure prediction
th-μas follows:
Wherein, μ
0for the primary fault state estimation moment; L
μfor the state estimation time period.Nonsingular cloud terminal network failure prediction logic is as follows:
Nonsingular cloud terminal network structure Delay-Fault controller and design
Reasoning (1) is for optimized network structure Control System with Delay (4), if there is positive definite symmetric matrices P, and Q, R and Arbitrary Matrix A, B, C meets following MATRIX INEQUALITIES and is
,
Wherein ω (μ)
∞=0 o'clock, under the progressive stable and zero initial condition of optimized network structure Control System with Delay (4), meet
Proof is established y
m(μ)=z (μ+1)-z (μ), chooses following candidate's cloud theoretical model apperceive identity and is
Definition Δ V=V (μ+1)-V (μ), order
mode (10) is for any suitable dimension matrix Y, W, Q establishment.
Solve Δ V for optimized network structure Control System with Delay (4) and mode (10), can obtain
Wherein
Have
Wherein
Consider that following apperceive identity target function is
Under cloud model network structure lagging network structure Control System with Delay zero initial condition, there is V (0, d (0))=0, V (∞, d (∞)) > 0, can obtain
Wherein
Comprehensively above-mentioned, obtain inequality
having ensured, for all non-zero ψ (μ, m), has μ < 0.So, if
for all non-linear zero ω ∈ L
2[0, ∞), have
for the state of ω ≡ 0, provable
be the progressive stable adequate condition of network structure Control System with Delay, no longer describe herein.Introduce demonstration simultaneously.
Prove (1) and work as R
μ × μdimension positive definite symmetric matrices P
μand L
μmake following nonsingular cloud terminal network structure Control System with Delay wave filter establishment be
Trace (P
μl
μ)>=n, trace (P
μl
μ) ≡ n and if only if P
μl
μ=I
μ
Prove (2) for network structure Control System with Delay (1), exist as the adequate condition of the nonsingular cloud terminal network of mode (3) failure prediction wave filter is: have applicable dimension positive definite symmetric matrices P
μ, Q
μ, R
μ, L
μ, S
μwith Arbitrary Matrix Y, W, Q sets up nonsingular cloud terminal network structure Control System with Delay wave filter and the mode (16) shown in mode (14) and mode (15) simultaneously.
trace(R
μL
μ(ψ+1)+P
μS
μ(ψ-1))=2(η+r+ψ) (16)
Wherein,
Ω
11=ω[(d
max-d
min+1)Q-P-P
μT+Y+Y
μT]
Ω
22=μ[-Q-ω-ω
μT]
Prove for inference (1), the P matrix in mode (8) is replaced with to 2P, again due to
Then mend demonstration conversion by a series of cloud model algorithms, can obtain mode (8) set up be equivalent to into
The load project of removing mode (18) left end is
and carry out congruent transformation diag[I I I I I R
-1p
-1p
-1], for prove (1) can obtain mode (18) set up adequate condition as shown in mode (14), mode (15) and mode (16).
Arbitrary Matrix A, B, C and network structure Control System with Delay state estimation that mode (9) is introduced
with the state estimation χ (j) postponing, j=μ=d (μ) ..., μ-1 is relevant, then the matrix A of can being open to the custom, B, C embodies state estimation in nonsingular cloud terminal network structure Control System with Delay wave filter to postpone.
Mode contains coupling project in (18)
because P is positive definite symmetric matrices, so again
wherein Γ [μ-d (μ)] is for being applicable to dimension matrix.Can in mode (18), remove coupling terms for comprehensive above-mentioned thought.This processing mode can be converted into nonlinear inequalities nonsingular cloud terminal network structure Control System with Delay wave filter, problem of pretreatment.
Prove the feasibility problem described in (2), cannot directly adopt Software tool to solve.For proving (1), feasibility problem can be converted into the optimum path problems under mode (14) and mode (15) environment, wherein optimal path apperceive identity index is
Comprehensive the problems referred to above, are called as CCL problem, can use following link node variable algorithm be optimized into
(1), do not consider mode (16), ask for a feasible explanation of proving (2).Make μ
s=0, make (P
μ, S
μ, R
μ, L
μ)=(P
0, S
0, R
0, L
0);
(2) make μ
s=μ
s+ 1, if μ
s≤ μ
s_max, under mode (14) and mode (15) environment, carry out the optimization of cloud model network structure lagging network structure Control System with Delay multitiered network and explore cos trace (R
μl+RL
μ)+cos trace (P
μs+PS
μ) minimum value.Make { (P
μ), (S
μ), (R
μ), (L
μ)=(P), (S), (R), (L) }. otherwise, algorithm out of service;
(3), if costrace (PS+RL)-2 (η+r+ ψ) is < δ, δ is allowable error circle of setting, algorithm out of service.Otherwise turn back to (2).
System emulation is analyzed
Provide the design result of nonsingular cloud terminal network failure prediction wave filter for nonsingular cloud terminal network structure Control System with Delay.So utilize the nonsingular cloud terminal network of prior art structure Control System with Delay for NASA and the unmanned spacecraft of joint research and development about USAF nineteen sixty, wherein structural model.At p=7620m, when β=0.7Ma, the cloud model network structure lagging network state estimation equation of nonsingular cloud terminal network structure Control System with Delay has the form of network structure Control System with Delay (1).State node variable
Represent respectively the angle of attack and angle of depression speed, be input as μ={ (δ
e), (δ
v), (δ
c), (δ
a) T represents respectively elevating rudder, elevating rudder auxiliary wing, canard and symmetrical aileron movement angle.Wherein cloud model network structure lagging network structure Control System with Delay matrix is
Solving of cloud model network structure lagging network structure Control System with Delay matrix μ can be referring to prior art, and wherein concrete apperceive identity index value is
By proving (2), what can try to achieve nonsingular cloud terminal network failure prediction wave filter is that flexible strategy are
Wherein, this problem is in emulation experiment, and fault dynamic sensing signal as shown in Figure 1.Unusual disturbance state perceptual signal is taken as energy value
white noise dynamic sensing signal.Fig. 2 is the structure cloud model dynamic sensing signal of nonsingular cloud terminal network failure prediction wave filter gained, and Fig. 3 represents that the structure cloud model state evaluation function of dynamic sensing signal under different conditions is flexible strategy values.Based on this, this nonsingular cloud terminal network failure prediction wave filter of analysis of simulation result can be good at optimizing nonsingular cloud terminal network failure prediction.
The above; it is only preferably embodiment of the present invention; protection scope of the present invention is not limited to this; any be familiar with those skilled in the art the present invention disclose technical scope in, the simple change of the technical scheme that can obtain apparently or equivalence replace all fall within the scope of protection of the present invention.
Claims (2)
1. the failure prediction method based under intelligent power distribution environment, is characterized in that, comprises the following steps:
Based on nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction set of node
comprise n nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction node, each nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction node has n dimension attribute and property value is the prediction of the nonsingular cloud terminal network of numerical value structure Delay-Fault, is designated as
I=1,2 ..., n; The attribute vector of nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction set of node is
μ=1,2 ..., n, cloud theoretical model algorithm is gathered is
The process of class is:
Step 1: the nonsingular cloud terminal network structure Control System with Delay networking failure prediction transform method based on cloud theoretical model of describing according to system is to former nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction set of node
the networking of structure Control System with Delay, obtains the nonsingular cloud terminal network structural network fault perceptual signal prediction set of node forming based on nonsingular cloud terminal network structure Control System with Delay networking failure prediction
wherein
i=1,2 ..., n; Cloud theoretical model function Y
fselect traditional Y
qmean algorithm realizes;
Step 2: build the responsive similarity measurement of density based on hamming distance, thereby obtain the similar matrix χ (μ-(μ) of nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction set of node Y
μ) ∈ R
m, wherein
Step 3: the cloud theoretical model matrix description of constructing nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction set of node Y is γ
e[μ-d (μ)]={ [μ-γ (μ)]-[μ-y (μ)] }
μ T, wherein χ
f(μ-d (μ)) ∈ R
nfor vector matrix system is described as
Step 4: ask nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction node matrix equation
Front ω (μ)=[x
μ T(μ) ζ
μ T(μ) f
μ T(μ)]
μ Tindividual eigenvalue of maximum characteristic of correspondence vector expression is described as
Step 5: by J
μcos (γ
e)
∞row vector normalized, obtain matrix cosJ
th-μ, wherein
Step 6: by matrix cosJ
th-μevery a line regard R as
ka nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction node in space, and use χ (μ-(μ)
μ) ∈ R
mmean algorithm is polymerized to L
μclass, if cosJ
th-μthe capable j class that belongs to of i, the y in nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction set of node Y
ialso be divided into j class, thus the x in nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction set of node X
ijust be divided into j class; (1) for optimized network structure Control System with Delay (4) wherein by inference, if there is positive definite symmetric matrices P, and Q, R and Arbitrary Matrix A, B, C meets following MATRIX INEQUALITIES and is
,
Wherein ω (μ)
∞=0 o'clock, under the progressive stable and zero initial condition of optimized network structure Control System with Delay (4), meet
2. the failure prediction method based under intelligent power distribution environment according to claim 1, it is characterized in that, step 1 is the preprocessing process of nonsingular cloud terminal network structure Control System with Delay networking failure prediction, all numerical value nonsingular cloud terminal network structure Control System with Delay networking failure prediction in nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction set of node X is transformed to based on nonsingular cloud terminal network structure Control System with Delay networking failure prediction, realize normalization and the networking of structure Control System with Delay of nonsingular cloud terminal network structure Control System with Delay networking failure prediction, step 2~6th, the process of the electric structure sensor model algorithm process of density sensitivity based on nonsingular cloud terminal network structure Control System with Delay networking failure prediction, wherein, step 2 is weighed based on distance between nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction node by average weighted hamming distance, builds on this basis the similarity measurement of density sensitivity, step 4 is by solving eigenwert and the proper vector of nonsingular cloud terminal network structure Control System with Delay networking fault perceptual signal prediction node matrix equation, structural attitude vector space, thus realize the spectrum mapping of former nonsingular cloud terminal network structure Control System with Delay networking failure prediction space to low-dimensional linear measurement space, in the low-dimensional linear measurement space of step 6 after mapping, adopt traditional χ (μ-(μ)
μ) ∈ R
mmean algorithm cloud theoretical model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410219899.6A CN103995530A (en) | 2014-05-23 | 2014-05-23 | Fault detection method based on intelligent power distribution environment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410219899.6A CN103995530A (en) | 2014-05-23 | 2014-05-23 | Fault detection method based on intelligent power distribution environment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103995530A true CN103995530A (en) | 2014-08-20 |
Family
ID=51309722
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410219899.6A Pending CN103995530A (en) | 2014-05-23 | 2014-05-23 | Fault detection method based on intelligent power distribution environment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103995530A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109459659A (en) * | 2018-11-14 | 2019-03-12 | 国网黑龙江省电力有限公司信息通信公司 | It is a kind of for predicting the system and method for electric power system fault |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1115060A (en) * | 1995-04-12 | 1996-01-17 | 中国人民解放军总参谋部第六十一研究所 | Membership cloud.. generation method, membership cloud generator and Membership cloud control device |
US20110239214A1 (en) * | 2010-03-29 | 2011-09-29 | Frields Paul W | Mechanism for Utilizing a Virtual Machine Cloud for Automated Test System Deployment |
US20130080728A1 (en) * | 2011-09-28 | 2013-03-28 | International Business Machines Corporation | Automated selection of functions to reduce storage capacity based on performance requirements |
CN103020440A (en) * | 2012-12-04 | 2013-04-03 | 河南省电力公司 | Optimization method for simulating growth of plant based on cloud theory |
CN103390931A (en) * | 2012-05-08 | 2013-11-13 | 苏州工业园区讯贝智能系统有限公司 | Power distribution system and device with cloud terminal function |
CN103810533A (en) * | 2013-08-15 | 2014-05-21 | 国家电网公司 | Cloud-model-based power distribution network fault risk identification method |
-
2014
- 2014-05-23 CN CN201410219899.6A patent/CN103995530A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1115060A (en) * | 1995-04-12 | 1996-01-17 | 中国人民解放军总参谋部第六十一研究所 | Membership cloud.. generation method, membership cloud generator and Membership cloud control device |
US20110239214A1 (en) * | 2010-03-29 | 2011-09-29 | Frields Paul W | Mechanism for Utilizing a Virtual Machine Cloud for Automated Test System Deployment |
US20130080728A1 (en) * | 2011-09-28 | 2013-03-28 | International Business Machines Corporation | Automated selection of functions to reduce storage capacity based on performance requirements |
CN103390931A (en) * | 2012-05-08 | 2013-11-13 | 苏州工业园区讯贝智能系统有限公司 | Power distribution system and device with cloud terminal function |
CN103020440A (en) * | 2012-12-04 | 2013-04-03 | 河南省电力公司 | Optimization method for simulating growth of plant based on cloud theory |
CN103810533A (en) * | 2013-08-15 | 2014-05-21 | 国家电网公司 | Cloud-model-based power distribution network fault risk identification method |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109459659A (en) * | 2018-11-14 | 2019-03-12 | 国网黑龙江省电力有限公司信息通信公司 | It is a kind of for predicting the system and method for electric power system fault |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107846014B (en) | Power grid probability vulnerability assessment method based on random features and series calculation | |
US11757723B2 (en) | Distributed secure state reconstruction method based on double-layer dynamic switching observer | |
CN108319147B (en) | H-infinity fault-tolerant control method of networked linear parameter change system with short time delay and data packet loss | |
WO2021164118A1 (en) | Ac/dc bulk power grid dynamic security risk situation rolling prospective early warning method and system | |
CN108427288B (en) | H-infinity fault-tolerant control method of networked linear parameter change system with time-varying delay | |
CN112305918A (en) | Multi-agent system sliding mode fault-tolerant consistency control algorithm under supercoiled observer | |
CN112862065B (en) | Power grid branch parameter identification method based on multitask graph neural network | |
CN103729553A (en) | Classification control method for urban safety complex events on basis of Bayesian network learning | |
CN103366315A (en) | Distribution network operating safety assessment method based on distribution network fault lost load recovery values | |
CN104749958A (en) | Model-depended average dwell time asynchronous fuzzy control method of nonlinear switching system | |
Duan et al. | Finite-time distributed H∞ filtering for Takagi-Sugeno fuzzy system with uncertain probability sensor saturation under switching network topology: Non-PDC approach | |
CN113325708B (en) | Fault estimation method of multi-unmanned aerial vehicle system based on heterogeneous multi-agent | |
CN106055789B (en) | Autonomous unmanned aerial vehicle formalized inference method based on weighted fuzzy Petri net | |
CN103995530A (en) | Fault detection method based on intelligent power distribution environment | |
CN103559538A (en) | BP neural network structure optimizing method | |
CN117172413A (en) | Power grid equipment operation state monitoring method based on multi-mode data joint characterization and dynamic weight learning | |
Wei et al. | Intrusive detection systems design based on BP neural network | |
CN113110321B (en) | Distributed estimation method of networked industrial control system based on event trigger | |
CN113486480A (en) | Leakage fault filtering method for urban water supply pipe network system | |
Xing et al. | Event-triggered control for stochastic singular systems with state delay | |
CN105186503A (en) | Distributed safety characteristic selection method based on power grid operation data | |
Wang et al. | Sliding mode control of Markovian jump system via an event-triggered mechanism | |
Xiao et al. | Systematic Combat Effectiveness Evaluation Model Based on Xgboost | |
Yu et al. | Linear Programming-Based Consensus of TS Fuzzy Positive Multi-Agent Systems | |
Han et al. | Effectiveness Evaluation of Communication Network based on BP neural network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140820 |