CN106404055A - Power transmission network tower monitoring system - Google Patents
Power transmission network tower monitoring system Download PDFInfo
- Publication number
- CN106404055A CN106404055A CN201610761746.3A CN201610761746A CN106404055A CN 106404055 A CN106404055 A CN 106404055A CN 201610761746 A CN201610761746 A CN 201610761746A CN 106404055 A CN106404055 A CN 106404055A
- Authority
- CN
- China
- Prior art keywords
- module
- sensor
- power transmission
- cloud
- transmission 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention provides a power transmission network tower monitoring system. The system comprises a cloud calculation monitoring platform, a client, cloud terminal access equipment and a field monitoring device, wherein the field monitoring device comprises a sensor fault diagnosis device, the sensor fault diagnosis device comprises a signal acquisition filtering module, a fault characteristic extraction module, an online characteristic extraction module, a characteristic vector optimization module, a fault classification identification module, a fault kind update module and a health record module, the field monitoring device is connected with the cloud calculation monitoring platform through the cloud terminal access equipment, the client is connected with the cloud calculation monitoring platform, and the cloud calculation monitoring platform comprises a power transmission network information database, a cloud application server and a line inspection server. The system is advantaged in that on the basis of the cloud calculation monitoring platform, rapid establishment of the monitoring system is realized, monitoring efficiency of a power transmission network tower is improved, and manpower investment is reduced.
Description
Technical field
The present invention relates to power domain is and in particular to a kind of monitoring system of power transmission network tower bar.
Background technology
At present, the operation conditions always electric power enterprise how effectively monitoring field transmission line of electricity focuses on asking of consideration
Topic.Super-pressure, UHV transmission line operate in wilderness field mostly, and with a varied topography, coverage rate is wide, in the portion of power tense
Region-by-region, line density is very big, and parallel cabling is a lot, and scissors crossing is complicated, brings very big being stranded to the maintenance of making an inspection tour of circuit
Difficult.Due to a varied topography, dangerous it is also possible to there is malicious honeybee, poisonous snake, wild beast, traps etc., along with trackman is unfamiliar with line
Road, easily gets lost and is strayed into non-tour trail, not only increased working time and the labour intensity of trackman, goes back the entail dangers to person
Safety.
Extra high voltage network equipment is complicated, producer and model are numerous, and artificial memory cannot meet the need of work on the spot
Will be it is therefore desirable to carry with some circuit data, in case inquiring about during making an inspection tour, because circuit data complexity is various, paper
Matter data is easily damaged, loses, and carries with very inconvenient.Workman carries out out patrolling and examining and also needs to during work carry a large amount of works
Make apparatus, such as mobile phone, camera, GPS locator, intercom etc., instrument is many, troublesome poeration, burden also weighs.Domestic at present general
All over the working method using manual patrol hand-made paper medium recording, this mode has that human factor is many, efficiency is low, manages into
This height.
Content of the invention
For solving the above problems, the present invention provides a kind of monitoring system of power transmission network tower bar.
The purpose of the present invention employs the following technical solutions to realize:
A kind of monitoring system of power transmission network tower bar, including cloud computing monitor supervision platform, client, cloud terminal access device and existing
Field monitoring device, described local supervising and measuring equipment includes sensor malfunction diagnostic device, and described sensor malfunction diagnostic device includes
Signals collecting filtration module, fault signature extraction module, online characteristic extracting module, characteristic vector preferred module, failure modes
Identification module, failure mode update module and health records module, described local supervising and measuring equipment pass through cloud terminal access device with
Described cloud computing monitor supervision platform connects, and described client is connected with described cloud computing monitor supervision platform, described cloud computing monitor supervision platform
Including power transmission network information database, cloud application server and line data-logging server.
Beneficial effects of the present invention are:Achieve the fast construction of monitoring system, improve the monitoring effect of power transmission network tower bar
Rate, reduces human input.
Brief description
Using accompanying drawing, the invention will be further described, but the embodiment in accompanying drawing does not constitute any limit to the present invention
System, for those of ordinary skill in the art, on the premise of not paying creative work, can also obtain according to the following drawings
Other accompanying drawings.
Fig. 1 is present configuration schematic diagram;
Fig. 2 is the schematic diagram of inventive sensor trouble-shooter.
Reference:
Signals collecting filtration module 1, fault signature extraction module 2, online characteristic extracting module 3, the preferred mould of characteristic vector
Block 4, failure modes identification module 5, failure mode update module 6, health records module 7.
Specific embodiment
The invention will be further described with the following Examples.
Application scenarios 1
Referring to Fig. 1, Fig. 2, a kind of monitoring system of power transmission network tower bar of an embodiment of this application scene, including cloud meter
Calculate monitor supervision platform, client, cloud terminal access device and local supervising and measuring equipment, described local supervising and measuring equipment includes sensor fault
Diagnostic device, described sensor malfunction diagnostic device includes signals collecting filtration module 1, fault signature extraction module 2, online spy
Levy extraction module 3, characteristic vector preferred module 4, failure modes identification module 5, failure mode update module 6 and health records mould
Block 7, described local supervising and measuring equipment is connected with described cloud computing monitor supervision platform by cloud terminal access device, described client and institute
State cloud computing monitor supervision platform to connect, described cloud computing monitor supervision platform includes power transmission network information database, cloud application server and line
Road patrol checking server.
The above embodiment of the present invention achieves the fast construction of monitoring system, improves the monitoring efficiency of power transmission network tower bar,
Reduce human input;Setting sensor malfunction diagnostic device, thus ensure the information gathering of local supervising and measuring equipment.
Preferably, described biography sensor group includes circuit humidity sensor, video monitor, circuit air velocity transducer, line
Road icing sensor and vibrating sensor.
This preferred embodiment is easy to power transmission network shaft tower be monitored comprehensively.
Preferably, described signals collecting filtration module 1 is used for gathering historical sensor signal and on-line sensor test letter
Number, and signal is filtered process using combination form wave filter.
This preferred embodiment arranges combination form wave filter, can effectively remove the various noise jamming of signal, preferably
The primitive character information of stick signal.
Preferably, described fault signature extraction module 2 is used for carrying out integrated experience to filtered historical sensor signal
Mode decomposition (EEMD) is processed, and extracts the Energy-Entropy of integrated empirical mode decomposition (EEMD) as training feature vector, including:
(1) the historical sensor signal of collection is divided into the fault-signal of nominal situation signal and plurality of classes;
(2) described historical sensor signal is carried out with integrated empirical mode decomposition (EEMD) process, obtain described history and pass
The intrinsic mode function of sensor signal and remainder function;
(3) intrinsic mode function of described historical sensor signal and the Energy-Entropy of remainder function are calculated;
(4) Energy-Entropy of historical sensor signal is normalized, extracts the Energy-Entropy after normalization as instruction
Practice characteristic vector;
Described online characteristic extracting module 3 is used for carrying out integrated empirical modal to filtered on-line sensor test signal
Decompose (EEMD) to process, and extract the Energy-Entropy of integrated empirical mode decomposition (EEMD) as characteristic vector to be measured, including:
(1) described on-line sensor test signal is carried out with EEMD process, obtains described on-line sensor test signal
Intrinsic mode function and remainder function;
(2) intrinsic mode function of described on-line sensor test signal and the Energy-Entropy of remainder function are calculated;
(3) Energy-Entropy of on-line sensor test signal is normalized, extracts the Energy-Entropy after normalization and make
For characteristic vector to be measured.
This preferred embodiment carries out integrated empirical mode decomposition (EEMD) to the sensor signal of collection and processes, can be effective
Elimination modal overlap phenomenon, the effect of decomposition is preferable.
Preferably, described characteristic vector preferred module 4 respectively training feature vector and characteristic vector to be measured are carried out similar
Property tolerance, the high characteristic vector of similarity is rejected, including:
(1) two vector similarities function S (X, Y) are defined:
In formula, X, Y represent two characteristic vectors respectively, and cov (X, Y) is the covariance of X and Y,For X,
Y standard deviation;
For any two training feature vector X1、X2, and any two characteristic vector D to be measured1、D2, it is respectively adopted similar
Degree its similarity of function pair is measured, and obtains S (X1,X2) and S (D1,D2);
(2) for S (X1,X2) and S (D1,D2), if S is (X1,X2)>T1, T1∈ (0.9,1), only chooses X1As training characteristics
Vector, if S is (D1,D2)>T2, T2∈ (0.95,1), only chooses D1As characteristic vector to be measured.
This preferred embodiment screens characteristic vector by measuring similarity, can reduce amount of calculation, improves efficiency.
Preferably, the least square method supporting vector machine that described failure modes identification module 5 is used for using optimizing is treated to described
Survey characteristic vector and carry out failure modes identification, select to optimize submodule, training submodule and identification submodule including parameter, specifically
For:
Described parameter selects to optimize the kernel function for constructing least square method supporting vector machine for the submodule, and to least square
The structural parameters of SVMs are worked in coordination with Chaos particle swarm optimization algorithm using multi-population and are optimized;
Described training submodule, for many classification side of the least square support vector machines using improved optimum binary tree structure
Method, is instructed to the least square method supporting vector machine after structure parameter optimizing using the training feature vector obtaining as training sample
Practice, and build sensor fault diagnosis model;
Described identification submodule is used for, using described sensor fault diagnosis model, described characteristic vector to be measured is carried out with event
Barrier Classification and Identification;
Wherein it is considered to the superiority of Polynomial kernel function and RBF kernel function, the core letter of described least square method supporting vector machine
Number is configured to:
K=(1- δ) (xxi+1)p+δexp(-‖x-xi‖2/σ2)
In formula, δ is the structure adjusting factor, and the span of δ is set as [0.45,0.55], and p is the rank of Polynomial kernel function
Number, σ2For RBF kernel functional parameter.
Wherein, shown using multi-population work in coordination with Chaos particle swarm optimization algorithm be optimized, including:
(1) initialize to main population with from population respectively, randomly generate one group of parameter initial as particle
Position and initial velocity, defining fitness function is:
In formula, N is training sample total number, and W is bug classification number, and T correctly classifies number for fault, qiIt is certainly
The weight coefficient setting, qiSpan be set as [0.4,0.5];
(2) carry out the renewal from population, in every generation renewal process, according to fitness function, from population difference
The speed of more new particle and position, then will be experienced in its history adaptive optimal control angle value and main population body to each particle
The fitness value of desired positions compares, if more preferably, as current global optimum position;
(3) optimum particle position in chaos optimization, and iteration current sequence and speed are carried out to described global optimum position
Degree, generates optimal particle sequence;
(4) choose optimum particle from population in the main population of every generation, and the position of more new particle and speed,
Until reaching maximum iteration time or the error requirements meeting fitness function.
Wherein, many sorting techniques of the least square support vector machines of described improved optimum binary tree structure specifically include:
(1) calculate the standard variance of all training samples and two classifications j,Between Separatory measure;
(2) output minimum separation estimate corresponding j,
(3) after the structural parameters to least square method supporting vector machine are optimized, the least square setting up two classification props up
Hold vector machine in order to train jth class andThe training sample of class, forms optimum two classification least square method supporting vector machines, output
The parameter of discriminant function,The training sample of class is merged in j class, constitutes new j class training sample;
(4) all of classification is circulated training according to (1)-(3), until the optimum root node of output;
(5) form the categorised decision tree of least square method supporting vector machine according to above output result, then to remaining instruction
Practice sample and carry out classifying quality test.
This preferred embodiment in order to improve the precision of fault diagnosis, using training speed is fast, generalization ability strong and robustness
Preferably least square support vector machines are as grader, and propose the many sorting techniques improving optimum binary tree structure, between class
Separatory measure substitutes weights, the nicety of grading that improve and the classification speed in binary tree structure;In view of RBF kernel function it is
Local kernel function, Polynomial kernel function is overall kernel function, and karyomerite function learning ability is strong, and Generalization Capability is relatively weak, and
Overall kernel function Generalization Capability is strong, and learning ability is relatively weak, carries out on the basis of the advantage of summary two class kernel function
The Kernel of least square method supporting vector machine, optimizes classification performance and the Generalization Capability of least square method supporting vector machine;
The multi-population of design works in coordination with Chaos particle swarm optimization algorithm, has preferable convergence rate, and has preferable global and local
Optimizing performance, can timely jump out Local Extremum, find the optimal value of the overall situation, thus working in coordination with chaotic particle using multi-population
Colony optimization algorithm is optimized to the structural parameters of least square method supporting vector machine, and effect of optimization is good.
Preferably, described failure mode update module 6 is used for training set is updated, and continues to optimize sensor fault and examines
Disconnected model, including:
(1) when sensor fault diagnosis model cannot carry out effective failure modes to characteristic vector to be measured, by feature to be measured
Vector is as new training feature vector;
(2) new training feature vector is updated to training sample, and the least square after structure parameter optimizing is supported
Vector machine is trained, and constructs new sensor fault diagnosis model;
(3) failure modes identification is carried out to described characteristic vector to be measured using new sensor fault diagnosis model, complete
Failure mode updates.
This preferred embodiment arranges failure mode update module 6, to improve adaptability and the range of application of model.
Preferably, described health records module 7 includes sub-module stored and secure access submodule, described sub-module stored
Using the storage model based on cloud storage, specifically, it is encrypted after fault message is compressed, is uploaded to cloud storage,
Described secure access submodule is used for information is conducted interviews, and specifically, corresponding to sub-module stored, downloads data to this
Ground, after being unlocked using corresponding secret key, then is decompressed to read information.
This preferred embodiment arranges health records module 7, on the one hand ensure that information security, on the other hand can be right at any time
Fault conducts interviews, and is easy to search problem.
In this application scenarios, given threshold T1Value be 0.96, the monitoring of system sensor trouble-shooter speed
Degree improves 10% relatively, and system monitoring precision improves 12% relatively.
Application scenarios 2
Referring to Fig. 1, Fig. 2, a kind of monitoring system of power transmission network tower bar of an embodiment of this application scene, including cloud meter
Calculate monitor supervision platform, client, cloud terminal access device and local supervising and measuring equipment, described local supervising and measuring equipment includes sensor fault
Diagnostic device, described sensor malfunction diagnostic device includes signals collecting filtration module 1, fault signature extraction module 2, online spy
Levy extraction module 3, characteristic vector preferred module 4, failure modes identification module 5, failure mode update module 6 and health records mould
Block 7, described local supervising and measuring equipment is connected with described cloud computing monitor supervision platform by cloud terminal access device, described client and institute
State cloud computing monitor supervision platform to connect, described cloud computing monitor supervision platform includes power transmission network information database, cloud application server and line
Road patrol checking server.
The above embodiment of the present invention achieves the fast construction of monitoring system, improves the monitoring efficiency of power transmission network tower bar,
Reduce human input;Setting sensor malfunction diagnostic device, thus ensure the information gathering of local supervising and measuring equipment.
Preferably, described biography sensor group includes circuit humidity sensor, video monitor, circuit air velocity transducer, line
Road icing sensor and vibrating sensor.
This preferred embodiment is easy to power transmission network shaft tower be monitored comprehensively.
Preferably, described signals collecting filtration module 1 is used for gathering historical sensor signal and on-line sensor test letter
Number, and signal is filtered process using combination form wave filter.
This preferred embodiment arranges combination form wave filter, can effectively remove the various noise jamming of signal, preferably
The primitive character information of stick signal.
Preferably, described fault signature extraction module 2 is used for carrying out integrated experience to filtered historical sensor signal
Mode decomposition (EEMD) is processed, and extracts the Energy-Entropy of integrated empirical mode decomposition (EEMD) as training feature vector, including:
(1) the historical sensor signal of collection is divided into the fault-signal of nominal situation signal and plurality of classes;
(2) described historical sensor signal is carried out with integrated empirical mode decomposition (EEMD) process, obtain described history and pass
The intrinsic mode function of sensor signal and remainder function;
(3) intrinsic mode function of described historical sensor signal and the Energy-Entropy of remainder function are calculated;
(4) Energy-Entropy of historical sensor signal is normalized, extracts the Energy-Entropy after normalization as instruction
Practice characteristic vector;
Described online characteristic extracting module 3 is used for carrying out integrated empirical modal to filtered on-line sensor test signal
Decompose (EEMD) to process, and extract the Energy-Entropy of integrated empirical mode decomposition (EEMD) as characteristic vector to be measured, including:
(1) described on-line sensor test signal is carried out with EEMD process, obtains described on-line sensor test signal
Intrinsic mode function and remainder function;
(2) intrinsic mode function of described on-line sensor test signal and the Energy-Entropy of remainder function are calculated;
(3) Energy-Entropy of on-line sensor test signal is normalized, extracts the Energy-Entropy after normalization and make
For characteristic vector to be measured.
This preferred embodiment carries out integrated empirical mode decomposition (EEMD) to the sensor signal of collection and processes, can be effective
Elimination modal overlap phenomenon, the effect of decomposition is preferable.
Preferably, described characteristic vector preferred module 4 respectively training feature vector and characteristic vector to be measured are carried out similar
Property tolerance, the high characteristic vector of similarity is rejected, including:
(1) two vector similarities function S (X, Y) are defined:
In formula, X, Y represent two characteristic vectors respectively, and cov (X, Y) is the covariance of X and Y,For X,
Y standard deviation;
For any two training feature vector X1、X2, and any two characteristic vector D to be measured1、D2, it is respectively adopted similar
Degree its similarity of function pair is measured, and obtains S (X1,X2) and S (D1,D2);
(2) for S (X1,X2) and S (D1,D2), if S is (X1,X2)>T1, T1∈ (0.9,1), only chooses X1As training characteristics
Vector, if S is (D1,D2)>T2, T2∈ (0.95,1), only chooses D1As characteristic vector to be measured.
This preferred embodiment screens characteristic vector by measuring similarity, can reduce amount of calculation, improves efficiency.
Preferably, the least square method supporting vector machine that described failure modes identification module 5 is used for using optimizing is treated to described
Survey characteristic vector and carry out failure modes identification, select to optimize submodule, training submodule and identification submodule including parameter, specifically
For:
Described parameter selects to optimize the kernel function for constructing least square method supporting vector machine for the submodule, and to least square
The structural parameters of SVMs are worked in coordination with Chaos particle swarm optimization algorithm using multi-population and are optimized;
Described training submodule, for many classification side of the least square support vector machines using improved optimum binary tree structure
Method, is instructed to the least square method supporting vector machine after structure parameter optimizing using the training feature vector obtaining as training sample
Practice, and build sensor fault diagnosis model;
Described identification submodule is used for, using described sensor fault diagnosis model, described characteristic vector to be measured is carried out with event
Barrier Classification and Identification;
Wherein it is considered to the superiority of Polynomial kernel function and RBF kernel function, the core letter of described least square method supporting vector machine
Number is configured to:
K=(1- δ) (xxi+1)p+δexp(-‖x-xi‖2/σ2)
In formula, δ is the structure adjusting factor, and the span of δ is set as [0.45,0.55], and p is the rank of Polynomial kernel function
Number, σ2For RBF kernel functional parameter.
Wherein, shown using multi-population work in coordination with Chaos particle swarm optimization algorithm be optimized, including:
(1) initialize to main population with from population respectively, randomly generate one group of parameter initial as particle
Position and initial velocity, defining fitness function is:
In formula, N is training sample total number, and W is bug classification number, and T correctly classifies number for fault, qiIt is certainly
The weight coefficient setting, qiSpan be set as [0.4,0.5];
(2) carry out the renewal from population, in every generation renewal process, according to fitness function, from population difference
The speed of more new particle and position, then will be experienced in its history adaptive optimal control angle value and main population body to each particle
The fitness value of desired positions compares, if more preferably, as current global optimum position;
(3) optimum particle position in chaos optimization, and iteration current sequence and speed are carried out to described global optimum position
Degree, generates optimal particle sequence;
(4) choose optimum particle from population in the main population of every generation, and the position of more new particle and speed,
Until reaching maximum iteration time or the error requirements meeting fitness function.
Wherein, many sorting techniques of the least square support vector machines of described improved optimum binary tree structure specifically include:
(1) calculate the standard variance of all training samples and two classifications j,Between Separatory measure;
(2) output minimum separation estimate corresponding j,
(3) after the structural parameters to least square method supporting vector machine are optimized, the least square setting up two classification props up
Hold vector machine in order to train jth class andThe training sample of class, forms optimum two classification least square method supporting vector machines, output
The parameter of discriminant function,The training sample of class is merged in j class, constitutes new j class training sample;
(4) all of classification is circulated training according to (1)-(3), until the optimum root node of output;
(5) form the categorised decision tree of least square method supporting vector machine according to above output result, then to remaining instruction
Practice sample and carry out classifying quality test.
This preferred embodiment in order to improve the precision of fault diagnosis, using training speed is fast, generalization ability strong and robustness
Preferably least square support vector machines are as grader, and propose the many sorting techniques improving optimum binary tree structure, between class
Separatory measure substitutes weights, the nicety of grading that improve and the classification speed in binary tree structure;In view of RBF kernel function it is
Local kernel function, Polynomial kernel function is overall kernel function, and karyomerite function learning ability is strong, and Generalization Capability is relatively weak, and
Overall kernel function Generalization Capability is strong, and learning ability is relatively weak, carries out on the basis of the advantage of summary two class kernel function
The Kernel of least square method supporting vector machine, optimizes classification performance and the Generalization Capability of least square method supporting vector machine;
The multi-population of design works in coordination with Chaos particle swarm optimization algorithm, has preferable convergence rate, and has preferable global and local
Optimizing performance, can timely jump out Local Extremum, find the optimal value of the overall situation, thus working in coordination with chaotic particle using multi-population
Colony optimization algorithm is optimized to the structural parameters of least square method supporting vector machine, and effect of optimization is good.
Preferably, described failure mode update module 6 is used for training set is updated, and continues to optimize sensor fault and examines
Disconnected model, including:
(1) when sensor fault diagnosis model cannot carry out effective failure modes to characteristic vector to be measured, by feature to be measured
Vector is as new training feature vector;
(2) new training feature vector is updated to training sample, and the least square after structure parameter optimizing is supported
Vector machine is trained, and constructs new sensor fault diagnosis model;
(3) failure modes identification is carried out to described characteristic vector to be measured using new sensor fault diagnosis model, complete
Failure mode updates.
This preferred embodiment arranges failure mode update module 6, to improve adaptability and the range of application of model.
Preferably, described health records module 7 includes sub-module stored and secure access submodule, described sub-module stored
Using the storage model based on cloud storage, specifically, it is encrypted after fault message is compressed, is uploaded to cloud storage,
Described secure access submodule is used for information is conducted interviews, and specifically, corresponding to sub-module stored, downloads data to this
Ground, after being unlocked using corresponding secret key, then is decompressed to read information.
This preferred embodiment arranges health records module 7, on the one hand ensure that information security, on the other hand can be right at any time
Fault conducts interviews, and is easy to search problem.
In this application scenarios, given threshold T1Value be 0.95, the monitoring velocity phase of sensor malfunction diagnostic device
To improve 11%, monitoring accuracy improves 11% relatively.
Application scenarios 3
Referring to Fig. 1, Fig. 2, a kind of monitoring system of power transmission network tower bar of an embodiment of this application scene, including cloud meter
Calculate monitor supervision platform, client, cloud terminal access device and local supervising and measuring equipment, described local supervising and measuring equipment includes sensor fault
Diagnostic device, described sensor malfunction diagnostic device includes signals collecting filtration module 1, fault signature extraction module 2, online spy
Levy extraction module 3, characteristic vector preferred module 4, failure modes identification module 5, failure mode update module 6 and health records mould
Block 7, described local supervising and measuring equipment is connected with described cloud computing monitor supervision platform by cloud terminal access device, described client and institute
State cloud computing monitor supervision platform to connect, described cloud computing monitor supervision platform includes power transmission network information database, cloud application server and line
Road patrol checking server.
The above embodiment of the present invention achieves the fast construction of monitoring system, improves the monitoring efficiency of power transmission network tower bar,
Reduce human input;Setting sensor malfunction diagnostic device, thus ensure the information gathering of local supervising and measuring equipment.
Preferably, described biography sensor group includes circuit humidity sensor, video monitor, circuit air velocity transducer, line
Road icing sensor and vibrating sensor.
This preferred embodiment is easy to power transmission network shaft tower be monitored comprehensively.
Preferably, described signals collecting filtration module 1 is used for gathering historical sensor signal and on-line sensor test letter
Number, and signal is filtered process using combination form wave filter.
This preferred embodiment arranges combination form wave filter, can effectively remove the various noise jamming of signal, preferably
The primitive character information of stick signal.
Preferably, described fault signature extraction module 2 is used for carrying out integrated experience to filtered historical sensor signal
Mode decomposition (EEMD) is processed, and extracts the Energy-Entropy of integrated empirical mode decomposition (EEMD) as training feature vector, including:
(1) the historical sensor signal of collection is divided into the fault-signal of nominal situation signal and plurality of classes;
(2) described historical sensor signal is carried out with integrated empirical mode decomposition (EEMD) process, obtain described history and pass
The intrinsic mode function of sensor signal and remainder function;
(3) intrinsic mode function of described historical sensor signal and the Energy-Entropy of remainder function are calculated;
(4) Energy-Entropy of historical sensor signal is normalized, extracts the Energy-Entropy after normalization as instruction
Practice characteristic vector;
Described online characteristic extracting module 3 is used for carrying out integrated empirical modal to filtered on-line sensor test signal
Decompose (EEMD) to process, and extract the Energy-Entropy of integrated empirical mode decomposition (EEMD) as characteristic vector to be measured, including:
(1) described on-line sensor test signal is carried out with EEMD process, obtains described on-line sensor test signal
Intrinsic mode function and remainder function;
(2) intrinsic mode function of described on-line sensor test signal and the Energy-Entropy of remainder function are calculated;
(3) Energy-Entropy of on-line sensor test signal is normalized, extracts the Energy-Entropy after normalization and make
For characteristic vector to be measured.
This preferred embodiment carries out integrated empirical mode decomposition (EEMD) to the sensor signal of collection and processes, can be effective
Elimination modal overlap phenomenon, the effect of decomposition is preferable.
Preferably, described characteristic vector preferred module 4 respectively training feature vector and characteristic vector to be measured are carried out similar
Property tolerance, the high characteristic vector of similarity is rejected, including:
(1) two vector similarities function S (X, Y) are defined:
In formula, X, Y represent two characteristic vectors respectively, and cov (X, Y) is the covariance of X and Y,For X,
Y standard deviation;
For any two training feature vector X1、X2, and any two characteristic vector D to be measured1、D2, it is respectively adopted similar
Degree its similarity of function pair is measured, and obtains S (X1,X2) and S (D1,D2);
(2) for S (X1,X2) and S (D1,D2), if S is (X1,X2)>T1, T1∈ (0.9,1), only chooses X1As training characteristics
Vector, if S is (D1,D2)>T2, T2∈ (0.95,1), only chooses D1As characteristic vector to be measured.
This preferred embodiment screens characteristic vector by measuring similarity, can reduce amount of calculation, improves efficiency.
Preferably, the least square method supporting vector machine that described failure modes identification module 5 is used for using optimizing is treated to described
Survey characteristic vector and carry out failure modes identification, select to optimize submodule, training submodule and identification submodule including parameter, specifically
For:
Described parameter selects to optimize the kernel function for constructing least square method supporting vector machine for the submodule, and to least square
The structural parameters of SVMs are worked in coordination with Chaos particle swarm optimization algorithm using multi-population and are optimized;
Described training submodule, for many classification side of the least square support vector machines using improved optimum binary tree structure
Method, is instructed to the least square method supporting vector machine after structure parameter optimizing using the training feature vector obtaining as training sample
Practice, and build sensor fault diagnosis model;
Described identification submodule is used for, using described sensor fault diagnosis model, described characteristic vector to be measured is carried out with event
Barrier Classification and Identification;
Wherein it is considered to the superiority of Polynomial kernel function and RBF kernel function, the core letter of described least square method supporting vector machine
Number is configured to:
K=(1- δ) (xxi+1)p+δexp(-‖x-xi‖2/σ2)
In formula, δ is the structure adjusting factor, and the span of δ is set as [0.45,0.55], and p is the rank of Polynomial kernel function
Number, σ2For RBF kernel functional parameter.
Wherein, shown using multi-population work in coordination with Chaos particle swarm optimization algorithm be optimized, including:
(1) initialize to main population with from population respectively, randomly generate one group of parameter initial as particle
Position and initial velocity, defining fitness function is:
In formula, N is training sample total number, and W is bug classification number, and T correctly classifies number for fault, qiIt is certainly
The weight coefficient setting, qiSpan be set as [0.4,0.5];
(2) carry out the renewal from population, in every generation renewal process, according to fitness function, from population difference
The speed of more new particle and position, then will be experienced in its history adaptive optimal control angle value and main population body to each particle
The fitness value of desired positions compares, if more preferably, as current global optimum position;
(3) optimum particle position in chaos optimization, and iteration current sequence and speed are carried out to described global optimum position
Degree, generates optimal particle sequence;
(4) choose optimum particle from population in the main population of every generation, and the position of more new particle and speed,
Until reaching maximum iteration time or the error requirements meeting fitness function.
Wherein, many sorting techniques of the least square support vector machines of described improved optimum binary tree structure specifically include:
(1) calculate the standard variance of all training samples and two classifications j,Between Separatory measure;
(2) output minimum separation estimate corresponding j,
(3) after the structural parameters to least square method supporting vector machine are optimized, the least square setting up two classification props up
Hold vector machine in order to train jth class andThe training sample of class, forms optimum two classification least square method supporting vector machines, output
The parameter of discriminant function,The training sample of class is merged in j class, constitutes new j class training sample;
(4) all of classification is circulated training according to (1)-(3), until the optimum root node of output;
(5) form the categorised decision tree of least square method supporting vector machine according to above output result, then to remaining instruction
Practice sample and carry out classifying quality test.
This preferred embodiment in order to improve the precision of fault diagnosis, using training speed is fast, generalization ability strong and robustness
Preferably least square support vector machines are as grader, and propose the many sorting techniques improving optimum binary tree structure, between class
Separatory measure substitutes weights, the nicety of grading that improve and the classification speed in binary tree structure;In view of RBF kernel function it is
Local kernel function, Polynomial kernel function is overall kernel function, and karyomerite function learning ability is strong, and Generalization Capability is relatively weak, and
Overall kernel function Generalization Capability is strong, and learning ability is relatively weak, carries out on the basis of the advantage of summary two class kernel function
The Kernel of least square method supporting vector machine, optimizes classification performance and the Generalization Capability of least square method supporting vector machine;
The multi-population of design works in coordination with Chaos particle swarm optimization algorithm, has preferable convergence rate, and has preferable global and local
Optimizing performance, can timely jump out Local Extremum, find the optimal value of the overall situation, thus working in coordination with chaotic particle using multi-population
Colony optimization algorithm is optimized to the structural parameters of least square method supporting vector machine, and effect of optimization is good.
Preferably, described failure mode update module 6 is used for training set is updated, and continues to optimize sensor fault and examines
Disconnected model, including:
(1) when sensor fault diagnosis model cannot carry out effective failure modes to characteristic vector to be measured, by feature to be measured
Vector is as new training feature vector;
(2) new training feature vector is updated to training sample, and the least square after structure parameter optimizing is supported
Vector machine is trained, and constructs new sensor fault diagnosis model;
(3) failure modes identification is carried out to described characteristic vector to be measured using new sensor fault diagnosis model, complete
Failure mode updates.
This preferred embodiment arranges failure mode update module 6, to improve adaptability and the range of application of model.
Preferably, described health records module 7 includes sub-module stored and secure access submodule, described sub-module stored
Using the storage model based on cloud storage, specifically, it is encrypted after fault message is compressed, is uploaded to cloud storage,
Described secure access submodule is used for information is conducted interviews, and specifically, corresponding to sub-module stored, downloads data to this
Ground, after being unlocked using corresponding secret key, then is decompressed to read information.
This preferred embodiment arranges health records module 7, on the one hand ensure that information security, on the other hand can be right at any time
Fault conducts interviews, and is easy to search problem.
In this application scenarios, given threshold T1Value be 0.94, the monitoring velocity phase of sensor malfunction diagnostic device
To improve 12%, monitoring accuracy improves 10% relatively.
Application scenarios 4
Referring to Fig. 1, Fig. 2, a kind of monitoring system of power transmission network tower bar of an embodiment of this application scene, including cloud meter
Calculate monitor supervision platform, client, cloud terminal access device and local supervising and measuring equipment, described local supervising and measuring equipment includes sensor fault
Diagnostic device, described sensor malfunction diagnostic device includes signals collecting filtration module 1, fault signature extraction module 2, online spy
Levy extraction module 3, characteristic vector preferred module 4, failure modes identification module 5, failure mode update module 6 and health records mould
Block 7, described local supervising and measuring equipment is connected with described cloud computing monitor supervision platform by cloud terminal access device, described client and institute
State cloud computing monitor supervision platform to connect, described cloud computing monitor supervision platform includes power transmission network information database, cloud application server and line
Road patrol checking server.
The above embodiment of the present invention achieves the fast construction of monitoring system, improves the monitoring efficiency of power transmission network tower bar,
Reduce human input;Setting sensor malfunction diagnostic device, thus ensure the information gathering of local supervising and measuring equipment.
Preferably, described biography sensor group includes circuit humidity sensor, video monitor, circuit air velocity transducer, line
Road icing sensor and vibrating sensor.
This preferred embodiment is easy to power transmission network shaft tower be monitored comprehensively.
Preferably, described signals collecting filtration module 1 is used for gathering historical sensor signal and on-line sensor test letter
Number, and signal is filtered process using combination form wave filter.
This preferred embodiment arranges combination form wave filter, can effectively remove the various noise jamming of signal, preferably
The primitive character information of stick signal.
Preferably, described fault signature extraction module 2 is used for carrying out integrated experience to filtered historical sensor signal
Mode decomposition (EEMD) is processed, and extracts the Energy-Entropy of integrated empirical mode decomposition (EEMD) as training feature vector, including:
(1) the historical sensor signal of collection is divided into the fault-signal of nominal situation signal and plurality of classes;
(2) described historical sensor signal is carried out with integrated empirical mode decomposition (EEMD) process, obtain described history and pass
The intrinsic mode function of sensor signal and remainder function;
(3) intrinsic mode function of described historical sensor signal and the Energy-Entropy of remainder function are calculated;
(4) Energy-Entropy of historical sensor signal is normalized, extracts the Energy-Entropy after normalization as instruction
Practice characteristic vector;
Described online characteristic extracting module 3 is used for carrying out integrated empirical modal to filtered on-line sensor test signal
Decompose (EEMD) to process, and extract the Energy-Entropy of integrated empirical mode decomposition (EEMD) as characteristic vector to be measured, including:
(1) described on-line sensor test signal is carried out with EEMD process, obtains described on-line sensor test signal
Intrinsic mode function and remainder function;
(2) intrinsic mode function of described on-line sensor test signal and the Energy-Entropy of remainder function are calculated;
(3) Energy-Entropy of on-line sensor test signal is normalized, extracts the Energy-Entropy after normalization and make
For characteristic vector to be measured.
This preferred embodiment carries out integrated empirical mode decomposition (EEMD) to the sensor signal of collection and processes, can be effective
Elimination modal overlap phenomenon, the effect of decomposition is preferable.
Preferably, described characteristic vector preferred module 4 respectively training feature vector and characteristic vector to be measured are carried out similar
Property tolerance, the high characteristic vector of similarity is rejected, including:
(1) two vector similarities function S (X, Y) are defined:
In formula, X, Y represent two characteristic vectors respectively, and cov (X, Y) is the covariance of X and Y,For X,
Y standard deviation;
For any two training feature vector X1、X2, and any two characteristic vector D to be measured1、D2, it is respectively adopted similar
Degree its similarity of function pair is measured, and obtains S (X1,X2) and S (D1,D2);
(2) for S (X1,X2) and S (D1,D2), if S is (X1,X2)>T1, T1∈ (0.9,1), only chooses X1As training characteristics
Vector, if S is (D1,D2)>T2, T2∈ (0.95,1), only chooses D1As characteristic vector to be measured.
This preferred embodiment screens characteristic vector by measuring similarity, can reduce amount of calculation, improves efficiency.
Preferably, the least square method supporting vector machine that described failure modes identification module 5 is used for using optimizing is treated to described
Survey characteristic vector and carry out failure modes identification, select to optimize submodule, training submodule and identification submodule including parameter, specifically
For:
Described parameter selects to optimize the kernel function for constructing least square method supporting vector machine for the submodule, and to least square
The structural parameters of SVMs are worked in coordination with Chaos particle swarm optimization algorithm using multi-population and are optimized;
Described training submodule, for many classification side of the least square support vector machines using improved optimum binary tree structure
Method, is instructed to the least square method supporting vector machine after structure parameter optimizing using the training feature vector obtaining as training sample
Practice, and build sensor fault diagnosis model;
Described identification submodule is used for, using described sensor fault diagnosis model, described characteristic vector to be measured is carried out with event
Barrier Classification and Identification;
Wherein it is considered to the superiority of Polynomial kernel function and RBF kernel function, the core letter of described least square method supporting vector machine
Number is configured to:
K=(1- δ) (xxi+1)p+δexp(-‖x-xi‖2/σ2)
In formula, δ is the structure adjusting factor, and the span of δ is set as [0.45,0.55], and p is the rank of Polynomial kernel function
Number, σ2For RBF kernel functional parameter.
Wherein, shown using multi-population work in coordination with Chaos particle swarm optimization algorithm be optimized, including:
(1) initialize to main population with from population respectively, randomly generate one group of parameter initial as particle
Position and initial velocity, defining fitness function is:
In formula, N is training sample total number, and W is bug classification number, and T correctly classifies number for fault, qiIt is certainly
The weight coefficient setting, qiSpan be set as [0.4,0.5];
(2) carry out the renewal from population, in every generation renewal process, according to fitness function, from population difference
The speed of more new particle and position, then will be experienced in its history adaptive optimal control angle value and main population body to each particle
The fitness value of desired positions compares, if more preferably, as current global optimum position;
(3) optimum particle position in chaos optimization, and iteration current sequence and speed are carried out to described global optimum position
Degree, generates optimal particle sequence;
(4) choose optimum particle from population in the main population of every generation, and the position of more new particle and speed,
Until reaching maximum iteration time or the error requirements meeting fitness function.
Wherein, many sorting techniques of the least square support vector machines of described improved optimum binary tree structure specifically include:
(1) calculate the standard variance of all training samples and two classifications j,Between Separatory measure;
(2) output minimum separation estimate corresponding j,
(3) after the structural parameters to least square method supporting vector machine are optimized, the least square setting up two classification props up
Hold vector machine in order to train jth class andThe training sample of class, forms optimum two classification least square method supporting vector machines, output
The parameter of discriminant function,The training sample of class is merged in j class, constitutes new j class training sample;
(4) all of classification is circulated training according to (1)-(3), until the optimum root node of output;
(5) form the categorised decision tree of least square method supporting vector machine according to above output result, then to remaining instruction
Practice sample and carry out classifying quality test.
This preferred embodiment in order to improve the precision of fault diagnosis, using training speed is fast, generalization ability strong and robustness
Preferably least square support vector machines are as grader, and propose the many sorting techniques improving optimum binary tree structure, between class
Separatory measure substitutes weights, the nicety of grading that improve and the classification speed in binary tree structure;In view of RBF kernel function it is
Local kernel function, Polynomial kernel function is overall kernel function, and karyomerite function learning ability is strong, and Generalization Capability is relatively weak, and
Overall kernel function Generalization Capability is strong, and learning ability is relatively weak, carries out on the basis of the advantage of summary two class kernel function
The Kernel of least square method supporting vector machine, optimizes classification performance and the Generalization Capability of least square method supporting vector machine;
The multi-population of design works in coordination with Chaos particle swarm optimization algorithm, has preferable convergence rate, and has preferable global and local
Optimizing performance, can timely jump out Local Extremum, find the optimal value of the overall situation, thus working in coordination with chaotic particle using multi-population
Colony optimization algorithm is optimized to the structural parameters of least square method supporting vector machine, and effect of optimization is good.
Preferably, described failure mode update module 6 is used for training set is updated, and continues to optimize sensor fault and examines
Disconnected model, including:
(1) when sensor fault diagnosis model cannot carry out effective failure modes to characteristic vector to be measured, by feature to be measured
Vector is as new training feature vector;
(2) new training feature vector is updated to training sample, and the least square after structure parameter optimizing is supported
Vector machine is trained, and constructs new sensor fault diagnosis model;
(3) failure modes identification is carried out to described characteristic vector to be measured using new sensor fault diagnosis model, complete
Failure mode updates.
This preferred embodiment arranges failure mode update module 6, to improve adaptability and the range of application of model.
Preferably, described health records module 7 includes sub-module stored and secure access submodule, described sub-module stored
Using the storage model based on cloud storage, specifically, it is encrypted after fault message is compressed, is uploaded to cloud storage,
Described secure access submodule is used for information is conducted interviews, and specifically, corresponding to sub-module stored, downloads data to this
Ground, after being unlocked using corresponding secret key, then is decompressed to read information.
This preferred embodiment arranges health records module 7, on the one hand ensure that information security, on the other hand can be right at any time
Fault conducts interviews, and is easy to search problem.
In this application scenarios, given threshold T1Value be 0.93, the monitoring velocity phase of sensor malfunction diagnostic device
To improve 13%, monitoring accuracy improves 9% relatively.
Application scenarios 5
Referring to Fig. 1, Fig. 2, a kind of monitoring system of power transmission network tower bar of an embodiment of this application scene, including cloud meter
Calculate monitor supervision platform, client, cloud terminal access device and local supervising and measuring equipment, described local supervising and measuring equipment includes sensor fault
Diagnostic device, described sensor malfunction diagnostic device includes signals collecting filtration module 1, fault signature extraction module 2, online spy
Levy extraction module 3, characteristic vector preferred module 4, failure modes identification module 5, failure mode update module 6 and health records mould
Block 7, described local supervising and measuring equipment is connected with described cloud computing monitor supervision platform by cloud terminal access device, described client and institute
State cloud computing monitor supervision platform to connect, described cloud computing monitor supervision platform includes power transmission network information database, cloud application server and line
Road patrol checking server.
The above embodiment of the present invention achieves the fast construction of monitoring system, improves the monitoring efficiency of power transmission network tower bar,
Reduce human input;Setting sensor malfunction diagnostic device, thus ensure the information gathering of local supervising and measuring equipment.
Preferably, described biography sensor group includes circuit humidity sensor, video monitor, circuit air velocity transducer, line
Road icing sensor and vibrating sensor.
This preferred embodiment is easy to power transmission network shaft tower be monitored comprehensively.
Preferably, described signals collecting filtration module 1 is used for gathering historical sensor signal and on-line sensor test letter
Number, and signal is filtered process using combination form wave filter.
This preferred embodiment arranges combination form wave filter, can effectively remove the various noise jamming of signal, preferably
The primitive character information of stick signal.
Preferably, described fault signature extraction module 2 is used for carrying out integrated experience to filtered historical sensor signal
Mode decomposition (EEMD) is processed, and extracts the Energy-Entropy of integrated empirical mode decomposition (EEMD) as training feature vector, including:
(1) the historical sensor signal of collection is divided into the fault-signal of nominal situation signal and plurality of classes;
(2) described historical sensor signal is carried out with integrated empirical mode decomposition (EEMD) process, obtain described history and pass
The intrinsic mode function of sensor signal and remainder function;
(3) intrinsic mode function of described historical sensor signal and the Energy-Entropy of remainder function are calculated;
(4) Energy-Entropy of historical sensor signal is normalized, extracts the Energy-Entropy after normalization as instruction
Practice characteristic vector;
Described online characteristic extracting module 3 is used for carrying out integrated empirical modal to filtered on-line sensor test signal
Decompose (EEMD) to process, and extract the Energy-Entropy of integrated empirical mode decomposition (EEMD) as characteristic vector to be measured, including:
(1) described on-line sensor test signal is carried out with EEMD process, obtains described on-line sensor test signal
Intrinsic mode function and remainder function;
(2) intrinsic mode function of described on-line sensor test signal and the Energy-Entropy of remainder function are calculated;
(3) Energy-Entropy of on-line sensor test signal is normalized, extracts the Energy-Entropy after normalization and make
For characteristic vector to be measured.
This preferred embodiment carries out integrated empirical mode decomposition (EEMD) to the sensor signal of collection and processes, can be effective
Elimination modal overlap phenomenon, the effect of decomposition is preferable.
Preferably, described characteristic vector preferred module 4 respectively training feature vector and characteristic vector to be measured are carried out similar
Property tolerance, the high characteristic vector of similarity is rejected, including:
(1) two vector similarities function S (X, Y) are defined:
In formula, X, Y represent two characteristic vectors respectively, and cov (X, Y) is the covariance of X and Y,For X,
Y standard deviation;
For any two training feature vector X1、X2, and any two characteristic vector D to be measured1、D2, it is respectively adopted similar
Degree its similarity of function pair is measured, and obtains S (X1,X2) and S (D1,D2);
(2) for S (X1,X2) and S (D1,D2), if S is (X1,X2)>T1, T1∈ (0.9,1), only chooses X1As training characteristics
Vector, if S is (D1,D2)>T2, T2∈ (0.95,1), only chooses D1As characteristic vector to be measured.
This preferred embodiment screens characteristic vector by measuring similarity, can reduce amount of calculation, improves efficiency.
Preferably, the least square method supporting vector machine that described failure modes identification module 5 is used for using optimizing is treated to described
Survey characteristic vector and carry out failure modes identification, select to optimize submodule, training submodule and identification submodule including parameter, specifically
For:
Described parameter selects to optimize the kernel function for constructing least square method supporting vector machine for the submodule, and to least square
The structural parameters of SVMs are worked in coordination with Chaos particle swarm optimization algorithm using multi-population and are optimized;
Described training submodule, for many classification side of the least square support vector machines using improved optimum binary tree structure
Method, is instructed to the least square method supporting vector machine after structure parameter optimizing using the training feature vector obtaining as training sample
Practice, and build sensor fault diagnosis model;
Described identification submodule is used for, using described sensor fault diagnosis model, described characteristic vector to be measured is carried out with event
Barrier Classification and Identification;
Wherein it is considered to the superiority of Polynomial kernel function and RBF kernel function, the core letter of described least square method supporting vector machine
Number is configured to:
K=(1- δ) (xxi+1)p+δexp(-‖x-xi‖2/σ2)
In formula, δ is the structure adjusting factor, and the span of δ is set as [0.45,0.55], and p is the rank of Polynomial kernel function
Number, σ2For RBF kernel functional parameter.
Wherein, shown using multi-population work in coordination with Chaos particle swarm optimization algorithm be optimized, including:
(1) initialize to main population with from population respectively, randomly generate one group of parameter initial as particle
Position and initial velocity, defining fitness function is:
In formula, N is training sample total number, and W is bug classification number, and T correctly classifies number for fault, qiIt is certainly
The weight coefficient setting, qiSpan be set as [0.4,0.5];
(2) carry out the renewal from population, in every generation renewal process, according to fitness function, from population difference
The speed of more new particle and position, then will be experienced in its history adaptive optimal control angle value and main population body to each particle
The fitness value of desired positions compares, if more preferably, as current global optimum position;
(3) optimum particle position in chaos optimization, and iteration current sequence and speed are carried out to described global optimum position
Degree, generates optimal particle sequence;
(4) choose optimum particle from population in the main population of every generation, and the position of more new particle and speed,
Until reaching maximum iteration time or the error requirements meeting fitness function.
Wherein, many sorting techniques of the least square support vector machines of described improved optimum binary tree structure specifically include:
(1) calculate the standard variance of all training samples and two classifications j,Between Separatory measure;
(2) output minimum separation estimate corresponding j,
(3) after the structural parameters to least square method supporting vector machine are optimized, the least square setting up two classification props up
Hold vector machine in order to train jth class andThe training sample of class, forms optimum two classification least square method supporting vector machines, output
The parameter of discriminant function,The training sample of class is merged in j class, constitutes new j class training sample;
(4) all of classification is circulated training according to (1)-(3), until the optimum root node of output;
(5) form the categorised decision tree of least square method supporting vector machine according to above output result, then to remaining instruction
Practice sample and carry out classifying quality test.
This preferred embodiment in order to improve the precision of fault diagnosis, using training speed is fast, generalization ability strong and robustness
Preferably least square support vector machines are as grader, and propose the many sorting techniques improving optimum binary tree structure, between class
Separatory measure substitutes weights, the nicety of grading that improve and the classification speed in binary tree structure;In view of RBF kernel function it is
Local kernel function, Polynomial kernel function is overall kernel function, and karyomerite function learning ability is strong, and Generalization Capability is relatively weak, and
Overall kernel function Generalization Capability is strong, and learning ability is relatively weak, carries out on the basis of the advantage of summary two class kernel function
The Kernel of least square method supporting vector machine, optimizes classification performance and the Generalization Capability of least square method supporting vector machine;
The multi-population of design works in coordination with Chaos particle swarm optimization algorithm, has preferable convergence rate, and has preferable global and local
Optimizing performance, can timely jump out Local Extremum, find the optimal value of the overall situation, thus working in coordination with chaotic particle using multi-population
Colony optimization algorithm is optimized to the structural parameters of least square method supporting vector machine, and effect of optimization is good.
Preferably, described failure mode update module 6 is used for training set is updated, and continues to optimize sensor fault and examines
Disconnected model, including:
(1) when sensor fault diagnosis model cannot carry out effective failure modes to characteristic vector to be measured, by feature to be measured
Vector is as new training feature vector;
(2) new training feature vector is updated to training sample, and the least square after structure parameter optimizing is supported
Vector machine is trained, and constructs new sensor fault diagnosis model;
(3) failure modes identification is carried out to described characteristic vector to be measured using new sensor fault diagnosis model, complete
Failure mode updates.
This preferred embodiment arranges failure mode update module 6, to improve adaptability and the range of application of model.
Preferably, described health records module 7 includes sub-module stored and secure access submodule, described sub-module stored
Using the storage model based on cloud storage, specifically, it is encrypted after fault message is compressed, is uploaded to cloud storage,
Described secure access submodule is used for information is conducted interviews, and specifically, corresponding to sub-module stored, downloads data to this
Ground, after being unlocked using corresponding secret key, then is decompressed to read information.
This preferred embodiment arranges health records module 7, on the one hand ensure that information security, on the other hand can be right at any time
Fault conducts interviews, and is easy to search problem.
In this application scenarios, given threshold T1Value be 0.92, the monitoring velocity phase of sensor malfunction diagnostic device
To improve 14%, monitoring accuracy improves 8% relatively.
Finally it should be noted that above example is only in order to illustrating technical scheme, rather than the present invention is protected
The restriction of shield scope, although having made to explain to the present invention with reference to preferred embodiment, those of ordinary skill in the art should
Work as understanding, technical scheme can be modified or equivalent, without deviating from the reality of technical solution of the present invention
Matter and scope.
Claims (3)
1. a kind of monitoring system of power transmission network tower bar is it is characterised in that inclusion cloud computing monitor supervision platform, client, cloud terminal connect
Enter equipment and local supervising and measuring equipment, described local supervising and measuring equipment passes through cloud terminal access device with described cloud computing monitor supervision platform even
Connect, described client is connected with described cloud computing monitor supervision platform, described cloud computing monitor supervision platform include power transmission network information database,
Cloud application server and line data-logging server.
2. the monitoring system of power transmission network tower bar according to claim 1 is it is characterised in that described local supervising and measuring equipment includes
Sensor malfunction diagnostic device, described sensor malfunction diagnostic device includes signals collecting filtration module, fault signature extracts mould
Block, online characteristic extracting module, characteristic vector preferred module, failure modes identification module, failure mode update module and health
Logging modle.
3. the monitoring system of power transmission network tower bar according to claim 2 is it is characterised in that described sensor group includes circuit
Humidity sensor, video monitor, circuit air velocity transducer, line ice coating sensor and vibrating sensor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610761746.3A CN106404055A (en) | 2016-08-29 | 2016-08-29 | Power transmission network tower monitoring system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610761746.3A CN106404055A (en) | 2016-08-29 | 2016-08-29 | Power transmission network tower monitoring system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106404055A true CN106404055A (en) | 2017-02-15 |
Family
ID=58003594
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610761746.3A Pending CN106404055A (en) | 2016-08-29 | 2016-08-29 | Power transmission network tower monitoring system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106404055A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111551593A (en) * | 2020-04-23 | 2020-08-18 | 西安工程大学 | Insulator ice melting water content monitoring method based on RBF-NN |
CN112216085A (en) * | 2020-09-15 | 2021-01-12 | 青岛科技大学 | Equipment key load-bearing structural member health monitoring system based on edge calculation and intelligent identification of updated samples |
CN112615740A (en) * | 2020-12-14 | 2021-04-06 | 广东电网有限责任公司佛山供电局 | Transmission network communication safety system |
CN116087770A (en) * | 2023-02-08 | 2023-05-09 | 中国船舶集团有限公司第七一一研究所 | Motor fault diagnosis method and device and ship management architecture |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102608545A (en) * | 2012-03-01 | 2012-07-25 | 西安电子科技大学 | Non-contact switch power failure diagnosis system |
CN102645633A (en) * | 2012-04-19 | 2012-08-22 | 北京国能伏安节能科技有限公司 | Online diagnosis device of motor faults based on FPGA+ARM (Field Programmable Gate Array+Accumulator Read-in Module) |
CN102706885A (en) * | 2012-05-15 | 2012-10-03 | 广东电网公司电力科学研究院 | On-line damage detecting system of blade of wind generating set |
CN102736027A (en) * | 2012-07-18 | 2012-10-17 | 南京因泰莱配电自动化设备有限公司 | Circuit breaker failure diagnosis method based on circuit breaker dynamic property test instrument |
CN204408021U (en) * | 2015-02-11 | 2015-06-17 | 国家电网公司 | A kind of supervisory control system of power transmission network tower bar |
-
2016
- 2016-08-29 CN CN201610761746.3A patent/CN106404055A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102608545A (en) * | 2012-03-01 | 2012-07-25 | 西安电子科技大学 | Non-contact switch power failure diagnosis system |
CN102645633A (en) * | 2012-04-19 | 2012-08-22 | 北京国能伏安节能科技有限公司 | Online diagnosis device of motor faults based on FPGA+ARM (Field Programmable Gate Array+Accumulator Read-in Module) |
CN102706885A (en) * | 2012-05-15 | 2012-10-03 | 广东电网公司电力科学研究院 | On-line damage detecting system of blade of wind generating set |
CN102736027A (en) * | 2012-07-18 | 2012-10-17 | 南京因泰莱配电自动化设备有限公司 | Circuit breaker failure diagnosis method based on circuit breaker dynamic property test instrument |
CN204408021U (en) * | 2015-02-11 | 2015-06-17 | 国家电网公司 | A kind of supervisory control system of power transmission network tower bar |
Non-Patent Citations (1)
Title |
---|
丁国君: "动车组制动控制系统故障诊断方法研究", 《中国博士学位论文全文数据库 工程科技II辑》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111551593A (en) * | 2020-04-23 | 2020-08-18 | 西安工程大学 | Insulator ice melting water content monitoring method based on RBF-NN |
CN112216085A (en) * | 2020-09-15 | 2021-01-12 | 青岛科技大学 | Equipment key load-bearing structural member health monitoring system based on edge calculation and intelligent identification of updated samples |
CN112216085B (en) * | 2020-09-15 | 2022-05-10 | 青岛科技大学 | Equipment key load-bearing structural member health monitoring system based on edge calculation and online update sample intelligent identification |
CN112615740A (en) * | 2020-12-14 | 2021-04-06 | 广东电网有限责任公司佛山供电局 | Transmission network communication safety system |
CN116087770A (en) * | 2023-02-08 | 2023-05-09 | 中国船舶集团有限公司第七一一研究所 | Motor fault diagnosis method and device and ship management architecture |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhang et al. | A real-time and ubiquitous network attack detection based on deep belief network and support vector machine | |
CN106404055A (en) | Power transmission network tower monitoring system | |
CN108566364B (en) | Intrusion detection method based on neural network | |
CN105024877B (en) | A kind of Hadoop malicious node detecting systems based on user's behaviors analysis | |
CN109818961B (en) | Network intrusion detection method, device and equipment | |
CN106292282A (en) | Reading intelligent agriculture environmental monitoring systems based on big data | |
CN117421684A (en) | Abnormal data monitoring and analyzing method based on data mining and neural network | |
CN110412368A (en) | Electrical equipment online supervision method and system based on Application on Voiceprint Recognition | |
Ducoffe et al. | Anomaly detection on time series with Wasserstein GAN applied to PHM | |
CN108848571A (en) | A kind of rail traffic safety monitoring system and monitoring method based on MEMS sensor | |
DE112021004808T5 (en) | DETECTING MALWARE THROUGH ANALYSIS OF DISTRIBUTED TELEMETRY DATA | |
CN116302809A (en) | Edge end data analysis and calculation device | |
CN115865483A (en) | Abnormal behavior analysis method and device based on machine learning | |
CN117609885A (en) | High-speed rail intrusion monitoring method based on distributed optical fiber sensing and fused neural network | |
CN117932358A (en) | Intelligent remote electric field fault diagnosis method and system | |
Samadzadeh et al. | Evaluating Security Anomalies by Classifying Traffic Using Deep Learning | |
Munir et al. | Extraction of forest power lines from LiDAR point cloud data | |
CN106081911A (en) | A kind of derrick crane on-line monitoring system | |
CN116192531A (en) | Log anomaly detection system based on isolated forest | |
CN106355715A (en) | Wireless speech-recognition door access system | |
CN106225846A (en) | Greenhouse monitoring system | |
CN106246164A (en) | Coal bed gas well level monitoring system based on Fibre Optical Sensor | |
JP2022036054A (en) | Inspection device, inspection method, and inspection program for strung wire | |
CN106124205A (en) | A kind of decelerator health analysis system | |
CN106404645A (en) | Online monitoring system of steel bar corrosion in concrete |
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: 20170215 |