CN107563414A - A kind of complex device degenerate state recognition methods based on Kohonen SVM - Google Patents
A kind of complex device degenerate state recognition methods based on Kohonen SVM Download PDFInfo
- Publication number
- CN107563414A CN107563414A CN201710691675.9A CN201710691675A CN107563414A CN 107563414 A CN107563414 A CN 107563414A CN 201710691675 A CN201710691675 A CN 201710691675A CN 107563414 A CN107563414 A CN 107563414A
- Authority
- CN
- China
- Prior art keywords
- data
- svm
- kohonen
- degenerate state
- sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Image Analysis (AREA)
Abstract
A kind of complex device degenerate state recognition methods based on Kohonen SVM, step are as follows：1st, the normal power data of complex device are acquired；2nd, feature extraction selection dimensionality reduction is carried out to the power data after screening；3rd, multidimensional characteristic vectors data input is subjected to Unsupervised clustering study into Kohonen networks；4th, division processing is carried out to degeneration sample set data；5th, on the basis of training sample set, optimizing solution is carried out to SVM parameter using PSO methods；6th, SVM model learnings are carried out using the parameter and training set sample data of optimization, obtains degenerate state identification model；7th, the accuracy rate of Classification and Identification model is verified using test set sample data；By above-mentioned steps, the present invention realizes the complex device degenerate state recognition methods based on Kohonen SVM, has obtained the typical degradation state sample collection data of equipment and the degenerate state identification model of complex device.
Description
Technical field
The present invention provides a kind of complex device degenerate state recognition methods based on Kohonen-SVM, and it is related to a kind of base
In the realization of Kohonen-SVM complex device degenerate state recognition methods, belong to complex device reliability, complex device failure
Diagnostic field.
Background technology
With the continuous improvement of industrialized level, the equipment applied to each industrial department is also increasingly sophisticated, these equipment
Reliability directly affects the development of related industry.Monitored and identified the failure classes that may occur in real time to complex device
Type, have great importance to the reliability of equipment.At present, the diagnosis for complex device both at home and abroad focuses primarily upon failure
The identification of pattern, but these researchs do not account for the degenerate state of equipment.Degenerate state image watermarking is in normal shape
In state data, increase over time, be eventually evolved into degradation failure.Wherein, degradation failure refers to that equipment is chronically at Asia
Health status, performance run down caused failure.Therefore, the Study of recognition to equipment degenerate state is very necessary.
The present invention proposes a kind of complex device degenerate state recognition methods based on Kohonen-SVM, and this method passes through Ke Helun
(Kohonen) neutral net carries out unsupervised learning to the normal power data of equipment, obtains degenerate state number among typical
According to.Then using SVMs (Support Vector Machine, abbreviation SVM) model of parameter optimization to status data
Exercise supervision study, generates degenerate state sorter model, the identification for complex device degenerate state.
This method is based on Kohonen neutral nets and SVM technologies, fusion accident analysis and troubleshooting etc. correlation theory,
Methods and techniques are realized, while complex device maintainability is improved, reach improve complex device reliability, security,
The purpose of availability.
The content of the invention
(1) the object of the invention
Generally only consider normal and failure two states currently for the method for fault pattern recognition of complex device, not
The middle degenerate state of equipment is accounted for, the accumulation that this degenerate state can be over time is evolved into degradation failure, pair sets
It is standby to cause serious damage.Therefore it is of the invention by overcome the deficiencies in the prior art, there is provided a kind of complexity based on Kohonen-SVM
Equipment degenerate state recognition methods.This method is using the degenerate state method for digging of Kohonen neutral nets to the normal of equipment
Power data carries out unsupervised learning, obtains typical degenerate state data.And on the basis of data, use parameter optimization
SVM models exercise supervision study to status data, generate degenerate state sorter model, the identification for equipment degenerate state.
This method can not only be excavated to the degenerate state of complex device, and classification can also be identified to degenerate state, be
Fault diagnosis field provides a kind of new solution method, and existing method of fault pattern recognition is innovated.
(2) technical scheme
A kind of complex device degenerate state recognition methods based on Kohonen-SVM of the present invention, its step are as follows：
Step 1, the normal power data to complex device are acquired, and wherein may be rejected by way of artificial screening
Existing fault data and bad value data；
Step 2, feature extraction-selection-dimensionality reduction is carried out to the power data after screening, obtain can be used for the more of input study
Dimensional feature vector data；
Step 3, multidimensional characteristic vectors data input is subjected to Unsupervised clustering study into Kohonen networks, moved back
Change state sample collection data；
Step 4, division processing is carried out to degeneration sample set data, obtain SVM training sample sets data and test sample collection
Data；
Step 5, on the basis of training sample set, using particle group optimizing method (Particle Swarm
Optimization, abbreviation PSO) optimizing solution is carried out to SVM parameter；
Step 6, parameter and training set sample data the progress SVM model learnings using optimization, obtain effectively identifying and move back
The SVM models of change state, i.e. degenerate state identification model；
Step 7, using test set sample data the accuracy rate of Classification and Identification model is verified.
Wherein, described " power data " in step 1, during referring to device action, is set by harvester
Standby real-time current, magnitude of voltage, and the sign equipment state obtained on the basis of these numerical value using computer automatic analysis
Data；Described " fault data ", when referring to that equipment running process breaks down, the abnormal work(that is detected by comparative analysis
Rate data；Described " bad value data ", refer in device action data acquisition, and data value is less than the work(of collection regulation threshold
Rate data, the presence of bad value data can influence the accuracy of plant capacity overall data.
Wherein, it is described " feature extraction-selection-dimensionality reduction is carried out to the power data after screening " in step 2, its practice
It is as follows：Time domain data and codomain data are divided into power data, after the completion of division, proceeds by the feature extraction work of data
Make.For power time domain data, this method extraction average, variance, root mean square, kurtosis, inlet and outlet difference, minimax difference,
Peak factor, the pulse factor, difference and, the parameter such as shape factor is as characteristic；For performance number numeric field data, this method carries
Maximum time value, average value, data points, minimax difference, value median, maximum, time median, mode etc. is taken to join
Number is used as characteristic.After the completion of extraction, using these characteristic construction feature vector spaces, using based on criterion function
Method carry out feature selecting；After feature selecting is completed, by principal component analysis, carry out Feature Dimension Reduction is locally linear embedding into,
The multidimensional characteristic vectors data of acquisition.
Wherein, described " multidimensional characteristic vectors data " in step 3, refer to power data by feature extraction-selection-
The data obtained after dimension-reduction treatment, multidimensional characteristic vectors data can be as the input datas of Kohonen networks, for degenerate state
Clustering learning.
Wherein, described " Kohonen networks " in step 3, refers to a kind of Self-organizing Competition type neutral net；The network
Network weight is adjusted by self-organizing feature map, neutral net is converged on a kind of expression form, one in this form
Neuron is only to the especially matching or sensitive of certain input pattern；Kohonen networks are comprising before two layers of input layer and competition layer
Present neutral net；Wherein, the 1st layer is input layer, and the number of input layer is consistent with the dimension of input sample vector,
It is m to take input layer number；2nd layer is competition layer, also referred to as output layer, and competition node layer is distributed in two-dimensional array, takes competition layer
Nodes are n；Connected entirely with variable weight between input node and output node, connection weight is Kohonen networks
Study is unsupervised self-organized learning process；By unsupervised learning, different neurons can be to different input moulds in network
Formula is sensitive, realizes that specific neuron can serve as the detector of a certain input pattern in pattern-recognition.After the completion of study, god
Different zones are divided into through member, each region has different response characteristics to input model.
Wherein, it is described in step 3 " to carry out into Kohonen networks multidimensional characteristic vectors data input unsupervised
Clustering learning ", its practice are as follows：By multidimensional characteristic vectors data input to network, the neuron on network competition layer calculates defeated
Enter the Euclidean distance between sample and competition layer neuron weights, the minimum neuron of distance is triumph neuron.Adjustment
Triumph neuron and adjacent neurons weights, make triumph neuron and periphery weights close to the input sample；By repetition training,
The connection weight of final each neuron has certain distribution, and the distribution is all kinds of to representing the similitude tissue between data
Under neuron, make similar neuron obvious with similar weight coefficient, inhomogeneous neuron weight coefficient difference.It should be noted
It is that in learning process, weights modification learning rate and neuron field are constantly being reduced, so that similar neuron is gradual
Concentrate, complete the automatic cluster of input data, generate different classes of degenerate state sample set data.
Wherein, described " carrying out division processing to degeneration sample set data " in step 4, its practice is as follows：To degenerating
The number of samples of state sample collection data carries out unified, it is specified that the number of samples of every kind of state is consistent, and presses 4:1 ratio will be every
Kind sample is divided into training set and test set；Training set data is used to carry out SVM modelings, and test set data are used for into row degradation shape
The recognition accuracy test of state identification model.
Wherein, described " SVM " in step 4, refers to supporting vector machine model, the model is the base in statistical theory
A kind of sorter model proposed on plinth, available for pattern classification, linear and nonlinear regression analysis；The original of SVMs
Reason is given training sample, establishes an Optimal Separating Hyperplane as decision-making curved surface, makes the isolated border between sample positive example and counter-example
Edge maximizes, so as to complete the classification of training sample.
Wherein, described " particle group optimizing method " in steps of 5, refers to that a kind of optimization theoretical based on swarm intelligence is calculated
Method, the algorithm have self-teaching and the two-fold advantage learnt to other people, can find optimal solution in less iterations.
Wherein, in steps of 5 it is described " using particle group optimizing method (Particle Swarm Optimization,
Abbreviation PSO) optimizing solution is carried out to SVM parameter ", i.e., " optimizing solution is carried out to SVM parameter using PSO methods ", its work
Method is as follows：Optimizing solution is carried out to SVM nuclear parameter g and penalty parameter c, first, produces initialization population, it is each in population
Individual particle represents a potential optimal solution, and each particle has three index expression its features：Position, speed and fitness
Value；Then, the fitness value of each particle is calculated according to object function, the quality of the value represents the quality of particle, works as particle
When solution space is moved, by track individual extreme value and colony's extreme value come the position of more new individual；Particle often updates a position,
Need to recalculate fitness value, and by comparing the fitness value and individual extreme value, the fitness of colony's extreme value of new particle
Value comes the more position of new individual extreme value and colony's extreme value；Finally, when finding optimal solution good enough or reaching iterations,
PSO algorithms terminate, and export optimal nuclear parameter g and penalty parameter c.
Wherein, it is described in step 6 " to carry out SVM models using the parameter after optimization and training set sample data
Practise ", its practice is as follows：
Step 6.1：If known training set：T={ (x1, y1) ..., (xi, yi)}∈(X×Y)l, wherein, xiBe characterized to
Amount, yiFor corresponding property value, xi∈X∈Rn, yi∈ Y={ -1,1 }, i=1,2 ..., l；
Step 6.2：The kernel function g (x, x ') and appropriate punishment parameter C of PSO optimizations are chosen, constructs and solves optimization
Problem：So that0≤αi≤ C, i=1,2 ..., l, so as to obtain optimal solution
Step 6.3：Choose α*A positive component 0<α*<C, and threshold value is calculated accordingly
Step 6.4：Construct decision function f (x)：
Step 6.5:Classification is exported according to decision function f (x) value.
Pass through above-mentioned steps, it is possible to achieve the complex device degenerate state recognition methods based on Kohonen-SVM, this method
Unsupervised degenerate state method for digging based on Kohonen neutral nets, the typical degradation state sample collection number of equipment is obtained
According to；Further, SVM model parameters are optimized using PSO methods on the basis of training sample data collection, by using excellent
The SVM models of change carry out Classification and Identification to degenerate state data, have obtained the degenerate state identification model of complex device.Finally adopt
Accuracy Verification with test sample data set to identification disaggregated model, to prove the feasible of this method identification degenerate state
Property.
(3) advantage
The present invention compared with prior art the advantages of be：At present, most of method of fault pattern recognition can only be to complexity
The normal and failure two states of equipment are identified, to that can not have in the normally degenerate state between malfunction
The excavation and identification of effect.And the present invention can excavate middle degenerate state data from the normal power data of complex device, and
Exercise supervision study on this basis, obtains equipment typically all kinds of degenerate state data.
Brief description of the drawings
Fig. 1 is the general steps flow of the present invention.
Fig. 2 is the power data feature extraction flow of the present invention.
Fig. 3 is the method flow based on Kohonen networks of the present invention.
Fig. 4 is the particle swarm optimization algorithm flow of the present invention.
Fig. 5 is the degenerate state identification process of the present invention.
Fig. 6 is the degenerate state recognition methods implementation process of the present invention.
Sequence number, symbol, code name are described as follows in figure：
In Fig. 1 " step 1-7 " is step corresponding in technical solution of the present invention；
" PSO " in Fig. 1 is particle group optimizing method, and the optimizing for completing SVMs parameter solves；
Fig. 1, the Kohonen networks in 6 are Ke Helun neutral nets, for completing the excacation of degenerate state；
Fig. 1, the SVM in 5,6 is supporting vector machine model, and the identification for completing degenerate state is classified work；
Fig. 3, " Y " in 4 represent that Rule of judgment be logic " true ", and " N " expression Rule of judgment is logic "false".
Embodiment
To make the technical problem to be solved in the present invention, technical scheme and advantage clearer, carried out below in conjunction with accompanying drawing
It is described in detail.
The present invention proposes a kind of complex device degenerate state recognition methods based on Kohonen-SVM, and this method passes through
Clustering processing is carried out to the normal power data of complex device, obtains the typical degradation state sample collection data of equipment.Further
On the basis of training sample data collection, SVM model parameters are optimized using PSO methods, by using parameter optimization
SVM models exercise supervision study to degenerate state data, obtain the degenerate state identification model of equipment.Finally use test sample
Data are to identifying that the accuracy rate of disaggregated model is verified, it was demonstrated that feasibility of this method in terms of degenerate state is identified.
A kind of complex device degenerate state recognition methods based on Kohonen-SVM of the present invention, as shown in figure 1, its is specific
Construction step is as follows：
Step 1：The normal power data of complex device are carried out with real-time collection and continual collection, data should use " when m- numerical value "
Form be indicated.After the completion of data acquisition, fault data wherein that may be present and bad is rejected by artificial screening method
Value Data；
Step 2：" feature extraction-selection-dimensionality reduction " processing is carried out to the power data after screening, as Kohonen nerves
The learning data of network model.Wherein, the processing method of " feature extraction-selection-dimensionality reduction " is as shown in Figure 2.This method is right first
Power data is divided, and is typically divided into time domain data and codomain data.After the completion of division, the feature for proceeding by data carries
Take work.For power time domain data, this method extraction average, variance, root mean square, kurtosis, inlet and outlet difference, minimax are poor
Value, peak factor, the pulse factor, difference and, the parameter such as shape factor is as characteristic；For performance number numeric field data, the party
Method extraction maximum time value, average value, data points, minimax difference, value median, maximum, time median, mode
Etc. parameter as characteristic.After the completion of extraction, using these characteristic construction feature vector spaces, using based on criterion
The method of function carries out feature selecting.After feature selecting is completed, by principal component analysis, progress feature drop is locally linear embedding into
Dimension, the multidimensional characteristic vectors data of acquisition；
Step 3：Multidimensional characteristic vectors data input is subjected to Unsupervised clustering study into Kohonen networks, moved back
Change state sample collection data.Degenerate state clustering method flow based on Kohonen networks is as shown in figure 3, power by extraction
Characteristic after the input data of model as, it is necessary to initialized according to the characteristics of data to network, determining network inputs
Output node number and learning parameter.Network inputs nodes should be consistent with the dimension of input feature value, output node
It is several then to be determined by the classification number of degenerate state.Kohonen network output layer node on behalf input data is potentially degenerated shape
State classification, general output layer nodes are more than the number of input data concrete class.For complex device, the present invention to be identified
Degenerate state classification be less than 10 kinds, so only selecting 36 output classifications of the competition node layers as network here, and provide
The box formation that these competition node layers are arranged with 6 rows 6 is arranged.
For the learning parameter of network, because field radius and learning rate can taper into during evolution, therefore
Need to optimize tune to the node weights in the winning node field radius r of network according to the field formula of Kohonen networks
Whole, such input data can obtain typical gradually into certain several output layer set of node, so as to realize the function of convergence of network
Degenerate state sample set data；
Step 4：Degenerate state sample set data are pre-processed, obtain training sample set data and test sample collection
Data.Here, it is necessary to be carried out to the numbers of samples of degenerate state sample set data unified, it is specified that the number of samples one of every kind of state
Cause, and by 4:Every kind of sample is divided into training set and test set by 1 ratio.Wherein, training set data is built for carrying out SVM
Mould, test set data are used for the recognition accuracy test for carrying out degenerate state identification model；
Step 5：On the basis of training set sample data, using particle swarm optimization algorithm (Particle Swarm
Optimization, PSO) optimizing solution is carried out to SVM nuclear parameter g and penalty parameter c, obtain optimal nuclear parameter g and punish
Penalty parameter c, the two parameters can produce conclusive influence to the optimal performance of grader.Using PSO algorithms to SVM nuclear parameters
With punishment parameter optimizing flow as shown in figure 4, first, producing initialization population, each particle represents one and dived in population
Optimal solution, each particle has three index expression its features：Position, speed and fitness value.Then, according to target letter
Number calculates the fitness value of each particle, and the quality of the value represents the quality of particle, when particle moves in solution space, passed through
Track individual extreme value and colony's extreme value come the position of more new individual.Particle often updates a position, it is necessary to recalculate fitness
Value, and by compare new particle fitness value and individual extreme value, colony's extreme value fitness value come more new individual extreme value and
The position of colony's extreme value.Finally, when finding optimal solution good enough or reaching iterations, PSO algorithms terminate, and output is most
Excellent nuclear parameter g and penalty parameter c；
Step 6：SVM model learnings are carried out using the parameter after optimization and training set sample data, obtain effectively identifying
The SVM models of degenerate state, i.e. degenerate state identification model.Because SVM models have very big in Small Sample Database classification
Superiority, and the number of samples that the degenerate state of Kohonen neutral nets is excavated to obtain not is a lot.Therefore the present invention adopts
The recognition methods of degenerate state is used as by the use of SVM.Overall flow such as Fig. 5 of complex device degenerate state recognition methods based on SVM
Shown, " selected training set and the test set data " and " data set pretreatment " in figure are in " step 2 " before to " step
Completed in four ".This step is substantially carried out " training SVM models " and " generation identification disaggregated model " two parts, SVM training process
It is the supervised learning process using classification accuracy rate as index, that is, finds the process of optimal classifying face.In training, penalty
C and nuclear parameter g can produce conclusive influence to the optimal performance of SVM classifier, and the present invention employs PSO in " step 5 "
Method completes the Optimization Work of both parameters, therefore combines the parameter and training set sample data of optimization, carries out SVM supervision and learns
The practice of habit is as follows：
Step 6.1：If known training set：T={ (x1, y1) ..., (xi, yi)}∈(X×Y)l, wherein, xiBe characterized to
Amount, yiFor corresponding property value, xi∈X∈Rn, yi∈ Y={ -1,1 }, i=1,2 ..., l；
Step 6.2：The kernel function g (x, x ') and appropriate punishment parameter C of PSO optimizations are chosen, constructs and solves optimization
Problem：So that0≤αi≤ C, i=1,2 ..., l, so as to obtain optimal solution
Step 6.3：Choose α*A positive component 0<α*<C, and threshold value b is calculated accordingly*：
Step 6.4：Construct decision function f (x)：
Step 6.5:Classification is exported according to decision function f (x) value.
After the completion of SVM training, point of the degenerate state recognition classifier model available for equipment degenerate state data is obtained
Class.And " the identification model checking " in Fig. 5 can " step 7 " middle completion below；
Step 7：The accuracy rate of Classification and Identification model is verified using test set sample data, passes through test set sample
The mode of notebook data injection verifies that classification results and actual classification result are predicted in contrast to the accuracy rate of sorter model,
Show that degenerate state identifies classification accuracy, so as to judge that can grader meet field demand.
Wherein, the field formula of the Kohonen networks described in step 3 is as follows：
Ni(t)=(t | find (norm (posc,post)<R)) t=1,2 ..., n
In formula, posc、postNeuron c and t position are represented respectively, and find is that distance searches function, and norm is used to calculate
Euclidean distance between two neurons, r are field radius, and η is learning rate.R, η typically with the increase of evolution number and
Linear decline；
R described in step 6nIt is n dimension real number spaces；
Sgn described in step 6 is a kind of sign function, for return an integer variable, it is indicated that parameter it is positive and negative
Number.The grammer of the function is sgn (number), and number parameters are any effective numerical expressions.If return value is digital
More than 0, then sgn returns to 1, and numeral is equal to 0, then returns to 0, and numeral is less than 0, then returns to -1, the symbol of digital parameters determines sgn
The return value of function；
By above-mentioned steps, the complex device degenerate state recognition methods based on Kohonen-SVM, its entirety can be completed
Implementation process is as shown in fig. 6, this method is obtained complexity and set by the unsupervised degenerate state excavation of Kohonen neutral nets
Standby typical degradation state sample collection data.Further, particle cluster algorithm is used on the basis of training sample data collection to SVM
Model parameter optimizes, and carries out Classification and Identification to degenerate state data by using the SVM models of optimization, has obtained complexity and set
Standby degenerate state identification model.Finally using test sample data to identifying that the accuracy of disaggregated model is verified, it was demonstrated that
This method identifies the feasibility of degenerate state.
Non-elaborated part of the present invention belongs to techniques well known.
It is described above, part embodiment only of the present invention, but protection scope of the present invention is not limited thereto, and is appointed
What those skilled in the art the invention discloses technical scope in, the change or replacement that can readily occur in should all be covered
Within protection scope of the present invention.
Claims (10)
- A kind of 1. complex device degenerate state recognition methods based on Kohonen-SVM, it is characterised in that：Its step is as follows：Step 1, the normal power data to complex device are acquired, and are rejected by way of artificial screening and wherein there may be Fault data and bad value data；Step 2, feature extraction-selection-dimensionality reduction is carried out to the power data after screening, the multidimensional for obtaining being used for input study is special Levy vector data；Step 3, multidimensional characteristic vectors data input is carried out to Unsupervised clustering study into Kohonen networks, obtain degeneration shape State sample set data；Step 4, division processing is carried out to degeneration sample set data, obtain SVM training sample sets data and test sample collection data；Step 5, on the basis of training sample set, using particle group optimizing method, to be PSO carry out optimizing to SVM parameter asks Solution；Step 6, parameter and training set sample data the progress SVM model learnings using optimization, obtain effectively identifying degeneration shape The SVM models of state, i.e. degenerate state identification model；Step 7, using test set sample data the accuracy rate of Classification and Identification model is verified；By above-mentioned steps, the complex device degenerate state recognition methods based on Kohonen-SVM can be realized, this method is based on The unsupervised degenerate state method for digging of Kohonen neutral nets, the typical degradation state sample collection data of equipment are obtained；Enter One step, SVM model parameters are optimized using PSO methods on the basis of training sample data collection, by using optimization SVM models carry out Classification and Identification to degenerate state data, have obtained the degenerate state identification model of complex device；Finally using survey Sample notebook data set pair identifies the Accuracy Verification of disaggregated model, to prove the feasibility of this method identification degenerate state.
- 2. a kind of complex device degenerate state recognition methods based on Kohonen-SVM according to claim 1, its feature It is：Described " power data " in step 1, during referring to device action, the real-time electricity of equipment is obtained by harvester Stream, magnitude of voltage, and the data of the sign equipment state obtained on the basis of these numerical value using computer automatic analysis；It is described " fault data ", when referring to that equipment running process breaks down, the abnormal power data that are detected by comparative analysis；It is described " bad value data ", refer in device action data acquisition, data value be less than collection regulation threshold power data, bad value The presence of data can influence the accuracy of plant capacity overall data.
- 3. a kind of complex device degenerate state recognition methods based on Kohonen-SVM according to claim 1, its feature It is：Described " carrying out feature extraction-selection-dimensionality reduction to the power data after screening " in step 2, its practice is as follows：To work( Rate data are divided into time domain data and codomain data, after the completion of division, proceed by the feature extraction work of data；For work( Rate time domain data, this method extraction average, variance, root mean square, kurtosis, inlet and outlet difference, minimax difference, peak factor, The pulse factor, difference and, the parameter such as shape factor is as characteristic；For performance number numeric field data, when this method extraction is maximum Between value, average value, data points, minimax difference, value median, maximum, time median and mode parameter as special Levy data；After the completion of extraction, using these characteristic construction feature vector spaces, entered using the method based on criterion function Row feature selecting；After feature selecting is completed, by principal component analysis, be locally linear embedding into carry out Feature Dimension Reduction, acquisition it is more Dimensional feature vector data.
- 4. a kind of complex device degenerate state recognition methods based on Kohonen-SVM according to claim 1, its feature It is：Described " multidimensional characteristic vectors data " in step 3, refer to that power data passes through feature extraction-selection-dimension-reduction treatment The data obtained afterwards, input data of the multidimensional characteristic vectors data as Kohonen networks, the cluster for degenerate state Practise；Described " Kohonen networks ", refers to a kind of Self-organizing Competition type neutral net；The network passes through self-organizing feature map Network weight is adjusted, neutral net is converged on a kind of expression form, a neuron is only to certain input in this form Pattern especially matching or sensitive；Kohonen networks are the feedforward neural networks comprising two layers of input layer and competition layer；Wherein, the 1st Layer is input layer, and the number of input layer is consistent with the dimension of input sample vector, and it is m to take input layer number； 2nd layer is competition layer, also referred to as output layer, and competition node layer is distributed in two-dimensional array, and it is n to take competition layer nodes；Input node Connected entirely with variable weight between output node, connection weight is unsupervised from group for the study of Kohonen networks Knit learning process；By unsupervised learning, different neurons can be sensitive to different input patterns in network, realizes specific god The detector of a certain input pattern can be served as in pattern-recognition through member；After the completion of study, neuron is divided into not same district Domain, each region have different response characteristics to input model.
- 5. a kind of complex device degenerate state recognition methods based on Kohonen-SVM according to claim 1, its feature It is：Described " multidimensional characteristic vectors data input is subjected to Unsupervised clustering study into Kohonen networks " in step 3, Its practice is as follows：By multidimensional characteristic vectors data input to network, the neuron on network competition layer calculate input sample with it is competing The Euclidean distance striven between layer neuron weights, the minimum neuron of distance is triumph neuron；Adjust triumph neuron With adjacent neurons weights, make triumph neuron and periphery weights close to the input sample；By repetition training, final each nerve The connection weight of member has certain distribution, the distribution the similitude tissue between data to representing under all kinds of neurons, Make similar neuron obvious with similar weight coefficient, inhomogeneous neuron weight coefficient difference；It should be noted that learning During, weights modification learning rate and neuron field are constantly being reduced, so that similar neuron is gradually concentrated, are completed The automatic cluster of input data, generate different classes of degenerate state sample set data.
- 6. a kind of complex device degenerate state recognition methods based on Kohonen-SVM according to claim 1, its feature It is：Described " carrying out division processing to degeneration sample set data " in step 4, its practice is as follows：To degenerate state sample set The number of samples of data carries out unified, it is specified that the number of samples of every kind of state is consistent, and presses 4:1 ratio divides every kind of sample For training set and test set；Training set data is used to carry out SVM modelings, and test set data are used to carry out degenerate state identification model Recognition accuracy test.
- 7. a kind of complex device degenerate state recognition methods based on Kohonen-SVM according to claim 1, its feature It is：Described " SVM " in step 4, refers to supporting vector machine model, and the model is proposed on the basis of statistical theory A kind of sorter model, for pattern classification, linear and nonlinear regression analysis；The method of SVMs is given instruction Practice sample, establish an Optimal Separating Hyperplane as decision-making curved surface, maximize the isolation edge between sample positive example and counter-example, from And complete the classification of training sample.
- 8. a kind of complex device degenerate state recognition methods based on Kohonen-SVM according to claim 1, its feature It is：Described " particle group optimizing method " in steps of 5, refer to a kind of optimized algorithm theoretical based on swarm intelligence, the algorithm The two-fold advantage learnt with self-teaching and to other people, can find optimal solution in less iterations.
- 9. a kind of complex device degenerate state recognition methods based on Kohonen-SVM according to claim 1, its feature It is：It is described in steps of 5 " right using particle group optimizing method (Particle Swarm Optimization, abbreviation PSO) SVM parameter carries out optimizing solution ", i.e., " optimizing solution is carried out to SVM parameter using PSO methods ", its practice is as follows：It is right SVM nuclear parameter g and penalty parameter c carries out optimizing solution, first, produces initialization population, each particle generation in population One potential optimal solution of table, each particle have three index expression its features：Position, speed and fitness value；Then, root The fitness value of each particle is calculated according to object function, the quality of the value represents the quality of particle, when particle is transported in solution space When dynamic, by track individual extreme value and colony's extreme value come the position of more new individual；Particle often updates a position, it is necessary to count again Fitness value is calculated, and fitness value and individual extreme value, the fitness value of colony's extreme value by comparing new particle are individual to update The position of body extreme value and colony's extreme value；Finally, when finding optimal solution good enough or reaching iterations, PSO algorithm knots Beam, export optimal nuclear parameter g and penalty parameter c.
- 10. a kind of complex device degenerate state recognition methods based on Kohonen-SVM according to claim 1, it is special Sign is：Described " carrying out SVM model learnings using the parameter after optimization and training set sample data " in step 6, its practice is such as Under：Step 6.1：If known training set：T={ (x1,y1),…,(xi,yi)}∈(X×Y)l, wherein, xiIt is characterized vector, yiFor Corresponding property value, xi∈X∈Rn, yi∈ Y={ -1,1 }, i=1,2 ..., l；Step 6.2：The kernel function g (x, x ') and appropriate punishment parameter C of PSO optimizations are chosen, constructs and solves optimization problem：So that0≤α i≤C, i=1,2 ..., l, so as to obtain optimal solutionStep 6.3：Choose α*A positive component 0<α*<C, and threshold value b is calculated accordingly*：Step 6.4：Construct decision function f (x)：Step 6.5:Classification is exported according to decision function f (x) value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710691675.9A CN107563414B (en) | 2017-08-14 | 2017-08-14 | A kind of complex device degenerate state recognition methods based on Kohonen-SVM |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710691675.9A CN107563414B (en) | 2017-08-14 | 2017-08-14 | A kind of complex device degenerate state recognition methods based on Kohonen-SVM |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107563414A true CN107563414A (en) | 2018-01-09 |
| CN107563414B CN107563414B (en) | 2018-05-29 |
Family
ID=60975504
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710691675.9A Active CN107563414B (en) | 2017-08-14 | 2017-08-14 | A kind of complex device degenerate state recognition methods based on Kohonen-SVM |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107563414B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109597315A (en) * | 2018-10-31 | 2019-04-09 | 华中科技大学 | A kind of mechanical equipment health degenerate state discrimination method, equipment and system |
| CN109856494A (en) * | 2019-01-02 | 2019-06-07 | 广东工业大学 | A kind of Diagnosis Method of Transformer Faults based on support vector machines |
| CN110033082A (en) * | 2019-03-19 | 2019-07-19 | 浙江工业大学 | A method of deep learning model in identification AI equipment |
| CN112418317A (en) * | 2020-11-24 | 2021-02-26 | 西南交通大学 | Method for identifying and classifying precision machining structural part based on PSO-SVM |
| CN113255795A (en) * | 2021-06-02 | 2021-08-13 | 杭州安脉盛智能技术有限公司 | Equipment state monitoring method based on multi-index cluster analysis |
| CN114397521A (en) * | 2021-12-24 | 2022-04-26 | 中国人民解放军海军航空大学 | Fault diagnosis method and system for electronic equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030002731A1 (en) * | 2001-05-28 | 2003-01-02 | Heiko Wersing | Pattern recognition with hierarchical networks |
| CN102609764A (en) * | 2012-02-01 | 2012-07-25 | 上海电力学院 | CPN neural network-based fault diagnosis method for stream-turbine generator set |
-
2017
- 2017-08-14 CN CN201710691675.9A patent/CN107563414B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030002731A1 (en) * | 2001-05-28 | 2003-01-02 | Heiko Wersing | Pattern recognition with hierarchical networks |
| CN102609764A (en) * | 2012-02-01 | 2012-07-25 | 上海电力学院 | CPN neural network-based fault diagnosis method for stream-turbine generator set |
Non-Patent Citations (2)
| Title |
|---|
| A. BAKHSHAI 等: "APPLICATION OF TIIE KOHONEN’CSOMPETITIVELAYERIN THE IMPLEMENTATION OF THE SPACE VECTOR MODULATIO", 《IEEE》 * |
| 李俭川 等: "贝叶斯网络理论及其在设备故障诊断中的应用", 《中国机械工程》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109597315A (en) * | 2018-10-31 | 2019-04-09 | 华中科技大学 | A kind of mechanical equipment health degenerate state discrimination method, equipment and system |
| CN109856494A (en) * | 2019-01-02 | 2019-06-07 | 广东工业大学 | A kind of Diagnosis Method of Transformer Faults based on support vector machines |
| CN110033082A (en) * | 2019-03-19 | 2019-07-19 | 浙江工业大学 | A method of deep learning model in identification AI equipment |
| CN110033082B (en) * | 2019-03-19 | 2021-05-18 | 浙江工业大学 | Method for identifying deep learning model in AI (Artificial intelligence) equipment |
| CN112418317A (en) * | 2020-11-24 | 2021-02-26 | 西南交通大学 | Method for identifying and classifying precision machining structural part based on PSO-SVM |
| CN113255795A (en) * | 2021-06-02 | 2021-08-13 | 杭州安脉盛智能技术有限公司 | Equipment state monitoring method based on multi-index cluster analysis |
| CN114397521A (en) * | 2021-12-24 | 2022-04-26 | 中国人民解放军海军航空大学 | Fault diagnosis method and system for electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107563414B (en) | 2018-05-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107563414B (en) | A kind of complex device degenerate state recognition methods based on Kohonen-SVM | |
| CN108062572A (en) | A kind of Fault Diagnosis Method of Hydro-generating Unit and system based on DdAE deep learning models | |
| CN109669087A (en) | A kind of method for diagnosing fault of power transformer based on Multi-source Information Fusion | |
| Han et al. | Information-utilization-method-assisted multimodal multiobjective optimization and application to credit card fraud detection | |
| CN103926526A (en) | Analog circuit fault diagnosis method based on improved RBF neural network | |
| CN102024179A (en) | Genetic algorithm-self-organization map (GA-SOM) clustering method based on semi-supervised learning | |
| Chang et al. | Enforced self‐organizing map neural networks for river flood forecasting | |
| Chen et al. | AI‐enhanced soil management and smart farming | |
| CN108366386A (en) | A method of using neural fusion wireless network fault detect | |
| CN106647272A (en) | Robot route planning method by employing improved convolutional neural network based on K mean value | |
| CN109255469A (en) | Merge the Forecasting Flood method of stack self-encoding encoder and support vector regression | |
| CN109902339A (en) | A kind of Fault Diagnosis of Roller Bearings based on IAGA-SVM | |
| Bong et al. | Multiobjective clustering with metaheuristic: current trends and methods in image segmentation | |
| Feng et al. | Spatial and temporal aware graph convolutional network for flood forecasting | |
| Wozniak et al. | Designing combining classifier with trained fuser—Analytical and experimental evaluation | |
| Mili et al. | A comparative study of expansion functions for evolutionary hybrid functional link artificial neural networks for data mining and classification | |
| Tsang et al. | Refinement of generated fuzzy production rules by using a fuzzy neural network | |
| Ismail et al. | River flow forecasting: a hybrid model of self organizing maps and least square support vector machine | |
| Baruque et al. | Hybrid classification ensemble using topology-preserving clustering | |
| CN112465253B (en) | Method and device for predicting links in urban road network | |
| CN114861792A (en) | Complex power grid key node identification method based on deep reinforcement learning | |
| Bao et al. | Back Propagation Optimization of Convolutional Neural Network Based on the left and the right hands Identification | |
| Gupta et al. | Selection of input variables for the prediction of wind speed in wind farms based on genetic algorithm | |
| Gonsalves et al. | Data clustering through particle swarm optimization driven self-organizing maps | |
| Marca¹ et al. | Check for updates Approximating Pareto Set Topology by Cubic Interpolation on Bi-objective Problems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |