CN107192951A - A kind of micro- method for diagnosing faults of wind-driven generator three-phase rotor current - Google Patents
A kind of micro- method for diagnosing faults of wind-driven generator three-phase rotor current Download PDFInfo
- Publication number
- CN107192951A CN107192951A CN201710640172.9A CN201710640172A CN107192951A CN 107192951 A CN107192951 A CN 107192951A CN 201710640172 A CN201710640172 A CN 201710640172A CN 107192951 A CN107192951 A CN 107192951A
- Authority
- CN
- China
- Prior art keywords
- mrow
- micro
- msub
- fault
- munderover
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/34—Testing dynamo-electric machines
- G01R31/346—Testing of armature or field windings
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Control Of Eletrric Generators (AREA)
Abstract
The invention discloses a kind of micro- method for diagnosing faults of wind-driven generator three-phase rotor current, comprise the following steps：Step one：Carry out three-phase rotor current fault message to extract, obtain training dataset, confirm data set and test data set；Step 2：The double-deck sparse Bayesian extreme learning machine model of construction；Step 3：Pairing multi-tag sorting technique is created, and combines double-deck sparse Bayesian extreme learning machine and builds the grader collection based on micro- fault diagnosis algorithm model；Step 4：It is trained using the micro- fault diagnosis algorithm model of training data set pair, and by confirming that data set and glowworm swarm algorithm carry out dynamic optimization iteration, finally determines optimized parameter, complete micro- fault diagnosis algorithm model；Step 5：Test data set is input in micro- fault diagnosis algorithm model, the diagnostic result of micro- failure is obtained.The present invention can be diagnosed to the micro- failure of wind-driven generator three-phase rotor current, have the advantages that diagnosis efficiency is high, it is high to diagnose accuracy.
Description
Technical field
The present invention relates to a kind of current failure diagnostic method, more particularly to a kind of micro- event of wind-driven generator three-phase rotor current
Hinder diagnostic method.
Background technology
Wind power generating set is for a long time always by the way of planned maintenance, and this maintenance mode can not comprehensively, in time
Ground understands the operation conditions of equipment；And correction maintenance is then because prior preparation is not abundant enough, causing maintenance work, time-consuming, damages
Lose serious.In recent years, domestic and foreign scholars are conducted extensive research and achieved good to the notable fault diagnosis of wind-driven generator
Good effect, but because the wind power system normally run can also produce a certain degree of fluctuation, cause to occur in systems is micro-
Glitch is often submerged in noise or the significant major break down of sign because its sign is smaller, signal is fainter.This causes
Traditional diagnosis method gets up relatively difficult to the signal transacting for being mixed with Weak fault, it is therefore necessary to which existing diagnostic method is carried out
New method is effectively improved or sets up just to be expected to realize the diagnosis to micro- failure.
The content of the invention
In order to solve the above-mentioned technical problem, the present invention provides the wind-power electricity generation that a kind of diagnosis efficiency is high, diagnosis accuracy is high
The micro- method for diagnosing faults of machine three-phase rotor current.
Technical proposal that the invention solves the above-mentioned problems is：A kind of micro- fault diagnosis side of wind-driven generator three-phase rotor current
Method, comprises the following steps：
Step one：Three-phase rotor current fault message is carried out based on depth belief network to extract, and obtains training dataset, really
Recognize data set and test data set；
Step 2：Based on sparse Bayesian extreme learning machine, increase the weight module layer being connected with output layer, structure
Make double-deck sparse Bayesian extreme learning machine model；
Step 3：Pairing strategy is introduced into multi-tag sorting technique, pairing multi-tag sorting technique is created, and combine double
Layer sparse Bayesian extreme learning machine builds the grader collection based on micro- fault diagnosis algorithm model；
Step 4：Be trained using the micro- fault diagnosis algorithm model of training data set pair, and by confirm data set with
And glowworm swarm algorithm carries out dynamic optimization iteration, optimized parameter is finally determined, micro- fault diagnosis algorithm model is completed；
Step 5：Test data set is input in micro- fault diagnosis algorithm model, the diagnostic result of micro- failure is obtained.
In the above-mentioned micro- method for diagnosing faults of wind-driven generator three-phase rotor current, the step one, sensed with Hall current
Device measures the three-phase rotor current of wind-driven generator, and current signal carries out sending into PC terminals, PC after signal modulation and analog-to-digital conversion
Terminal, which is received, carries out the extraction of depth belief network fault message after signal, will be carried by fuzzy clustering and fuzzy neuron network
The fault message taken is divided into two classes, and a class is notable fault data, and a class is small fault data；Small fault data are carried out
Classification, is divided into training dataset, is defined as d1；Confirm data set, be defined as d2；Test data set, is defined as d3.
In the above-mentioned micro- method for diagnosing faults of wind-driven generator three-phase rotor current, the step 2, with d hidden layer section
Point double-deck sparse Bayesian extreme learning machine model be：
Wherein n is hidden layer number, and w is hidden layer weights, and β is output layer weights, h (θ, xn,j)=[1, h1(θ1,
xn,j),…,hd(θd,xn,j)]TIt is j-th of hidden layer node relative to input sample xn,jOutput, input sample xn,jBelong to instruction
Practice data set, HnFor input xn,jHidden layer output matrix.
In the above-mentioned micro- method for diagnosing faults of wind-driven generator three-phase rotor current, the step 3, the fault type collection is made to be
M, fault mode number is d, and the grader of micro- fault diagnosis algorithm model integrates as C=(C1,C2,…,Cd), each grader
Cl(l=1,2 ..., d) include d-1 sub-classifier Cls, wherein s ≠ l, s=1,2 ..., d, ClsRepresent l kinds fault mode and
The sample of s kind fault modes is trained, due to ClsAnd CslEquivalence, therefore in C sub-classifier sum be d (d-1)/2, Pl
The probability of happening of l kind fault modes is represented, is defined as：
plsFor sub-classifier ClsThe result of output, xlsConcentrated for training data and belong to l kinds fault mode and the event of s kinds
The sample of barrier pattern.
In the above-mentioned micro- method for diagnosing faults of wind-driven generator three-phase rotor current, the step 4, training dataset is utilized
Micro- fault diagnosis algorithm model is trained, diagnosis algorithm is evaluated followed by performance evaluation formula；In failure judgement
During the probability of generation, judgment threshold is introduced, more than the threshold value, then is judged as there occurs failure, otherwise, judging should without generation
Failure；In order to obtain optimal diagnostic threshold εj, hidden layer weight wj, output layer weights βj, by parameter (εj,wj,βj) pass through firefly
Fireworm algorithm iteration formula：Optimizing iteration is carried out, here xi(t+1) it is the
Position vector of the i firefly individual at the t+1 moment, xj(t) it is j-th of the individual position vector in t of firefly,For the Attraction Degree of firefly, α is the random number between 0 to 1；When performance evaluation formula value is interval at [90%, 95%],
Complete iteration and determine three optimized parameter (ε-opt,w-opt,β-opt), (ε-opt,w-opt,β-opt) three parameters mean after determining
Micro- fault diagnosis algorithm model structure is determined.
In the above-mentioned micro- method for diagnosing faults of wind-driven generator three-phase rotor current, the step 4, Performance Evaluation formula is
Wherein, pilFor the data x of input validation sample setiThe probability of obtained l kind fault modes；tilFor input input
The data x of sample setiThe percentage of corresponding l kind fault modes, N is actual coupling fault number of modes.
The beneficial effects of the present invention are：The present invention is using three-phase rotor current as Study of Support, based on depth belief network
Carry out three-phase rotor current fault message to extract, reduce conventional method because artificial participation causes the uncertain of feature extraction
Property；It is then based on the classification of pairing multi-tag and double-deck sparse Bayesian extreme learning machine is combined construction probability classification collection；Again
Independent confirmation sample set, object function are combined it with intelligent optimization algorithm, dynamic optimization is carried out using glowworm swarm algorithm
Iteration determines PMLC-DLELM optimized parameters, completes micro- fault diagnosis algorithm model；Finally obtain the diagnostic result of micro- failure；This
Invention has the advantages that diagnosis efficiency is high, it is high to diagnose accuracy.
Brief description of the drawings
Fig. 1 is diagnostic flow chart of the invention.
Fig. 2 is the structure chart of feature of present invention extraction element.
Fig. 3 sets up the schematic diagram of double-deck sparse Bayesian extreme learning machine model for the present invention.
Fig. 4 builds the schematic diagram of micro- fault diagnosis algorithm model for the present invention.
Fig. 5 carries out the schematic diagram of dynamic optimization iteration for present invention application glowworm swarm algorithm.
Embodiment
The present invention is further illustrated with reference to the accompanying drawings and examples.
As shown in figure 1, the present invention is a kind of micro- method for diagnosing faults of wind-driven generator three-phase rotor current, including following step
Suddenly：
Step one：Three-phase rotor current fault message is carried out based on depth belief network (DBN) to extract.
The failure of various kinds of equipment can be reflected directly in the stator current of wind-driven generator in Wind turbines main drive chain, and
Current signal collection then belongs to contactless, as shown in Fig. 2 harvester mainly includes Hall current sensor, signal condition
And A/D change-over circuits, industrial computer, wireless signal transmission and receiving module and PC.
Signal condition is carried out after the three-phase rotor current that wind-driven generator is measured using Hall current sensor and modulus turns
Change, signal is transmitted in industrial computer by wireless transmitter module and receiving module, and user passes through PC terminal received signals
Depth belief network (DBN) is carried out afterwards and glowworm swarm algorithm-extreme learning machine (FA-ELM) carries out fault message extraction.
When being extracted to fault sample, successively unsupervised training DBN model first, then using reversely fine setting algorithm
Training is carried out to depth belief network (DBN) model, testing data collection is finally input to the DBN model trained
In, record the output vector of each hidden layer.
The training of depth belief network (DBN) includes calculating to the unsupervised self-training process of RBM networks and using FA-ELM
Method is adjusted the process of training, and sdpecific dispersion algorithm (FPCD) is trained to network model using Fast Persistence.
Fault signature extraction is carried out to gathered data using depth belief network (DBN), then passes through fuzzy clustering and mould
Paste neuroid is classified as two classes, and a class is notable fault data, and a class is small fault data.Present invention is generally directed to
Micro- failure is studied, and capable diagnosis can be tapped into using depth belief network (DBN) for notable failure.
For micro- characteristic vector, three parts are divided into after sample data is handled：That is training dataset X-Train, it is used for
Micro- fault diagnosis algorithm model is trained；Confirm data set X-Vail, pass through glowworm swarm algorithm (FA) and object function F-meBuild
Vertical optimizing iterative relation, determines three optimized parameter (ε-opt,w-opt,β-opt)；Test data set X-Test, obtain examining for micro- failure
Disconnected result.
Step 2：As shown in figure 3, setting up double-deck sparse Bayesian extreme learning machine model, wherein wiFor hidden layer weights,
βjFor unknown weights.
Based on sparse Bayesian extreme learning machine (SBELM), the unknown weight mould being connected with output layer is added
Block layer, constructs double-deck sparse Bayesian extreme learning machine (DLELM) model, and the model sets one to surpass for each output weights
Parameter, and in the study stage by the way that part is exported into weighed value adjusting for 0 to obtain hidden layer simple in construction, so as to improve
Efficiency is practised, makes model that there is probability output, high generalization, openness, Fast Learning.
Double-deck sparse Bayesian extreme learning machine model with d hidden layer node is：
Wherein n is hidden layer number, and w is hidden layer weights, and β is output layer weights, h (θ, xn,j)=[1, h1(θ1,
xn,j),…,hd(θd,xn,j)]TIt is j-th of hidden layer node relative to input sample xn,jOutput, input sample xn,jBelong to instruction
Practice data set, HnFor input xn,jHidden layer output matrix.
Step 3：As shown in figure 4, due to there is certain correlation between each fault mode, in order to improve classification
Pairing strategy is introduced into multi-tag sorting technique by accuracy, the present invention, creates pairing multi-tag sorting technique, and be directed to micro-
Fault diagnosis, builds micro- fault grader collection based on double-deck sparse Bayesian extreme learning machine.
Fault type is made to integrate as M, fault mode number is d, and the grader of micro- fault diagnosis algorithm model integrates as C=
(C1,C2,…,Cd), each grader Cl(l=1,2 ..., d) include d-1 sub-classifier Cls, wherein s ≠ l, s=1,2 ...,
D, ClsIt is trained with the sample for belonging to l kinds fault mode and s kind fault modes, due to ClsAnd CslEquivalence, therefore C
Middle sub-classifier sum is d (d-1)/2, PlThe probability of happening of l kind fault modes is represented, is defined as：
plsFor sub-classifier ClsThe result of output, xlsConcentrated for training data and belong to l kinds fault mode and the event of s kinds
The sample of barrier pattern.
Step 4：As shown in figure 5, be trained using the micro- fault diagnosis algorithm model of training data set pair, and by true
Recognize data set and glowworm swarm algorithm carries out dynamic optimization iteration, finally determine optimized parameter, complete micro- fault diagnosis algorithm mould
Type.
The result of category set generation based on micro- fault diagnosis algorithm model is a d dimensional vector p=(p1,p2,…,pd),
It is trained using the micro- fault diagnosis algorithm model of training data set pair, diagnosis is evaluated followed by performance evaluation formula and is calculated
Method, Performance Evaluation formula is
Wherein, pilFor the data x of input validation sample setiThe probability of obtained l kind fault modes；tilFor input validation
The data x of sample setiThe percentage of corresponding l kind fault modes, N is actual coupling fault number of modes.
In the probability that failure judgement occurs, judgment threshold is introduced, more than the threshold value, then is judged as there occurs failure,
Otherwise, judge do not occur the failure；In order to obtain optimal diagnostic threshold εj, hidden layer weight wj, output layer weights βj, will
Parameter (εj,wj,βj) pass through glowworm swarm algorithm iterative formula：Carry out optimizing
Iteration, here xi(t+1) position vector for i-th of firefly individual at the t+1 moment, xj(t) it is j-th of firefly individual
In the position vector of t,For the Attraction Degree of firefly, α is the random number between 0 to 1；When Performance Evaluation formula value
When [90%, 95%] is interval, completes iteration and determine three optimized parameter (ε-opt,w-opt,β-opt), (ε-opt,w-opt,β-opt)
Three parameters mean that micro- fault diagnosis algorithm model structure is determined after determining.
Step 5：The diagnostic result of micro- failure is obtained by test data set.
Finally test data set X-TestIn generation, to having determined that in micro- fault diagnosis algorithm model of structure, is tested and is obtained
To the diagnostic result of micro- failure.
Claims (6)
1. a kind of micro- method for diagnosing faults of wind-driven generator three-phase rotor current, comprises the following steps：
Step one：Three-phase rotor current fault message is carried out based on depth belief network to extract, and is obtained training dataset, is confirmed number
According to collection and test data set；
Step 2：Based on sparse Bayesian extreme learning machine, increase the weight module layer being connected with output layer, construction is double
Layer sparse Bayesian extreme learning machine model；
Step 3：Pairing strategy is introduced into multi-tag sorting technique, pairing multi-tag sorting technique is created, and combine double-deck dilute
Dredge Bayes's extreme learning machine and build the grader collection based on micro- fault diagnosis algorithm model；
Step 4：It is trained using the micro- fault diagnosis algorithm model of training data set pair, and by confirming data set and firefly
Fireworm algorithm carries out dynamic optimization iteration, finally determines optimized parameter, completes micro- fault diagnosis algorithm model；
Step 5：Test data set is input in micro- fault diagnosis algorithm model, the diagnostic result of micro- failure is obtained.
2. the micro- method for diagnosing faults of wind-driven generator three-phase rotor current according to claim 1, it is characterised in that：It is described
In step one, with Hall current sensor measure wind-driven generator three-phase rotor current, current signal carry out signal modulation and
PC terminals are sent into after analog-to-digital conversion, PC terminals, which are received, carries out the extraction of depth belief network fault message after signal, by fuzzy
The fault message of extraction is divided into two classes by cluster and fuzzy neuron network, and a class is notable fault data, and a class is small event
Hinder data；Small fault data are classified, are divided into training dataset, d1 is defined as；Confirm data set, be defined as d2；Survey
Data set is tried, d3 is defined as.
3. the micro- method for diagnosing faults of wind-driven generator three-phase rotor current according to claim 2, it is characterised in that：It is described
In step 2, the double-deck sparse Bayesian extreme learning machine model with d hidden layer node is：
<mrow>
<msub>
<mi>P</mi>
<mi>n</mi>
</msub>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>d</mi>
</munderover>
<mrow>
<mo>(</mo>
<msup>
<mi>w</mi>
<mi>T</mi>
</msup>
<mi>h</mi>
<mo>(</mo>
<mrow>
<mi>&theta;</mi>
<mo>,</mo>
<msub>
<mi>x</mi>
<mrow>
<mi>n</mi>
<mo>,</mo>
<mi>j</mi>
</mrow>
</msub>
</mrow>
<mo>)</mo>
<mo>)</mo>
</mrow>
<msub>
<mi>&beta;</mi>
<mi>j</mi>
</msub>
<mo>=</mo>
<msup>
<mi>w</mi>
<mi>T</mi>
</msup>
<msub>
<mi>H</mi>
<mi>n</mi>
</msub>
<mi>&beta;</mi>
</mrow>
Wherein n is hidden layer number, and w is hidden layer weights, and β is output layer weights, h (θ, xn,j)=[1, h1(θ1,xn,j),…,
hd(θd,xn,j)]TIt is j-th of hidden layer node relative to input sample xn,jOutput, input sample xn,jBelong to training data
Collection, HnFor input xn,jHidden layer output matrix.
4. the micro- method for diagnosing faults of wind-driven generator three-phase rotor current according to claim 3, it is characterised in that：It is described
In step 3, fault type is made to integrate as M, fault mode number is d, and the grader of micro- fault diagnosis algorithm model integrates as C=
(C1,C2,…,Cd), each grader Cl(l=1,2 ..., d) include d-1 sub-classifier Cls, wherein s ≠ l, s=1,2 ...,
D, ClsRepresent that l kinds fault mode and the sample of s kind fault modes are trained, due to ClsAnd CslEquivalence, therefore in C
Sub-classifier sum is d (d-1)/2, PlThe probability of happening of l kind fault modes is represented, is defined as：
<mrow>
<msub>
<mi>P</mi>
<mi>l</mi>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>s</mi>
<mo>=</mo>
<mn>1</mn>
<mo>,</mo>
<mi>s</mi>
<mo>&NotEqual;</mo>
<mi>l</mi>
</mrow>
<mi>d</mi>
</munderover>
<msub>
<mi>x</mi>
<mrow>
<mi>l</mi>
<mi>s</mi>
</mrow>
</msub>
<msub>
<mi>p</mi>
<mrow>
<mi>l</mi>
<mi>s</mi>
</mrow>
</msub>
</mrow>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>s</mi>
<mo>=</mo>
<mn>1</mn>
<mo>,</mo>
<mi>s</mi>
<mo>&NotEqual;</mo>
<mi>i</mi>
</mrow>
<mi>d</mi>
</munderover>
<msub>
<mi>x</mi>
<mrow>
<mi>l</mi>
<mi>s</mi>
</mrow>
</msub>
</mrow>
</mfrac>
</mrow>
plsFor sub-classifier ClsThe result of output, xlsConcentrated for training data and belong to l kinds fault mode and s kind failure moulds
The sample of formula.
5. the micro- method for diagnosing faults of wind-driven generator three-phase rotor current according to claim 4, it is characterised in that：It is described
In step 4, it is trained, is come followed by performance evaluation formula using the micro- fault diagnosis algorithm model of training data set pair
Evaluate diagnosis algorithm；In the probability that failure judgement occurs, judgment threshold is introduced, more than the threshold value, then is judged as there occurs
The failure does not occur for failure, otherwise, judgement；In order to obtain optimal diagnostic threshold εj, hidden layer weight wj, output layer weights
βj, by parameter (εj,wj,βj) pass through glowworm swarm algorithm iterative formula：Carry out
Optimizing iteration, here xi(t+1) position vector for i-th of firefly individual at the t+1 moment, xj(t) it is j-th of firefly
The individual position vector in t,For the Attraction Degree of firefly, α is the random number between 0 to 1；When performance evaluation formula
Value completes iteration and determines three optimized parameter (ε when [90%, 95%] is interval-opt,w-opt,β-opt), (ε-opt,w-opt,
β-opt) three parameters mean that micro- fault diagnosis algorithm model structure is determined after determining.
6. the micro- method for diagnosing faults of wind-driven generator three-phase rotor current according to claim 5, it is characterised in that：It is described
In step 4, performance evaluation formula is
<mrow>
<msub>
<mi>F</mi>
<mrow>
<mi>m</mi>
<mi>e</mi>
</mrow>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<mn>2</mn>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>l</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>d</mi>
</munderover>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>p</mi>
<mrow>
<mi>i</mi>
<mi>l</mi>
</mrow>
</msub>
<msub>
<mi>t</mi>
<mrow>
<mi>i</mi>
<mi>l</mi>
</mrow>
</msub>
</mrow>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>l</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>d</mi>
</munderover>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>p</mi>
<mrow>
<mi>i</mi>
<mi>l</mi>
</mrow>
</msub>
<mo>+</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>l</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>d</mi>
</munderover>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>t</mi>
<mrow>
<mi>i</mi>
<mi>l</mi>
</mrow>
</msub>
</mrow>
</mfrac>
</mrow>
Wherein, pilFor the data x of input validation sample setiThe probability of obtained l kind fault modes；tilFor input sample collection
Data xiThe percentage of corresponding l kind fault modes, N is actual coupling fault number of modes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710640172.9A CN107192951B (en) | 2017-07-31 | 2017-07-31 | A kind of micro- method for diagnosing faults of wind-driven generator three-phase rotor current |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710640172.9A CN107192951B (en) | 2017-07-31 | 2017-07-31 | A kind of micro- method for diagnosing faults of wind-driven generator three-phase rotor current |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107192951A true CN107192951A (en) | 2017-09-22 |
| CN107192951B CN107192951B (en) | 2019-07-23 |
Family
ID=59884930
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710640172.9A Active CN107192951B (en) | 2017-07-31 | 2017-07-31 | A kind of micro- method for diagnosing faults of wind-driven generator three-phase rotor current |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107192951B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108152738A (en) * | 2017-12-25 | 2018-06-12 | 深圳怡化电脑股份有限公司 | Motor work condition inspection method and its device |
| CN108256556A (en) * | 2017-12-22 | 2018-07-06 | 上海电机学院 | Wind-driven generator group wheel box method for diagnosing faults based on depth belief network |
| CN108304927A (en) * | 2018-01-25 | 2018-07-20 | 清华大学 | Bearing fault modality diagnostic method and system based on deep learning |
| CN108646725A (en) * | 2018-07-31 | 2018-10-12 | 河北工业大学 | Dual model method for diagnosing faults based on dynamic weighting |
| CN109444740A (en) * | 2018-11-14 | 2019-03-08 | 湖南大学 | A kind of the malfunction intellectual monitoring and diagnostic method of Wind turbines |
| CN109711062A (en) * | 2018-12-28 | 2019-05-03 | 广东电网有限责任公司 | A kind of equipment fault diagnosis method and device based on cloud service |
| CN110046562A (en) * | 2019-04-01 | 2019-07-23 | 湖南大学 | A kind of wind power system health monitor method and device |
| CN111458640A (en) * | 2020-04-22 | 2020-07-28 | 西安交通大学 | Three-phase current-based alternating current asynchronous motor rotor broken bar fault diagnosis method |
| CN111695611A (en) * | 2020-05-27 | 2020-09-22 | 电子科技大学 | Bee colony optimization kernel extreme learning and sparse representation mechanical fault identification method |
| CN111812504A (en) * | 2019-04-10 | 2020-10-23 | 北京金风科创风电设备有限公司 | Fault diagnosis method and system for wind generating set |
| CN112798956A (en) * | 2020-12-31 | 2021-05-14 | 江苏国科智能电气有限公司 | Wind turbine generator fault diagnosis method based on multi-resolution time sequence cyclic neural network |
| CN113361372A (en) * | 2021-06-02 | 2021-09-07 | 长江大学 | Main reducer multi-fault intelligent diagnosis method based on multi-channel data deep mining |
| CN113364362A (en) * | 2021-06-30 | 2021-09-07 | 青岛恒星智能装备有限公司 | Firefly optimization-based induction motor rotation speed estimation method |
| CN114298079A (en) * | 2021-07-20 | 2022-04-08 | 齐丰科技股份有限公司 | Transformer substation high-voltage circuit breaker fault diagnosis method based on coil current signals |
| CN114822823A (en) * | 2022-05-11 | 2022-07-29 | 云南升玥信息技术有限公司 | Tumor fine classification system based on cloud computing and artificial intelligence fusion multi-dimensional medical data |
| CN115267538A (en) * | 2022-09-27 | 2022-11-01 | 江苏中工高端装备研究院有限公司 | Demagnetization fault detection system of permanent magnet synchronous motor |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105606914A (en) * | 2015-09-06 | 2016-05-25 | 南京航空航天大学 | IWO-ELM-based Aviation power converter fault diagnosis method |
| CN105976051A (en) * | 2016-04-29 | 2016-09-28 | 武汉大学 | Wavelet transformation and improved firefly-optimized extreme learning machine-based short-term load prediction method |
| CN106707221A (en) * | 2017-01-05 | 2017-05-24 | 云南电网有限责任公司电力科学研究院 | Fault diagnosis method and system for sensor in electric energy metering device |
| CN106874934A (en) * | 2017-01-12 | 2017-06-20 | 华南理工大学 | Sewage disposal method for diagnosing faults based on weighting extreme learning machine Integrated Algorithm |
-
2017
- 2017-07-31 CN CN201710640172.9A patent/CN107192951B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105606914A (en) * | 2015-09-06 | 2016-05-25 | 南京航空航天大学 | IWO-ELM-based Aviation power converter fault diagnosis method |
| CN105976051A (en) * | 2016-04-29 | 2016-09-28 | 武汉大学 | Wavelet transformation and improved firefly-optimized extreme learning machine-based short-term load prediction method |
| CN106707221A (en) * | 2017-01-05 | 2017-05-24 | 云南电网有限责任公司电力科学研究院 | Fault diagnosis method and system for sensor in electric energy metering device |
| CN106874934A (en) * | 2017-01-12 | 2017-06-20 | 华南理工大学 | Sewage disposal method for diagnosing faults based on weighting extreme learning machine Integrated Algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 赵光权 等: "基于DBN 的故障特征提取及诊断方法研究", 《仪器仪表学报》 * |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108256556A (en) * | 2017-12-22 | 2018-07-06 | 上海电机学院 | Wind-driven generator group wheel box method for diagnosing faults based on depth belief network |
| CN108152738A (en) * | 2017-12-25 | 2018-06-12 | 深圳怡化电脑股份有限公司 | Motor work condition inspection method and its device |
| CN108304927A (en) * | 2018-01-25 | 2018-07-20 | 清华大学 | Bearing fault modality diagnostic method and system based on deep learning |
| CN108646725A (en) * | 2018-07-31 | 2018-10-12 | 河北工业大学 | Dual model method for diagnosing faults based on dynamic weighting |
| CN109444740B (en) * | 2018-11-14 | 2020-10-02 | 湖南大学 | Intelligent fault state monitoring and diagnosing method for wind turbine generator |
| CN109444740A (en) * | 2018-11-14 | 2019-03-08 | 湖南大学 | A kind of the malfunction intellectual monitoring and diagnostic method of Wind turbines |
| CN109711062A (en) * | 2018-12-28 | 2019-05-03 | 广东电网有限责任公司 | A kind of equipment fault diagnosis method and device based on cloud service |
| CN110046562A (en) * | 2019-04-01 | 2019-07-23 | 湖南大学 | A kind of wind power system health monitor method and device |
| CN110046562B (en) * | 2019-04-01 | 2021-01-26 | 湖南大学 | Health monitoring method and device for wind power system |
| CN111812504A (en) * | 2019-04-10 | 2020-10-23 | 北京金风科创风电设备有限公司 | Fault diagnosis method and system for wind generating set |
| CN111458640A (en) * | 2020-04-22 | 2020-07-28 | 西安交通大学 | Three-phase current-based alternating current asynchronous motor rotor broken bar fault diagnosis method |
| CN111458640B (en) * | 2020-04-22 | 2021-05-28 | 西安交通大学 | Three-phase current-based alternating current asynchronous motor rotor broken bar fault diagnosis method |
| CN111695611A (en) * | 2020-05-27 | 2020-09-22 | 电子科技大学 | Bee colony optimization kernel extreme learning and sparse representation mechanical fault identification method |
| CN111695611B (en) * | 2020-05-27 | 2022-05-03 | 电子科技大学 | Bee colony optimization kernel extreme learning and sparse representation mechanical fault identification method |
| CN112798956A (en) * | 2020-12-31 | 2021-05-14 | 江苏国科智能电气有限公司 | Wind turbine generator fault diagnosis method based on multi-resolution time sequence cyclic neural network |
| CN113361372A (en) * | 2021-06-02 | 2021-09-07 | 长江大学 | Main reducer multi-fault intelligent diagnosis method based on multi-channel data deep mining |
| CN113364362A (en) * | 2021-06-30 | 2021-09-07 | 青岛恒星智能装备有限公司 | Firefly optimization-based induction motor rotation speed estimation method |
| CN113364362B (en) * | 2021-06-30 | 2023-03-24 | 青岛恒星智能装备有限公司 | Firefly optimization-based induction motor rotation speed estimation method |
| CN114298079A (en) * | 2021-07-20 | 2022-04-08 | 齐丰科技股份有限公司 | Transformer substation high-voltage circuit breaker fault diagnosis method based on coil current signals |
| CN114298079B (en) * | 2021-07-20 | 2024-08-06 | 齐丰科技股份有限公司 | Transformer substation high-voltage circuit breaker fault diagnosis method based on coil current signals |
| CN114822823A (en) * | 2022-05-11 | 2022-07-29 | 云南升玥信息技术有限公司 | Tumor fine classification system based on cloud computing and artificial intelligence fusion multi-dimensional medical data |
| CN115267538A (en) * | 2022-09-27 | 2022-11-01 | 江苏中工高端装备研究院有限公司 | Demagnetization fault detection system of permanent magnet synchronous motor |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107192951B (en) | 2019-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107192951A (en) | A kind of micro- method for diagnosing faults of wind-driven generator three-phase rotor current | |
| CN110135079B (en) | Macroscopic elasticity evaluation method and system for offshore oil well control equipment | |
| CN110579709B (en) | Fault diagnosis method for proton exchange membrane fuel cell for tramcar | |
| CN102944418B (en) | Wind turbine generator group blade fault diagnosis method | |
| CN105846780B (en) | A kind of photovoltaic module method for diagnosing faults based on decision-tree model | |
| CN107884475A (en) | A kind of city gas pipeline method for diagnosing faults based on deep learning neutral net | |
| CN104751229A (en) | Bearing fault diagnosis method capable of recovering missing data of back propagation neural network estimation values | |
| CN104809722A (en) | Electrical device fault diagnosis method based on infrared thermography | |
| CN104915747A (en) | Electricity generation performance evaluation method of generator set and equipment thereof | |
| CN101726688A (en) | Method for diagnosing multi-data-source information fusion-based power system fault | |
| CN107563069A (en) | A kind of wind power generating set intelligent fault diagnosis method | |
| CN109297689A (en) | A kind of large-scale hydraulic intelligent diagnosing method introducing weight factor | |
| CN110555478B (en) | Fan multi-fault diagnosis method based on depth measurement network of difficult sample mining | |
| CN107153845A (en) | A kind of isolated island detection method of the adaptive grid-connected photovoltaic system based on machine learning | |
| CN109376801A (en) | Blade of wind-driven generator icing diagnostic method based on integrated deep neural network | |
| CN103064008A (en) | Nolinear analog circuit soft fault diagnostic method based on Hilbert-huang transform | |
| CN104748962A (en) | Planetary gear box intelligent diagnosis method based on stacking automatic encoding machine | |
| CN110595778B (en) | Wind turbine generator bearing fault diagnosis method based on MMF and IGRA | |
| CN104616061A (en) | Island detection method based on wavelet packet logarithmic energy entropy and genetic algorithm optimization | |
| CN105388884A (en) | Alarm system for detecting leakage fault of heat supply network based on identification algorithm driven by data and method | |
| CN112327189A (en) | KNN algorithm-based energy storage battery health state comprehensive judgment method | |
| CN107036808A (en) | Gearbox of wind turbine combined failure diagnostic method based on SVMs probability Estimation | |
| CN115235766A (en) | IWOA-based improved LightGBM-based fan main shaft bearing fault diagnosis method | |
| CN116778272A (en) | Hydropower unit small sample working condition identification method based on multichannel information fusion | |
| CN111091141A (en) | Photovoltaic backboard fault diagnosis method based on layered Softmax |
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 |