CN109657647A - A kind of Fault Diagnosis Method of Hydro-generating Unit based on information fusion technology - Google Patents
A kind of Fault Diagnosis Method of Hydro-generating Unit based on information fusion technology Download PDFInfo
- Publication number
- CN109657647A CN109657647A CN201910020679.3A CN201910020679A CN109657647A CN 109657647 A CN109657647 A CN 109657647A CN 201910020679 A CN201910020679 A CN 201910020679A CN 109657647 A CN109657647 A CN 109657647A
- Authority
- CN
- China
- Prior art keywords
- hydro
- information fusion
- generating unit
- fault
- neural 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 48
- 230000004927 fusion Effects 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000005516 engineering process Methods 0.000 title claims abstract description 22
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 31
- 241000544061 Cuculus canorus Species 0.000 claims abstract description 24
- 238000012549 training Methods 0.000 claims abstract description 15
- 238000003062 neural network model Methods 0.000 claims abstract description 9
- 238000012360 testing method Methods 0.000 claims abstract description 8
- 238000013528 artificial neural network Methods 0.000 claims description 29
- 230000006870 function Effects 0.000 claims description 17
- 238000005457 optimization Methods 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 7
- 238000009826 distribution Methods 0.000 claims description 7
- 238000012546 transfer Methods 0.000 claims description 7
- 239000000203 mixture Substances 0.000 claims description 6
- 238000005295 random walk Methods 0.000 claims description 6
- 230000006978 adaptation Effects 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 4
- 230000001133 acceleration Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000000977 initiatory effect Effects 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 241000208340 Araliaceae Species 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 238000012804 iterative process Methods 0.000 abstract 1
- 239000008186 active pharmaceutical agent Substances 0.000 description 4
- 238000012706 support-vector machine Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 241000272177 Cuculiformes Species 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Signal Processing (AREA)
- Bioinformatics & Computational Biology (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a kind of Fault Diagnosis Method of Hydro-generating Unit based on information fusion technology, firstly, extracting the characteristic parameter of Hydropower Unit difference vibration fault;Construct corresponding training set and test set;Three independent improvement cuckoo searching algorithm Optimized BP Neural Network models are resettled, primary diagnosis is carried out to the vibration fault of Hydropower Unit;Using primary diagnosis result as the corroboration body of evidence theory, final fusion decision is carried out.The present invention, come the adjusting step factor, enhances the adaptability towards complicated optimum problem using cuckoo searching algorithm fitness in an iterative process;In addition, the present invention uses the method for diagnosing faults based on information fusion technology, the robustness and fault-tolerance of diagnostic model are enhanced, and then effectively increase the accuracy of vibration fault diagnosis of hydro-turbine generating unit.
Description
Technical field
The invention belongs to Approach for Hydroelectric Generating Unit Fault Diagnosis technical fields, are related to a kind of Hydropower Unit based on information fusion technology
Method for diagnosing faults.
Background technique
Hydropower Unit (HGU) coupling influence vulnerable to factors such as waterpower, machinery, electromagnetism in the process of running, with fortune
The accumulation of row time, Hydropower Unit and its ancillary equipment, which can inevitably break down, even to fail, and failure is usually with the shape of vibration
Formula shows;Therefore, it accurately extracts the feature of vibration signal and correctly identifies its fault type, to the peace for guaranteeing Hydropower Unit
Full stable operation is of great significance.
In recent years, with the development of artificial intelligence technology, a variety of intelligent diagnosing methods have been applied to Hydropower Unit (HGU)
In fault diagnosis, such as support vector machines (SVM), BP neural network (BPNN) and self-organizing map neural network (SOM);So
And support vector machines is sensitive to missing data;And BPNN has the defects of convergence rate is slow, ability of processing challenge is poor;
Different primary condition has very sensitive influence to the learning process and learning outcome of SOM network.Based on this, researcher
Select the vibration fault that artificial intelligence is combined and then diagnosed with optimization algorithm Hydropower Unit.But due to algorithm operation it is random
Property, need many experiments that could obtain relatively satisfactory diagnostic result.Therefore, suitable optimization algorithm is selected to be very important.
It is a kind of novel optimization algorithm that cuckoo, which searches for (CS), simple in view of its model and be easily achieved, and is applied
In different engineering fields.Studies have shown that CS is better than genetic algorithm (GA) and particle group optimizing (PSO) algorithm.However, original
In CS algorithm, step factor is more sensitive to optimization problem;For different problems, it can be set to 1,0.1 or 0.01.It is aobvious
So, rationally setting step factor is a challenging job.Therefore, it is necessary to be improved to CS algorithm, to improve its optimization property
Energy.In addition, the diagnosis performance of BP neural network is influenced serious by initial power threshold parameter setting, solves complex nonlinear and ask
Easily occurs over-fitting when topic.
Summary of the invention
The object of the present invention is to provide a kind of Fault Diagnosis Method of Hydro-generating Unit based on information fusion technology, solve existing
The intelligent diagnosing method bad adaptability that has CS algorithm present in technology to merge with BP neural network, step factor are to optimization problem
Sensitive and BP neural network solves the problem of complex nonlinear problem ability difference.
The technical scheme adopted by the invention is that a kind of Fault Diagnosis Method of Hydro-generating Unit based on information fusion technology,
It is specifically implemented according to the following steps:
Step 1, the information that Hydropower Unit vibration fault is collected using at least one set of acceleration transducer, and extract spy
Levy parameter;
Characteristic parameter is divided into training data and test data by step 2, and training data is for constructing neural network mould
Type, test data are used to verify the diagnosis performance of neural network model;
Step 3 establishes at least two primary diagnosis models based on improvement cuckoo searching algorithm Optimized BP Neural Network,
Obtain Basic Probability As-signment;
Step 4 carries out information fusion to Basic Probability As-signment using the composition rule of evidence theory, obtains the hydroelectric machine
The diagnosis of group vibration fault.
The features of the present invention also characterized in that:
In step 1, the type of vibration fault is divided into: rotor unbalance, rotor misalignment and draft tube eccentric vortex band, above-mentioned
Three types constitute the identification framework of vibration fault, and characteristic parameter is the amplitude of vibration signals spectrograph component: < 0.5f0, f0,
2f0,3f0, > 3f0, wherein f0 is fundamental frequency;
In step 3, establishes based on the primary diagnosis model for improving cuckoo searching algorithm Optimized BP Neural Network, specifically press
Implement according to following steps:
Step 3.1, building BP neural network model, initialize following parameter: train epochs, learning rate, study
Target and hidden layer neuron number, and determine transfer function and training function;
Step 3.2, initialization improve cuckoo searching algorithm, and initiation parameter includes: population scale N, greatest iteration time
Number tmax, probability of detection paAnd calibration factor α0;
Step 3.3 generates initial solution xi(i=1,2 ..., N) calculates its fitness f (xi);
Step 3.4, record optimal solution xbestAnd its fitness fbest;
If step 3.5, current iteration number t < tmax, optimal solution is searched for, and every time after circulation, the number of iterations adds 1;Otherwise
Go to step 3.12;
Step 3.6, the material calculation factor;
Step 3.7 generates new explanation using Levy countermeasures;
Step 3.8, the fitness for calculating new explanation, if new explanation replaces current solution better than current solution, with new explanation;Otherwise retain
Current solution;
Step 3.9 generates new explanation using preference random walk again;
Step 3.10, the fitness for calculating new explanation, if new explanation replaces current solution better than current solution, with new explanation;
Step 3.11, record optimal adaptation degree and optimal solution;
Step 3.12, using optimal solution as the power threshold parameter of BP neural network;
Step 3.13 carries out Hydropower Unit vibration fault using the BP neural network for improving the optimization of cuckoo searching algorithm
Diagnosis, and the Basic Probability As-signment after diagnostic result is normalized as evidence theory.
In step 3.1, BP neural network selection has the network structure of three etale topologies;Transfer function select tansig and
logsig;Training function selects trainlm function.
In step 3.6, the computation rule of step factor is indicated are as follows:
In formula (1), favgFor the average fitness of population, a0For calibration factor.
In step 3.7, Levy countermeasures are indicated are as follows:
In formula (2) and (3), uiWith xiRespectively new explanation and current solution;Indicate dot-product;Z and v is two obedience normal states
The random number of distribution;β is distribution parameter.
In step 3.9, preference random walk is indicated are as follows:
In formula (4), r and rand are two and obey equally distributed random number;paFor probability of detection;xmAnd xnFor two with
Machine solution.
In step 4, the composition rule of evidence theory is described are as follows:
In formula (5) and (6), m1(Ai) and m2(Bj) it is respectively proposition AiAnd BjBasic Probability As-signment;The size of k indicates card
According to Conflict Intensity.
The beneficial effects of the present invention are: carrying out the adaptively adjusting step factor, and then improve according to the fitness value of population
The search capability and optimization efficiency of cuckoo searching algorithm;BP neural network is found with improved cuckoo searching algorithm
Optimized parameter, and then obtain the diagnostic model with superperformance;The optimization of cuckoo searching algorithm is improved by three
BP neural network model is respectively used in the vibrating failure diagnosis of Hydropower Unit, and is normalized diagnostic result to obtain
To basic probability assignment value, objectifying for Basic Probability As-signment is realized;Final diagnosis is generated using evidence theory,
Effectively increase the accuracy of Approach for Hydroelectric Generating Unit Fault Diagnosis.
Detailed description of the invention
Fig. 1 is a kind of flow chart of the Fault Diagnosis Method of Hydro-generating Unit based on information fusion technology of the present invention;
Fig. 2 is a kind of system block diagram of the Fault Diagnosis Method of Hydro-generating Unit based on information fusion technology of the present invention;
Fig. 3 is that the present invention improves cuckoo searching algorithm Optimized BP Neural Network (MCSBP) and CSBP, ACSBP, BCSBP
And the fitness convergence curve figure of VCSBP.
Specific embodiment
The following describes the present invention in detail with reference to the accompanying drawings and specific embodiments.
The present invention, from the adaptively adjusting step factor, proposes a kind of adaptable improvement according to Population adaptation angle value
CS algorithm;In order to improve the ability that BP neural network solves complex nonlinear problem, BP nerve is found using CS algorithm is improved
The optimized parameter of network;The present invention is obtained using the BP neural network after optimization as the primary fault diagnostic model of Hydropower Unit
Basic probability assignment value carries out information using evidence theory therewith and merges decision, finally realizes the intelligence of Hydropower Unit failure
Diagnosis.
As shown in Figure 1, a kind of Fault Diagnosis Method of Hydro-generating Unit based on information fusion technology of the present invention, specifically according to
Lower step is implemented:
Step 1, the information that Hydropower Unit vibration fault is collected using at least one set of acceleration transducer, and extract spy
Levy parameter;
Wherein, the type of vibration fault is divided into: rotor unbalance, rotor misalignment and draft tube eccentric vortex band, and above-mentioned three
Seed type constitutes the identification framework of vibration fault;Characteristic parameter is the amplitude of vibration signals spectrograph component: < 0.5f0, f0,
2f0,3f0, > 3f0, wherein f0 is fundamental frequency;
Characteristic parameter is divided into training data and test data by step 2, and training data is for constructing neural network mould
Type, test data are used to verify the diagnosis performance of neural network model;
Step 3 establishes at least two primary diagnosis models based on improvement cuckoo searching algorithm Optimized BP Neural Network,
Obtain Basic Probability As-signment;
Wherein, establish based on improve cuckoo searching algorithm Optimized BP Neural Network primary diagnosis model, specifically according to
Following steps are implemented:
Step 3.1, building BP neural network model, initialize following parameter: train epochs, learning rate, study
Target and hidden layer neuron number, and determine transfer function and training function;
Wherein, BP neural network is the network of three etale topologies;Transfer function selects tansig and logsig;Training function choosing
Select trainlm function.
Step 3.2, initialization improve cuckoo searching algorithm, and initiation parameter includes: population scale N, greatest iteration time
Number tmax, probability of detection paAnd calibration factor α0;
Step 3.3 generates initial solution xi(i=1,2 ..., N) calculates its fitness f (xi);
Step 3.4, record optimal solution xbestAnd its fitness fbest;
If step 3.5, current iteration number t < tmax, optimal solution is searched for, and every time after circulation, the number of iterations adds 1;Otherwise
Go to step 3.12;
Step 3.6, the material calculation factor;
Wherein, the computation rule of step factor indicates are as follows:
In formula (1), favgFor the average fitness of population, a0For calibration factor.
Step 3.7 generates new explanation using Levy countermeasures;
Wherein, Levy countermeasures indicate are as follows:
In formula (2) and (3), uiWith xiRespectively new explanation and current solution;Indicate dot-product;Z and v is two obedience normal states
The random number of distribution;β is distribution parameter, is typically set to 1.5.
Step 3.8, the fitness for calculating new explanation, if new explanation replaces current solution better than current solution, with new explanation;Otherwise retain
Current solution;
Step 3.9 generates new explanation using preference random walk again;
Wherein, preference random walk indicates are as follows:
In formula (4), r and rand are two and obey equally distributed random number;paFor probability of detection;xmAnd xnFor two with
Machine solution.
Step 3.10, the fitness for calculating new explanation, if new explanation replaces current solution better than current solution, with new explanation;
Step 3.11, record optimal adaptation degree and optimal solution;
Step 3.12, using optimal solution as the power threshold parameter of BP neural network;
Step 3.13, the BP neural network optimized using improvement cuckoo searching algorithm are to the Hydropower Unit vibration fault
It is diagnosed, and the Basic Probability As-signment after diagnostic result is normalized as evidence theory.
Step 4 carries out information fusion to the Basic Probability As-signment using the composition rule of evidence theory, obtains the water
The diagnosis of motor group vibration fault;
Wherein, the composition rule description of evidence theory are as follows:
In formula (5) and (6), m1(Ai) and m2(Bj) it is respectively proposition AiAnd BjBasic Probability As-signment;The size of k indicates card
According to Conflict Intensity.
In order to verify a kind of validity of the Fault Diagnosis Method of Hydro-generating Unit based on information fusion technology of the present invention, will have
Representational Hydropower Unit vibration fault: rotor unbalance, rotor misalignment and draft tube eccentric vortex band, the event as diagnosis
Hinder type;3 kinds of fault modes use vector [1 0 0], [0 1 0] and [0 0 1] are corresponding to indicate respectively, by vibration signals spectrograph point
The amplitude of amount is as feature vector, comprising: 0.5f0, f0,2f0,3f0 and > 3f0 (f0 is fundamental frequency), using three improvement cuckoos
Primary mold of the bird chess game optimization BP neural network as diagnosis, is abbreviated as MCSBP1, MCSBP2 and MCSBP3, finally using card
Final information fusion is carried out according to theoretical, which is abbreviated as MCSBP-DS model.System block diagram is as shown in Figure 2.
In above-mentioned primary diagnosis model, 30 groups of test samples are selected;The setting difference of control parameter and function is as follows: BP
The topological structure of neural network is 5-10-4, and the transfer function from input layer to output layer is tansig and logsig, training letter
Number is trainlm, frequency of training 5000, convergence factor 0.001;The parameter setting of improved cuckoo searching algorithm is such as
Under: population scale is set as 30, maximum number of iterations 300, probability of detection 0.25, calibration factor 0.2.
In order to verify the competitiveness of MCSBP algorithm, cuckoo is searched for into training BP neural network (CSBP), adaptive cuckoo
Bird searches for BP network (ACSBP), cuckoo search BP network (BCSBP) with beta distribution and becomes scale cuckoo
Bird search BP network (VCSBP) is used to diagnose Hydropower Unit vibration fault, and fitness convergence curve is as shown in Figure 3.
The present invention carries out information using evidence theory and merges decision.Firstly, the primary according to provided by 3 MCSBP models
Diagnostic result obtains Basic Probability As-signment after normalization;Then, the information fusion faculty powerful using evidence theory, by these
Basic Probability As-signment is merged to implement final decision.Table 1 gives the Basic Probability As-signment of four kinds of schemes;Table 2 gives
The statistical result of four kinds of scheme accuracy rates of diagnosis.
1 Basic Probability As-signment of table
The statistical result of 2 accuracy rate of diagnosis of table
Method | MCSBP1 | MCSBP2 | MCSBP3 | MCSBP-DS |
Accuracy rate/% | 83.3 | 76.7 | 76.7 | 86.7 |
From table 2 it can be seen that the accuracy rate of diagnosis that MCSBP-DS is obtained is 86.7%.Obviously, MCSBP-DS has relatively strong
Robustness and fault-tolerance, to demonstrate a kind of Fault Diagnosis Method of Hydro-generating Unit based on information fusion technology of the present invention
Validity.
Claims (8)
1. a kind of Fault Diagnosis Method of Hydro-generating Unit based on information fusion technology, which is characterized in that specifically according to the following steps
Implement:
Step 1, the information that Hydropower Unit vibration fault is collected using at least one set of acceleration transducer, and extract feature ginseng
Number;
The characteristic parameter is divided into training data and test data by step 2, and the training data is for constructing neural network
Model, the test data are used to verify the diagnosis performance of neural network model;
Step 3 establishes at least two based on the primary diagnosis model for improving cuckoo searching algorithm Optimized BP Neural Network, obtains
Basic Probability As-signment;
Step 4 carries out information fusion to the Basic Probability As-signment using the composition rule of evidence theory, obtains the hydroelectric machine
The diagnosis of group vibration fault.
2. a kind of Fault Diagnosis Method of Hydro-generating Unit based on information fusion technology according to claim 1, feature exist
In in step 1, the type of the vibration fault is divided into: rotor unbalance, rotor misalignment and draft tube eccentric vortex band, it is above-mentioned
Three types constitute the identification framework of vibration fault;The characteristic parameter is the amplitude of vibration signals spectrograph component: < 0.5f0,
F0,2f0,3f0, > 3f0, wherein f0 is fundamental frequency.
3. a kind of Fault Diagnosis Method of Hydro-generating Unit based on information fusion technology according to claim 1, feature exist
In, it is described to establish based on the primary diagnosis model for improving cuckoo searching algorithm Optimized BP Neural Network in step 3, specifically press
Implement according to following steps:
Step 3.1, building BP neural network model, initialize following parameter: train epochs, learning rate, learning objective
And hidden layer neuron number, and determine transfer function and training function;
Step 3.2, initialization improve cuckoo searching algorithm, and initiation parameter includes: population scale N, maximum number of iterations
tmax, probability of detection paAnd calibration factor α0;
Step 3.3 generates initial solution xi(i=1,2 ..., N) calculates its fitness f (xi);
Step 3.4, record optimal solution xbestAnd its fitness fbest;
If step 3.5, current iteration number t < tmax, optimal solution is searched for, and every time after circulation, the number of iterations adds 1;Otherwise it jumps
To step 3.12;
Step 3.6, the material calculation factor;
Step 3.7 generates new explanation using Levy countermeasures;
Step 3.8, the fitness for calculating new explanation, if new explanation replaces current solution better than current solution, with new explanation;Otherwise retain current
Solution;
Step 3.9 generates new explanation using preference random walk again;
Step 3.10, the fitness for calculating new explanation, if new explanation replaces current solution better than current solution, with new explanation;
Step 3.11, record optimal adaptation degree and optimal solution;
Step 3.12, using optimal solution as the power threshold parameter of BP neural network;
Step 3.13 carries out the Hydropower Unit vibration fault using the BP neural network for improving the optimization of cuckoo searching algorithm
Diagnosis, and the Basic Probability As-signment after diagnostic result is normalized as evidence theory.
4. a kind of Fault Diagnosis Method of Hydro-generating Unit based on information fusion technology according to claim 3, feature exist
In in step 3.1, the BP neural network selects the network of three etale topologies;The transfer function selects tansig and logsig;
The trained function selects trainlm function.
5. a kind of Fault Diagnosis Method of Hydro-generating Unit based on information fusion technology according to claim 3, feature exist
In in step 3.6, the computation rule of the step factor is indicated are as follows:
In formula (1), favgFor the average fitness of population, a0For calibration factor.
6. a kind of Fault Diagnosis Method of Hydro-generating Unit based on information fusion technology according to claim 3, feature exist
In in step 3.7, the Levy countermeasures are indicated are as follows:
In formula (2) and (3), uiWith xiRespectively new explanation and current solution;Indicate dot-product;Z and v is two Normal Distributions
Random number;β is distribution parameter.
7. a kind of Fault Diagnosis Method of Hydro-generating Unit based on information fusion technology according to claim 3, feature exist
In in step 3.9, the preference random walk is indicated are as follows:
In formula (4), r and rand are two and obey equally distributed random number;paFor probability of detection;xmAnd xnFor two RANDOM SOLUTIONs.
8. a kind of Fault Diagnosis Method of Hydro-generating Unit based on information fusion technology according to claim 1, feature exist
In in step 4, the composition rule of the evidence theory is described are as follows:
In formula (5) and (6), m1(Ai) and m2(Bj) it is respectively proposition AiAnd BjBasic Probability As-signment;The size of k indicates between evidence
Conflict Intensity.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910020679.3A CN109657647A (en) | 2019-01-09 | 2019-01-09 | A kind of Fault Diagnosis Method of Hydro-generating Unit based on information fusion technology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910020679.3A CN109657647A (en) | 2019-01-09 | 2019-01-09 | A kind of Fault Diagnosis Method of Hydro-generating Unit based on information fusion technology |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109657647A true CN109657647A (en) | 2019-04-19 |
Family
ID=66119344
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910020679.3A Pending CN109657647A (en) | 2019-01-09 | 2019-01-09 | A kind of Fault Diagnosis Method of Hydro-generating Unit based on information fusion technology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109657647A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110617960A (en) * | 2019-10-12 | 2019-12-27 | 华北电力大学 | Wind turbine generator gearbox fault diagnosis method and system |
CN111580506A (en) * | 2020-06-03 | 2020-08-25 | 南京理工大学 | Industrial process fault diagnosis method based on information fusion |
CN114742201A (en) * | 2022-03-16 | 2022-07-12 | 三峡大学 | Power grid partition fault diagnosis method based on particle swarm optimization generalized regression neural network and D-S evidence theory |
CN115856623A (en) * | 2022-12-13 | 2023-03-28 | 淮阴工学院 | Motor fault diagnosis method based on uniformity and kurtosis calculation |
CN117171659A (en) * | 2023-10-31 | 2023-12-05 | 国网浙江省电力有限公司宁波供电公司 | Intelligent distribution transformer high-voltage side fault diagnosis method |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107515964A (en) * | 2017-07-27 | 2017-12-26 | 宁波大学 | A kind of area-optimized method of fixed polarity RM circuits |
CN108600959A (en) * | 2018-01-03 | 2018-09-28 | 中山大学 | A kind of WSN node positioning methods based on improvement cuckoo searching algorithm |
CN108596212A (en) * | 2018-03-29 | 2018-09-28 | 红河学院 | Based on the Diagnosis Method of Transformer Faults for improving cuckoo chess game optimization neural network |
CN108896330A (en) * | 2018-04-26 | 2018-11-27 | 红河学院 | A kind of method for diagnosing faults of Hydropower Unit |
CN108985438A (en) * | 2018-06-26 | 2018-12-11 | 红河学院 | A kind of cuckoo searching algorithm based on neighborhood topology |
CN109029975A (en) * | 2018-06-26 | 2018-12-18 | 红河学院 | A kind of method for diagnosing faults of wind turbine gearbox |
-
2019
- 2019-01-09 CN CN201910020679.3A patent/CN109657647A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107515964A (en) * | 2017-07-27 | 2017-12-26 | 宁波大学 | A kind of area-optimized method of fixed polarity RM circuits |
CN108600959A (en) * | 2018-01-03 | 2018-09-28 | 中山大学 | A kind of WSN node positioning methods based on improvement cuckoo searching algorithm |
CN108596212A (en) * | 2018-03-29 | 2018-09-28 | 红河学院 | Based on the Diagnosis Method of Transformer Faults for improving cuckoo chess game optimization neural network |
CN108896330A (en) * | 2018-04-26 | 2018-11-27 | 红河学院 | A kind of method for diagnosing faults of Hydropower Unit |
CN108985438A (en) * | 2018-06-26 | 2018-12-11 | 红河学院 | A kind of cuckoo searching algorithm based on neighborhood topology |
CN109029975A (en) * | 2018-06-26 | 2018-12-18 | 红河学院 | A kind of method for diagnosing faults of wind turbine gearbox |
Non-Patent Citations (2)
Title |
---|
PAULINE ONG: "Adaptive Cuckoo Search Algorithm for Unconstrained Optimization", 《THE SCIENTIFIC WORLD JOURNAL》 * |
程加堂 等: "基于QPSO-BP和改进D-S的水电机组振动故障诊断", 《电力系统保护与控制》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110617960A (en) * | 2019-10-12 | 2019-12-27 | 华北电力大学 | Wind turbine generator gearbox fault diagnosis method and system |
CN111580506A (en) * | 2020-06-03 | 2020-08-25 | 南京理工大学 | Industrial process fault diagnosis method based on information fusion |
CN114742201A (en) * | 2022-03-16 | 2022-07-12 | 三峡大学 | Power grid partition fault diagnosis method based on particle swarm optimization generalized regression neural network and D-S evidence theory |
CN114742201B (en) * | 2022-03-16 | 2024-07-09 | 三峡大学 | Grid partition fault diagnosis method based on particle swarm optimization generalized regression neural network and D-S evidence theory |
CN115856623A (en) * | 2022-12-13 | 2023-03-28 | 淮阴工学院 | Motor fault diagnosis method based on uniformity and kurtosis calculation |
CN117171659A (en) * | 2023-10-31 | 2023-12-05 | 国网浙江省电力有限公司宁波供电公司 | Intelligent distribution transformer high-voltage side fault diagnosis method |
CN117171659B (en) * | 2023-10-31 | 2024-01-26 | 国网浙江省电力有限公司宁波供电公司 | Intelligent distribution transformer high-voltage side fault diagnosis method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109657647A (en) | A kind of Fault Diagnosis Method of Hydro-generating Unit based on information fusion technology | |
CN104330721B (en) | IC Hardware Trojan detecting method and system | |
CN108062572A (en) | A kind of Fault Diagnosis Method of Hydro-generating Unit and system based on DdAE deep learning models | |
CN112883994B (en) | Rotating machinery variable working condition fault diagnosis method with balanced distribution adaptation | |
CN103926526A (en) | Analog circuit fault diagnosis method based on improved RBF neural network | |
CN104751229A (en) | Bearing fault diagnosis method capable of recovering missing data of back propagation neural network estimation values | |
CN110110434B (en) | Initialization method for probability load flow deep neural network calculation | |
CN114022693A (en) | Double-self-supervision-based single-cell RNA-seq data clustering method | |
CN111783531A (en) | Water turbine set fault diagnosis method based on SDAE-IELM | |
CN114721336B (en) | Information security event early warning method for technological parameters of instrument control system | |
Xiao et al. | Network security situation prediction method based on MEA-BP | |
Zhang | An incremental learning algorithm that optimizes network size and sample size in one trial | |
CN115791174B (en) | Rolling bearing abnormality diagnosis method, system, electronic equipment and storage medium | |
CN108896330B (en) | Fault diagnosis method for hydroelectric generating sets | |
CN115129607A (en) | Power grid safety analysis machine learning model test method, device, equipment and medium | |
CN117273409A (en) | Intelligent operation and maintenance method, system and storage medium for intelligent environment-friendly system of park | |
Abbaskhah et al. | Optimization of horizontal axis wind turbine performance with the dimpled blades by using CNN and MLP models | |
CN114548154A (en) | Intelligent diagnosis method and device for important service water pump | |
Li et al. | Class imbalanced fault diagnosis via combining K-means clustering algorithm with generative adversarial networks | |
Guo et al. | WSN cluster head selection algorithm based on neural network | |
CN112163474A (en) | Intelligent gearbox diagnosis method based on model fusion | |
CN115081483B (en) | Hydraulic generator rotor fault diagnosis method based on feature selection and GWO-BP | |
Li | Research on bank credit risk assessment based on BP neural network | |
CN116910513A (en) | Centrifugal pump rotor fault diagnosis method based on CWGAN-GP and double-flow CNN model | |
CN114511158B (en) | Wind turbine power prediction method based on wake deflection effect and 2DJensen model |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190419 |