CN111855816A - Fan blade fault identification method integrating probability model and cnn network - Google Patents
Fan blade fault identification method integrating probability model and cnn network Download PDFInfo
- Publication number
- CN111855816A CN111855816A CN202010545026.XA CN202010545026A CN111855816A CN 111855816 A CN111855816 A CN 111855816A CN 202010545026 A CN202010545026 A CN 202010545026A CN 111855816 A CN111855816 A CN 111855816A
- Authority
- CN
- China
- Prior art keywords
- fan blade
- model
- matrix
- blade
- fault
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 239000011159 matrix material Substances 0.000 claims abstract description 27
- 238000001514 detection method Methods 0.000 claims abstract description 14
- 230000008569 process Effects 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 12
- 238000002790 cross-validation Methods 0.000 claims abstract description 4
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 238000012545 processing Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000003321 amplification Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 238000003745 diagnosis Methods 0.000 abstract description 8
- 238000010801 machine learning Methods 0.000 abstract description 2
- 238000012423 maintenance Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/14—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object using acoustic emission techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/4409—Processing the detected response signal, e.g. electronic circuits specially adapted therefor by comparison
- G01N29/4418—Processing the detected response signal, e.g. electronic circuits specially adapted therefor by comparison with a model, e.g. best-fit, regression analysis
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/4481—Neural networks
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/02—Indexing codes associated with the analysed material
- G01N2291/023—Solids
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/02—Indexing codes associated with the analysed material
- G01N2291/028—Material parameters
- G01N2291/0289—Internal structure, e.g. defects, grain size, texture
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/26—Scanned objects
- G01N2291/269—Various geometry objects
- G01N2291/2698—Other discrete objects, e.g. bricks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
Abstract
The invention discloses a fan blade fault identification method for a comprehensive probability model and a cnn network, which comprises the steps of firstly, adopting blade acoustic emission detection to collect signals of a wind blade; preprocessing the data using MFCC to generate labels and an MFCC map; transmitting the data into a CNN model for convolution operation and Feature _ map generation; simultaneously using LSTM and HMM to process time sequence information and output observation sequence probability matrix P1And P2(ii) a Will P1And P2Calculating a state probability matrix by adopting Softmax after matrix connection is carried out; then, performing iterative training and cross validation on the model by using the existing data to obtain the optimal weight; the trained model is used for identifying the fan blade fault, and the standard with the maximum probability of the output layer is calculatedAnd signing the result, and converting the result into a state corresponding to the fan blade, namely a fan blade fault identification result. The method combines signal acquisition and machine learning algorithm, adopts a mode of fusing a plurality of time sequence discrimination models to sense the whole process of the fan blade state, and provides influential thought and guidance for crack fault diagnosis of the wind turbine blade.
Description
Technical Field
The invention relates to the field of fault detection, in particular to a fan blade fault identification method based on a comprehensive probability model and a cnn network.
Background
The wind turbine blade can be subjected to fatigue damage after long-term operation, the blade can generate cracks of different degrees, and the continuous expansion of the cracks finally leads to the fracture and failure of the blade. At present, the maintenance mode of the fan mainly comprises regular maintenance and post-fault maintenance, and the two methods have higher cost. The introduction of the fault detection and diagnosis technology reduces the overhaul workload, saves the overhaul economic cost and optimizes the overhaul scheme. The fault detection method can find the fault in time and accurately judge the fault, thereby being convenient for establishing a maintenance strategy and avoiding redundant maintenance and repair.
Various fault detection and diagnosis methods are proposed by different scientific research institutes and manufacturers at home and abroad, so that great contribution is made to the development of modern fault detection and diagnosis technology, but the application research of the wind turbine blade detection and fault diagnosis is less. Therefore, intensive research needs to be carried out on the fault detection and fault diagnosis of the wind turbine blade, and a blade fault diagnosis method which can be widely applied to practice is provided.
Disclosure of Invention
In order to solve the above problems, the present invention provides a method for identifying a blade fault by integrating a probability model and a cnn network, so as to solve the problems in the background art.
A fan blade fault identification method integrating a probability model and a cnn network comprises the following steps:
s1: firstly, acquiring signals of a wind turbine blade by adopting blade acoustic emission detection;
s2: preprocessing the data using MFCC to generate labels and an MFCC map;
s3: transmitting the data into a cnn model to perform convolution operation and Feature _ map generation;
s4: simultaneously using LSTM and HMM to process time sequence information and output observation sequence probability matrix P1 and P2；
S5: will P1 and P2Calculating a state probability matrix by adopting Softmax after matrix connection is carried out;
s6: then, performing iterative training and cross validation on the model by using the existing data to obtain the optimal weight;
s7: and (3) using the trained model for fan blade fault recognition, calculating the label with the maximum probability of the output layer as a result, and converting the result into a state corresponding to the fan blade, namely a fan blade fault recognition result.
As a preferred technical solution of the present invention, the basic process of blade acoustic emission detection in S1 includes a series of processes such as signal acquisition, signal conversion, signal input, signal amplification, signal processing, signal output, and signal display.
As a preferred technical solution of the present invention, the calculation formula of MFCC and frequency f in S2 is: mel (f) ═ 2595 × lg (1+ f/700), where Mel represents MFCC value and f represents frequency.
As a preferred embodiment of the present invention, the label in S2 may summarize various fault states of the blade, including: normal, frozen, loose screw, cracked, present as represented by "1"; "0" represents absent.
As a preferred technical scheme of the invention, the cnn model in S3 mainly comprises 3 convolution layers conv1、conv2、conv3And 3 pooling layer pool1、pool2、pool3The convolution kernel size used was 3x 3.
As a preferred embodiment of the present invention, the matrix P in S4 is1And matrix P2Are equal in length.
As a preferred technical solution of the present invention, the formula of the matrix connection in S5 is:
wherein ,
is a matrix P1The elements (A) and (B) in (B),
is a matrix P2Of (1).
As a preferred technical solution of the present invention, the judgment condition of the iterative training in S6 is cross entropy loss, and its formula is:
wherein: l represents cross entropy loss, M represents the number of categories, and N represents the number of samples, namely the total number of fault categories; y isicRepresents an indicator variable, and represents fault states, namely '1' and '0' in the patent; p is a radical of icAnd representing the prediction probability that the observation sample i belongs to the class c in the model discrimination.
The invention has the beneficial effects that: the method combines signal acquisition and machine learning algorithm, adopts a mode of fusing a plurality of time sequence discrimination models to sense the whole process of the fan blade state, and provides influential thought and guidance for crack fault diagnosis of the wind turbine blade.
Drawings
To more clearly illustrate the implementation of the present invention or the technical solutions in the prior art, the following brief descriptions of the drawings required in the embodiments or the description of the prior art are provided:
FIG. 1 is a flow chart of a method of fan blade fault identification of a comprehensive probabilistic model and cnn network according to the present invention;
FIG. 2 is a diagram of acquired signals prior to MFCC processing in accordance with the present invention
FIG. 3 is a diagram of MFCC before MFCC processing according to the present invention;
FIG. 4 is a diagram of the construction of the cnn model according to the present invention;
FIG. 5 is a graph of training loss according to the present invention;
FIG. 6 is a test ACC map according to the present invention;
FIG. 7 is a graph of a training ROC according to the present invention.
Detailed Description
The following detailed description of the preferred embodiments of the present invention, taken in conjunction with the accompanying drawings, will make the advantages and features of the invention more readily understood by those skilled in the art, and thus will more clearly and distinctly define the scope of the invention.
Example 1: referring to fig. 1, the present invention provides a technical solution: a fan blade fault identification method integrating a probability model and a cnn network comprises the following steps:
s1: firstly, acquiring a wind blade signal by adopting blade acoustic emission detection; the basic process of blade acoustic emission detection comprises a series of processes such as signal acquisition, signal conversion, signal input, signal amplification, signal processing, signal output and signal display.
S2: preprocessing the data using MFCCs produces tags and an MFCC map,
characteristic 2-1: the formula for MFCC and frequency f is: mel (f) ═ 2595 × lg (1+ f/700), where Mel represents MFCC value and f represents frequency;
characteristic 2-2: the tags may generalize various fault conditions of the blade, including: normal, frozen, loose screw, cracked, present as represented by "1"; "0" represents absent.
S3: transmitting the data into a cnn model to perform convolution operation and Feature _ map generation; as shown in fig. 4: the cnn model mainly comprises 3 convolution layers conv1、conv2、conv3And 3 pooling layer pool1、pool2、pool3The convolution kernel size used was 3x 3.
S4: simultaneously using LSTM and HMM to process time sequence information and output observation sequence probability matrix P1 and P2The matrix P1And matrix P2Are equal in length.
S5: will P1 and P2After matrix connection is carried out, a state probability matrix is calculated by adopting Softmax, and the formula for calculating the state probability matrix is as follows:
wherein ,
is a matrix P1The elements (A) and (B) in (B),
is a matrix P2Of (1).
S6: then, iterative training and cross validation are carried out on the model by using the existing data to obtain the optimal weight, the loss function of the iterative training is cross entropy loss, and the calculation formula is as follows:
wherein: l represents cross entropy loss, M represents the number of categories, and N represents the number of samples, namely the total number of fault categories; y isicRepresents an indicator variable, and represents fault states, namely '1' and '0' in the patent; p is a radical oficAnd representing the prediction probability that the observation sample i belongs to the class c in the model discrimination.
S7: and (3) using the trained model for fan blade fault recognition, calculating the label with the maximum probability of the output layer as a result, and converting the result into a state corresponding to the fan blade, namely a fan blade fault recognition result.
The invention adopts 200 groups of data randomly generated by using a unifrng function as training data. The vibration signals of different states of the blade are subjected to frequency translation and fractal dimension methods to obtain four characteristic values FL (translation distance characteristic value), DC (correlation dimension), DL (length fractal dimension) and DF (box dimension), the four characteristic values are used as input data of a neural network, the output states (normal state, icing state, root bolt loosening state and crack state) of the blade are used as output labels of the neural network, iterative training and parameter updating are carried out on the model provided by the invention, and the loss is reduced as shown in figure 5. Model parameters and structures were saved as an experimental model case of the present invention when the cross entropy loss was below 0.01. Meanwhile, 50 groups of data are randomly generated by using a unifrng function and are independent of test data of training data, and ACC and AUC indexes are used as evaluation indexes to carry out multi-model comparison, so that the validity of the patent scheme and the guiding significance to the industry are verified.
The calculation formula for ACC is as follows:
wherein TP represents the correct number of the positive case predictions; FP represents the number of negative prediction errors; TN represents the number of correct negative case predictions; FN represents the number of positive prediction errors.
The multi-model ACC comparison results are shown in table 1:
TABLE 1
To verify the stability of the test of the present invention across all the test data, an ACC plot (as shown in fig. 6) and a ROC plot (as shown in fig. 7) were plotted, where the area enclosed by the ROC curves represents the AUC values.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention.
Claims (8)
1. A fan blade fault identification method integrating a probability model and a cnn network is characterized in that: the method comprises the following steps:
s1: firstly, acquiring signals of a wind turbine blade by adopting blade acoustic emission detection;
s2: preprocessing the data using MFCC to generate labels and an MFCC map;
s3: transmitting the data into a cnn model to perform convolution operation and Feature _ map generation;
S4: simultaneously using LSTM and HMM to process time sequence information and output observation sequence probability matrix P1 and P2；
S5: will P1 and P2Calculating a state probability matrix by adopting Softmax after matrix connection is carried out;
s6: then, performing iterative training and cross validation on the model by using the existing data to obtain the optimal weight;
s7: and (3) using the trained model for fan blade fault recognition, calculating the label with the maximum probability of the output layer as a result, and converting the result into a state corresponding to the fan blade, namely a fan blade fault recognition result.
2. The method for identifying the fan blade faults of the comprehensive probability model and the cnn network according to claim 1, is characterized in that: the basic process of blade acoustic emission detection in S1 includes a series of processes such as signal acquisition, signal conversion, signal input, signal amplification, signal processing, signal output, and signal display.
3. The method for identifying the fan blade faults of the comprehensive probability model and the cnn network according to claim 1, is characterized in that: the calculation formula of MFCC and frequency f in S2 is: mel (f) ═ 2595 × lg (1+ f/700), where Mel represents MFCC value and f represents frequency.
4. The method for identifying the fan blade faults of the comprehensive probability model and the cnn network according to claim 1, is characterized in that: the tag in S2 may generalize various fault conditions of the blade, including: normal, frozen, loose screw, cracked, present as represented by "1"; "0" represents absent.
5. The method for identifying the fan blade faults of the comprehensive probability model and the cnn network according to claim 1, is characterized in that: the cnn model in S3 mainly comprises 3 convolution layers conv1、conv2、conv3And 3 pooling layer pool1、pool2、pool3The convolution kernel size used was 3x 3.
6. The method for identifying the fan blade faults of the comprehensive probability model and the cnn network according to claim 1, is characterized in that: the matrix P in S41And matrix P2Are equal in length.
7. The method for identifying the fan blade faults of the comprehensive probability model and the cnn network according to claim 1, is characterized in that: the formula of the matrix connection in S5 is:
wherein ,
is a matrix P1The elements (A) and (B) in (B),
is a matrix P2Of (1).
8. The method for identifying the fan blade faults of the comprehensive probability model and the cnn network according to claim 1, is characterized in that: the judgment condition of the iterative training in S6 is cross entropy loss, and the formula is:
wherein: l represents cross entropy loss, M represents the number of categories, and N represents the number of samples, namely the total number of fault categories;yicrepresents an indicator variable, and represents fault states, namely '1' and '0' in the patent; p is a radical oficAnd representing the prediction probability that the observation sample i belongs to the class c in the model discrimination.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010545026.XA CN111855816B (en) | 2020-06-15 | 2020-06-15 | Fan blade fault identification method for comprehensive probability model and cnn network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010545026.XA CN111855816B (en) | 2020-06-15 | 2020-06-15 | Fan blade fault identification method for comprehensive probability model and cnn network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111855816A true CN111855816A (en) | 2020-10-30 |
| CN111855816B CN111855816B (en) | 2023-06-13 |
Family
ID=72986660
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010545026.XA Active CN111855816B (en) | 2020-06-15 | 2020-06-15 | Fan blade fault identification method for comprehensive probability model and cnn network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111855816B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112559971A (en) * | 2021-02-25 | 2021-03-26 | 北京芯盾时代科技有限公司 | Probability prediction method and device and computer readable storage medium |
| CN112729783A (en) * | 2020-12-04 | 2021-04-30 | 西人马联合测控（泉州）科技有限公司 | Fan blade fault diagnosis method, device, equipment and computer storage medium |
| CN112733927A (en) * | 2021-01-05 | 2021-04-30 | 福州数据技术研究院有限公司 | Fan blade sound boundary positioning method based on one-dimensional convolutional neural network and storage device |
| CN113537122A (en) * | 2021-07-28 | 2021-10-22 | 浙江大华技术股份有限公司 | Motion recognition method and device, storage medium and electronic equipment |
| CN115166032A (en) * | 2022-05-23 | 2022-10-11 | 东南大学 | Device and method for detecting cracks of fan blade |
| CN117647587A (en) * | 2024-01-30 | 2024-03-05 | 浙江大学海南研究院 | Acoustic emission signal classification method, computer equipment and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2941729A1 (en) * | 2015-09-14 | 2017-03-14 | Sightline Innovation Inc. | System and method for specular surface inspection |
| US20180348764A1 (en) * | 2017-06-05 | 2018-12-06 | Hangzhou Zero Zero Technology Co., Ltd. | System and method for providing easy-to-use release and auto-positioning for drone applications |
| WO2019037700A1 (en) * | 2017-08-22 | 2019-02-28 | 腾讯科技（深圳）有限公司 | Speech emotion detection method and apparatus, computer device, and storage medium |
| US20200027444A1 (en) * | 2018-07-20 | 2020-01-23 | Google Llc | Speech recognition with sequence-to-sequence models |
-
2020
- 2020-06-15 CN CN202010545026.XA patent/CN111855816B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2941729A1 (en) * | 2015-09-14 | 2017-03-14 | Sightline Innovation Inc. | System and method for specular surface inspection |
| US20180348764A1 (en) * | 2017-06-05 | 2018-12-06 | Hangzhou Zero Zero Technology Co., Ltd. | System and method for providing easy-to-use release and auto-positioning for drone applications |
| WO2019037700A1 (en) * | 2017-08-22 | 2019-02-28 | 腾讯科技（深圳）有限公司 | Speech emotion detection method and apparatus, computer device, and storage medium |
| US20200027444A1 (en) * | 2018-07-20 | 2020-01-23 | Google Llc | Speech recognition with sequence-to-sequence models |
Non-Patent Citations (5)
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112729783A (en) * | 2020-12-04 | 2021-04-30 | 西人马联合测控（泉州）科技有限公司 | Fan blade fault diagnosis method, device, equipment and computer storage medium |
| CN112733927A (en) * | 2021-01-05 | 2021-04-30 | 福州数据技术研究院有限公司 | Fan blade sound boundary positioning method based on one-dimensional convolutional neural network and storage device |
| CN112559971A (en) * | 2021-02-25 | 2021-03-26 | 北京芯盾时代科技有限公司 | Probability prediction method and device and computer readable storage medium |
| CN113537122A (en) * | 2021-07-28 | 2021-10-22 | 浙江大华技术股份有限公司 | Motion recognition method and device, storage medium and electronic equipment |
| CN115166032A (en) * | 2022-05-23 | 2022-10-11 | 东南大学 | Device and method for detecting cracks of fan blade |
| CN115166032B (en) * | 2022-05-23 | 2024-04-19 | 东南大学 | Device and method for detecting cracks of fan blades |
| CN117647587A (en) * | 2024-01-30 | 2024-03-05 | 浙江大学海南研究院 | Acoustic emission signal classification method, computer equipment and medium |
| CN117647587B (en) * | 2024-01-30 | 2024-04-09 | 浙江大学海南研究院 | Acoustic emission signal classification method, computer equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111855816B (en) | 2023-06-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111855816A (en) | Fan blade fault identification method integrating probability model and cnn network | |
| WO2022077901A1 (en) | Bearing failure mode diagnosis method using small sample data sets, and system | |
| CN112629863B (en) | Bearing fault diagnosis method for dynamic joint distribution alignment network under variable working conditions | |
| WO2022077605A1 (en) | Wind turbine blade image-based damage detection and localization method | |
| CN109555566B (en) | Steam turbine rotor fault diagnosis method based on LSTM | |
| CN108256173B (en) | Gas circuit fault diagnosis method and system for dynamic process of aircraft engine | |
| CN109376801B (en) | Wind driven generator blade icing diagnosis method based on integrated deep neural network | |
| CN113723010B (en) | Bridge damage early warning method based on LSTM temperature-displacement correlation model | |
| Bao et al. | A deep transfer learning network for structural condition identification with limited real-world training data | |
| Li et al. | Joint attention feature transfer network for gearbox fault diagnosis with imbalanced data | |
| CN105607631B (en) | The weak fault model control limit method for building up of batch process and weak fault monitoring method | |
| CN113738595A (en) | Method and system for monitoring state of blade of wind generating set | |
| CN113866455A (en) | Bridge acceleration monitoring data anomaly detection method, system and device based on deep learning | |
| CN109681391A (en) | A kind of blade root bolt fracture fault detection method and medium | |
| CN113339204A (en) | Wind driven generator fault identification method based on hybrid neural network | |
| CN114565006A (en) | Wind driven generator blade damage detection method and system based on deep learning | |
| CN110276385B (en) | Similarity-based mechanical part residual service life prediction method | |
| CN112802011A (en) | Fan blade defect detection method based on VGG-BLS | |
| CN116503612A (en) | Fan blade damage identification method and system based on multitasking association | |
| CN114992063B (en) | Automatic fan blade fault detection method and system | |
| CN116244600A (en) | Method, system and equipment for constructing GIS intermittent discharge mode identification model | |
| CN115618733A (en) | Multi-scale hybrid attention mechanism modeling method for predicting remaining service life of aircraft engine | |
| CN115730255A (en) | Motor fault diagnosis and analysis method based on transfer learning and multi-source information fusion | |
| Chen et al. | Research on adaptive diagnosis algorithm for fuel injection failure system of construction machinery diesel engine | |
| CN110598674A (en) | Point switch fault identification method based on pattern identification |
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 |