CN110987494A - Method for monitoring cavitation state of water turbine based on acoustic emission - Google Patents
Method for monitoring cavitation state of water turbine based on acoustic emission Download PDFInfo
- Publication number
- CN110987494A CN110987494A CN201911212768.4A CN201911212768A CN110987494A CN 110987494 A CN110987494 A CN 110987494A CN 201911212768 A CN201911212768 A CN 201911212768A CN 110987494 A CN110987494 A CN 110987494A
- Authority
- CN
- China
- Prior art keywords
- signal
- water turbine
- cavitation
- acoustic emission
- fcm
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
- G01M99/005—Testing of complete machines, e.g. washing-machines or mobile phones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a method for monitoring a cavitation state of a water turbine based on acoustic emission. The method comprises the following steps: collecting vibration signals of the water turbine in normal and fault states, decomposing the vibration of the water turbine by adopting CEEMDAN, calculating the permutation entropy, and selecting the first three modes for calculation; and substituting the first three modes into the CGWO-FCM for cluster center calculation, finally selecting the BSA-SVM as a classifier, and taking part of the characteristic quantity as a test sample for diagnosis based on the trained cluster center. The invention can improve the efficiency of the unit and the safety and stability of the operation of the unit, realize the effective monitoring of the cavitation of the water turbine and improve the efficiency and the precision of fault diagnosis.
Description
Technical Field
The invention relates to the technical field of water turbine state monitoring, in particular to a method for monitoring a cavitation state of a water turbine based on an acoustic emission technology and a CEEMDAN signal processing method.
Background
In recent years, hydropower industry has been greatly developed along with the adjustment of energy structures in national planning. By 2016, the total installed capacity of hydropower generation in China exceeds 3.3 hundred million kilowatts, which accounts for 27 percent of the world, and the installed capacity of hydropower generation is strived to reach 3.5 hundred million kilowatts by planning 2020. With the vigorous development of hydropower industry, domestic large and medium hydropower stations are built and put into production in succession, the proportion of hydroelectric power generation in power supply is larger and larger, and the problem of safe reliability of water turbine operation is obvious day by day. The water turbine is used as a key device for converting hydroelectric energy and is a main power device participating in energy conversion. Due to the fact that partial load and transition process working conditions are needed to enter for power grid dispatching or flood season operation, cavitation damage is easy to happen. Cavitation erosion is a common damage phenomenon in the operation of a water turbine and is a main factor causing damage of flow passage components, reduction of unit output and aggravation of vibration. The cavitation erosion of water turbines of a plurality of hydropower stations put into operation in China is very serious, so that the output of a unit is reduced, the efficiency is reduced, the vibration is intensified, the stable operation of the hydropower stations is threatened, and the operation safety of a power grid is also seriously threatened.
Although there have been attempts in the prior art to monitor the cavitation condition of water turbines to improve the efficiency of the unit and the safety and stability of the operation of the unit. However, due to the complexity of cavitation, there is no method for effectively monitoring the cavitation of the turbine and improving the efficiency and accuracy of fault diagnosis in the prior art.
Disclosure of Invention
In order to solve the defects in the prior art, the invention provides the method for monitoring the cavitation state of the water turbine based on the acoustic emission technology, which has the advantages of obvious fault characteristics, simple result and strong operability, can improve the efficiency of a unit and the safety and stability of the operation of the unit, realizes the effective monitoring of the cavitation of the water turbine and improves the efficiency and the precision of fault diagnosis.
Specifically, the invention provides a method for integrating empirical mode decomposition (EEMD) and complete integrated empirical mode decomposition (CEEMDAN) with adaptive white noise on the basis of an acoustic emission technology and EMD (empirical mode decomposition) for monitoring the cavitation state of a water turbine, and improves and optimizes the modal aliasing phenomenon occurring in the EMD, thereby solving the problems in the prior art.
In order to achieve the above object, the present invention provides a method for monitoring cavitation state of a water turbine based on acoustic emission, comprising:
loading an original signal of a water turbine;
CEEMDAN signal decomposition;
calculating permutation entropy, namely selecting the first three modes for calculation;
three modes are substituted into a CGWO-FCM calculation clustering center;
selecting a BSA-SVM as a classifier, and based on a trained clustering center, using part of feature quantities as test samples to diagnose;
and obtaining the accuracy of cavitation faults of the water turbine.
In order to achieve the above object, the present invention specifically adopts the following technical solutions:
a method for monitoring the cavitation state of a water turbine based on an acoustic emission technology is characterized in that: the method comprises the following steps:
(1) acquiring and loading vibration signals of the water turbine in a normal state and in a fault state through an acceleration sensor, and preprocessing the acquired and loaded vibration signals;
(2) adopting CEEMDAN to carry out signal decomposition aiming at the signals of the water turbine;
(3) calculating permutation entropy for the first n modes: when the transformer winding is in different fault states, the distribution of the generated vibration signal energy along with the frequency is different; when the signal is decomposed by CEEMDAN, the frequency components contained in n-1 IMF components are different, and MF is obtained by CEEMDAN decomposition1、MF2、…、MFnRespectively calculate their permutation entropy Q1、Q2、Q3、…、Qi、…、Qn,SiThe permutation entropy of the ith Q accounts for the proportion of the total permutation entropy PE, where i is 1,2, … n; taking a plurality of the permutation entropies as characteristic vectors of on-load tap-changer mechanical fault diagnosis;
(4) will Q1、Q2、Q3And carrying out clustering center calculation in CGWO-FCM to serve as a characteristic quantity, and finally selecting BSA-SVM as a classifier to use the characteristic quantity as a test sample for diagnosis.
According to an embodiment of the present invention, in step (2), the decomposition process of CEEMDAN is as follows:
first, operator E is definedk(x) The k-th modal component generated by the EMD method for signal x is denoted as the k-th modal component generated by CEEMDAN
① S (t) is a non-linear and non-stationary original signal sequence, Vi(t) denotes the i-th testThe white noise sequence with standard normal distribution added in the method is used for carrying out I times of tests on the signal, and the 1 st modal component is obtained through EMD decomposition as follows:
② at this stage, when k is 1, the 1 st residue signal is calculated:
③ test I, where I is 1,2, …, I, for the signal r in each test1(t)+ε1E1(Vi(t)) performing EMD until every 1 st modal component is obtained, at which time the second modal component is calculated as follows:
wherein epsilon1Represents added white noise;
④ calculating the K-th residual signal for each subsequent stage, i.e., K2, …, K, of synchronization step ③
The calculation process is consistent, and the calculation of the (k + 1) th modal component is as follows:
wherein epsilonkRepresenting the signal-to-noise ratio of white noise to the original signal;
⑤, the step ④ is continued until the number of the extreme points of the obtained residual signal is not more than 2 at most, and the decomposition is stopped, and then the final residual signal is obtained, that is, the residual signal is:
wherein R (t) represents the remainder.
According to an embodiment of the present invention, in step (2), white noise is added on the basis of EEMD for decomposition during CEEMDAN.
According to an embodiment of the present invention, in step (3), according to a plurality of QiThe corresponding total specific gravity is more than 97.5%, and Q in the arrangement entropy1、Q2、Q3As a feature vector for on-load tap-changer mechanical fault diagnosis.
According to an embodiment of the present invention, in step (4), the center cluster center of the CGWO-FCM is used as the feature quantity.
According to an embodiment of the present invention, in step (4), the training of the cluster center includes: one part of the sample is used as training, the other part of the sample is used as testing for diagnosis, and finally the diagnosis is compared with the traditional SVM so as to carry out validity verification of the method, wherein the method comprises the following steps:
① the initial cluster center of the FCM is improved by using the initial cluster center of CGWO-FCM, wherein the FCM improves the data sample xjDividing into C fuzzy clusters, wherein j is 1,2, …, n, and finding the clustering center of each cluster to minimize the cost function of the non-similarity index, wherein the general form of the objective function of FCM is as follows:
in the formula uijIs the membership of the jth sample belonging to the ith cluster,dijis the Euclidean distance between the ith cluster center and the j data points, dij=||Cj-xjL; m is a weighting index, m belongs to [1, ∞ ]];
② bringing the first three in permutation entropy for training into the CGWO-FCM computational cluster center;
③ the calculated cluster centers are brought into a portion of the BSA-SVM for training, and a portion is tested and compared with other SVM's.
According to an embodiment of the present invention, the proportion of the samples used for training is 80%, and the proportion of the samples used for testing is 20%.
Compared with the traditional SVM, the invention has the following beneficial technical effects:
the method is simple and easy to implement, and is simple; the efficiency of the unit and the safety and stability of the unit operation can be improved, the cavitation of the water turbine can be effectively monitored, and the efficiency and the precision of fault diagnosis can be improved.
Drawings
Fig. 1 is a flow chart of a method for monitoring turbine cavitation conditions based on acoustic emission according to the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following embodiments are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
Fig. 1 is a flow chart of a method for monitoring a cavitation state of a water turbine based on acoustic emission according to the present invention, wherein the method for monitoring a cavitation state of a water turbine based on acoustic emission comprises:
loading an original signal of a water turbine;
CEEMDAN signal decomposition;
calculating permutation entropy, namely selecting the first three modes for calculation;
three modes are substituted into a CGWO-FCM calculation clustering center;
selecting a BSA-SVM as a classifier, and based on a trained clustering center, using part of feature quantities as test samples to diagnose;
and obtaining the accuracy of cavitation faults of the water turbine.
According to the embodiment of the invention, the method for monitoring the cavitation state of the water turbine based on acoustic emission comprises the following steps:
(1) acquiring and loading vibration signals of the water turbine in a normal state and in a fault state through an acceleration sensor, and preprocessing the acquired and loaded vibration signals;
(2) for signals of the water turbine, CEEMDAN is adopted for signal decomposition:
the decomposition process of CEEMDAN is as follows:
first, operator E is definedk(x) The k-th modal component generated by the EMD method for signal x is denoted as the k-th modal component generated by CEEMDAN
① S (t) is a non-linear and non-stationary original signal sequence, Vi(t) represents a white noise sequence with a standard normal distribution added in the ith experiment, the signal is subjected to the I experiment, and the 1 st modal component is obtained by EMD decomposition as follows:
② at this stage, when k is 1, the 1 st residue signal is calculated:
③ test I, where I is 1,2, …, I, for the signal r in each test1(t)+ε1E1(Vi(t)) performing EMD until every 1 st modal component is obtained, at which time the second modal component is calculated as follows:
wherein epsilon1Represents added white noise;
④ for each subsequent stage, i.e. K2, …, K, the K-th residual signal is calculated, the calculation process of the synchronization step ③ is consistent, and the K + 1-th modal component is calculated as follows:
wherein epsilonkRepresenting the signal-to-noise ratio of white noise to the original signal;
⑤, the step ④ is continued until the number of the extreme points of the obtained residual signal is not more than 2 at most, and the decomposition is stopped, and then the final residual signal is obtained, that is, the residual signal is:
wherein R (t) represents the remainder;
(3) calculating permutation entropy for the first n modes: when the transformer winding is in different fault states, the distribution of the generated vibration signal energy along with the frequency is different; when the signal is decomposed by CEEMDAN, the frequency components contained in n-1 IMF components are different, and MF is obtained by CEEMDAN decomposition1、MF2、…、MFnRespectively calculate their permutation entropy Q1、Q2、Q3、…、Qi、…、Qn,SiThe permutation entropy of the ith Q accounts for the proportion of the total permutation entropy PE, where i is 1,2, … n; taking a plurality of the permutation entropies as characteristic vectors of on-load tap-changer mechanical fault diagnosis;
preferably according to multiple QiThe corresponding total weight is more than 97.5%, and the invention arranges Q in the entropy1、Q2、Q3As a feature vector for on-load tap-changer mechanical fault diagnosis;
(4) will Q1、Q2、Q3And carrying out clustering center calculation in CGWO-FCM to serve as a characteristic quantity, and finally selecting BSA-SVM as a classifier to use the characteristic quantity as a test sample for diagnosis.
Wherein the training of the cluster center comprises: one part of the sample is used as training, the other part of the sample is used as testing for diagnosis, and finally the diagnosis is compared with the traditional SVM so as to carry out validity verification of the method, wherein the method comprises the following steps:
① the initial cluster center of the FCM is improved by using the initial cluster center of CGWO-FCM, wherein the FCM improves the data sample xjDividing into C fuzzy clusters, wherein j is 1,2, …, n, and finding the clustering center of each cluster to minimize the cost function of the non-similarity index, wherein the general form of the objective function of FCM is as follows:
in the formula uijIs the membership of the jth sample belonging to the ith cluster,dijis the Euclidean distance between the ith cluster center and the j data points, dij=||Cj-xjL; m is a weighting index, m belongs to [1, ∞ ]];
② bringing the first three in permutation entropy for training into the CGWO-FCM computational cluster center;
③ the calculated cluster centers are brought into a portion of the BSA-SVM for training, and a portion is tested and compared with other SVM's.
Preferably, the proportion of the sample used for training is 80%, and the proportion of the sample used for testing is 20%.
According to a specific embodiment of the invention, the acoustic emission technology is carried out on the water turbine of a certain hydropower station, and the cavitation state diagnosis is carried out by combining the CEEMDAN signal processing method. Where the states are classified as normal and fault. According to the above steps, 50 groups of normal state and cavitation state are used as samples, any 40 groups of data in each group are used as test data, then each 10 groups of data are used as test data, and the arrangement entropy obtained by the first 3 IMF components is used as characteristic quantity, which is equivalent to 120 groups of training group and 30 groups of test group. The results of the prediction of the training set data are shown in table 1, wherein the results of the prediction of the BSA-SVM are compared with the results of the prediction of other SVMs, and it can be seen from the table that the cavitation state of the water turbine can be identified based on acoustic emission combined with the CEEMDAN signal processing method. The diagnosis effect of the invention is superior to that of the traditional SVM. Particularly, the method can improve the efficiency of the unit and the safety and stability of the operation of the unit, realize the effective monitoring of the cavitation of the water turbine and improve the efficiency and the precision of fault diagnosis.
TABLE 1
Claims (8)
1. A method for monitoring the cavitation state of a water turbine based on acoustic emission comprises the following steps:
loading an original signal of a water turbine;
CEEMDAN signal decomposition;
calculating permutation entropy, namely selecting the first three modes for calculation;
three modes are substituted into a CGWO-FCM calculation clustering center;
selecting a BSA-SVM as a classifier, and based on a trained clustering center, using part of feature quantities as test samples to diagnose;
and obtaining the accuracy of cavitation faults of the water turbine.
2. A method for monitoring the cavitation state of a water turbine based on acoustic emission comprises the following steps:
(1) acquiring and loading vibration signals of the water turbine in a normal state and in a fault state through an acceleration sensor, and preprocessing the acquired and loaded vibration signals;
(2) adopting CEEMDAN to carry out signal decomposition aiming at the signals of the water turbine;
(3) calculating permutation entropy for the first n modes: when the transformer winding is in different fault states, the distribution of the generated vibration signal energy along with the frequency is different; when the signal is decomposed by CEEMDAN, the frequency components contained in n-1 IMF components are different, and MF is obtained by CEEMDAN decomposition1、MF2、…、MFnRespectively calculate their permutation entropy Q1、Q2、Q3、…、Qi、…、Qn,SiThe permutation entropy of the ith Q accounts for the proportion of the total permutation entropy PE, where i is 1,2, … n; taking a plurality of the permutation entropies as characteristic vectors of on-load tap-changer mechanical fault diagnosis;
(4) will Q1、Q2、Q3And carrying out clustering center calculation in CGWO-FCM to serve as a characteristic quantity, and finally selecting BSA-SVM as a classifier to use the characteristic quantity as a test sample for diagnosis.
3. The method for monitoring the cavitation state of a water turbine based on acoustic emission technology as claimed in claim 2, wherein: in step (2), the decomposition process of CEEMDAN is as follows:
first, operator E is definedk(x) The k-th modal component generated by the EMD method for signal x is denoted as the k-th modal component generated by CEEMDAN
① S (t) is a non-linear and non-stationary original signal sequence, Vi(t) represents a white noise sequence with a standard normal distribution added in the ith experiment, the signal is subjected to the I experiment, and the 1 st modal component is obtained by EMD decomposition as follows:
② at this stage, when k is 1, the 1 st residue signal is calculated:
③ test I, where I is 1,2, …, I, for the signal r in each test1(t)+ε1E1(Vi(t)) EMD decomposition until the 1 st mode is obtained each timeThe state component, in this case, the second modal component is calculated as follows:
wherein epsilon1Represents added white noise;
④ for each subsequent stage, i.e. K2, …, K, the K-th residual signal is calculated, the calculation process of the synchronization step ③ is consistent, and the K + 1-th modal component is calculated as follows:
wherein epsilonkRepresenting the signal-to-noise ratio of white noise to the original signal;
⑤, the step ④ is continued until the number of the extreme points of the obtained residual signal is not more than 2 at most, and the decomposition is stopped, and then the final residual signal is obtained, that is, the residual signal is:
wherein R (t) represents the remainder.
4. A method for monitoring turbine cavitation conditions based on acoustic emission as set forth in claim 3 wherein: in step (2), white noise is added to the EEMD for decomposition during CEEMDAN.
5. The method for monitoring turbine cavitation condition based on acoustic emission according to claim 4, wherein: in step (3), according to a plurality of QiThe corresponding total specific gravity is more than 97.5%, and Q in the arrangement entropy1、Q2、Q3As on-load tap-changerFeature vectors for mechanical fault diagnosis.
6. The method for monitoring turbine cavitation condition based on acoustic emission according to claim 5, wherein: in the step (4), the center cluster center of the CGWO-FCM is used as the feature quantity.
7. The method for monitoring turbine cavitation conditions based on acoustic emission of claim 6, wherein: in step (4), the training of the cluster center includes: one part of the sample is used as training, the other part of the sample is used as testing for diagnosis, and finally the diagnosis is compared with the traditional SVM so as to carry out validity verification of the method, wherein the method comprises the following steps:
① the initial cluster center of the FCM is improved by using the initial cluster center of CGWO-FCM, wherein the FCM improves the data sample xjDividing into C fuzzy clusters, wherein j is 1,2, …, n, and finding the clustering center of each cluster to minimize the cost function of the non-similarity index, wherein the general form of the objective function of FCM is as follows:
in the formula uijMembership, u, for the jth sample belonging to the ith clusterij∈[0,1],dijIs the Euclidean distance between the ith cluster center and the j data points, dij=||Cj-xjL; m is a weighting index, m belongs to [1, ∞ ]];
② bringing the first three in permutation entropy for training into the CGWO-FCM computational cluster center;
③ the calculated cluster centers are brought into a portion of the BSA-SVM for training, and a portion is tested and compared with other SVM's.
8. The method for monitoring turbine cavitation conditions based on acoustic emission of claim 7, wherein: the above-mentioned proportion of samples for training was 80%, and the proportion of samples for testing was 20%.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911212768.4A CN110987494A (en) | 2019-12-02 | 2019-12-02 | Method for monitoring cavitation state of water turbine based on acoustic emission |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911212768.4A CN110987494A (en) | 2019-12-02 | 2019-12-02 | Method for monitoring cavitation state of water turbine based on acoustic emission |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110987494A true CN110987494A (en) | 2020-04-10 |
Family
ID=70089110
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911212768.4A Pending CN110987494A (en) | 2019-12-02 | 2019-12-02 | Method for monitoring cavitation state of water turbine based on acoustic emission |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110987494A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113155266A (en) * | 2021-03-08 | 2021-07-23 | 西安理工大学 | Water turbine cavitation initial determination method integrating vibration test and pressure pulsation test |
CN113571136A (en) * | 2021-06-08 | 2021-10-29 | 广州地铁设计研究院股份有限公司 | Polycyclic aromatic hydrocarbon prediction method, device, medium and equipment |
WO2021250549A1 (en) * | 2020-06-08 | 2021-12-16 | Canadian Powerplus Corporation | System and method for cavitation reduction using an adjustable weir |
CN114934868A (en) * | 2022-06-06 | 2022-08-23 | 兰州工业学院 | AE and EMD wireless transmission fused hydroelectric generating set cavitation detection method |
CN116662920A (en) * | 2023-07-31 | 2023-08-29 | 深圳大学 | Abnormal data identification method, system, equipment and medium for drilling and blasting method construction equipment |
CN117476039A (en) * | 2023-12-25 | 2024-01-30 | 西安理工大学 | Acoustic signal-based primary cavitation early warning method for water turbine |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109253872A (en) * | 2018-09-17 | 2019-01-22 | 华西能源工程有限公司 | A kind of rotor operation state monitoring method based on CEEMDAN |
CN110146268A (en) * | 2019-05-28 | 2019-08-20 | 河海大学 | A kind of OLTC method for diagnosing faults based on mean value decomposition algorithm |
-
2019
- 2019-12-02 CN CN201911212768.4A patent/CN110987494A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109253872A (en) * | 2018-09-17 | 2019-01-22 | 华西能源工程有限公司 | A kind of rotor operation state monitoring method based on CEEMDAN |
CN110146268A (en) * | 2019-05-28 | 2019-08-20 | 河海大学 | A kind of OLTC method for diagnosing faults based on mean value decomposition algorithm |
Non-Patent Citations (6)
Title |
---|
张鹏林 等: "基于CEEMDAN-深度信念网络的超低速滚动轴承故障诊断", 《组合机床与自动化加工》 * |
石月春 等: "《水轮发电机组状态监测技术研究与实践》", 31 December 2016 * |
肖海军 等: "基于鸟群算法的SVM参数选择", 《中南民族大学学报(自然科学版)》 * |
谢亮亮 等: "基于灰狼优化的模糊C-均值聚类算法", 《软件导刊》 * |
韩龙 等: "滚动轴承声发射信号降噪的CEEMDAN算法", 《黑龙江科技大学学报》 * |
齐丙娟 等: "基于FCM隶属度的支持向量机", 《微电子学与计算机》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021250549A1 (en) * | 2020-06-08 | 2021-12-16 | Canadian Powerplus Corporation | System and method for cavitation reduction using an adjustable weir |
CN113155266A (en) * | 2021-03-08 | 2021-07-23 | 西安理工大学 | Water turbine cavitation initial determination method integrating vibration test and pressure pulsation test |
CN113155266B (en) * | 2021-03-08 | 2022-11-01 | 西安理工大学 | Water turbine cavitation initiation determination method integrating vibration test and pressure pulsation test |
CN113571136A (en) * | 2021-06-08 | 2021-10-29 | 广州地铁设计研究院股份有限公司 | Polycyclic aromatic hydrocarbon prediction method, device, medium and equipment |
CN114934868A (en) * | 2022-06-06 | 2022-08-23 | 兰州工业学院 | AE and EMD wireless transmission fused hydroelectric generating set cavitation detection method |
CN114934868B (en) * | 2022-06-06 | 2024-03-01 | 重庆水利电力职业技术学院 | Cavitation detection method for hydroelectric generating set by combining AE and EMD through wireless transmission |
CN116662920A (en) * | 2023-07-31 | 2023-08-29 | 深圳大学 | Abnormal data identification method, system, equipment and medium for drilling and blasting method construction equipment |
CN116662920B (en) * | 2023-07-31 | 2023-10-24 | 深圳大学 | Abnormal data identification method, system, equipment and medium for drilling and blasting method construction equipment |
CN117476039A (en) * | 2023-12-25 | 2024-01-30 | 西安理工大学 | Acoustic signal-based primary cavitation early warning method for water turbine |
CN117476039B (en) * | 2023-12-25 | 2024-03-08 | 西安理工大学 | Acoustic signal-based primary cavitation early warning method for water turbine |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110987494A (en) | Method for monitoring cavitation state of water turbine based on acoustic emission | |
Qin et al. | The optimized deep belief networks with improved logistic sigmoid units and their application in fault diagnosis for planetary gearboxes of wind turbines | |
CN109376801B (en) | Wind driven generator blade icing diagnosis method based on integrated deep neural network | |
CN109753951A (en) | A kind of OLTC method for diagnosing faults based on instantaneous energy entropy and SVM | |
CN102221655A (en) | Random-forest-model-based power transformer fault diagnosis method | |
CN103115789A (en) | Second generation small-wave support vector machine assessment method for damage and remaining life of metal structure | |
Di et al. | Ensemble deep transfer learning driven by multisensor signals for the fault diagnosis of bevel-gear cross-operation conditions | |
CN108921347B (en) | Wind power converter fault prediction method | |
CN109472288A (en) | A kind of pump-storage generator vibration hybrid feature extraction and classification method | |
CN111077386A (en) | Early fault signal noise reduction method for electrical equipment | |
Afrasiabi et al. | Wind turbine fault diagnosis with generative-temporal convolutional neural network | |
CN113255458A (en) | Bearing fault diagnosis method based on multi-view associated feature learning | |
CN116089857A (en) | Transformer fault identification method based on CEEMDAN-DBN | |
CN112036718B (en) | Electric power system safety risk assessment method considering new energy uncertainty | |
CN114386452A (en) | Method for detecting faults of sun wheel of nuclear power circulating water pump | |
CN111639852B (en) | Real-time evaluation method and system for vibration state of hydroelectric generating set based on wavelet singular value | |
CN112990710A (en) | DEA-based wind power plant electric energy quality multi-level comprehensive evaluation method | |
Yan et al. | Fault diagnosis of wind turbine based on PCA and GSA-SVM | |
CN113255215B (en) | Lithium battery health state estimation method based on voltage segments | |
CN114814391A (en) | Charging pile fault identification method and storage medium | |
CN114662584A (en) | Method for detecting electricity stealing and electricity leakage of user in large range based on time convolution network | |
CN111242345A (en) | Nuclear power unit electric power prediction method based on cluster analysis and random forest regression | |
Yang et al. | Attachment Fault Diagnosis for Tidal Stream Turbine based on Improved ShuffleNet_v2 | |
Zhang et al. | Non-intrusive load recognition method based on combined weighting-TOPSIS algorithm | |
CN117390508B (en) | Hydroelectric generating set signal state identification method based on time-shifting multi-scale cosine similarity entropy |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200410 |