CN113837251A - Petroleum pipeline vibration detection device based on GA-SVM and control method thereof - Google Patents
Petroleum pipeline vibration detection device based on GA-SVM and control method thereof Download PDFInfo
- Publication number
- CN113837251A CN113837251A CN202111061562.3A CN202111061562A CN113837251A CN 113837251 A CN113837251 A CN 113837251A CN 202111061562 A CN202111061562 A CN 202111061562A CN 113837251 A CN113837251 A CN 113837251A
- Authority
- CN
- China
- Prior art keywords
- support vector
- vector machine
- parameters
- svm
- vibration
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 239000003208 petroleum Substances 0.000 title claims abstract description 28
- 238000001514 detection method Methods 0.000 title claims abstract description 14
- 238000012706 support-vector machine Methods 0.000 claims abstract description 73
- 230000002068 genetic effect Effects 0.000 claims abstract description 35
- 238000012549 training Methods 0.000 claims abstract description 13
- 238000012360 testing method Methods 0.000 claims abstract description 12
- 238000005457 optimization Methods 0.000 claims abstract description 10
- 230000008569 process Effects 0.000 claims abstract description 9
- 238000002790 cross-validation Methods 0.000 claims abstract description 6
- 108090000623 proteins and genes Proteins 0.000 claims description 16
- 230000035772 mutation Effects 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 206010064571 Gene mutation Diseases 0.000 claims description 5
- 230000036541 health Effects 0.000 claims description 5
- 108700028369 Alleles Proteins 0.000 claims description 3
- 230000008878 coupling Effects 0.000 claims description 3
- 238000010168 coupling process Methods 0.000 claims description 3
- 238000005859 coupling reaction Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 abstract description 11
- 238000004364 calculation method Methods 0.000 abstract description 4
- 239000013598 vector Substances 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D5/00—Protection or supervision of installations
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mechanical Engineering (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a GA-SVM (genetic algorithm-support vector machine) -based petroleum pipeline vibration detection device and a control method thereof, wherein a check valve, two symmetrical switch valves, a pump, a motor and a vibration sensor are arranged on a petroleum pipeline; and optimizing the parameters of the trained support vector machine model by using an evolutionary parameter optimization algorithm, namely a genetic algorithm. Performing parameter optimization on the multi-classification support vector machine by using a genetic algorithm, wherein objects to be optimized are a penalty factor C and a Gaussian kernel function parameter g; training a multi-classification support vector machine according to set SVM parameters and input samples, and testing by using a cross validation method to obtain the accuracy of the multi-classification support vector machine, wherein the accuracy is used as the individual fitness; the method has the advantages of low calculated amount and low occupied amount of the program memory, reduces the error probability in the calculation process and improves the probability of correct final classification.
Description
Technical Field
The invention relates to a petroleum pipeline vibration detection device based on a GA-SVM and a control method thereof, which are oriented to the requirement of pipeline state recognition and applied to the field of pipeline health state monitoring.
Background
Genetic Algorithm (GA) is a global search Algorithm, and the idea of the Algorithm refers to the evolutionary theory and the Genetic theory of organisms. The algorithm is visual in thought, mature in implementation method, self-adaptive and comprehensive, and is often applied to the fields of optimization, image processing, data mining and the like in engineering practice.
In the genetic algorithm, the setting change of some parameters has a great influence on the calculation result. For example, the number of individuals in the population affects the search range, and when the number of the population is not large enough, the search in the whole range is not easy to be realized in the search optimization process, which causes the problem of insufficient coverage of the search range. For another example, because gene crossing is the main way to generate new individuals, when the probability of gene crossing is too small, the population stability is too strong, and it is difficult to perform effective search on the whole range, which affects the performance of the algorithm. In addition to these, parameters such as mutation probability and planting algebra also have a great influence on the performance of the genetic algorithm.
A Support Vector Machine (SVM) is a widely accepted classification method, and the main theoretical basis of the method is a statistical learning related theoretical basis. The basis of the SVM is the structure risk minimization principle of a statistical learning theory and a VC dimension theory. In the process, the input sample may be in a low-dimensional nonlinear space initially, and the sample is mapped to a high-dimensional linear space based on a kernel function and a nonlinear support vector machine theory, so that the class division of the input sample is realized. The support vector machine has many advantages, such as relatively high fitting precision, relatively strong learning ability, fast training speed, few parameters needing to be selected, difficult falling into local optimal solution, and suitability for popularization and divergence, and the characteristics provide good solution ideas and solutions for the problems of small samples, nonlinearity and the like.
The support vector machine is a supervised machine learning algorithm, and selects a series of feature subsets during the basic principle, thereby realizing the equivalent classification of a target function on the series of feature subsets and the classification of an integral data set. This subset of features is called Support Vector (SV). Support vector machine algorithms are often used in engineering applications for classification between different samples. In general, it has several advantages as follows:
(1) the classification condition of the final algorithm of the support vector machine depends on a series of feature subsets in all samples instead of a sample complete set, all operations are carried out according to the selected series of feature subsets, and the final classification condition is irrelevant to the dimension of the samples, so that the calculation amount of the support vector machine algorithm is reduced, the occupation amount of a program memory is also reduced, the error probability in the calculation process is reduced, and the final classification correct probability is improved;
(2) the classification condition of the final algorithm of the support vector machine is determined by a group of feature vectors, so that most of the vectors except the feature vectors can be omitted, redundant irrelevant samples are removed, and the training time and the classification time are greatly reduced;
(3) the support vector machine is easy to popularize, can be almost applied to the classification problem of various industries, and is widely applied to various fields and industries.
The result of the machine learning algorithm depends on parameters, and the specific setting of the parameters also restricts the classification effect of the support vector machine. Therefore, optimizing the parameters of the support vector machine and further selecting the proper parameters of the support vector machine are important ways for improving the performance of the support vector machine.
Disclosure of Invention
The invention provides a GA-SVM (genetic algorithm-support vector machine) -based petroleum pipeline vibration detection device and a control method thereof.
The invention is realized by the following scheme:
a petroleum pipeline vibration detection device based on GA-SVM:
the petroleum pipeline is provided with a check valve, two symmetrical switch valves, a pump, a motor and a vibration sensor;
the motor is connected with the pump through a coupling, a motor shaft and a pump shaft;
the check valve, the two symmetrical switch valves, the pump and the petroleum pipeline form a branch; when the check valve is closed, oil is conveyed through the branch;
the vibration sensors are respectively arranged on the motor, the pump and the petroleum pipeline.
Further, during the operation of the petroleum pipeline, 6 working states are divided:
(1) no vibration exists; (2) knocking and vibrating; (3) normal vibration; (4) abnormal vibration of the rotating speed of the motor; (5) abnormal vibration due to misalignment of the rotor; (6) abnormal vibration caused by loosening of the connecting piece;
the pipeline health is detected through a vibration sensor, specific vibration is generated according to a vibration table, a data board card is used for collecting signals, classification is carried out through a Support Vector Machine (SVM) algorithm, and Support Vector Machine (SVM) parameters are optimized through a Genetic Algorithm (GA).
A control method applied to a GA-SVM-based petroleum pipeline vibration detection device comprises the following steps:
the process for optimizing SVM parameters by using a genetic algorithm comprises the following steps:
step 1: and (3) encoding: given the parameters that need to be optimized in the support vector machine SVM given the situation given to the sample set of the input in the support vector machine SVM,
the parameters to be optimized of the support vector machine are set as follows: the penalty factor C, the Gaussian kernel function parameter g and other parameters of the genetic algorithm are respectively set as: the method comprises the following steps of (1) setting a search range for optimizing parameters, namely initial population quantity sizespop, maximum evolution algebra maxgen, gene crossing probability pcrossover, and gene mutation probability pmutation, and coding the parameters;
step 2: generating an initial population: randomly generating individuals and genotypes of the initial population;
and step 3: calculating the fitness of the individual: training a multi-classification support vector machine, testing by using a cross validation method to obtain the accuracy of the multi-classification support vector machine, and taking the accuracy as the fitness of the individual corresponding to the genotype under the parameters;
and 4, step 4: selecting: selecting individuals from all individuals of the population of the current generation to copy according to the fitness value; the probability that each individual is replicated is related to the magnitude of the fitness;
and 5: and (3) crossing: pairing all individuals in the population pairwise, calculating whether crossover occurs in the combination according to crossover operators, and calculating the size and the position of a crossover gene segment, and performing gene crossover operation to generate a new genotype;
step 6: mutation: carrying out mutation operation on all individuals in the population by using a mutation operator, and changing a certain gene in the individual into an allele thereof with a certain probability;
and 7: and (4) judging termination conditions: selecting the current evolution interpage number to compare with the set interpage number, and if the current evolution interpage number does not reach the set interpage number, repeating the steps 2 to 6; if the optimal penalty factor C is reached, stopping the operation, outputting a parameter optimization result and obtaining the optimal penalty factor CbestOptimum Gaussian kernel function 1/σ2 best。
The invention has the beneficial effects
(1) The method optimizes the parameters of the trained support vector machine model by using an evolutionary parameter optimization algorithm, namely a genetic algorithm;
(2) the invention uses genetic algorithm to optimize the parameters of the multi-classification support vector machine, and the objects to be optimized are penalty factor C and Gaussian kernel function parameter g
(3) According to the method, on the data set, when the genetic algorithm runs to the generation, the average fitness value is increased to the maximum value and tends to a steady state, the optimal fitness value is kept unchanged along with the increase of the iteration number, and the algorithm is stopped until the genetic algorithm runs to the generation 100.
Drawings
FIG. 1 is a flow chart of the present invention for optimizing SVM parameters using a genetic algorithm;
FIG. 2 is a fitness curve and test results output by the genetic algorithm of the present invention;
fig. 3 is a simplified diagram of the vibration sensor mounting of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments; all other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In conjunction with the figures 1 to 3,
a GA-SVM based petroleum pipeline vibration detection device and a control method thereof are disclosed, wherein an evolutionary parameter optimization algorithm, namely a genetic algorithm, is used for optimizing the model parameters of a trained support vector machine, the genetic algorithm is used for optimizing the parameters of a multi-classification support vector machine, the objects to be optimized are a penalty factor C and a Gaussian kernel function parameter g, and a flow chart of SVM parameter optimization by the genetic algorithm is shown in an attached figure 1. The vibration sensor for pipeline health detection is mainly applied to a petroleum pipeline pump scene. In petroleum pipelines, vibration sensors are mounted on motors and pumps, and the structure diagram is shown in FIG. 3.
A petroleum pipeline vibration detection device based on GA-SVM:
the petroleum pipeline is provided with a check valve, two symmetrical switch valves, a pump, a motor and a vibration sensor;
the motor is connected with the pump through a coupling, a motor shaft and a pump shaft;
the check valve, the two symmetrical switch valves, the pump and the petroleum pipeline form a branch; when the check valve is closed, oil is conveyed through the branch;
the vibration sensors are respectively arranged on the motor, the pump and the petroleum pipeline.
In the running process of the petroleum pipeline, 6 working states are divided:
(1) no vibration exists; (2) knocking and vibrating; (3) normal vibration; (4) abnormal vibration of the rotating speed of the motor; (5) abnormal vibration due to misalignment of the rotor; (6) abnormal vibration caused by loosening of the connecting piece;
the pipeline health is detected through a vibration sensor, specific vibration is generated according to a vibration table, a data board card is used for collecting signals, classification is carried out through a Support Vector Machine (SVM) algorithm, and Support Vector Machine (SVM) parameters are optimized through a Genetic Algorithm (GA).
A control method applied to a GA-SVM-based petroleum pipeline vibration detection device comprises the following steps:
the process for optimizing SVM parameters by using a genetic algorithm comprises the following steps:
step 1: and (3) encoding: given the parameters that need to be optimized in the support vector machine SVM given the situation given to the sample set of the input in the support vector machine SVM,
the parameters to be optimized of the support vector machine are set as follows: the penalty factor C, the Gaussian kernel function parameter g and other parameters of the genetic algorithm are respectively set as: the method comprises the following steps of (1) setting a search range for optimizing parameters, namely initial population quantity sizespop, maximum evolution algebra maxgen, gene crossing probability pcrossover, and gene mutation probability pmutation, and coding the parameters;
step 2: generating an initial population: randomly generating individuals and genotypes of the initial population;
and step 3: calculating the fitness of the individual: training a multi-classification support vector machine, testing by using a cross validation method to obtain the accuracy of the multi-classification support vector machine, and taking the accuracy as the fitness of the individual corresponding to the genotype under the parameters;
and 4, step 4: selecting: selecting individuals from all individuals of the population of the current generation to copy according to the fitness value; the probability that each individual is replicated is related to the magnitude of the fitness;
and 5: and (3) crossing: pairing all individuals in the population pairwise, calculating whether crossover occurs in the combination according to crossover operators, and calculating the size and the position of a crossover gene segment, and performing gene crossover operation to generate a new genotype;
step 6: mutation: carrying out mutation operation on all individuals in the population by using a mutation operator, and changing a certain gene in the individual into an allele thereof with a certain probability;
and 7: and (4) judging termination conditions: selecting the current evolution interpage number to compare with the set interpage number, and if the current evolution interpage number does not reach the set interpage number, repeating the steps 2 to 6; if the optimal penalty factor C is reached, stopping the operation, outputting a parameter optimization result and obtaining the optimal penalty factor CbestOptimum Gaussian kernel function 1/σ2 best。
In the actual design, the parameters to be optimized of the support vector machine are set as follows: c is more than or equal to 0 and less than or equal to 100, and 0 is more than or equal to 1/sigma2Less than or equal to 1000. Other parameters of the genetic algorithm are respectively set as: the number of initial populations sizespop is 50, the maximum evolution generation maxgen is 100, the gene crossover probability pcrossover is 0.5, and the gene mutation probability pmutation is 0.1. Training a multi-classification support vector machine according to set SVM parameters and input samples, and testing by using a cross validation method to obtain the accuracy of the multi-classification support vector machine, wherein the accuracy is used as the individual fitness.
The training results show that the fitness curve and the test results output by the genetic algorithm are shown in the attached figure 2. The fitness curve of figure 2 shows that on this data set, after the genetic algorithm has run through 24 generations, the average fitness value increases to a maximum value and tends to plateau, while the best fitness increases until it reaches a maximum value after 31 generations and does not change until after 100 generations, the algorithm stops. At this time, the optimal penalty factor C is Cbest13.797, optimal Gaussian kernel function 1/σ2Parameter is 1/sigma2 best0.516. When C is 13.797, 1/sigma2The classification results for the training set and the test set are shown in table 1, when it is 0.516.
TABLE 1 training set and test set Classification results
TABLE 2 genetic Algorithm parameter settings
Penalty factor C and Gaussian kernel function 1/sigma for support vector machine using genetic algorithm2And optimizing the parameters. The genetic algorithm parameter settings are as in table 2. In the actual design, the parameters to be optimized of the support vector machine are set as follows: c is more than or equal to 0 and less than or equal to 100, and 0 is more than or equal to 1/sigma2Less than or equal to 1000. Other parameters of the genetic algorithm are respectively set as: the number of initial populations sizespop is 50, the maximum evolution generation maxgen is 100, the gene crossover probability pcrossover is 0.5, and the gene mutation probability pmutation is 0.1. Training a multi-classification support vector machine according to set SVM parameters and input samples, and testing by using a cross validation method to obtain the accuracy of the multi-classification support vector machine, wherein the accuracy is used as the individual fitness.
The training results show that the fitness curve and the test results output by the genetic algorithm are shown in the attached figure 2. On the data set, when the average fitness value of the genetic algorithm increases to the maximum value and tends to a steady state after running to the generation, the optimal fitness value keeps unchanged along with the increase of the iteration number until the algorithm stops after running to 100 generations. The cvccuracy of the figure is 100% of the classification result on the training set, and the output SVM optimal parameter C is 14.6203, and g is 0.095564. When the parameters C-14.6203 and g-0.095564, the classification accuracy on the test set is shown in table 1.
The GA-SVM-based petroleum pipeline vibration detection apparatus and the control method thereof proposed by the present invention are described in detail above, and the principle and the implementation of the present invention are explained, and the above description of the embodiments is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (3)
1. The utility model provides a petroleum pipeline vibration detection device based on GA-SVM which characterized in that:
the petroleum pipeline is provided with a check valve, two symmetrical switch valves, a pump, a motor and a vibration sensor;
the motor is connected with the pump through a coupling, a motor shaft and a pump shaft;
the check valve, the two symmetrical switch valves, the pump and the petroleum pipeline form a branch; when the check valve is closed, oil is conveyed through the branch;
the vibration sensors are respectively arranged on the motor, the pump and the petroleum pipeline.
2. The apparatus of claim 1, wherein:
in the running process of the petroleum pipeline, 6 working states are divided:
(1) no vibration exists; (2) knocking and vibrating; (3) normal vibration; (4) abnormal vibration of the rotating speed of the motor; (5) abnormal vibration due to misalignment of the rotor; (6) abnormal vibration caused by loosening of the connecting piece;
the pipeline health is detected through a vibration sensor, specific vibration is generated according to a vibration table, a data board card is used for collecting signals, classification is carried out through a Support Vector Machine (SVM) algorithm, and Support Vector Machine (SVM) parameters are optimized through a Genetic Algorithm (GA).
3. A control method applied to a GA-SVM-based petroleum pipeline vibration detection device is characterized by comprising the following steps:
the process for optimizing SVM parameters by using a genetic algorithm comprises the following steps:
step 1: and (3) encoding: given the parameters that need to be optimized in the support vector machine SVM given the situation given to the sample set of the input in the support vector machine SVM,
the parameters to be optimized of the support vector machine are set as follows: the penalty factor C, the Gaussian kernel function parameter g and other parameters of the genetic algorithm are respectively set as: the method comprises the following steps of (1) setting a search range for optimizing parameters, namely initial population quantity sizespop, maximum evolution algebra maxgen, gene crossing probability pcrossover, and gene mutation probability pmutation, and coding the parameters;
step 2: generating an initial population: randomly generating individuals and genotypes of the initial population;
and step 3: calculating the fitness of the individual: training a multi-classification support vector machine, testing by using a cross validation method to obtain the accuracy of the multi-classification support vector machine, and taking the accuracy as the fitness of the individual corresponding to the genotype under the parameters;
and 4, step 4: selecting: selecting individuals from all individuals of the population of the current generation to copy according to the fitness value; the probability that each individual is replicated is related to the magnitude of the fitness;
and 5: and (3) crossing: pairing all individuals in the population pairwise, calculating whether crossover occurs in the combination according to crossover operators, and calculating the size and the position of a crossover gene segment, and performing gene crossover operation to generate a new genotype;
step 6: mutation: carrying out mutation operation on all individuals in the population by using a mutation operator, and changing a certain gene in the individual into an allele thereof with a certain probability;
and 7: and (4) judging termination conditions: selecting the current evolution interpage number to compare with the set interpage number, and if the current evolution interpage number does not reach the set interpage number, repeating the steps 2 to 6; if the optimal penalty factor C is reached, stopping the operation, outputting a parameter optimization result and obtaining the optimal penalty factor CbestOptimum Gaussian kernel function 1/σ2 best。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111061562.3A CN113837251A (en) | 2021-09-10 | 2021-09-10 | Petroleum pipeline vibration detection device based on GA-SVM and control method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111061562.3A CN113837251A (en) | 2021-09-10 | 2021-09-10 | Petroleum pipeline vibration detection device based on GA-SVM and control method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113837251A true CN113837251A (en) | 2021-12-24 |
Family
ID=78958917
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111061562.3A Pending CN113837251A (en) | 2021-09-10 | 2021-09-10 | Petroleum pipeline vibration detection device based on GA-SVM and control method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113837251A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040167721A1 (en) * | 2001-07-27 | 2004-08-26 | Masahiro Murakawa | Optimal fitting parameter determining method and device, and optimal fitting parameter determining program |
| CN202281044U (en) * | 2011-10-21 | 2012-06-20 | 王宇慧 | Pressure-stabilizing system for oil transmission pipeline |
| CN106053067A (en) * | 2016-05-24 | 2016-10-26 | 广东石油化工学院 | Bearing fault diagnosis method based on quantum genetic algorithm optimized support vector machine |
| CN106596116A (en) * | 2016-11-29 | 2017-04-26 | 西安理工大学 | Vibration fault diagnosis method of wind generating set |
| CN107796507A (en) * | 2017-09-18 | 2018-03-13 | 洛阳双瑞精铸钛业有限公司 | A kind of heat-exchange unit Vibration Condition Monitoring platform |
| CN110044602A (en) * | 2019-03-15 | 2019-07-23 | 昆明理工大学 | A kind of high-pressure diaphragm pump one-way valve fault diagnostic method based on analysis of vibration signal |
| CN112150413A (en) * | 2020-09-01 | 2020-12-29 | 珠海格力电器股份有限公司 | Pipeline vibration detection method, device, equipment and storage medium |
| CN113119425A (en) * | 2021-03-22 | 2021-07-16 | 广东工业大学 | Injection molding product quality prediction method based on improved support vector machine |
-
2021
- 2021-09-10 CN CN202111061562.3A patent/CN113837251A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040167721A1 (en) * | 2001-07-27 | 2004-08-26 | Masahiro Murakawa | Optimal fitting parameter determining method and device, and optimal fitting parameter determining program |
| CN202281044U (en) * | 2011-10-21 | 2012-06-20 | 王宇慧 | Pressure-stabilizing system for oil transmission pipeline |
| CN106053067A (en) * | 2016-05-24 | 2016-10-26 | 广东石油化工学院 | Bearing fault diagnosis method based on quantum genetic algorithm optimized support vector machine |
| CN106596116A (en) * | 2016-11-29 | 2017-04-26 | 西安理工大学 | Vibration fault diagnosis method of wind generating set |
| CN107796507A (en) * | 2017-09-18 | 2018-03-13 | 洛阳双瑞精铸钛业有限公司 | A kind of heat-exchange unit Vibration Condition Monitoring platform |
| CN110044602A (en) * | 2019-03-15 | 2019-07-23 | 昆明理工大学 | A kind of high-pressure diaphragm pump one-way valve fault diagnostic method based on analysis of vibration signal |
| CN112150413A (en) * | 2020-09-01 | 2020-12-29 | 珠海格力电器股份有限公司 | Pipeline vibration detection method, device, equipment and storage medium |
| CN113119425A (en) * | 2021-03-22 | 2021-07-16 | 广东工业大学 | Injection molding product quality prediction method based on improved support vector machine |
Non-Patent Citations (1)
| Title |
|---|
| 张建平等: "《电气设备检修技术问答》", 中国电力出版社, pages: 215 - 216 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113505655B (en) | Intelligent bearing fault diagnosis method for digital twin system | |
| CN105678343A (en) | Adaptive-weighted-group-sparse-representation-based diagnosis method for noise abnormity of hydroelectric generating set | |
| US20160335548A1 (en) | Methods and apparatus for predicting fault occurrence in mechanical systems and electrical systems | |
| CN115115090A (en) | Wind power short-term prediction method based on improved LSTM-CNN | |
| CN109472302A (en) | A kind of support vector machine ensembles learning method based on AdaBoost | |
| CN112611584A (en) | Fatigue failure detection method, device, equipment and medium for wind generating set | |
| CN107239789A (en) | A kind of industrial Fault Classification of the unbalanced data based on k means | |
| CN115600140A (en) | Fan variable pitch system fault identification method and system based on multi-source data fusion | |
| CN111207067A (en) | Air compressor fault diagnosis method based on fuzzy support vector machine | |
| Yin et al. | Deep learning based feature reduction for power system transient stability assessment | |
| CN115545070A (en) | Intelligent diagnosis method for unbalance-like bearing based on comprehensive balance network | |
| CN113837251A (en) | Petroleum pipeline vibration detection device based on GA-SVM and control method thereof | |
| CN108536877B (en) | Method and system for evaluating vibration degree of wind generating set | |
| Xiong et al. | Combining the Multi‐Genetic Algorithm and Support Vector Machine for Fault Diagnosis of Bearings | |
| CN116522121A (en) | Transformer online fault diagnosis method under unbalanced small sample condition | |
| CN114595788B (en) | Transformer fault diagnosis method, device and equipment | |
| CN116541778A (en) | Equipment data processing and caching method based on Internet of things | |
| CN108459585B (en) | Power station fan fault diagnosis method based on sparse local embedded deep convolutional network | |
| CN113837096B (en) | Rolling bearing fault diagnosis method based on GA random forest | |
| Qiao et al. | Study on K-means method based on Data-Mining | |
| CN113610148A (en) | Fault diagnosis method based on bias weighting AdaBoost | |
| CN116432507A (en) | Method and device for predicting oxygen content of boiler flue gas and computing equipment | |
| CN110874088B (en) | Monitoring method of ship key equipment system based on multi-dimensional vector model | |
| CN116010896B (en) | Wind driven generator fault diagnosis method based on countermeasure training and transducer | |
| CN110032981B (en) | Rotary machine fault identification method based on improved support vector machine |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Tian Zhongshan Inventor after: Yi Lin Inventor after: Yang Changqun Inventor after: Niu Daodong Inventor after: Liang Jiaming Inventor before: Tian Zhongshan Inventor before: Yi Lin Inventor before: Yang Changqun Inventor before: Niu Daodong Inventor before: Liang Gaming |