CN113609787A - Electric valve fault diagnosis method, terminal equipment and readable storage medium - Google Patents
Electric valve fault diagnosis method, terminal equipment and readable storage medium Download PDFInfo
- Publication number
- CN113609787A CN113609787A CN202110993663.8A CN202110993663A CN113609787A CN 113609787 A CN113609787 A CN 113609787A CN 202110993663 A CN202110993663 A CN 202110993663A CN 113609787 A CN113609787 A CN 113609787A
- Authority
- CN
- China
- Prior art keywords
- sample
- groups
- electric valve
- fault diagnosis
- training
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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
- G06F18/24—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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a fault diagnosis method for an electric valve, which is based on a support vector machine and comprises the steps of collecting a plurality of groups of sample data in the working process of the electric valve; inputting the collected sample data into a support vector machine in groups; the support vector machine trains a classification model by inputting sample data and obtains a final classification model; inputting real-time data in the opening and closing process of the electric valve, and performing fault diagnosis through a classification model; the invention provides a diagnosis method based on a support vector machine and k-fold optimization, which fully utilizes limited fault data samples to train to obtain an optimal fault diagnosis model, and the model can be utilized to greatly improve the accuracy of fault diagnosis of an electric valve.
Description
Technical Field
The invention relates to the field of fault diagnosis, in particular to a fault diagnosis method for an electric valve, terminal equipment and a readable storage medium.
Background
In scientific research and engineering, the electric valve is an important component equipment of a reactor and a loop system. Once the electric valve can not be normally opened or closed in the working process, the safe operation of the reactor can be influenced, and even the reactor is stopped.
The opening and closing times of the electric valve in a loop system are not frequent, data acquired during operation are relatively few, particularly fault data are more scarce, and the small sample data have great significance for fault diagnosis of the electric valve.
How to correctly diagnose the fault information of the electric valve by using the limited fault data is a problem which is urgently needed to be solved at present.
Disclosure of Invention
The invention aims to solve the technical problem that the electric valve has less operation data, and aims to provide a fault diagnosis method, terminal equipment and a readable storage medium for the electric valve, so that the fault diagnosis problem of the electric valve is solved.
The invention is realized by the following technical scheme:
a fault diagnosis method for an electric valve is based on a support vector machine and comprises the following steps:
s1, collecting multiple groups of sample data in the working process of the electric valve;
s2, inputting the collected sample data into a support vector machine in groups;
s3, the support vector machine trains a classification model by inputting sample data and obtains a final classification model;
and S4, inputting real-time data in the opening and closing process of the electric valve, and performing fault diagnosis through a classification model.
Specifically, step S1 specifically includes the following steps:
s11, collecting sample signals by taking one valve opening action and one valve closing action as a collecting period;
the sample signals comprise AB phase voltage signals, BC phase voltage signals, CA phase voltage signals, A phase current signals, B phase current signals, C phase current signals, A phase power signals, B phase power signals, C phase power signals and total power signals;
s12, extracting characteristic quantity of the collected sample signals to obtain a plurality of groups of sample data, wherein the plurality of groups of sample data comprise n groups of normal samples and m groups of abnormal samples, and n is larger than m;
wherein the sample data comprises: mean, maximum, minimum, variance, root mean square, skewness, and kurtosis.
Specifically, step S2 specifically includes the following steps:
s21, dividing n groups of normal samples into two groups, and dividing m groups of abnormal samples into k groups;
wherein the normal sample comprises T1Group sum T2Group (d);
s22, mixing T2Taking the group and any abnormal sample as test samples;
s23, mixing T1Taking the abnormal samples of the group and the rest k-1 groups as training samples;
s24, inputting the training sample and the testing sample into a support vector machine, and repeating the steps S22-S23 k times;
each abnormal sample in the k groups of abnormal samples is required to be used as a test sample for training;
specifically, in step S3, the penalty parameter and the kernel function parameter need to be optimized by a k-fold cross validation method, and the specific optimization method includes the following steps:
s31 initialization scope parameter n1And n2The optimal classification accuracy rate b _ A, the optimal penalty coefficient b _ c and the optimal kernel function parameter value b _ g;
s32, assigning a value to the penalty coefficient c, wherein the value is assigned according to the formula
S33, assigning the kernel function parameter g with the assignment formula
S34, training k models according to the data input in the step S2, and obtaining the average classification accuracy A;
s35, if A > b _ A, jumping to step S36; otherwise, go directly to step S37;
s36, assigning values to b _ A, b _ c and b _ g, so that b _ a is a, b _ c is c, and b _ g is g;
s37, judgment
If yes, go to step S38; if not, assigning a value to g, and assigning a formula: g ═ g + t2Then, it goes to step S34;
wherein t is2The iteration step length when the kernel function parameters are optimized is obtained;
s38, judging c + t1＞2n1And if not, assigning a value to the c, and assigning a formula: c ═ c + t1Then, it goes to step S33; if yes, outputting b _ c and b _ g;
wherein t is1The iteration step length when the penalty coefficient is optimized;
and S39, training to obtain a final classification model by using the output b _ c and b _ g as training parameters of the support vector machine.
Preferably, the initial value of b _ A, b _ c, b _ g is 0 at initialization.
An electric valve fault diagnosis terminal device, comprising:
the acquisition module is used for acquiring a plurality of groups of sample signals of the electric valve in the working process;
the characteristic processing module is used for extracting characteristic quantity of the sample signal acquired by the acquisition module to obtain sample data;
the first processing module is used for outputting the sample data through a k-fold cross verification method;
the second processing module is used for operating the support vector machine, training a classification model by inputting sample data and obtaining a final classification model;
and the diagnosis module is used for carrying out fault diagnosis on real-time data in the opening and closing process of the electric valve through the classification model.
The electric valve fault diagnosis terminal device comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor executes the computer program to realize the steps of the electric valve fault diagnosis method.
A computer-readable storage medium storing a computer program which, when executed by a processor, implements the steps of a method of diagnosing a malfunction of an electrically operated valve as described above.
Compared with the prior art, the invention has the following advantages and beneficial effects:
the invention provides a diagnosis method based on a support vector machine and k-fold optimization aiming at the fault condition of a small sample of an electric valve, and the diagnosis method fully utilizes limited fault data samples to train so as to obtain an optimal fault diagnosis model, and the model can be utilized to greatly improve the fault diagnosis accuracy of the electric valve.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the principles of the invention.
FIG. 1 is a model diagram of a training mode of a support vector machine according to the present invention.
FIG. 2 is a flow chart of support vector machine parameter optimization according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are for purposes of illustration only and are not to be construed as limitations of the invention.
It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings.
In the present invention, the embodiments and features of the embodiments may be combined with each other without conflict. The present invention will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
The method mainly aims at the problems of small quantity of electric valve fault data samples and difficulty in diagnosis in the current electromechanical equipment, and can accurately diagnose the fault information of the valve by fully utilizing the limited fault sample data. The invention can be widely applied to the fields of nuclear power, wind power, thermal power, chemical industry, petroleum and the like.
Example one
A fault diagnosis method for an electric valve comprises the following steps:
s1, collecting multiple groups of sample data in the working process of the electric valve;
s2, inputting the collected sample data to a support vector machine;
s3, the support vector machine trains a classification model by inputting sample data and obtains a final classification model;
the Support Vector Machine (SVM) is a generalized linear classifier for binary classification of data according to a supervised learning mode, a decision boundary of the SVM is a maximum edge distance hyperplane for solving a learning sample, the SVM calculates empirical risks by using a hinge loss function and adds a regularization item in a solving system to optimize structural risks, and the SVM is a classifier with sparsity and robustness and can perform nonlinear classification by a kernel method, and the SVM is one of common kernel learning methods.
Therefore, in the present embodiment and for explaining the specific working principle of the support vector machine, those skilled in the art can understand and implement the working process of the support vector machine according to the input data.
And S4, inputting real-time data in the opening and closing process of the electric valve, and performing fault diagnosis through a classification model.
After the final classification model is obtained in steps S1-S3, in actual use, only data generated in the opening or closing process of the electric valve needs to be input to the classification model, so that fault diagnosis can be realized, and whether normal operation is performed or not is output.
Example two
The embodiment provides a sample data acquisition method and a sample data processing method.
S11, collecting sample signals by taking one valve opening action and one valve closing action as a collecting period;
the sample signals in this embodiment include AB phase voltage signals, BC phase voltage signals, CA phase voltage signals, a phase current signals, B phase current signals, C phase current signals, a phase power signals, B phase power signals, C phase power signals, and total power signals;
of course, in actual use, the index may be a frequency domain characteristic waveform index, a peak index, a pulse index, a margin index, a kurtosis index, a skewness index, or the like.
The acquisition of the sample signal is performed by an electronic element connected to the electrically operated valve, and those skilled in the art can select an appropriate acquisition mode according to the data to be acquired, which need not be described in detail herein.
And S12, extracting the characteristic quantity of the acquired sample signals to obtain a plurality of groups of sample data, wherein the plurality of groups of sample data comprise n groups of normal samples and m groups of abnormal samples, n is greater than m, and n is far greater than m.
The sample data includes: mean, maximum, minimum, variance, root mean square, skewness, and kurtosis.
The specific feature extraction method is shown in the following table:
EXAMPLE III
The present embodiment provides a method for packet training for a support vector machine, and refer to fig. 1.
S21, dividing n groups of normal samples into two groups, and dividing m groups of abnormal samples into k groups;
wherein the normal sample comprises T1Group sum T2Group (d);
s22, mixing T2Taking the group and any abnormal sample as test samples;
s23, mixing T1Taking the abnormal samples of the group and the rest k-1 groups as training samples;
s24, inputting the training sample and the testing sample into a support vector machine, and repeating the steps S22-S23 k times;
each abnormal sample in the k groups of abnormal samples needs to be used as a test sample for training.
The training method is explained with reference to fig. 1.
This embodiment requires k training sessions.
For the first training, the T1,x1,x2…,xk-2,xk-1As training samples, T2,xkAs a test sample;
second training, to T1,x1,x2…,xk-3,xk-2As training samples, T2,xk-1As a test sample;
training for the third time, and combining T1,x1,x2…,xk-3,xk-1As training samples, T2,xk-2As a test sample;
…………
k-2 training, and T1,x1,x2…,xk-1,xkAs training samples, T2,x3As a test sample;
training the k-1 st time, and combining T1,x1,x3…,xk-1,xkAs training samples, T2,x2As a test sample;
training the k time, and combining T1,x2,x3…,xk-1,xkAs training samples, T2,x1As a test sample;
x in the aboveiIs the sample extracted in example twoCharacteristic values of the data.
Example four
In the embodiment, the optimized support vector machine is put by adopting a k-fold cross verification method.
The penalty parameters and the kernel function parameters are optimized by a k-fold cross validation method, as shown in fig. 2, the specific optimization method comprises the following steps:
s31 initialization scope parameter n1And n2The optimal classification accuracy rate b _ A, the optimal penalty coefficient b _ c and the optimal kernel function parameter value b _ g;
the range parameters are initialized and assigned to specific values as known to those skilled in the art.
Meanwhile, the optimal classification accuracy rate b _ A, the optimal penalty coefficient b _ c and the optimal kernel function parameter value b _ g are all assigned to be 0
S32, assigning a value to the penalty coefficient c, wherein the value is assigned according to the formula
S33, assigning the kernel function parameter g with the assignment formula
Setting a penalty coefficient c and a kernel function parameter g, and according to a range parameter n1And n2And carrying out initialization assignment on the data.
S34, training k models according to the data input in the step S2, and obtaining the average classification accuracy A;
the training is performed according to a training mode inside the support vector machine, and those skilled in the art can know the training and do not need to describe the training.
S35, if A > b _ A, jumping to step S36; otherwise, go directly to step S37;
s36, assigning values to b _ A, b _ c and b _ g, such that b _ a is a, b _ c is c, and b _ g is g, and executing step S37 after assigning values is completed.
S37, judgment
If yes, go to step S38; if not, assigning a value to g, and assigning a formula: g ═ g + t2Then, it goes to step S34;
wherein t is2The iteration step length when the kernel function parameters are optimized is obtained;
s38, judging c + t1＞2n1And if not, assigning a value to the c, and assigning a formula: c ═ c + t1Then, it goes to step S33; if yes, outputting b _ c and b _ g;
wherein t is1The iteration step length when the penalty coefficient is optimized;
and S39, training to obtain a final classification model by using the output b _ c and b _ g as training parameters of the support vector machine.
EXAMPLE five
The embodiment provides an electric valve fault diagnosis terminal device which comprises an acquisition module, a feature processing module, a first processing module, a second processing module and a diagnosis module.
The acquisition module is used for acquiring a plurality of groups of sample signals of the electric valve in the working process;
the characteristic processing module is used for extracting characteristic quantity of the sample signal acquired by the acquisition module to obtain sample data;
the first processing module is used for outputting the sample data through a k-fold cross verification method;
the second processing module is used for operating the support vector machine, training a classification model by inputting sample data and obtaining a final classification model;
the diagnosis module is used for carrying out fault diagnosis on real-time data in the opening and closing process of the electric valve through the classification model.
By carrying out data transmission and method operation among the modules, terminal equipment can be obtained by combination, and the terminal equipment can be an integral body or a combination body which can be divided into a plurality of different terminals to carry out cooperative work.
The fault diagnosis terminal equipment for the electrically operated valve comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the steps of the fault diagnosis method for the electrically operated valve are realized when the processor executes the computer program.
The memory may be used to store software programs and modules, and the processor may execute various functional applications of the terminal and data processing by operating the software programs and modules stored in the memory. The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an execution program required for at least one function, and the like.
The storage data area may store data created according to the use of the terminal, and the like. Further, the memory may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
A computer-readable storage medium storing a computer program which, when executed by a processor, implements the steps of a method for diagnosing a malfunction of an electrically operated valve as described above.
Without loss of generality, computer readable media may comprise computer storage media and communication media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instruction data structures, program modules or other data. Computer storage media includes RAM, ROM, EPROM, EEPROM, flash memory or other solid state storage technology, CD-ROM, DVD, or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that computer storage media is not limited to the foregoing. The system memory and mass storage devices described above may be collectively referred to as memory.
The support vector machine is selected by the invention because the support vector machine has inherent advantages for handling small sample problems compared to other machine learning algorithms.
The method optimizes the parameters of the support vector machine in a k-fold cross validation mode, and can fully mine limited fault data of the electric valve.
The invention can accurately decide whether the current electric valve has faults or not through the trained diagnosis model.
The method can automatically adjust the number of the training samples in the optimization process according to the size of the electric valve fault data sample size.
In the description herein, reference to the description of the terms "one embodiment/mode," "some embodiments/modes," "example," "specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment/mode or example is included in at least one embodiment/mode or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to be the same embodiment/mode or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments/modes or examples. Furthermore, the various embodiments/aspects or examples and features of the various embodiments/aspects or examples described in this specification can be combined and combined by one skilled in the art without conflicting therewith.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
It will be understood by those skilled in the art that the foregoing embodiments are merely for clarity of description and are not intended to limit the scope of the invention. It will be apparent to those skilled in the art that other variations or modifications may be made on the above invention and still be within the scope of the invention.
Claims (8)
1. The method for diagnosing the fault of the electric valve is characterized by being based on a support vector machine and comprising the following steps of:
s1, collecting multiple groups of sample data in the working process of the electric valve;
s2, inputting the collected sample data into a support vector machine in groups;
s3, the support vector machine trains a classification model by inputting sample data and obtains a final classification model;
and S4, inputting real-time data in the opening and closing process of the electric valve, and performing fault diagnosis through a classification model.
2. The electric valve fault diagnosis method according to claim 1, wherein the step S1 specifically includes the steps of:
s11, collecting sample signals by taking one valve opening action and one valve closing action as a collecting period;
the sample signals comprise AB phase voltage signals, BC phase voltage signals, CA phase voltage signals, A phase current signals, B phase current signals, C phase current signals, A phase power signals, B phase power signals, C phase power signals and total power signals;
s12, extracting characteristic quantity of the collected sample signals to obtain a plurality of groups of sample data, wherein the plurality of groups of sample data comprise n groups of normal samples and m groups of abnormal samples, and n is larger than m;
wherein the sample data comprises: mean, maximum, minimum, variance, root mean square, skewness, and kurtosis.
3. The electric valve fault diagnosis method according to claim 2, wherein the step S2 specifically includes the steps of:
s21, dividing n groups of normal samples into two groups, and dividing m groups of abnormal samples into k groups;
wherein the normal sample comprises T1Group sum T2Group (d);
s22, mixing T2Taking the group and any abnormal sample as test samples;
s23, mixing T1Taking the abnormal samples of the group and the rest k-1 groups as training samples;
s24, inputting the training sample and the testing sample into a support vector machine, and repeating the steps S22-S23 k times;
each abnormal sample in the k groups of abnormal samples needs to be used as a test sample for training.
4. The method for diagnosing the fault of the electric valve according to claim 3, wherein in step S3, the penalty parameter and the kernel function parameter are further optimized by a k-fold cross validation method, and the specific optimization method includes the following steps:
s31 initialization scope parameter n1And n2The optimal classification accuracy rate b _ A, the optimal penalty coefficient b _ c and the optimal kernel function parameter value b _ g;
s32, assigning a value to the penalty coefficient c, wherein the value is assigned according to the formula
S33, assigning the kernel function parameter g with the assignment formula
S34, training k models according to the data input in the step S2, and obtaining the average classification accuracy A;
s35, if A > b _ A, jumping to step S36; otherwise, go directly to step S37;
s36, assigning values to b _ A, b _ c and b _ g, so that b _ a is a, b _ c is c, and b _ g is g;
s37, judgment
If yes, go to step S38; if not, assigning a value to g, and assigning a formula: g ═ g + t2Then, it goes to step S34;
wherein t is2The iteration step length when the kernel function parameters are optimized is obtained;
s38, judging c + t1＞2n1And if not, assigning a value to the c, and assigning a formula: c. C＝c+t1Then, it goes to step S33; if yes, outputting b _ c and b _ g;
wherein t is1The iteration step length when the penalty coefficient is optimized;
and S39, training to obtain a final classification model by using the output b _ c and b _ g as training parameters of the support vector machine.
5. The electric valve fault diagnosis method according to claim 4, wherein the initial value of b _ A, b _ c, b _ g is 0 at initialization.
6. An electric valve fault diagnosis terminal device, comprising:
the acquisition module is used for acquiring a plurality of groups of sample signals of the electric valve in the working process;
the characteristic processing module is used for extracting characteristic quantity of the sample signal acquired by the acquisition module to obtain sample data;
the first processing module is used for outputting the sample data through a k-fold cross verification method;
the second processing module is used for operating the support vector machine, training a classification model by inputting sample data and obtaining a final classification model;
and the diagnosis module is used for carrying out fault diagnosis on real-time data in the opening and closing process of the electric valve through the classification model.
7. An electrically operated valve fault diagnosis terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program, carries out the steps of the method according to any one of claims 1 to 5.
8. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110993663.8A CN113609787A (en) | 2021-08-27 | 2021-08-27 | Electric valve fault diagnosis method, terminal equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110993663.8A CN113609787A (en) | 2021-08-27 | 2021-08-27 | Electric valve fault diagnosis method, terminal equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113609787A true CN113609787A (en) | 2021-11-05 |
Family
ID=78309526
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110993663.8A Pending CN113609787A (en) | 2021-08-27 | 2021-08-27 | Electric valve fault diagnosis method, terminal equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113609787A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109165687A (en) * | 2018-08-28 | 2019-01-08 | 哈尔滨理工大学 | Vehicle lithium battery method for diagnosing faults based on multi-category support vector machines algorithm |
| CN110313990A (en) * | 2019-06-26 | 2019-10-11 | 北京工业大学 | A method of prediction bridge vasopermeability model being established based on wall shear stress characteristics of image in bypass surgery |
| CN110852017A (en) * | 2019-10-08 | 2020-02-28 | 湖南省计量检测研究院 | Hydrogen fuel cell fault diagnosis method based on particle swarm optimization and supporting vector machine |
| US20200271720A1 (en) * | 2020-05-09 | 2020-08-27 | Hefei University Of Technology | Method for diagnosing analog circuit fault based on vector-valued regularized kernel function approximation |
-
2021
- 2021-08-27 CN CN202110993663.8A patent/CN113609787A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109165687A (en) * | 2018-08-28 | 2019-01-08 | 哈尔滨理工大学 | Vehicle lithium battery method for diagnosing faults based on multi-category support vector machines algorithm |
| CN110313990A (en) * | 2019-06-26 | 2019-10-11 | 北京工业大学 | A method of prediction bridge vasopermeability model being established based on wall shear stress characteristics of image in bypass surgery |
| CN110852017A (en) * | 2019-10-08 | 2020-02-28 | 湖南省计量检测研究院 | Hydrogen fuel cell fault diagnosis method based on particle swarm optimization and supporting vector machine |
| US20200271720A1 (en) * | 2020-05-09 | 2020-08-27 | Hefei University Of Technology | Method for diagnosing analog circuit fault based on vector-valued regularized kernel function approximation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dey et al. | Extreme value modeling and risk analysis: methods and applications | |
| CN110058178A (en) | A kind of lithium battery method for detecting health status and system | |
| Zhang et al. | Cloud-based in-situ battery life prediction and classification using machine learning | |
| Chai et al. | A novel global MPPT technique using improved PS-FW algorithm for PV system under partial shading conditions | |
| CN109817267B (en) | Deep learning-based flash memory life prediction method and system and computer-readable access medium | |
| Li et al. | State‐of‐health prediction for lithium‐ion batteries via electrochemical impedance spectroscopy and artificial neural networks | |
| CN103649858A (en) | Method and device for predicting the condition of a component or system, computer program product | |
| CN104734504B (en) | DC-DC converter control method and system | |
| Cai et al. | TEA-DNN: the quest for time-energy-accuracy co-optimized deep neural networks | |
| CN116401532A (en) | Method and system for recognizing frequency instability of power system after disturbance | |
| Sun et al. | Local feature sufficiency exploration for predicting security-constrained generation dispatch in multi-area power systems | |
| Beltran et al. | Machine learning techniques suitability to estimate the retained capacity in lithium-ion batteries from partial charge/discharge curves | |
| CN113609787A (en) | Electric valve fault diagnosis method, terminal equipment and readable storage medium | |
| Zheng et al. | Embedded implementation of SOC estimation based on the Luenberger observer technique | |
| CN109743200B (en) | Resource feature-based cloud computing platform computing task cost prediction method and system | |
| Zhao et al. | Lithium-ion battery state-of-health estimation method using isobaric energy analysis and pso-lstm | |
| CN112100902B (en) | Lithium ion battery life prediction method based on flow data | |
| Liu et al. | State of health estimation of lithium-ion batteries based on multi-feature extraction and temporal convolutional network | |
| Huang et al. | SOC prediction of Lithium battery based on fuzzy information granulation and support vector regression | |
| CN113048012A (en) | Wind turbine generator yaw angle identification method and device based on Gaussian mixture model | |
| Hilal et al. | Forecasting Lithium-Ion Battery Longevity with Limited Data Availability: Benchmarking Different Machine Learning Algorithms | |
| Chen et al. | Active requirement mining of bounded-time temporal properties of cyber-physical systems | |
| Hu et al. | Learning from output‐feedback control of sampled‐data systems in normal form | |
| Rahmanian et al. | Attention towards chemistry agnostic and explainable battery lifetime prediction | |
| WO2024033147A1 (en) | Method and system for specifying a target battery cell |
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 |