CN117929952B - Novel arc fault detection method for electric automobile charging pile - Google Patents
Novel arc fault detection method for electric automobile charging pile Download PDFInfo
- Publication number
- CN117929952B CN117929952B CN202410323994.4A CN202410323994A CN117929952B CN 117929952 B CN117929952 B CN 117929952B CN 202410323994 A CN202410323994 A CN 202410323994A CN 117929952 B CN117929952 B CN 117929952B
- Authority
- CN
- China
- Prior art keywords
- data
- signal
- charging pile
- differential
- real
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 46
- 238000003062 neural network model Methods 0.000 claims abstract description 23
- 101100420776 Arabidopsis thaliana SYN1 gene Proteins 0.000 claims abstract description 13
- VUDQSRFCCHQIIU-UHFFFAOYSA-N DIF1 Natural products CCCCCC(=O)C1=C(O)C(Cl)=C(OC)C(Cl)=C1O VUDQSRFCCHQIIU-UHFFFAOYSA-N 0.000 claims abstract description 13
- 101150001108 DIF1 gene Proteins 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000012216 screening Methods 0.000 claims abstract description 10
- 238000000034 method Methods 0.000 claims description 46
- 230000008569 process Effects 0.000 claims description 20
- 230000009466 transformation Effects 0.000 claims description 15
- 238000001228 spectrum Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000011176 pooling Methods 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 9
- 238000013527 convolutional neural network Methods 0.000 claims description 9
- 230000000052 comparative effect Effects 0.000 claims description 6
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 238000013178 mathematical model Methods 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 3
- 230000003213 activating effect Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 238000007500 overflow downdraw method Methods 0.000 claims description 3
- 230000008447 perception Effects 0.000 claims description 3
- 230000001105 regulatory effect Effects 0.000 claims description 3
- 238000010183 spectrum analysis Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 7
- 238000000605 extraction Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000010891 electric arc Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
- Testing Electric Properties And Detecting Electric Faults (AREA)
Abstract
The invention provides a novel arc fault detection method of an electric automobile charging pile, which belongs to the technical field of charging piles and comprises the following steps: s1: respectively collecting normal working and real-time working electrical parameters of the charging pile, constructing an original data set, and obtaining a normal electric signal differential data feature set DIF0 according to the normal working electrical parameters; s2: processing and analyzing the data in the original data set to obtain a preprocessed data set; s3: screening the data in the preprocessed data set, and fusing the screened data with a neural network model to obtain a real-time electric signal differential data feature set DIF1; s4: and comparing and judging the DIF1 and the DIF0, and identifying arc faults. The invention can be suitable for accurately extracting the arc fault characteristics in the noise environment, reduces the influence of the shielding effect on the data in the current environment of the charging pile, can further improve the detection accuracy, and has higher detection accuracy.
Description
Technical Field
The invention belongs to the technical field of charging piles, and particularly relates to a novel arc fault detection method for an electric vehicle charging pile.
Background
The utility model provides an electric automobile fills electric pile and provides electric quantity supplementary energy device for electric automobile, can fix on ground or wall, installs in public building (charging station, mall, public parking area etc.) and residential area parking area, can charge for electric automobile of various models according to adjustment voltage and current. The input end of the charging pile is directly connected with an alternating current power grid, and the output end of the charging pile is provided with a charging plug for charging the electric automobile.
With the popularization of electric vehicles and the wide application of charging piles, the safety and reliability of the charging piles become one of important concerns. In the charging process of the electric automobile, arc faults can occur due to uncertain reasons, so that electric energy is wasted, and serious consequences such as equipment damage and even fire disaster can be caused seriously. Therefore, the detection and timely treatment of arc faults is particularly important.
The traditional arc fault detection method mainly detects arc characteristics based on amplitude and frequency changes of current and voltage signals, but the detection result is not accurate and reliable enough under the noise interference environment. In addition, the traditional detection method is also influenced by the current shielding effect in the charging environment, so that the detection effect of the arc faults is limited, and the accuracy of the arc fault detection is influenced.
Disclosure of Invention
In order to solve the problems in the prior art, a novel arc fault detection method for the electric vehicle charging pile is provided.
The technical scheme adopted for solving the technical problems is as follows:
the technical scheme provides a novel arc fault detection method of an electric automobile charging pile, which comprises the following steps:
S1: respectively collecting normal working and real-time working electric parameters of the charging pile, constructing an original data set according to the real-time working electric parameters, and obtaining a normal electric signal differential data feature set DIF0 after processing and analyzing according to the normal working electric parameters;
S2: processing and analyzing the data in the original data set, and obtaining real-time spectrum data by using variation modal decomposition and Fourier transformation to obtain a preprocessed data set;
s3: screening the data in the preprocessed data set through a comparison algorithm, and fusing the screened data with a neural network model to obtain a real-time electric signal differential data feature set DIF1;
S4: and comparing and judging the real-time electric signal differential data characteristic set DIF1 with the normal electric signal differential data characteristic set DIF0, and identifying the arc fault.
Preferably, in S2, the data processing analysis method includes:
s11: the Hilbert transformation is carried out on the components of different modes, and single-side frequency spectrum of an analysis signal is obtained through calculation:
(1)
In the method, in the process of the invention, For the impulse signal used in Hilbert transform,/>For the bias component under the corresponding modal component,Real-time current signals corresponding to the charging piles;
the single-side frequency spectrum of the analysis signal under the corresponding modal component can be obtained by (1) revising the offset of the impulse signal required by Hilbert transformation;
s12: adding an exponential term into each mode, adjusting the estimated center frequency, and adjusting the frequency of each mode component to a corresponding baseband:
(2)
In the method, in the process of the invention, For the expression of frequencies corresponding to different modal components,/>Is the imaginary unit in signal gradient calculation,/>The amount of time in calculating for the signal gradient;
s13: calculating the square of the two norms of the demodulation signal gradient, and finally obtaining the following variation problems from the bandwidths of all modes:
(3)
(4)
In the method, in the process of the invention, Representing partial differential calculation of the subsequent equation,/>Is the constraint quantity of the current data;
(3) The equation obtains the variation problem under the constraint of the equation (4) through regulating the square of the two norms of the signal gradient and partial differential calculation, and carries out Fourier transformation on the demodulated variation modal signal to finish the pretreatment of data, wherein, the design is set according to the actual current frequency of the charging pile 。
Preferably, in S3, the data screening method includes:
s21: determining positive and negative sample pairs using a data screening module;
S22: using CNN networks Obtaining the coding result, wherein,/>Output result for pooling layer of corresponding neural network,/>For the corresponding sample;
s23: converting the encoding result to a contrast loss space using hidden layer multi-layer perception:
(5)
Wherein, For the pooling layer to output the result as a comparative loss space function expression under the independent variable,/>Activating a function for Relu for use in contrast training,/>And/>And outputting results respectively for the corresponding codes.
Preferably, in S3, the neural network model fusion method includes:
s31: parallelly combining a CNN network and an LSTM network, adding Flattern layers after pooling layers to build a fused neural network model by using middle layer information;
The CNN network consists of an input layer, two-dimensional convolution layers, two separable convolution layers, two maximum pooling layers and two Flattern layers, and the LSTM network consists of an input layer, an LSTM layer and a Flattern layer;
s32: the sample S (x, y) obtained after comparison learning is in a bounded variation space Differential data fusion is carried out, and partial differential gradient operators/>And (3) performing integral operation to obtain an energy universal function of the differential mathematical model:
(6)
In the method, in the process of the invention, Is Lagrangian operator,/>And/>Samples after and before the contrast learning,Fractional derivative of the influence factor of the data signal,/>Is a norm unit;
the integral of the sample and the partial differential gradient operator under the comparative learning is used for obtaining the expression of the differential mathematical model energy universal function, and the signal detection equation is obtained through differential definition and Euler equation definition:
(7)
In the method, in the process of the invention, For a specific step value,/>To derive a factor,/>To accumulate the detection times,/>Representing the corresponding current detection times, and obtaining an expression based on a signal detection equation under a fused neural network model through accumulation of Euler equations and sample information under different times;
And comparing the learned sample data, and obtaining a real-time electric signal differential data feature set DIF1 through a fused neural network model.
Preferably, in S1, the normal electric signal differential data feature set DIF0 is sample data obtained by collecting current signals of a mass of charging piles during normal operation, spectrum data of the mass of charging piles during normal operation is obtained through spectrum analysis based on the collected sample data, and the normal electric signal differential data feature set DIF0 of the charging piles during normal operation is established.
Preferably, the electrical parameter is the operating current of the charging pile.
Compared with the prior art, the invention has the following advantages:
1. According to the invention, the spectrum data of the charging pile current signal is extracted by adopting variation modal decomposition and Fourier transformation, and the data is screened and preprocessed by improving a contrast learning algorithm, so that the method can adapt to the accurate extraction of arc fault characteristics in a noise environment, and the characteristics of a real-time electric signal are judged by constructing a fused neural network model and adopting a differential characteristic set, so that the influence of shielding effect on the data in the charging pile current environment is reduced, and the accuracy of detection can be further improved by judging the fused neural network model and the differential characteristic set, and the method has higher detection precision.
2. The method provided by the invention has higher detection accuracy and robustness, can be suitable for extracting the arc fault characteristics in a noise environment, reduces the influence of the shielding effect of the current environment of the charging pile on data, improves the accuracy and precision of arc fault detection, adopts an advanced method for judging a fused neural network model and a differential characteristic set, ensures that the detection result is more reliable and stable, improves the safety and stability of the operation of the charging pile, and has wide application prospects in the electric automobile industry.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and may be better understood from the following description of embodiments taken in conjunction with the accompanying drawings in which:
Fig. 1 is a schematic view of a charging pile according to the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the invention.
As shown in fig. 1, this embodiment provides a novel arc fault detection method for an electric vehicle charging pile, including the following steps:
S1: respectively collecting normal working and real-time working electric parameters of the charging pile, constructing an original data set according to the real-time working electric parameters, and obtaining a normal electric signal differential data feature set DIF0 after processing and analyzing according to the normal working electric parameters;
S2: processing and analyzing the data in the original data set, and obtaining real-time spectrum data by using variation modal decomposition and Fourier transformation to obtain a preprocessed data set;
s3: screening the data in the preprocessed data set through a comparison algorithm, and fusing the screened data with a neural network model to obtain a real-time electric signal differential data feature set DIF1;
S4: and comparing and judging the real-time electric signal differential data characteristic set DIF1 with the normal electric signal differential data characteristic set DIF0, and identifying the arc fault.
S2, the data processing analysis method comprises the following steps:
s11: the Hilbert transformation is carried out on the components of different modes, and single-side frequency spectrum of an analysis signal is obtained through calculation:
(1)
In the method, in the process of the invention, For the impulse signal used in Hilbert transform,/>For the bias component under the corresponding modal component,Real-time current signals corresponding to the charging piles;
the single-side frequency spectrum of the analysis signal under the corresponding modal component can be obtained by (1) revising the offset of the impulse signal required by Hilbert transformation;
s12: adding an exponential term into each mode, adjusting the estimated center frequency, and adjusting the frequency of each mode component to a corresponding baseband:
(2)
In the method, in the process of the invention, For the expression of frequencies corresponding to different modal components,/>Is the imaginary unit in signal gradient calculation,/>The amount of time in calculating for the signal gradient;
(2) The formula realizes the adjustment of the component frequency of each mode by adding an index term to each mode;
s13: calculating the square of the two norms of the demodulation signal gradient, and finally obtaining the following variation problems from the bandwidths of all modes:
(3)
(4)
In the method, in the process of the invention, Representing partial differential calculation of the subsequent equation,/>Is the constraint quantity of the current data;
(3) The equation obtains the variation problem under the constraint of the equation (4) through regulating the square of the two norms of the signal gradient and partial differential calculation, and carries out Fourier transformation on the demodulated variation modal signal to finish the pretreatment of data, wherein, the design is set according to the actual current frequency of the charging pile 。
S3, the data screening method comprises the following steps:
s21: determining positive and negative sample pairs using a data screening module;
S22: using CNN networks Obtaining the coding result, wherein,/>Output result for pooling layer of corresponding neural network,/>For the corresponding sample;
s23: converting the encoding result to a contrast loss space using hidden layer multi-layer perception:
(5)
Wherein, For the pooling layer to output the result as a comparative loss space function expression under the independent variable,/>Activating a function for Relu for use in contrast training,/>And/>And outputting results respectively for the corresponding codes.
In S3, the neural network model fusion method comprises the following steps:
s31: parallelly combining a CNN network and an LSTM network, adding Flattern layers after pooling layers to build a fused neural network model by using middle layer information;
The CNN network consists of an input layer, two-dimensional convolution layers, two separable convolution layers, two maximum pooling layers and two Flattern layers, and the LSTM network consists of an input layer, an LSTM layer and a Flattern layer;
s32: the sample S (x, y) obtained after comparison learning is in a bounded variation space Differential data fusion is carried out, and partial differential gradient operators/>And (3) performing integral operation to obtain an energy universal function of the differential mathematical model:
(6)
In the method, in the process of the invention, Is Lagrangian operator,/>And/>Sample after and before contrast learning,/>, respectivelyFractional derivative of the influence factor of the data signal,/>Is a norm unit;
the integral of the sample and the partial differential gradient operator under the comparative learning is used for obtaining the expression of the differential mathematical model energy universal function, and the signal detection equation is obtained through differential definition and Euler equation definition:
(7)
In the method, in the process of the invention, For a specific step value,/>To derive a factor,/>To accumulate the detection times,/>Representing the corresponding current detection times, and obtaining an expression based on a signal detection equation under a fused neural network model through accumulation of Euler equations and sample information under different times;
And comparing the learned sample data, and obtaining a real-time electric signal differential data feature set DIF1 through a fused neural network model.
In the S1, the normal electric signal differential data feature set DIF0 is sample data obtained by collecting current signals of a mass of charging piles during normal operation, spectrum data during mass operation is obtained through spectrum analysis based on the collected sample data, and the normal electric signal differential data feature set DIF0 during normal operation of the charging piles is established, so that subsequent analogy judgment with fault arc data is facilitated.
With a 750V/120kW direct current charging pile as an implementation case, the cable, the connector and the port of the device can meet the high power transmission requirement. The detection device is shown in fig. 1, and fig. 1 is a schematic diagram of a charging pile structure according to the present invention. The direct current charging pile comprises a signal acquisition module, a signal processing module, a signal sending module and a voltage reduction and stabilization module, and is powered by alternating current 220V.
The mutual inductor on the surface of the equipment is used as a first ring of the signal acquisition module to introduce an electric signal to be detected and processed, the electric signal is judged through the signal processing module, if the electric signal is an arc signal, the signal sending module is used for alarming an arc fault, and meanwhile, a signal sending port outside the device is used for outputting the arc signal.
The direct current output part is connected with a signal acquisition module of the electric arc detection device, and a high-performance transformer acquires the output current signal of the charging pile in real time. The chassis shell is fixed on the wall, and aviation terminals at the lower end of the chassis shell are respectively connected with the transformer and the signal output port, the signal output port can output 485 signals, and a user can monitor and further process the signals in real time.
In the charging process of the electric automobile, the electric signal is monitored in real time, and the electric signal is judged through a high-performance chip. The collected current data is subjected to variation modal decomposition and Fourier transformation to obtain current spectrum data, the data is further screened by a comparison learning algorithm after data preprocessing, the screened data is subjected to fusion neural network model to obtain a real-time electric signal differential data feature set DIF1, and arc fault identification can be realized by comparing and judging the real-time electric signal differential data feature set DIF1 with a large number of normal electric signal differential data feature sets DIF0 under normal work in advance.
When no arc is generated, the high-performance chip does not judge the arc signal as an arc signal, and the arc detection device does not generate further actions; when the high-performance chip judges the electric signal as an arc signal, the signal sending module sends out a specific threshold condition to indicate that an arc fault occurs in the charging process, the buzzer continuously alarms, and the signal output port continuously outputs the arc signal. Therefore, the user can timely receive the fault prompt, and is convenient to take corresponding measures, such as stopping charging, reporting repair and the like.
The detection method provides an effective fault detection and protection strategy for the charging process of the charging pile of the direct-current 750V/120kW electric automobile, can ensure the safety of the charging pile and the charging equipment, and improves the charging experience of users.
The method has the advantages that the spectral data of the current signal of the charging pile is extracted through variation modal decomposition and Fourier transformation, the data is screened and preprocessed through improvement of a contrast learning algorithm, the method can adapt to accurate extraction of arc fault characteristics in a noise environment, the characteristics of real-time electric signals are judged through construction of a fused neural network model and adoption of a differential characteristic set, the influence of shielding effect on the data in the current environment of the charging pile is reduced, and the accuracy of detection can be further improved through judgment of the fused neural network model and the differential characteristic set, and the method has higher detection accuracy.
Meanwhile, the detection method has higher detection accuracy and robustness, can be suitable for extracting the arc fault characteristics in a noise environment, reduces the influence of the shielding effect of the current environment of the charging pile on data, improves the accuracy and precision of arc fault detection, adopts an advanced judgment method of fusing a neural network model and a differential characteristic set, ensures that the detection result is more reliable and stable, improves the safety and stability of the operation of the charging pile, and has wide application prospect in the electric automobile industry.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the invention, the scope of which is defined by the claims and their equivalents.
Claims (3)
1. The novel arc fault detection method for the electric automobile charging pile is characterized by comprising the following steps of:
S1: respectively collecting normal working and real-time working electric parameters of the charging pile, constructing an original data set according to the real-time working electric parameters, and obtaining a normal electric signal differential data feature set DIF0 after processing and analyzing according to the normal working electric parameters;
S2: processing and analyzing the data in the original data set, and obtaining real-time spectrum data by using variation modal decomposition and Fourier transformation to obtain a preprocessed data set;
s3: screening the data in the preprocessed data set through a comparison algorithm, and fusing the screened data with a neural network model to obtain a real-time electric signal differential data feature set DIF1;
S4: comparing and judging the real-time electric signal differential data feature set DIF1 with the normal electric signal differential data feature set DIF0, and identifying arc faults;
S2, the data processing analysis method comprises the following steps:
s11: the Hilbert transformation is carried out on the components of different modes, and single-side frequency spectrum of an analysis signal is obtained through calculation:
(1)
In the method, in the process of the invention, For the impulse signal used in Hilbert transform,/>For the bias component under the corresponding modal component,/>Real-time current signals corresponding to the charging piles;
the single-side frequency spectrum of the analysis signal under the corresponding modal component can be obtained by (1) revising the offset of the impulse signal required by Hilbert transformation;
s12: adding an exponential term into each mode, adjusting the estimated center frequency, and adjusting the frequency of each mode component to a corresponding baseband:
(2)
In the method, in the process of the invention, For the expression of frequencies corresponding to different modal components,/>Is the imaginary unit in signal gradient calculation,/>The amount of time in calculating for the signal gradient;
s13: calculating the square of the two norms of the demodulation signal gradient, and finally obtaining the following variation problems from the bandwidths of all modes:
(3)
(4)
In the method, in the process of the invention, Representing partial differential calculation of the subsequent equation,/>Is the constraint quantity of the current data;
(3) The equation obtains the variation problem under the constraint of the equation (4) through regulating the square of the two norms of the signal gradient and partial differential calculation, and carries out Fourier transformation on the demodulated variation modal signal to finish the pretreatment of data, wherein, the design is set according to the actual current frequency of the charging pile ;
S3, the data screening method comprises the following steps:
s21: determining positive and negative sample pairs using a data screening module;
S22: using CNN networks Obtaining the coding result, wherein,/>Output result for pooling layer of corresponding neural network,/>For the corresponding sample;
s23: converting the encoding result to a contrast loss space using hidden layer multi-layer perception:
(5)
Wherein, For the pooling layer to output the result as a comparative loss space function expression under the independent variable,/>Activating a function for Relu for use in contrast training,/>And/>Respectively outputting results of corresponding codes;
in S3, the neural network model fusion method comprises the following steps:
s31: parallelly combining a CNN network and an LSTM network, adding Flattern layers after pooling layers to build a fused neural network model by using middle layer information;
The CNN network consists of an input layer, two-dimensional convolution layers, two separable convolution layers, two maximum pooling layers and two Flattern layers, and the LSTM network consists of an input layer, an LSTM layer and a Flattern layer;
s32: the sample S (x, y) obtained after comparison learning is in a bounded variation space Differential data fusion is carried out, and partial differential gradient operators/>And (3) performing integral operation to obtain an energy universal function of the differential mathematical model:
(6)
In the method, in the process of the invention, Is Lagrangian operator,/>And/>Sample after and before contrast learning,/>, respectivelyFractional derivative of the influence factor of the data signal,/>Is a norm unit;
the integral of the sample and the partial differential gradient operator under the comparative learning is used for obtaining the expression of the differential mathematical model energy universal function, and the signal detection equation is obtained through differential definition and Euler equation definition:
(7)
In the method, in the process of the invention, For a specific step value,/>To derive a factor,/>To accumulate the detection times,/>Representing the corresponding current detection times, and obtaining an expression based on a signal detection equation under a fused neural network model through accumulation of Euler equations and sample information under different times;
And comparing the learned sample data, and obtaining a real-time electric signal differential data feature set DIF1 through a fused neural network model.
2. The novel arc fault detection method for the electric vehicle charging pile according to claim 1, wherein in S1, the normal electric signal differential data feature set DIF0 is sample data obtained by collecting current signals of a mass of charging piles during normal operation, spectrum data of the mass of charging piles during normal operation is obtained through spectrum analysis based on the collected sample data, and the normal electric signal differential data feature set DIF0 of the charging piles during normal operation is established.
3. The novel arc fault detection method for an electric vehicle charging pile according to claim 1, wherein the electrical parameter is an operating current of the charging pile.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410323994.4A CN117929952B (en) | 2024-03-21 | 2024-03-21 | Novel arc fault detection method for electric automobile charging pile |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410323994.4A CN117929952B (en) | 2024-03-21 | 2024-03-21 | Novel arc fault detection method for electric automobile charging pile |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117929952A CN117929952A (en) | 2024-04-26 |
CN117929952B true CN117929952B (en) | 2024-05-28 |
Family
ID=90752311
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410323994.4A Active CN117929952B (en) | 2024-03-21 | 2024-03-21 | Novel arc fault detection method for electric automobile charging pile |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117929952B (en) |
Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108197648A (en) * | 2017-12-28 | 2018-06-22 | 华中科技大学 | A kind of Fault Diagnosis Method of Hydro-generating Unit and system based on LSTM deep learning models |
CN109975673A (en) * | 2019-04-23 | 2019-07-05 | 辽宁工程技术大学 | A kind of photovoltaic micro DC side fault electric arc recognition methods |
CN110069886A (en) * | 2019-05-05 | 2019-07-30 | 四川大学 | The identification of cable initial failure and classification method based on VMD and CNN |
CN110186682A (en) * | 2019-07-08 | 2019-08-30 | 石家庄铁道大学 | Fault Diagnosis of Roller Bearings based on fractional order variation mode decomposition |
CN110276303A (en) * | 2019-06-25 | 2019-09-24 | 湖南科技大学 | Rotor misalignment quantitative identification method based on VMD and DBN |
CN112668518A (en) * | 2020-12-31 | 2021-04-16 | 中国地质大学(武汉) | VMSST time-frequency analysis method for vibration fault signal |
CN113740671A (en) * | 2020-10-22 | 2021-12-03 | 国网河北省电力有限公司雄安新区供电公司 | Fault arc identification method based on VMD and ELM |
CN113866614A (en) * | 2021-07-02 | 2021-12-31 | 国网河北省电力有限公司雄安新区供电公司 | Multi-scenario user side low-voltage direct-current switch arc fault diagnosis method and device |
CN114397569A (en) * | 2022-01-19 | 2022-04-26 | 西安零壹智能电器有限公司 | Circuit breaker fault arc detection method based on VMD parameter optimization and sample entropy |
CN114580829A (en) * | 2021-12-29 | 2022-06-03 | 国网湖南省电力有限公司 | Power utilization safety sensing method, equipment and medium based on random forest algorithm |
CN115238752A (en) * | 2022-08-15 | 2022-10-25 | 福州亿力卓越管理顾问有限公司 | Fill electric pile fault prediction system based on artificial intelligence |
CN116577612A (en) * | 2023-05-05 | 2023-08-11 | 重庆邮电大学 | Series fault arc detection method based on VMD Hilbert marginal spectrum multi-feature fusion |
CN116609615A (en) * | 2023-05-31 | 2023-08-18 | 国网陕西省电力有限公司电力科学研究院 | High-resistance fault detection method, device and equipment based on arc current change trend |
CN116842364A (en) * | 2023-07-04 | 2023-10-03 | 国能大渡河枕头坝发电有限公司 | Rolling bearing fault method for asynchronous motor |
CN117113180A (en) * | 2023-08-22 | 2023-11-24 | 国家电网有限公司 | Direct current distribution network high-resistance fault identification method based on VMD and convolutional neural network |
-
2024
- 2024-03-21 CN CN202410323994.4A patent/CN117929952B/en active Active
Patent Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108197648A (en) * | 2017-12-28 | 2018-06-22 | 华中科技大学 | A kind of Fault Diagnosis Method of Hydro-generating Unit and system based on LSTM deep learning models |
CN109975673A (en) * | 2019-04-23 | 2019-07-05 | 辽宁工程技术大学 | A kind of photovoltaic micro DC side fault electric arc recognition methods |
CN110069886A (en) * | 2019-05-05 | 2019-07-30 | 四川大学 | The identification of cable initial failure and classification method based on VMD and CNN |
CN110276303A (en) * | 2019-06-25 | 2019-09-24 | 湖南科技大学 | Rotor misalignment quantitative identification method based on VMD and DBN |
CN110186682A (en) * | 2019-07-08 | 2019-08-30 | 石家庄铁道大学 | Fault Diagnosis of Roller Bearings based on fractional order variation mode decomposition |
CN113740671A (en) * | 2020-10-22 | 2021-12-03 | 国网河北省电力有限公司雄安新区供电公司 | Fault arc identification method based on VMD and ELM |
CN112668518A (en) * | 2020-12-31 | 2021-04-16 | 中国地质大学(武汉) | VMSST time-frequency analysis method for vibration fault signal |
CN113866614A (en) * | 2021-07-02 | 2021-12-31 | 国网河北省电力有限公司雄安新区供电公司 | Multi-scenario user side low-voltage direct-current switch arc fault diagnosis method and device |
CN114580829A (en) * | 2021-12-29 | 2022-06-03 | 国网湖南省电力有限公司 | Power utilization safety sensing method, equipment and medium based on random forest algorithm |
CN114397569A (en) * | 2022-01-19 | 2022-04-26 | 西安零壹智能电器有限公司 | Circuit breaker fault arc detection method based on VMD parameter optimization and sample entropy |
CN115238752A (en) * | 2022-08-15 | 2022-10-25 | 福州亿力卓越管理顾问有限公司 | Fill electric pile fault prediction system based on artificial intelligence |
CN116577612A (en) * | 2023-05-05 | 2023-08-11 | 重庆邮电大学 | Series fault arc detection method based on VMD Hilbert marginal spectrum multi-feature fusion |
CN116609615A (en) * | 2023-05-31 | 2023-08-18 | 国网陕西省电力有限公司电力科学研究院 | High-resistance fault detection method, device and equipment based on arc current change trend |
CN116842364A (en) * | 2023-07-04 | 2023-10-03 | 国能大渡河枕头坝发电有限公司 | Rolling bearing fault method for asynchronous motor |
CN117113180A (en) * | 2023-08-22 | 2023-11-24 | 国家电网有限公司 | Direct current distribution network high-resistance fault identification method based on VMD and convolutional neural network |
Non-Patent Citations (2)
Title |
---|
EEMD与改进ITD的微电网电弧故障检测;钟毅;朱澈;;四川轻化工大学学报(自然科学版);20200820(04);全文 * |
基于VMD-BP神经网络模型的天然气管道工况检测研究;梁洪卫;张旭;邹岱峰;;化工自动化及仪表;20170710(07);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN117929952A (en) | 2024-04-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103645425B (en) | High-voltage cable insulation defect partial discharge on-line monitoring diagnosis method | |
CN103576059B (en) | A kind of transformer turn-to-turn electric discharge resultant fault diagnostic method and system | |
CN104809722A (en) | Electrical device fault diagnosis method based on infrared thermography | |
US11143706B2 (en) | Battery capacity estimation method and battery capacity estimation device | |
CN111459061A (en) | Electric power safety monitoring system based on 5G network | |
CN111413588A (en) | Power distribution network single-phase earth fault line selection method | |
CN108344917A (en) | The cross interconnected cable on-line fault diagnosis method of 110kV crosslinked polyethylenes based on method of loci | |
CN105510760A (en) | Method for detecting short circuit fault data based on wavelet analysis | |
CN111579939A (en) | Method for detecting partial discharge phenomenon of high-voltage power cable based on deep learning | |
CN110187242A (en) | A kind of power distribution network abnormality detection and localization method based on spatio-temporal correlation analysis | |
CN116028536A (en) | External electricity stealing checking and detecting system for consistent power grid | |
CN117929952B (en) | Novel arc fault detection method for electric automobile charging pile | |
CN111693829A (en) | Partial discharge noise and discharge distinguishing method for non-contact ultrasonic detection | |
CN112199888A (en) | Rotary equipment fault diagnosis method and system based on deep residual error network and readable storage medium | |
CN117169639B (en) | Product detection method and system for power adapter production | |
CN111516548B (en) | Cloud platform-based charging pile system for realizing power battery fault diagnosis | |
CN115343579B (en) | Power grid fault analysis method and device and electronic equipment | |
CN109324268B (en) | Power distribution network early fault detection method and device based on Bayesian inference | |
CN116884432A (en) | VMD-JS divergence-based power transformer fault voiceprint diagnosis method | |
CN110579672A (en) | Power transmission line fault detection system and method based on energy characteristic analysis | |
CN115656830A (en) | Low-temperature quick-charging lithium battery negative electrode lithium deposition detection method based on alternating-current impedance spectrum | |
CN115456013A (en) | Wind turbine generator converter power module fault diagnosis method based on operation data | |
CN114091340A (en) | Method for constructing and distinguishing direct current partial discharge model based on multiple physical fields | |
CN112834959A (en) | Direct-current power distribution system fault detection method based on high-frequency feature extraction | |
Mishra et al. | Diagnostics analysis of partial discharge events of the power cables at various voltage levels using ramping behavior analysis method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |