CN114325197A - Power quality disturbance detection method and device - Google Patents
Power quality disturbance detection method and device Download PDFInfo
- Publication number
- CN114325197A CN114325197A CN202111679366.2A CN202111679366A CN114325197A CN 114325197 A CN114325197 A CN 114325197A CN 202111679366 A CN202111679366 A CN 202111679366A CN 114325197 A CN114325197 A CN 114325197A
- Authority
- CN
- China
- Prior art keywords
- signal
- data
- original
- power quality
- quality disturbance
- 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
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention discloses a method and a device for detecting power quality disturbance, wherein the method comprises the following steps: s1, collecting power quality information of the power grid through a voltage transformer and a current transformer, and outputting collected multi-path sampling signal data; s2, preprocessing, after sparse representation is carried out through a compressed sensing algorithm by adopting a sparse transformation base, using a measurement matrix observation signal to obtain a measurement value, reconstructing the measurement value into an original discrete signal and obtaining a sparse vector containing details of the original disturbance signal to obtain a structure of the original signal, and finally accurately reconstructing the original signal by solving a numerical optimization problem; and S3, training a deep convolutional neural network model consisting of a convolutional layer, a pooling layer, a full-link layer and a Softmax layer until errors meet preset accuracy, performing power quality disturbance classification on the original signals and outputting classification results. And by adopting a compressed sensing technology and a deep learning framework, the influence of noise on the identification precision is reduced, the identification precision is improved, and quick classification is realized.
Description
Technical Field
The invention relates to the technical field of power quality, in particular to a method and a device for detecting power quality disturbance.
Background
At present, the energy and power load of a power grid are more and more, on one hand, along with the reduction of the storage amount of fossil energy, the development cost is increased, the pollution degree to the environment is larger, and along with the continuous maturity of the technology of new energy such as wind energy, solar energy and the like, the power generation cost is continuously reduced, so that the power generation cost of various new energy sources is possibly lower than that of the power generation of the traditional fossil energy, the power generated by various different electric fields can be mixed in the power grid, meanwhile, a large amount of new energy sources of the power grid are merged into the power grid, the influence on the power quality can be brought to a certain degree, for example, wind power generation has randomness, and the power generator can generate fluctuating output power; on the other hand, as the direct current converter station, the photovoltaic inverter and various nonlinear power electronic devices are more and more applied to the power grid, the collected power quality data is more and more. Therefore, the generation of a large amount of power information imposes a huge burden on the data transmission and storage of the current power grid.
In order to reduce the communication pressure and the storage problem of the acquisition end, the compression sensing technology can break through the limitation of the sampling theorem, and the original signal is recovered by acquiring data which is much smaller than the sampling theorem, so that the acquisition quantity of the power quality information is reduced. However, the recovery and reconstruction algorithm in the compressed sensing technology has large calculation amount and low calculation speed, and is difficult to be applied to the problem of reconstruction of a large amount of data. In addition, the power quality disturbance data volume is large, and the recovery reconstruction algorithm of the compressive sensing technology runs slowly, so that the method is not suitable for recovery reconstruction of a large number of signals.
At present, the power quality disturbance detection method extracts features of power quality disturbance, and then realizes classification of the features through different classifiers, so as to finally identify the disturbance. The classifiers commonly used in the classification of the power quality disturbance include: probabilistic neural network algorithms, support vector machines, artificial neural networks, and the like. These conventional artificial intelligence methods have achieved some effectiveness in practical applications, but their ability to extract features and process large amounts of data is still poor. Moreover, a feature extraction process is required, which affects their classification speed.
Therefore, how to realize the detection of the power quality disturbance in an efficient and low-computation mode is one of the work focuses of those skilled in the art.
Disclosure of Invention
The invention aims to provide a method and a device for detecting power quality disturbance, which solve the problems that when the power quality disturbance type is judged in the detection method in the prior art, the detection result is inaccurate, and various single and composite disturbance signals cannot be effectively identified.
In order to solve the above technical problem, an embodiment of the present invention provides a method for detecting power quality disturbance, including:
s1, collecting power quality information of the power grid through a voltage transformer and a current transformer, and outputting collected multi-path sampling signal data;
s2, preprocessing the multi-channel sampling signal data, carrying out sparse representation on the multi-channel sampling signal data by adopting a sparse transformation basis through a compressed sensing algorithm, then using a measurement matrix observation signal to obtain a measurement value, reconstructing the measurement value into an original discrete signal and obtaining a sparse vector containing details of the original disturbance signal to obtain a structure of the original signal, and finally accurately reconstructing the original signal by solving a numerical optimization problem;
and S3, training a deep convolutional neural network model consisting of a convolutional layer, a pooling layer, a full-link layer and a Softmax layer until errors meet preset accuracy, performing power quality disturbance classification on the original signals and outputting classification results.
Wherein, between the S1 and the S2, further comprising:
and performing hysteresis compensation processing on the data of the multi-path sampling signals, and eliminating the angle deviation of the voltage transformer and the current transformer to enable the multi-path sampling signals to be synchronous signals.
Wherein, still include:
and storing the multi-channel sampling signal data, the original signal, the training data of the deep convolutional neural network and the classification result in a storage unit.
Wherein, after the S3, the method further comprises:
and displaying the classification result and sending alarm information after judging that the classification result is abnormal.
Besides, the embodiment of the present application further provides a power quality disturbance detection apparatus, including:
the sampling unit is used for acquiring the electric energy quality information of the power grid through a voltage transformer and a current transformer, and outputting the acquired multi-path sampling signal data;
the data preprocessing unit is used for preprocessing the multi-channel sampling signal data, performing sparse representation on the multi-channel sampling signal data by adopting a sparse transformation basis through a compressed sensing algorithm, acquiring a measured value by using a measurement matrix observation signal, reconstructing the measured value into an original discrete signal and acquiring a sparse vector containing details of the original disturbing signal to acquire a structure of the original signal, and finally accurately reconstructing the original signal by solving a numerical optimization problem;
and the data processing unit is used for performing power quality disturbance classification on the original signals and outputting classification results after training is performed on a deep convolutional neural network model consisting of a convolutional layer, a pooling layer, a full-link layer and a Softmax layer until errors meet preset accuracy.
The device comprises a sampling unit, a data preprocessing unit, a voltage transformer, a current transformer, a voltage transformer, a current transformer, a sampling unit, a data processing unit and a compensation circuit, wherein the data preprocessing unit is used for processing the sampled signals to obtain the sampled signals, and the compensation circuit is connected with the sampling unit and the data processing unit and used for performing hysteresis compensation processing on the sampled signals to eliminate the angle deviation of the voltage transformer and the current transformer so that the sampled signals are output to the data processing unit after being synchronous signals.
The device also comprises a storage unit connected with the sampling unit, the compensation circuit, the data preprocessing unit and the data processing unit and used for storing the multi-path sampling signal data, the original signal, the training data of the deep convolutional neural network and the classification result.
Wherein, the storage unit comprises at least one of TF memory card, hard disk and U disk.
The device also comprises a warning display unit connected with the data processing unit and the storage unit and used for displaying the classification result and sending out alarm information after judging that the classification result is abnormal.
The system also comprises a communication unit connected with the warning display unit and used for sending the classification result and the alarm information to designated personnel.
Compared with the prior art, the method and the device for detecting the power quality disturbance, provided by the embodiment of the invention, have the following advantages:
according to the method and the device for detecting the power quality disturbance, provided by the embodiment of the invention, the power quality information of a power grid is acquired through a voltage transformer and a current transformer, the acquired multi-channel sampling signal data is output, the original signal is processed and reconstructed by adopting a compressed sensing algorithm, the original signal is trained to have an error meeting a preset accuracy through a deep convolutional neural network model consisting of a convolutional layer, a pooling layer, a full-link layer and a Softmax layer, the power quality disturbance classification is carried out on the original signal, and a classification result is output. And by adopting a compressed sensing technology and a deep learning framework, the influence of noise on the identification precision is reduced, the identification precision is improved, and quick classification is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flowchart illustrating steps of a method for detecting disturbance of power quality according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an embodiment of a power quality disturbance detection apparatus according to the present invention;
fig. 3 is a schematic structural diagram of another specific implementation of the power quality disturbance detection apparatus according to the embodiment 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.
Referring to fig. 1-3, fig. 1 is a schematic flow chart illustrating steps of a power quality disturbance detection method according to an embodiment of the invention; fig. 2 is a schematic structural diagram of an embodiment of a power quality disturbance detection apparatus according to the present invention; fig. 3 is a schematic structural diagram of another specific implementation of the power quality disturbance detection apparatus according to the embodiment of the present invention.
In one embodiment, the method for detecting disturbance of power quality includes:
s1, collecting power quality information of the power grid through a voltage transformer and a current transformer, and outputting collected multi-path sampling signal data;
s2, preprocessing the multi-channel sampling signal data, carrying out sparse representation on the multi-channel sampling signal data by adopting a sparse transformation basis through a compressed sensing algorithm, then using a measurement matrix observation signal to obtain a measurement value, reconstructing the measurement value into an original discrete signal and obtaining a sparse vector containing details of the original disturbance signal to obtain a structure of the original signal, and finally accurately reconstructing the original signal by solving a numerical optimization problem;
and S3, training a deep convolutional neural network model consisting of a convolutional layer, a pooling layer, a full-link layer and a Softmax layer until errors meet preset accuracy, performing power quality disturbance classification on the original signals and outputting classification results.
The electric energy quality information of the power grid is collected through a voltage transformer and a current transformer, the collected multi-channel sampling signal data are output, after the original signals are processed and reconstructed through a compressed sensing algorithm, the original signals are trained to have errors meeting the preset accuracy through a deep convolutional neural network model composed of a convolutional layer, a pooling layer, a full-link layer and a Softmax layer, and then the original signals are subjected to electric energy quality disturbance classification and classification results are output. And by adopting a compressed sensing technology and a deep learning framework, the influence of noise on the identification precision is reduced, the identification precision is improved, and quick classification is realized. .
In order to further improve the detection accuracy and efficiency, in an embodiment, between the S1 and the S2, the method further includes:
and performing hysteresis compensation processing on the data of the multi-path sampling signals, and eliminating the angle deviation of the voltage transformer and the current transformer to enable the multi-path sampling signals to be synchronous signals.
The data of the multi-path sampling signals which may be asynchronous originally is subjected to hysteresis compensation processing to be changed into synchronous signals, so that the adopted data becomes reliable and accurate.
It should be noted that the circuit of the hysteresis compensation process is not limited in the present application.
Since in the present application, if a lot of data is generated, and if the data is directly processed, such as preprocessing the collected multi-channel sampling signal data and processing the convolutional neural network, if a calculation error occurs in a subsequent process, the subsequent fault maintenance becomes larger, in an embodiment, the method for detecting power quality disturbance further includes:
and storing the multi-channel sampling signal data, the original signal, the training data of the deep convolutional neural network and the classification result in a storage unit.
By storing various data and classification results in the storage unit, data verification can be performed in the storage unit in the subsequent verification process, and data can be recalled even if a calculation fault occurs, so that the reliability of data detection is improved.
The storage type and the storage space of the storage unit are not limited in the application.
Further, since the actual power quality detection is performed in real time, in order to improve the management efficiency, the method further includes, after the step S3:
and displaying the classification result and sending alarm information after judging that the classification result is abnormal.
By displaying the classification result and sending alarm information after judging that the classification result is abnormal, the staff can manage more efficiently.
In one embodiment, the liquid crystal display screen is adopted to display the power quality disturbance alarm signal and the recording data, so that an operator can intuitively sense the change of the power quality, network communication is carried out with the communication server through the 4G by using an RTP & HTTP protocol so as to realize data transmission, and the classification condition of the power quality disturbance is sent to the communication equipment of the operator, so that the disturbance warning effect is achieved.
Besides, the embodiment of the present application further provides a power quality disturbance detection apparatus, including:
the sampling unit is used for acquiring the electric energy quality information of the power grid through a voltage transformer and a current transformer, and outputting the acquired multi-path sampling signal data;
the data preprocessing unit is used for preprocessing the multi-channel sampling signal data, performing sparse representation on the multi-channel sampling signal data by adopting a sparse transformation basis through a compressed sensing algorithm, acquiring a measured value by using a measurement matrix observation signal, reconstructing the measured value into an original discrete signal and acquiring a sparse vector containing details of the original disturbing signal to acquire a structure of the original signal, and finally accurately reconstructing the original signal by solving a numerical optimization problem;
and the data processing unit is used for performing power quality disturbance classification on the original signals and outputting classification results after training is performed on a deep convolutional neural network model consisting of a convolutional layer, a pooling layer, a full-link layer and a Softmax layer until errors meet preset accuracy.
Because the power quality disturbance detection device is a device corresponding to the power quality disturbance detection method, the same beneficial effects are achieved, and the description is omitted in the application.
In one embodiment, the power quality disturbance detection device further comprises a compensation circuit connected to the sampling unit and the data preprocessing unit, and configured to perform hysteresis compensation processing on the multiple sampled signal signals, eliminate the angular deviation between the voltage transformer and the current transformer, and output the multiple sampled signals to the data preprocessing unit after the multiple sampled signals are synchronous signals.
The structure of the compensation circuit is not limited in the present application.
Since a large amount of data may exist in actual operation, if a fault or a classification result is abnormal, the fault may be true or may be an equipment fault, in order to improve maintenance efficiency, in an embodiment, the power quality disturbance detection apparatus further includes a storage unit connected to the sampling unit, the compensation circuit, the data preprocessing unit, and the data processing unit, and configured to store the multi-channel sampled signal data, the original signal, the training data of the deep convolutional neural network, and the classification result.
By storing various data and classification results in the storage unit, data verification can be performed in the storage unit in the subsequent verification process, and data can be recalled even if a calculation fault occurs, so that the reliability of data detection is improved.
The type and the size of the storage space of the storage unit are not limited, and the storage unit comprises at least one of a TF (Transflash) storage card, a hard disk and a U disk
Further, in order to improve the management efficiency and the warning efficiency, in an embodiment, the power quality disturbance detection apparatus further includes a warning display unit connected to the data processing unit and the storage unit, and configured to display the classification result and send out warning information after determining that the classification result is abnormal.
Through warning display element, can make the staff obtain classification result and alarm information fast, improve the management efficiency, this application does not limit to the type of its display and alarm type, alarm information.
Further, in order to improve management efficiency and maintenance efficiency, in one embodiment, the power quality disturbance detection apparatus further includes a communication unit connected to an alarm display unit, and configured to transmit the classification result and the alarm information to a designated person.
The type of the communication unit is not limited in the present application, and the data transmission may be implemented by using broadband, 4G, 5G, WIFI, and the like.
In one embodiment, the sampling unit collects power quality information of a power grid through a voltage transformer and a current transformer, and the collected multi-path sampling signals are subjected to hysteresis compensation processing to eliminate angle deviation of the voltage transformer and the current transformer, so that the multi-path sampling signals obtained by the data sampling unit are synchronous signals. It is stored in a memory unit as raw data.
The data preprocessing unit comprises a single chip microcomputer with the model number of STM32F103RE, sampling signals collected by the sampling unit are preprocessed, the electric energy quality disturbance signals are sparsely represented by adopting a proper sparse transformation base through a compressive sensing algorithm, measurement values are obtained by observing signals through a measurement matrix, the measurement values are reconstructed into original discrete signals, sparse vectors containing details of the original disturbance signals are obtained to obtain signals which keep the original signal structure, the feature signals are far smaller than the signal length of direct measurement, and then the original signals are accurately reconstructed by solving a numerical optimization problem.
The data processing unit comprises a processor of a CPU for deep learning, and can identify the power quality disturbance through a deep convolutional neural network, the outline of the deep convolutional neural network is shown in figure 2, and the deep convolutional neural network consists of a convolutional layer, a pooling layer, a full-link layer and a Softmax layer, and each layer has different functions. The method comprises the steps of collecting voltage quality characteristic information processed by a compressed sensing algorithm, storing the voltage quality characteristic information in a storage unit, then carrying out model training through a deep convolution neural network, storing the trained data in the storage unit, reading test data again, and carrying out model training in a circulating mode until model training errors meet the accuracy of actual needs to carry out power quality disturbance classification.
The storage unit comprises a TF memory card with the model number of SDSQUNC-032G-ZN3MN, and is used for storing original data, training data and classification results of power quality disturbance, so that an operator can conveniently check and analyze the reason of the power quality disturbance.
The warning display unit comprises a G121X1-L03 liquid crystal display screen and a communication module. The liquid crystal display screen is used for displaying the electric energy quality disturbance alarm signal and the wave recording data, so that an operator can intuitively sense the change of the electric energy quality. The communication module is in network communication with the communication server through a 4G RTP & HTTP protocol to realize data transmission, and the power quality disturbance classification condition is sent to communication equipment of an operator, so that the function of disturbance warning is achieved.
In summary, according to the method and the device for detecting power quality disturbance provided by the embodiments of the present invention, power quality information of a power grid is acquired through a voltage transformer and a current transformer, the acquired data of multiple channels of sampled signals is output, an original signal is reconstructed by using a compressed sensing algorithm, and after an error satisfies a preset accuracy through a deep convolutional neural network model composed of a convolutional layer, a pooling layer, a full link layer, and a Softmax layer is trained, power quality disturbance classification is performed on the original signal, and a classification result is output. And by adopting a compressed sensing technology and a deep learning framework, the influence of noise on the identification precision is reduced, the identification precision is improved, and quick classification is realized.
The method and the device for detecting the power quality disturbance provided by the invention are described in detail above. The principles and embodiments of the present invention are explained herein using specific examples, which are presented only to assist in understanding the method and its core concepts. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.
Claims (10)
1. A power quality disturbance detection method is characterized by comprising the following steps:
s1, collecting power quality information of the power grid through a voltage transformer and a current transformer, and outputting collected multi-path sampling signal data;
s2, preprocessing the multi-channel sampling signal data, carrying out sparse representation on the multi-channel sampling signal data by adopting a sparse transformation basis through a compressed sensing algorithm, then using a measurement matrix observation signal to obtain a measurement value, reconstructing the measurement value into an original discrete signal and obtaining a sparse vector containing details of the original disturbance signal to obtain a structure of the original signal, and finally accurately reconstructing the original signal by solving a numerical optimization problem;
and S3, training a deep convolutional neural network model consisting of a convolutional layer, a pooling layer, a full-link layer and a Softmax layer until errors meet preset accuracy, performing power quality disturbance classification on the original signals and outputting classification results.
2. The power quality disturbance detection method according to claim 1, wherein between the S1 and the S2, further comprising:
and performing hysteresis compensation processing on the data of the multi-path sampling signals, and eliminating the angle deviation of the voltage transformer and the current transformer to enable the multi-path sampling signals to be synchronous signals.
3. The power quality disturbance detection method according to claim 2, further comprising:
and storing the multi-channel sampling signal data, the original signal, the training data of the deep convolutional neural network and the classification result in a storage unit.
4. The power quality disturbance detection method according to claim 3, further comprising, after the step S3:
and displaying the classification result and sending alarm information after judging that the classification result is abnormal.
5. An electrical energy quality disturbance detection device, comprising:
the sampling unit is used for acquiring the electric energy quality information of the power grid through a voltage transformer and a current transformer, and outputting the acquired multi-path sampling signal data;
the data preprocessing unit is used for preprocessing the multi-channel sampling signal data, performing sparse representation on the multi-channel sampling signal data by adopting a sparse transformation basis through a compressed sensing algorithm, acquiring a measured value by using a measurement matrix observation signal, reconstructing the measured value into an original discrete signal and acquiring a sparse vector containing details of the original disturbing signal to acquire a structure of the original signal, and finally accurately reconstructing the original signal by solving a numerical optimization problem;
and the data processing unit is used for performing power quality disturbance classification on the original signals and outputting classification results after training is performed on a deep convolutional neural network model consisting of a convolutional layer, a pooling layer, a full-link layer and a Softmax layer until errors meet preset accuracy.
6. The apparatus according to claim 5, further comprising a compensation circuit connected to the sampling unit and the data preprocessing unit, for performing hysteresis compensation on the multi-channel sampled signal, and eliminating the angular deviation between the voltage transformer and the current transformer, so that the multi-channel sampled signal is output to the data preprocessing unit after being a synchronous signal.
7. The power quality disturbance detection device according to claim 6, further comprising a storage unit connected to the sampling unit, the compensation circuit, the data preprocessing unit, and the data processing unit, for storing the multi-channel sampled signal data, the original signal, the training data of the deep convolutional neural network, and the classification result.
8. The apparatus for detecting disturbance of quality of electric energy according to claim 7, wherein the storage unit comprises at least one of a TF storage card, a hard disk and a U-disk.
9. The power quality disturbance detection device according to claim 8, further comprising a warning display unit connected to the data processing unit and the storage unit, for displaying the classification result and issuing a warning message after determining that the classification result is abnormal.
10. The power quality disturbance detection device according to claim 9, further comprising a communication unit connected to a warning display unit for transmitting the classification result and the alarm information to a specified person.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111679366.2A CN114325197A (en) | 2021-12-31 | 2021-12-31 | Power quality disturbance detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111679366.2A CN114325197A (en) | 2021-12-31 | 2021-12-31 | Power quality disturbance detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114325197A true CN114325197A (en) | 2022-04-12 |
Family
ID=81023030
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111679366.2A Pending CN114325197A (en) | 2021-12-31 | 2021-12-31 | Power quality disturbance detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114325197A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150326246A1 (en) * | 2013-06-05 | 2015-11-12 | Institute of Microelectronics, Chinese Academy of Sciences | Method for collecting signal with sampling frequency lower than nyquist frequency |
| US20190049525A1 (en) * | 2017-08-10 | 2019-02-14 | United States Of America As Represented By Secretary Of The Navy | Methods and Systems for Classifying Optically Detected Power Quality Disturbances |
| CN110048724A (en) * | 2019-04-11 | 2019-07-23 | 池州学院 | A kind of electric energy quality signal compression sampling reconstructing method |
| CN112629651A (en) * | 2020-10-16 | 2021-04-09 | 国网江苏省电力有限公司盐城供电分公司 | Power transmission line galloping information reconstruction method based on compressed sensing |
| CN113807446A (en) * | 2021-09-18 | 2021-12-17 | 国网黑龙江省电力有限公司七台河供电公司 | Electric energy quality disturbance identification and classification method |
-
2021
- 2021-12-31 CN CN202111679366.2A patent/CN114325197A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150326246A1 (en) * | 2013-06-05 | 2015-11-12 | Institute of Microelectronics, Chinese Academy of Sciences | Method for collecting signal with sampling frequency lower than nyquist frequency |
| US20190049525A1 (en) * | 2017-08-10 | 2019-02-14 | United States Of America As Represented By Secretary Of The Navy | Methods and Systems for Classifying Optically Detected Power Quality Disturbances |
| CN110048724A (en) * | 2019-04-11 | 2019-07-23 | 池州学院 | A kind of electric energy quality signal compression sampling reconstructing method |
| CN112629651A (en) * | 2020-10-16 | 2021-04-09 | 国网江苏省电力有限公司盐城供电分公司 | Power transmission line galloping information reconstruction method based on compressed sensing |
| CN113807446A (en) * | 2021-09-18 | 2021-12-17 | 国网黑龙江省电力有限公司七台河供电公司 | Electric energy quality disturbance identification and classification method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115170000B (en) | Remote monitoring method and system based on electric energy meter communication module | |
| CN105974273A (en) | Power distribution network fault positioning system | |
| CN201083800Y (en) | Transformer substation insulated live-wire detector based on dummy instrument technology | |
| CN115236451A (en) | Power distribution network overhead line fault monitoring device and method | |
| US11657148B2 (en) | Event analysis in an electric power system | |
| CN106908753A (en) | A kind of Watt-hour meter's field test device and safe data cloud storage system based on the Internet transmission data | |
| CN106649765A (en) | Smart power grid panoramic data analysis method based on big data technology | |
| CN111894814A (en) | Fault processing system and method for power generation system | |
| CN114325197A (en) | Power quality disturbance detection method and device | |
| CN117036732A (en) | Electromechanical equipment detection system, method and equipment based on fusion model | |
| CN116520068A (en) | Diagnostic method, device, equipment and storage medium for electric power data | |
| CN111352365A (en) | Dustproof ventilation type electric power and electrical equipment cabinet and control method | |
| CN108761258A (en) | Transformer short period overload capability assessment system based on artificial intelligence and big data technology | |
| CN113270944A (en) | Low-voltage power distribution user side state evaluation method | |
| CN206193229U (en) | Long -range on -line measuring of electronic electric energy meter and failure analysis system | |
| Li et al. | Cable Fault on-Line Monitoring Based on Transient Traveling Wave Signal Analysis Technology | |
| CN109375139A (en) | A kind of device and method of automatic testing light fiber current mutual inductor | |
| LU500121B1 (en) | A method, device and equipment for electric meter detecting | |
| CN113960124B (en) | Portable ECT system with image correction function | |
| CN117554864B (en) | On-line sensing and diagnosing system and method for abnormal wiring of electric energy meter | |
| CN109991485A (en) | A kind of warning device based on power quality index monitoring | |
| CN117723917B (en) | Monitoring application method based on optical fiber extrinsic Fabry-Perot type ultrasonic sensor | |
| CN208156088U (en) | A kind of warning device based on power quality index monitoring | |
| Li et al. | Remote data acquisition model for abnormal operation of power equipment based on. NET technology | |
| CN106405478A (en) | Remote on-line detection and fault analysis system for electronic type electric energy meter |
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 |