CN115935284A - Power grid abnormal voltage detection method, device, equipment and storage medium - Google Patents
Power grid abnormal voltage detection method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115935284A CN115935284A CN202211378671.2A CN202211378671A CN115935284A CN 115935284 A CN115935284 A CN 115935284A CN 202211378671 A CN202211378671 A CN 202211378671A CN 115935284 A CN115935284 A CN 115935284A
- Authority
- CN
- China
- Prior art keywords
- power grid
- short
- percentage
- loss
- circuit
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 186
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 166
- 238000000034 method Methods 0.000 claims abstract description 46
- 238000012545 processing Methods 0.000 claims abstract description 31
- 230000006870 function Effects 0.000 claims description 34
- 230000005856 abnormality Effects 0.000 claims description 4
- 230000009897 systematic effect Effects 0.000 claims description 4
- 238000012549 training Methods 0.000 description 9
- 238000013528 artificial neural network Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000004804 winding Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 4
- 238000012216 screening Methods 0.000 description 3
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000005295 random walk Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention belongs to the field of intelligent power grids, and particularly relates to a method, a device, equipment and a storage medium for detecting abnormal voltage of a power grid, wherein the method comprises the following steps: carrying out data processing on the preprocessed sample data of the short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid to obtain an optimal weight of the power grid voltage anomaly detection model; establishing a power grid abnormal voltage detection model according to the optimal weight and the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage; the current short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid are detected through a power grid voltage abnormity detection model to obtain a detection result, so that the power grid voltage abnormity detection model is established, and power grid working data are input, so that the intelligent detection of the abnormal voltage in the power grid data is realized, and the intelligent management and control of the power grid are facilitated.
Description
Technical Field
The invention relates to the technical field of smart power grids, in particular to a method, a device, equipment and a storage medium for detecting abnormal voltage of a power grid.
Background
With the gradual increase of data volume to be processed by various devices in a power grid system, the data volume of the power grid is rapidly increased, so that the difficulty of statistical analysis of the power grid is increased, and especially, abnormal voltage data of the power grid is difficult to analyze, and the safety of the power grid is seriously influenced by the problems of abnormal voltage of the power grid and the like. Therefore, how to timely and accurately detect abnormal voltage data of the power grid from a large amount of power grid data becomes a technical problem to be solved urgently at present, the traditional mode mainly adopts manual screening to acquire information manually, and then judges whether the power grid voltage is abnormal or not through own subjective consciousness and experience, but the manual screening method is easy to process a large amount of power grid data, so that the problems of inaccurate and slow detection are caused.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a method, a device, equipment and a storage medium for detecting abnormal voltage of a power grid, and aims to solve the technical problem that the safety of the power grid is seriously influenced because the abnormal voltage of the power grid is difficult to accurately detect in the prior art.
In order to achieve the above object, the present invention provides a method for detecting abnormal voltage of a power grid, which comprises the following steps:
acquiring sample data of short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of the preprocessed power grid;
carrying out data processing on the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage to obtain an optimal weight of the power grid voltage anomaly detection model;
establishing a power grid abnormal voltage detection model according to the optimal weight and the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage;
and detecting the current short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid through a power grid voltage anomaly detection model to obtain a detection result.
Optionally, the performing data processing on the power grid sample working data to obtain an optimal weight of the power grid voltage anomaly detection model includes:
processing sample data of the short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid to obtain a weight of a power grid abnormal voltage detection model;
and performing nonlinear recursive least square tracking on the weight to obtain a weight after least square tracking, repeating the operation until the weight after least square tracking meets a preset error threshold, and taking the weight after least square tracking meeting the preset error threshold as an optimal weight.
Optionally, the performing nonlinear recursive least square tracking on the weight to obtain a weight after least square tracking includes:
inputting the samples of the short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid into a power grid voltage anomaly detection model to obtain actual output, and obtaining an estimated value of a weight according to the expected output and the actual output;
carrying out Taylor expansion on the estimated value of the weight, and keeping a linear term of the Taylor expansion;
and obtaining an error function of the system according to the linear term of the Taylor expansion, and carrying out nonlinear recursive least square tracking on the error function of the system to obtain a weight value after least square tracking.
Optionally, the obtaining an error function of a system according to the linear term of the taylor expansion, and performing nonlinear recursive least square tracking on the error function of the system to obtain a weight after least square tracking includes:
calculating to obtain an error function according to the linear term of the Taylor expansion, judging whether the error function meets the preset precision requirement, and determining the gradient direction according to the error function when the error function is smaller than the expected convergence precision;
and when the gradient direction tends to zero along the x axis, selecting the first coordinate direction and the second coordinate direction as search directions and coordinate directions corresponding to the weight, and adjusting the weight according to the coordinate directions corresponding to the weight to obtain a new weight.
Optionally, the establishing a power grid abnormal voltage detection model according to the optimal weight and the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss, and the no-load current percentage further includes:
processing the sample data of the preprocessed power grid short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage and the optimal weight to obtain an input vector of a power grid abnormal voltage detection model;
obtaining an output vector of the power grid abnormal voltage detection model according to the vector relation between the input vector of the power grid abnormal voltage detection model and a preset output vector, the input vector and the parameter vector;
comparing the input vector of the power grid abnormal voltage detection model with a preset expected vector to obtain an error value of the power grid abnormal voltage detection model, and judging whether the error value of the power grid abnormal voltage detection model meets a preset precision range or not;
and if the error value of the power grid abnormal voltage detection model does not meet the preset precision range, updating the weight and the threshold of the power grid abnormal voltage detection model according to the error value of the power grid abnormal voltage detection model until the weight and the threshold of the power grid abnormal voltage detection model meet the preset precision requirement, and obtaining the power grid voltage abnormal detection model.
Optionally, before obtaining sample data of the short-circuit loss, the percentage of short-circuit voltage, the percentage of no-load loss, and the percentage of no-load current of the pre-processed power grid, the method further includes:
acquiring sample data of short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of a power grid, and judging whether the sample data of the short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid meet a preset abnormal threshold value or not;
and if the data do not meet the preset abnormal threshold, rejecting the sample data of the short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid until all the data which do not meet the preset abnormal threshold are rejected.
In addition, in order to achieve the above object, the present invention further provides a grid abnormal voltage detection apparatus, including:
the acquisition module is used for acquiring sample data of the short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the preprocessed power grid;
the processing module is used for carrying out data processing on the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage to obtain an optimal weight of the power grid voltage anomaly detection model;
the modeling module is used for establishing a power grid abnormal voltage detection model according to the optimal weight and the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage;
and the detection module is used for detecting the current short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of the power grid through a power grid voltage abnormity detection model to obtain a detection result.
In addition, in order to achieve the above object, the present invention further provides a device for detecting abnormal voltage of a power grid, the device comprising: the system comprises a memory, a processor and a power grid abnormal voltage detection program stored on the memory and running on the processor, wherein the power grid abnormal voltage detection program is configured to realize the power grid abnormal voltage detection method.
In addition, in order to achieve the above object, the present invention further provides a storage medium, where a power grid abnormal voltage detection program is stored, and the power grid abnormal voltage detection program, when executed by a processor, implements the power grid abnormal voltage detection method as described above.
The invention discloses a method, a device, equipment and a storage medium for detecting abnormal voltage of a power grid, wherein the method comprises the following steps: acquiring sample data of short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of the preprocessed power grid; carrying out data processing on the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage to obtain an optimal weight of the power grid voltage anomaly detection model; establishing a power grid abnormal voltage detection model according to the optimal weight and the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage; the current short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid are detected through a power grid voltage abnormity detection model to obtain a detection result, so that a power grid voltage abnormity detection model is established, power grid working data are input, abnormal voltage of the power grid is timely and accurately detected, intelligent detection of a large amount of power grid data is realized, abnormal voltage is timely and quickly screened out, and informatization and intelligent management of the power grid is facilitated.
Drawings
Fig. 1 is a schematic structural diagram of a power grid abnormal voltage detection device in a hardware operating environment according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of a method for detecting abnormal voltage of a power grid according to a first embodiment of the present invention;
fig. 3 is a schematic flow chart of a power grid abnormal voltage detection method according to a second embodiment of the present invention;
fig. 4 is a schematic flow chart of a power grid abnormal voltage detection method according to a third embodiment of the present invention;
fig. 5 is a schematic functional block diagram of a power grid abnormal voltage detection apparatus according to a first embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
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 obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a device for detecting abnormal voltage of a power grid in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the grid abnormal voltage detecting apparatus may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to implement connection communication among these components. The user interface 1003 may include a Display screen (Display), and the optional user interface 1003 may further include a standard wired interface and a wireless interface, and the wired interface for the user interface 1003 may be a USB interface in the present invention. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or a Non-volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of the grid abnormal voltage detection apparatus and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, a memory 1005, identified as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a grid abnormal voltage detection program.
In the device for detecting abnormal voltage of the power grid shown in fig. 1, the network interface 1004 is mainly used for connecting a background server and performing data communication with the background server; the user interface 1003 is mainly used for connecting user equipment; the grid abnormal voltage detection device calls a grid abnormal voltage detection program stored in the memory 1005 through the processor 1001, and executes the grid abnormal voltage detection method provided by the embodiment of the invention.
Based on the hardware structure, the embodiment of the power grid abnormal voltage detection method is provided.
Referring to fig. 2, fig. 2 is a schematic flow chart of a method for detecting abnormal voltage of a power grid according to a first embodiment of the present invention, and the method for detecting abnormal voltage of a power grid according to the first embodiment of the present invention is provided.
In a first embodiment, the grid abnormal voltage detection method includes the following steps:
step S10: and acquiring sample data of the short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the preprocessed power grid.
It is understood that the main execution body of the present embodiment is a power grid abnormal voltage detection device, and the power grid abnormal voltage detection device has functions of data processing, data communication, program operation, and the like.
It should be noted that, when the secondary winding of the transformer is short-circuited and the primary winding applies voltage to make the current reach the rated value, the power absorbed by the transformer from the power supply is called short-circuit loss, which is copper loss at the rated current; the short-circuit voltage percentage uk% means: x = Uk% × Un square 1000/(100 Sn). It is the percentage of the ratio of the voltage applied by the primary winding to the rated voltage when the secondary winding passes the rated current. The short circuit impedance percentage of the transformer is equal in value to the short circuit voltage percentage of the transformer; the short-circuit impedance value percentage of the transformer is an important parameter of the transformer, and indicates the magnitude of the impedance in the transformer, namely the magnitude of the impedance voltage drop of the transformer when the transformer operates at a rated load. The method has a decisive significance for how large short-circuit current can be generated when the transformer is suddenly short-circuited on the secondary side, and has an important significance for the manufacturing price and the parallel operation of the transformer; the no-load loss refers to active power consumed when a secondary winding of the transformer is open-circuited and a primary winding applies rated voltage with a rated frequency sine waveform; the percentage of the no-load current in the rated current refers to the current flowing through the primary winding when the transformer operates under the rated voltage in the no-load (secondary open circuit) mode.
In a specific implementation, the preprocessing of the grid data includes: acquiring sample data of short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of a power grid, and judging whether the sample data of the short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid meet a preset abnormal threshold value or not; and if the abnormal voltage does not meet the preset abnormal threshold, removing sample data of the short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid until all the data which do not meet the preset abnormal threshold are removed, so that the preprocessed power grid data are obtained, and the intelligent detection of the abnormal voltage of the power grid is prepared in advance.
Step S20: and carrying out data processing on the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage to obtain the optimal weight of the power grid voltage anomaly detection model.
In specific implementation, sample data of short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of the power grid are processed to obtain a weight of a power grid abnormal voltage detection model; and performing nonlinear recursive least square tracking on the weight to obtain a weight after least square tracking, repeating the operation until the weight after least square tracking meets a preset error threshold, and taking the weight after least square tracking meeting the preset error threshold as an optimal weight. Calculating to obtain an error function according to the linear term of the Taylor expansion, judging whether the error function meets the preset precision requirement, and determining the gradient direction according to the error function when the error function is smaller than the expected convergence precision; and when the gradient direction tends to zero along the x axis, selecting the first coordinate direction and the second coordinate direction as search directions and coordinate directions corresponding to the weights, and adjusting the weights according to the coordinate directions corresponding to the weights to obtain new weights, so as to obtain the weights of the abnormal voltage intelligent detection model and establish the abnormal voltage intelligent detection model.
It should be noted that the optimal weight here refers to the weight of the BP neural network model, i.e., the frequency of each number in the weighted average in the BP neural network model.
Step S30: and establishing a power grid abnormal voltage detection model according to the optimal weight and the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage.
In specific implementation, the preprocessed sample data of the short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid are processed with the optimal weight to obtain an input vector of the abnormal voltage detection model of the power grid; obtaining an output vector of the power grid abnormal voltage detection model according to the vector relation between the input vector of the power grid abnormal voltage detection model and a preset output vector, the input vector and the parameter vector; comparing the input vector of the power grid abnormal voltage detection model with a preset expected vector to obtain an error value of the power grid abnormal voltage detection model, and judging whether the error value of the power grid abnormal voltage detection model meets a preset precision range or not; if the error value of the power grid abnormal voltage detection model does not meet the preset precision range, updating the weight and the threshold of the power grid abnormal voltage detection model according to the error value of the power grid abnormal voltage detection model until the weight and the threshold of the power grid abnormal voltage detection model meet the preset precision requirement to obtain the power grid voltage abnormal detection model, so that the current sample data of power grid short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage can be input to intelligently detect the abnormal voltage.
It should be noted that the obtained power grid abnormal voltage detection model should include 4 parameter input ports and one parameter output port, for example, after the power grid abnormal voltage detection model is obtained, only sample data of current power grid short-circuit loss, short-circuit voltage percentage, no-load loss, and no-load current percentage needs to be input, so that a detection result of normal voltage detection can be obtained.
Step S40: and detecting the current short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid through a power grid voltage anomaly detection model to obtain a detection result.
In specific implementation, according to a preset detection time period, acquiring the current short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of a power grid; adding the obtained current short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of the power grid to the sample data to obtain new sample data; the method comprises the steps of detecting the current short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid through a power grid voltage abnormity detection model to obtain a detection result, adding newly acquired working data into sample working data, and correcting the power grid voltage abnormity detection model according to the new sample working data, so that a large number of data samples are continuously added, the model is continuously updated according to a large number of data samples, and the accuracy of intelligent detection of abnormal voltage of the power grid is ensured.
In the embodiment, sample data of short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of the preprocessed power grid are obtained; carrying out data processing on the sample data of the preprocessed power grid short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage to obtain an optimal weight of a power grid voltage anomaly detection model; establishing a power grid abnormal voltage detection model according to the optimal weight and the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage; the current short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid are detected through a power grid voltage abnormity detection model to obtain a detection result, so that a power grid voltage abnormity detection model is established, power grid working data are input, abnormal voltage of the power grid is timely and accurately detected, intelligent detection of a large amount of power grid data is realized, abnormal voltage is timely and quickly screened out, and informatization and intellectualization of the power grid is realized.
Referring to fig. 3, fig. 3 is a schematic flow chart of a method for detecting abnormal voltage of a power grid according to a second embodiment of the present invention, and the method for detecting abnormal voltage of a power grid according to the second embodiment of the present invention is proposed based on the first embodiment shown in fig. 2.
In the second embodiment, the step S20 includes:
step S201: and processing sample data of the short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid to obtain a weight of the power grid abnormal voltage detection model.
It should be noted that, according to the linear term of the taylor expansion, an error function is obtained through calculation, whether the error function meets the preset precision requirement or not is judged, and when the error function is smaller than the expected convergence precision, the gradient direction is determined according to the error function; and when the gradient direction tends to zero along the x axis, selecting the first coordinate direction and the second coordinate direction as search directions and coordinate directions corresponding to the weight, and adjusting the weight according to the coordinate directions corresponding to the weight to obtain a new weight.
Step S202: and performing nonlinear recursive least square tracking on the weight to obtain a weight after least square tracking, repeating the operation until the weight after least square tracking meets a preset error threshold, and taking the weight after least square tracking meeting the preset error threshold as an optimal weight.
It should be noted that, in practice, an error range may be preset in advance, after the weight is obtained, it may be determined that the obtained weight is not within the preset error range, if the obtained weight is within the preset error range, an optimal weight may be obtained, and if the obtained weight is not within the error range, the nonlinear recursive least square tracking may be performed continuously, so that the optimal weight may be obtained.
It should be noted that, the weight of the neural network is used as a parameter of the system to reflect that the output of the system changes with the change of the input. The weight is calculated by using a Recursive Least Square (RLS) method, and generally conforms to a random walk rule, namely, the relation of formula 1 is satisfied, wherein the relation is between the time k and the time k-1.
θ (k) = θ (k-1) + v (k) (formula 1)
The model error e (k) generated by the neural network, which can be expressed as e (k) = d (k) -y (k), is:
d (k) = y (k) = e (k) = f (u (k), θ (k)) + e (k) (formula 2)
It should be understood that d (k), y (k) in equation 2 represent the desired output and the actual output of the network, respectively. Is provided with
Is an estimate of θ (k), is->
The state equation of the system, which is represented by equation 3, in which the nonlinear function f (u (K), θ (K)) is taylor expanded (representing the estimated value of the state vector at time K-1) and only the linear term is retained, is represented.
In formula 3, F (k) is an N × m order matrix, and η (k) is a high order term of taylor expansion, which is negligible in practical calculation; minimum variance estimation of theta (k)
The formula 4 is directly obtained by a recursive least square algorithm identification formula. />
In practical implementation, the above process can be calculated recursively as long as an initial value is given, which has been proved to be convergent, but this step has the disadvantages of slow convergence speed and low recognition accuracy, so that it is required to improve this. As can be seen from the above algorithm recursion formula, one main process of the algorithm is the change of P (k), the change mode of the P (k) is changed, so that the change mode tends to be simplified, and then the P (k) is applied to the learning of the neural network as a learning algorithm. The step of estimating the network weight after the change is shown in equation 5.
The meaning of each variable in the equation is unchanged, only one intermediate variable is introduced, but the calculation of P (k) of the new algorithm is simplified to a certain extent, the method has certain advantages in calculation accuracy and calculation amount, and the excellent performance of the same algorithm is maintained, so that the accuracy requirement of intelligent detection of abnormal voltage of the power grid is ensured.
In the embodiment, sample data of short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of the preprocessed power grid are obtained; processing sample data of the short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid to obtain a weight of the power grid abnormal voltage detection model; and performing nonlinear recursive least square tracking on the weight to obtain a weight after least square tracking, repeating the operation until the weight after least square tracking meets a preset error threshold, and taking the weight after least square tracking meeting the preset error threshold as an optimal weight. Establishing a power grid abnormal voltage detection model according to the optimal weight and the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage; the current short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid are detected through a power grid voltage anomaly detection model to obtain a detection result, so that an intelligent power grid anomaly voltage detection model can be obtained according to an optimal weight obtained by nonlinear recursive least square tracking, and a large amount of power grid data are intelligently detected to obtain an intelligent detection result.
Referring to fig. 4, fig. 4 is a schematic flow chart of a method for detecting abnormal voltage of a power grid according to a third embodiment of the present invention, and the third embodiment of the method for detecting abnormal voltage of a power grid according to the present invention is proposed based on the first embodiment shown in fig. 2.
In the third embodiment, after the step S40, the method further includes:
step S50: and acquiring the current short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid according to a preset detection time period.
The method comprises the steps of extracting sample data of short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of a power grid, clustering and screening to obtain suspicious characteristic data clusters, carrying out manual examination and marking on data in the screened suspicious characteristic data clusters, and adding marked data into the sample data; the training model utilizes the marked suspicious characteristic data cluster to carry out on-line training learning until the maturity of the training model meets the requirement, defines the training maturity of the training model, and stores the model parameters of the training maturity; and reading mature model parameters to initialize the corresponding model, performing online detection on input sample data of the short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid, judging whether the voltage is abnormal according to the marking result, and storing the abnormal voltage into an abnormal database, so that an abnormal database case base is established, managers can conveniently look up and check the abnormal voltage, and the information management of the power grid is facilitated.
Step S60: and adding the obtained current short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of the power grid to the sample data to obtain new sample data.
It should be noted that the power grid abnormal voltage detection model has the capability of self-correction and self-regulation, a large amount of sample data is input when training is performed, so that the corresponding data BP neural network can be self-trained to find the corresponding mathematical relationship between the data BP neural network and the data BP neural network, the threshold value and the weight value are important parameters in the mathematical relationship, if no other algorithm is added, the MAYLAB can self-select the weight value and the threshold value, the scheme is to combine a recursive least square method to select the weight value, the value of an output layer is the power grid voltage abnormal detection result calculated by the BP neural network obtained through preliminary training, the power grid voltage abnormal detection result is compared with the actual power grid voltage abnormal detection result, an error is calculated, if the error does not meet the requirement, a new weight value or the threshold value is reselected until the power grid voltage abnormal detection result output by the obtained BP neural network model is compared with the actual power grid voltage abnormal detection result, and the error meets the requirement, namely, the correct BP neural network model is obtained. Therefore, the detection result of the abnormal voltage of the power grid can be accurately and intelligently obtained, and the intelligent detection of the power grid is realized.
Step S70: and detecting the current short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid through a power grid voltage abnormality detection model to obtain a detection result.
It should be noted that the detection result is stored by using a hash table, for a feature value that may appear in each data feature item in the training model, an index is generated for the hash thereof, and is used as a key to generate an FTRL parameter W [ hash (Mi) ], and each FTRL parameter W [ hash (Mi) ] is initialized to 0, and all FTRL parameters form an array, in the array, hash (Mi) is an array subscript, and W [ hash (Mi) ] represents the FTRL parameter corresponding to the array subscript.
In the embodiment, sample data of short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of the preprocessed power grid are obtained; carrying out data processing on the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage to obtain an optimal weight of the power grid voltage anomaly detection model; establishing a power grid abnormal voltage detection model according to the optimal weight and the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage; and detecting the current short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid through a power grid voltage anomaly detection model to obtain a detection result. Acquiring current short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of a power grid according to a preset detection time period; adding the obtained current short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of the power grid to the sample data to obtain new sample data; the current short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid are detected through a power grid voltage abnormity detection model to obtain a detection result, so that the power grid voltage abnormity detection model is continuously corrected according to preprocessed sample data of the short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid, a corrected intelligent detection model is obtained, and the accuracy of intelligent detection of abnormal voltage of the power grid is further ensured.
In addition, an embodiment of the present invention further provides a storage medium, where a power grid abnormal voltage detection program is stored on the storage medium, and when the power grid abnormal voltage detection program is executed by a processor, the power grid abnormal voltage detection program implements the steps of the power grid abnormal voltage detection method described above.
Since the storage medium may adopt the technical solutions of all the embodiments, beneficial effects brought by the technical solutions of the embodiments are at least achieved, and are not described in detail herein.
Referring to fig. 5, fig. 5 is a functional module schematic diagram of the abnormal voltage detection apparatus of the power grid according to the first embodiment of the present invention.
In a first embodiment of the apparatus for detecting abnormal voltage of a power grid according to the present invention, the apparatus includes:
the acquisition module 10 is configured to acquire sample data of the preprocessed short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of the power grid;
the processing module 20 is configured to perform data processing on the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss, and the no-load current percentage to obtain an optimal weight of the power grid voltage anomaly detection model;
the modeling module 30 is used for establishing a power grid abnormal voltage detection model according to the optimal weight and the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage;
and the detection module 40 is used for detecting the current short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of the power grid through a power grid voltage anomaly detection model to obtain a detection result.
In the embodiment, sample data of short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of the preprocessed power grid are obtained; carrying out data processing on the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage to obtain an optimal weight of the power grid voltage anomaly detection model; establishing a power grid abnormal voltage detection model according to the optimal weight and the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage; the current short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid are detected through a power grid voltage abnormity detection model to obtain a detection result, so that the power grid voltage abnormity detection model is established, intelligent detection on a large amount of power grid data is further realized, abnormal voltage is screened out timely and rapidly, and informatization and intellectualization of the power grid are realized.
In an embodiment, the processing module 20 is further configured to perform data processing on the power grid sample working data to obtain an optimal weight of the power grid voltage anomaly detection model, and the method includes:
processing sample data of the short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid to obtain a weight of the power grid abnormal voltage detection model;
and performing nonlinear recursive least square tracking on the weight to obtain a weight after least square tracking, repeating the operation until the weight after least square tracking meets a preset error threshold, and taking the weight after least square tracking meeting the preset error threshold as an optimal weight.
In an embodiment, the modeling module 30 is further configured to perform a nonlinear recursive least square tracking on the weight to obtain a least-squares tracked weight, and includes:
inputting samples of the short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid into a power grid voltage abnormality detection model to obtain actual output, and obtaining an estimated value of a weight according to the expected output and the actual output;
carrying out Taylor expansion on the estimated value of the weight, and keeping a linear term of the Taylor expansion;
and obtaining an error function of the system according to the linear term of the Taylor expansion, and carrying out nonlinear recursive least square tracking on the error function of the system to obtain a weight value after least square tracking.
In an embodiment, the processing module 20 is further configured to obtain a systematic error function according to the linear term of the taylor expansion, and perform nonlinear recursive least square tracking on the systematic error function to obtain a weight after the least square tracking, where the method includes:
calculating to obtain an error function according to the linear term of the Taylor expansion, judging whether the error function meets the preset precision requirement, and determining the gradient direction according to the error function when the error function is smaller than the expected convergence precision;
and when the gradient direction tends to zero along the x axis, selecting the first coordinate direction and the second coordinate direction as search directions and coordinate directions corresponding to the weight, and adjusting the weight according to the coordinate directions corresponding to the weight to obtain a new weight.
In an embodiment, the processing module 20 is further configured to establish a power grid abnormal voltage detection model according to the optimal weight and the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss, and the no-load current percentage, and further includes:
processing the sample data of the preprocessed power grid short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage and the optimal weight to obtain an input vector of a power grid abnormal voltage detection model;
obtaining an output vector of the power grid abnormal voltage detection model according to the vector relation between the input vector of the power grid abnormal voltage detection model and a preset output vector, the input vector and the parameter vector;
comparing the input vector of the power grid abnormal voltage detection model with a preset expected vector to obtain an error value of the power grid abnormal voltage detection model, and judging whether the error value of the power grid abnormal voltage detection model meets a preset precision range or not;
and if the error value of the power grid abnormal voltage detection model does not meet the preset precision range, updating the weight and the threshold of the power grid abnormal voltage detection model according to the error value of the power grid abnormal voltage detection model until the weight and the threshold of the power grid abnormal voltage detection model meet the preset precision requirement, and obtaining the power grid voltage abnormal detection model.
In an embodiment, before the obtaining sample data of the short-circuit loss, the short-circuit voltage percentage, the no-load loss, and the no-load current percentage of the preprocessed power grid, the processing module 20 is further configured to:
acquiring sample data of short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of a power grid, and judging whether the sample data of the short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid meet a preset abnormal threshold value or not;
and if the data does not meet the preset abnormal threshold, rejecting sample data of short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of the power grid until all data which do not meet the preset abnormal threshold are rejected.
In an embodiment, the detecting module 40 is further configured to detect the current short-circuit loss, the short-circuit voltage percentage, the no-load loss, and the no-load current percentage of the power grid through a power grid voltage anomaly detection model, and after obtaining a detection result, further include:
acquiring current short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of a power grid according to a preset detection time period;
adding the obtained current short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of the power grid to the sample data to obtain new sample data;
and detecting the current short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid through a power grid voltage abnormality detection model to obtain a detection result.
Other embodiments or specific implementation manners of the device for detecting abnormal voltage of a power grid according to the present invention may refer to the above method embodiments, so that at least all the beneficial effects brought by the technical solutions of the above embodiments are provided, and no further description is provided herein.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of other like elements in a process, method, article, or system comprising the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order, but rather the words first, second, third, etc. are to be interpreted as names.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention or portions thereof that contribute to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (e.g., a Read Only Memory (ROM)/Random Access Memory (RAM), a magnetic disk, or an optical disk), and includes several instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A power grid abnormal voltage detection method is characterized by comprising the following steps:
acquiring sample data of short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of the preprocessed power grid;
carrying out data processing on the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage to obtain an optimal weight of the power grid voltage anomaly detection model;
establishing a power grid abnormal voltage detection model according to the optimal weight and the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage;
and detecting the current short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid through a power grid voltage anomaly detection model to obtain a detection result.
2. The method of claim 1, wherein the performing data processing on the power grid sample working data to obtain an optimal weight of a power grid voltage anomaly detection model comprises:
processing sample data of the short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid to obtain a weight of a power grid abnormal voltage detection model;
and performing nonlinear recursive least square tracking on the weight to obtain a weight after least square tracking, repeating the operation until the weight after least square tracking meets a preset error threshold, and taking the weight after least square tracking meeting the preset error threshold as an optimal weight.
3. The method of claim 2, wherein the performing nonlinear recursive least squares tracking on the weights to obtain least squares tracked weights comprises:
inputting the samples of the short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid into a power grid voltage anomaly detection model to obtain actual output, and obtaining an estimated value of a weight according to the expected output and the actual output;
carrying out Taylor expansion on the estimated value of the weight, and keeping a linear term of the Taylor expansion;
and obtaining an error function of the system according to the linear term of the Taylor expansion, and carrying out nonlinear recursive least square tracking on the error function of the system to obtain a weight value after least square tracking.
4. The method of claim 3, wherein obtaining a systematic error function from the linear terms of the Taylor expansion and performing a non-linear recursive least squares tracking on the systematic error function to obtain least squares tracked weights comprises:
calculating to obtain an error function according to the linear term of the Taylor expansion, judging whether the error function meets the preset precision requirement, and determining the gradient direction according to the error function when the error function is smaller than the expected convergence precision;
and when the gradient direction tends to zero along the x axis, selecting the first coordinate direction and the second coordinate direction as search directions and coordinate directions corresponding to the weight, and adjusting the weight according to the coordinate directions corresponding to the weight to obtain a new weight.
5. The method of claim 4, wherein the establishing a power grid abnormal voltage detection model according to the optimal weight and the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage further comprises:
processing the sample data of the preprocessed power grid short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage and the optimal weight to obtain an input vector of a power grid abnormal voltage detection model;
obtaining an output vector of the power grid abnormal voltage detection model according to the vector relation between the input vector of the power grid abnormal voltage detection model and a preset output vector, the input vector and the parameter vector;
comparing the input vector of the power grid abnormal voltage detection model with a preset expected vector to obtain an error value of the power grid abnormal voltage detection model, and judging whether the error value of the power grid abnormal voltage detection model meets a preset precision range or not;
and if the error value of the power grid abnormal voltage detection model does not meet the preset precision range, updating the weight and the threshold of the power grid abnormal voltage detection model according to the error value of the power grid abnormal voltage detection model until the weight and the threshold of the power grid abnormal voltage detection model meet the preset precision requirement, and obtaining the power grid abnormal voltage detection model.
6. The method of claim 1, wherein before obtaining sample data of short-circuit loss, short-circuit voltage percentage, no-load loss, and no-load current percentage of the pre-processed power grid, the method further comprises:
acquiring sample data of short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of a power grid, and judging whether the sample data of the short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid meet a preset abnormal threshold value or not;
and if the data does not meet the preset abnormal threshold, rejecting sample data of short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of the power grid until all data which do not meet the preset abnormal threshold are rejected.
7. The method according to any one of claims 1 to 6, wherein the detecting the current short-circuit loss, the short-circuit voltage percentage, the no-load loss, and the no-load current percentage of the power grid through a power grid voltage anomaly detection model, and after obtaining the detection result, further comprises:
acquiring the current short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid according to a preset detection time period;
adding the obtained current short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of the power grid to the sample data to obtain new sample data;
and detecting the current short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the power grid through a power grid voltage abnormality detection model to obtain a detection result.
8. An abnormal voltage detection device of a power grid, the abnormal voltage detection device of the power grid comprising:
the acquisition module is used for acquiring sample data of the short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage of the preprocessed power grid;
the processing module is used for carrying out data processing on the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage to obtain an optimal weight of the power grid voltage anomaly detection model;
the modeling module is used for establishing a power grid abnormal voltage detection model according to the optimal weight and the preprocessed sample data of the power grid short-circuit loss, the short-circuit voltage percentage, the no-load loss and the no-load current percentage;
and the detection module is used for detecting the current short-circuit loss, short-circuit voltage percentage, no-load loss and no-load current percentage of the power grid through a power grid voltage abnormity detection model to obtain a detection result.
9. A grid abnormal voltage detection apparatus, characterized in that the grid abnormal voltage detection apparatus comprises a memory, a processor and a grid abnormal voltage detection program stored on the memory and operable on the processor, the grid abnormal voltage detection program, when executed by the processor, implementing the grid abnormal voltage detection method according to any one of claims 1 to 7.
10. A storage medium, wherein a power grid abnormal voltage detection program is stored on the storage medium, and when executed by a processor, the power grid abnormal voltage detection program implements the power grid abnormal voltage detection method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211378671.2A CN115935284A (en) | 2022-11-04 | 2022-11-04 | Power grid abnormal voltage detection method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211378671.2A CN115935284A (en) | 2022-11-04 | 2022-11-04 | Power grid abnormal voltage detection method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115935284A true CN115935284A (en) | 2023-04-07 |
Family
ID=86549741
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211378671.2A Pending CN115935284A (en) | 2022-11-04 | 2022-11-04 | Power grid abnormal voltage detection method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115935284A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116248959A (en) * | 2023-05-12 | 2023-06-09 | 深圳市橙视科技发展有限公司 | Network player fault detection method, device, equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101533058A (en) * | 2009-04-24 | 2009-09-16 | 东北大学 | Power abnormal failure data analyzing device and diagnosing method |
| US20110089954A1 (en) * | 2009-10-16 | 2011-04-21 | Industrial Technology Research Institute | Station for detecting winding products and method for detecting inter-turn short circuit |
| CN110334726A (en) * | 2019-04-24 | 2019-10-15 | 华北电力大学 | A kind of identification of the electric load abnormal data based on Density Clustering and LSTM and restorative procedure |
| CN111222139A (en) * | 2020-02-24 | 2020-06-02 | 南京邮电大学 | GEP optimization-based smart power grid data anomaly effective identification method |
| JP2020092569A (en) * | 2018-12-07 | 2020-06-11 | パナソニックＩｐマネジメント株式会社 | Abnormal current sign detection system and abnormal current sign detection method |
| CN112308168A (en) * | 2020-11-09 | 2021-02-02 | 国家电网有限公司 | Method for detecting voltage data abnormity in power grid |
| CN113901666A (en) * | 2021-10-20 | 2022-01-07 | 赵茵茵 | Real-time monitoring and anomaly detection method applied to smart power grid |
| CN115236535A (en) * | 2022-07-18 | 2022-10-25 | 湖北文理学院 | Battery SOC estimation method, device, equipment and storage medium |
-
2022
- 2022-11-04 CN CN202211378671.2A patent/CN115935284A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101533058A (en) * | 2009-04-24 | 2009-09-16 | 东北大学 | Power abnormal failure data analyzing device and diagnosing method |
| US20110089954A1 (en) * | 2009-10-16 | 2011-04-21 | Industrial Technology Research Institute | Station for detecting winding products and method for detecting inter-turn short circuit |
| JP2020092569A (en) * | 2018-12-07 | 2020-06-11 | パナソニックＩｐマネジメント株式会社 | Abnormal current sign detection system and abnormal current sign detection method |
| CN110334726A (en) * | 2019-04-24 | 2019-10-15 | 华北电力大学 | A kind of identification of the electric load abnormal data based on Density Clustering and LSTM and restorative procedure |
| CN111222139A (en) * | 2020-02-24 | 2020-06-02 | 南京邮电大学 | GEP optimization-based smart power grid data anomaly effective identification method |
| CN112308168A (en) * | 2020-11-09 | 2021-02-02 | 国家电网有限公司 | Method for detecting voltage data abnormity in power grid |
| CN113901666A (en) * | 2021-10-20 | 2022-01-07 | 赵茵茵 | Real-time monitoring and anomaly detection method applied to smart power grid |
| CN115236535A (en) * | 2022-07-18 | 2022-10-25 | 湖北文理学院 | Battery SOC estimation method, device, equipment and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| 华东六省一市电机工程（电力）学会联合编委会: "电工进网作业考核培训教材 建筑电工部分", 中国电力出版社, pages: 110 - 111 * |
| 周福举;王洪寅;庞吉年;花俊;毕键爽;: "基于BP神经网络的线损不良数据辨识及其预测", 节能, no. 01, pages 33 - 37 * |
| 王海云;张岩;闫富荣;陈雁;杨莉萍;常乾坤;张再驰;陈茜;袁清芳;: "基于深度神经网络的低压台区线损异常识别方法", 电力需求侧管理, no. 06, pages 37 - 41 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116248959A (en) * | 2023-05-12 | 2023-06-09 | 深圳市橙视科技发展有限公司 | Network player fault detection method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109495296A (en) | Intelligent substation communication network state evaluation method based on clustering and neural network | |
| CN111833583B (en) | Training method, device, equipment and medium for power data anomaly detection model | |
| CN111898839B (en) | Importance degree classification method and device for power users | |
| CN109670611A (en) | A kind of power information system method for diagnosing faults and device | |
| CN113868953B (en) | Multi-unit operation optimization method, device and system in industrial system and storage medium | |
| CN112561303B (en) | Power system dynamic analysis method based on integrated learning and power grid topology change | |
| CN112308459A (en) | Power grid household transformation relation identification method and identification device, and electronic equipment | |
| CN115542236B (en) | Electric energy meter operation error estimation method and device | |
| CN115423594A (en) | Enterprise financial risk assessment method, device, equipment and storage medium | |
| CN113902946A (en) | Power system fault direction judging method and device, terminal equipment and storage medium | |
| CN115935284A (en) | Power grid abnormal voltage detection method, device, equipment and storage medium | |
| CN111612149A (en) | Main network line state detection method, system and medium based on decision tree | |
| CN114583767B (en) | Data-driven wind power plant frequency modulation response characteristic modeling method and system | |
| CN117156442A (en) | Cloud data security protection method and system based on 5G network | |
| CN111027841A (en) | Low-voltage transformer area line loss calculation method based on gradient lifting decision tree | |
| CN107274025B (en) | System and method for realizing intelligent identification and management of power consumption mode | |
| CN112035552B (en) | Method and device for predicting severity of voltage sag based on association rule | |
| CN112966965A (en) | Import and export big data analysis and decision method, device, equipment and storage medium | |
| CN113110961A (en) | Equipment abnormality detection method and device, computer equipment and readable storage medium | |
| CN116955182A (en) | Abnormality index analysis method, abnormality index analysis device, abnormality index analysis storage medium, abnormality index analysis device, abnormality index analysis program, and | |
| CN114861800B (en) | Model training method, probability determining device, model training equipment, model training medium and model training product | |
| CN116662840A (en) | Low-voltage station user phase identification method based on machine learning | |
| CN116400266A (en) | Transformer fault detection method, device and medium based on digital twin model | |
| CN115760486A (en) | Method, device and equipment for estimating temporary construction scale and readable storage medium | |
| CN114971053A (en) | Training method and device for online prediction model of network line loss rate of low-voltage transformer area |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230407 |
|
| RJ01 | Rejection of invention patent application after publication |