CN117216649A - Sensitivity determination method and device for unbalance degree of cable and computer equipment - Google Patents
Sensitivity determination method and device for unbalance degree of cable and computer equipment Download PDFInfo
- Publication number
- CN117216649A CN117216649A CN202311018664.6A CN202311018664A CN117216649A CN 117216649 A CN117216649 A CN 117216649A CN 202311018664 A CN202311018664 A CN 202311018664A CN 117216649 A CN117216649 A CN 117216649A
- Authority
- CN
- China
- Prior art keywords
- influence factor
- data
- cable
- feature
- sensitivity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 71
- 230000035945 sensitivity Effects 0.000 title claims abstract description 69
- 238000010206 sensitivity analysis Methods 0.000 claims abstract description 28
- 239000011159 matrix material Substances 0.000 claims description 85
- 238000004088 simulation Methods 0.000 claims description 71
- 238000012545 processing Methods 0.000 claims description 30
- 238000013528 artificial neural network Methods 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 23
- 238000011176 pooling Methods 0.000 claims description 12
- 238000012512 characterization method Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 6
- 238000001228 spectrum Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 210000002364 input neuron Anatomy 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/50—Arrangements for eliminating or reducing asymmetry in polyphase networks
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a sensitivity determination method, a sensitivity determination device and computer equipment for cable unbalance. The method comprises the following steps: acquiring each influence factor of the unbalance of the cable in the in-phase cable and each characteristic data of the unbalance of the cable corresponding to each influence factor, and constructing a plurality of characteristic matrixes based on each characteristic data corresponding to each influence factor; based on the feature matrixes, building a feature map corresponding to each influence factor, inputting the feature map into a sensitivity analysis network, and calculating the sub-sensitivity of the cable unbalance corresponding to each influence factor; and taking the sub sensitivity corresponding to all the influencing factors as the sensitivity of the unbalance degree of the cable. By adopting the method, the sensitivity accuracy of the cable unbalance degree can be improved.
Description
Technical Field
The present application relates to the field of power cable technologies, and in particular, to a cable imbalance sensitivity method, apparatus, and computer device.
Background
As the use demand of electric power increases, the parallel cable cannot meet the electric power development gradually, and a plurality of parallel cables with large cross sections and single cores are required to replace the original electric power transmission line. And the parallel operation of the cables can not only increase the power transmission capacity, but also effectively improve the fault tolerance of the system, so that the parallel operation of the multi-loop cables is widely adopted. In-phase parallel high-voltage cable lines have been used in cities more, and the imbalance of in-phase parallel cables has more influence factors. The sensitivity of how to detect the cable unbalance of the grid line is therefore the current focus of research.
The sensitivity of the cable unbalance is analyzed by carrying out equal ratio addition calculation on all influence factors in the traditional mode, but the accuracy of the sensitivity of the cable unbalance is lower because the influence information of different influence factors on the cable unbalance is different and the influence depth on the cable unbalance is different.
Disclosure of Invention
Based on this, it is necessary to provide a sensitivity determination method, an apparatus, a computer device, a computer readable storage medium and a computer program product of the cable unbalance degree in view of the above technical problems.
In a first aspect, the present application provides a method of sensitivity determination of a cable imbalance. The method comprises the following steps:
acquiring each influence factor of the unbalance of the cable in the in-phase cable and each characteristic data of the unbalance of the cable corresponding to each influence factor, and constructing a plurality of characteristic matrixes based on each characteristic data corresponding to each influence factor;
based on the feature matrixes, building a feature map corresponding to each influence factor, inputting the feature map into a sensitivity analysis network, and calculating the sub-sensitivity of the cable unbalance corresponding to each influence factor;
And taking the sub sensitivity corresponding to all the influencing factors as the sensitivity of the unbalance degree of the cable.
Optionally, the acquiring each feature data of the cable unbalance corresponding to each influence factor includes:
acquiring influence factor data corresponding to each influence factor of the unbalance of the cable in the same-phase cable, and establishing a cable simulation model based on each influence factor data;
and carrying out simulation processing on the cable simulation model to obtain unbalance degree data corresponding to the cable simulation model, and respectively adjusting each influence factor data corresponding to each influence factor through a single variable method strategy to obtain each characteristic data corresponding to each influence factor.
Optionally, the step of respectively adjusting the data of each influence factor corresponding to each influence factor by using a single variable method policy to obtain the feature data corresponding to each influence factor includes:
for each influence factor, acquiring a plurality of influence factor data of the influence factor, replacing the influence factor data of the influence factor based on the influence factor data and a single variable method strategy to obtain new influence factor data corresponding to the influence factor, and updating the cable simulation model based on the new influence factor data to obtain a new cable simulation model corresponding to the new influence factor data;
Respectively carrying out simulation processing on each new cable simulation model to obtain new unbalance degree data corresponding to each new cable simulation model, and respectively calculating data variables between the unbalance degree data and each new unbalance degree data;
and respectively carrying out characterization processing on each data variable to obtain each characteristic data corresponding to the influence factors.
Optionally, the constructing a plurality of feature matrices based on the feature data corresponding to each influencing factor includes:
randomly screening target feature data in the feature data corresponding to each influence factor, and constructing a first feature matrix of each influence factor based on the target feature data of each influence factor;
based on the characteristic data corresponding to each influence factor, randomly adjusting the target characteristic data of any influence factor in the first characteristic matrix by a single variable method to obtain each second characteristic matrix;
and taking the first feature matrix and each second feature matrix as feature matrices corresponding to all influencing factors.
Optionally, the establishing a feature map corresponding to each influencing factor based on each feature matrix includes:
Based on the data variable corresponding to each feature data in each feature matrix, respectively identifying the criticality of each feature data in each feature matrix through a convolution layer of a feature map neural network, and extracting the critical feature data in each feature matrix through a pooling layer of the feature map neural network based on the criticality of each feature data in each feature matrix;
and carrying out data connection processing on each key characteristic data according to the influence factors corresponding to each key characteristic data through the full connection layer of the characteristic map neural network to obtain a characteristic map corresponding to each influence factor.
Optionally, the inputting the characteristic spectrum into a sensitivity analysis network, calculating a sub-sensitivity of the cable unbalance corresponding to each influence factor, including:
inputting the key feature data of the same influence factors in the feature map into a sensitivity analysis model, and analyzing the influence sensitivity of the key feature data of each influence factor on the unbalance degree of the cable;
for each influence factor, determining the sub-sensitivity of the cable unbalance corresponding to the influence factor based on the influence sensitivity of the key characteristic data of the influence factor to the cable unbalance.
In a second aspect, the application also provides a device for determining the sensitivity of the unbalance degree of the cable. The device comprises:
the acquisition module is used for acquiring each influence factor of the cable unbalance degree in the in-phase cable and each characteristic data of the cable unbalance degree corresponding to each influence factor, and constructing a plurality of characteristic matrixes based on each characteristic data corresponding to each influence factor;
the computing module is used for building a characteristic map corresponding to each influence factor based on each characteristic matrix, inputting the characteristic map into a sensitivity analysis network and computing the sub-sensitivity of the cable unbalance corresponding to each influence factor;
and the determining module is used for taking the sub-sensitivity corresponding to all the influencing factors as the sensitivity of the unbalance degree of the cable.
Optionally, the acquiring module is specifically configured to:
acquiring influence factor data corresponding to each influence factor of the unbalance of the cable in the same-phase cable, and establishing a cable simulation model based on each influence factor data;
and carrying out simulation processing on the cable simulation model to obtain unbalance degree data corresponding to the cable simulation model, and respectively adjusting each influence factor data corresponding to each influence factor through a single variable method strategy to obtain each characteristic data corresponding to each influence factor.
Optionally, the acquiring module is specifically configured to:
for each influence factor, acquiring a plurality of influence factor data of the influence factor, replacing the influence factor data of the influence factor based on the influence factor data and a single variable method strategy to obtain new influence factor data corresponding to the influence factor, and updating the cable simulation model based on the new influence factor data to obtain a new cable simulation model corresponding to the new influence factor data;
respectively carrying out simulation processing on each new cable simulation model to obtain new unbalance degree data corresponding to each new cable simulation model, and respectively calculating data variables between the unbalance degree data and each new unbalance degree data;
and respectively carrying out characterization processing on each data variable to obtain each characteristic data corresponding to the influence factors.
Optionally, the acquiring module is specifically configured to:
randomly screening target feature data in the feature data corresponding to each influence factor, and constructing a first feature matrix of each influence factor based on the target feature data of each influence factor;
Based on the characteristic data corresponding to each influence factor, randomly adjusting the target characteristic data of any influence factor in the first characteristic matrix by a single variable method to obtain each second characteristic matrix;
and taking the first feature matrix and each second feature matrix as feature matrices corresponding to all influencing factors.
Optionally, the computing module is specifically configured to:
based on the data variable corresponding to each feature data in each feature matrix, respectively identifying the criticality of each feature data in each feature matrix through a convolution layer of a feature map neural network, and extracting the critical feature data in each feature matrix through a pooling layer of the feature map neural network based on the criticality of each feature data in each feature matrix;
and carrying out data connection processing on each key characteristic data according to the influence factors corresponding to each key characteristic data through the full connection layer of the characteristic map neural network to obtain a characteristic map corresponding to each influence factor.
Optionally, the computing module is specifically configured to:
inputting the key feature data of the same influence factors in the feature map into a sensitivity analysis model, and analyzing the influence sensitivity of the key feature data of each influence factor on the unbalance degree of the cable;
For each influence factor, determining the sub-sensitivity of the cable unbalance corresponding to the influence factor based on the influence sensitivity of the key characteristic data of the influence factor to the cable unbalance.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the steps of the method of any of the first aspects when the processor executes the computer program.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method of any of the first aspects.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprising a computer program which, when executed by a processor, implements the steps of the method of any of the first aspects.
The sensitivity determination method, the sensitivity determination device and the computer equipment for the cable unbalance degree are characterized in that each influence factor of the cable unbalance degree in the in-phase cable and each characteristic data of the cable unbalance degree corresponding to each influence factor are obtained, and a plurality of characteristic matrixes are constructed based on each characteristic data corresponding to each influence factor; based on the feature matrixes, building a feature map corresponding to each influence factor, inputting the feature map into a sensitivity analysis network, and calculating the sub-sensitivity of the cable unbalance corresponding to each influence factor; and taking the sub sensitivity corresponding to all the influencing factors as the sensitivity of the unbalance degree of the cable. By acquiring the data of each influence factor of the unbalance degree of the cables in the same-phase cable, a feature matrix of the arrangement and combination of the plurality of influence factor data is established, so that the data comprehensiveness in the process of identifying the sub-sensitivity corresponding to each influence factor is improved. Then, by establishing the feature patterns corresponding to the influence factors based on the feature matrices, the feature data of all the influence factors can be ensured to synchronously perform sensitivity analysis, and by converting the feature matrices into the feature patterns, the operation data quantity is reduced, the operation efficiency is improved, the key feature data in the feature patterns is extracted, and the accuracy of calculating the sub-sensitivity corresponding to each influence factor is improved. And finally, calculating the sub-sensitivity of the cable unbalance corresponding to each influence factor through a sensitivity analysis network, so as to obtain the sensitivity of the cable unbalance, comprehensively considering the influence weights of different influence factors on the cable unbalance, and improving the accuracy of the sensitivity of the analyzed cable unbalance.
Drawings
FIG. 1 is a flow chart of a method for sensitivity determination of cable unbalance in one embodiment;
FIG. 2 is a flow chart of extraction of key feature data in one embodiment;
FIG. 3 is a flow diagram of an example sensitivity determination for cable imbalance in one embodiment;
FIG. 4 is a block diagram of a cable imbalance sensitivity determination apparatus in one embodiment;
fig. 5 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The sensitivity determination method for the unbalance degree of the cable provided by the embodiment of the application is mainly applied to application environments corresponding to the in-phase parallel high-voltage cable lines. The method can be applied to the terminal, the server and a system comprising the terminal and the server, and is realized through interaction of the terminal and the server. The server may be implemented as a stand-alone server or as a server cluster formed by a plurality of servers. The terminal may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, etc. The terminal establishes a feature matrix of the arrangement and combination of a plurality of influence factor data by acquiring each influence factor data of the unbalance degree of the cables in the same phase, so that the data comprehensiveness in the process of identifying the sub-sensitivity corresponding to each influence factor is improved. Then, by establishing the feature patterns corresponding to the influence factors based on the feature matrices, the feature data of all the influence factors can be ensured to synchronously perform sensitivity analysis, and by converting the feature matrices into the feature patterns, the operation data quantity is reduced, the operation efficiency is improved, the key feature data in the feature patterns is extracted, and the accuracy of calculating the sub-sensitivity corresponding to each influence factor is improved. And finally, calculating the sub-sensitivity of the cable unbalance corresponding to each influence factor through a sensitivity analysis network, so as to obtain the sensitivity of the cable unbalance, comprehensively considering the influence weights of different influence factors on the cable unbalance, and improving the accuracy of the sensitivity of the analyzed cable unbalance.
In one embodiment, as shown in fig. 1, there is provided a method for determining sensitivity of unbalance of a cable, which is described as an example of application to a terminal, and includes the following steps:
step S101, each influence factor of the cable unbalance degree in the in-phase cable and each characteristic data of the cable unbalance degree corresponding to each influence factor are obtained, and a plurality of characteristic matrixes are constructed based on each characteristic data corresponding to each influence factor.
In this embodiment, the terminal responds to the user uploading influence factor operation, collects structural information related to the unbalance degree of the cable in the in-phase cable to obtain each influence factor, and then collects a plurality of conventional data corresponding to each influence factor to obtain each influence factor data corresponding to each influence factor. The structural information includes, but is not limited to, cable laying soil resistivity, cable core resistivity, cable laying mode, cable arrangement mode, cable insulation layer thickness, cable center distance, cable length, cable tail end outgoing line length, cable sheath connection mode, cable stacking coefficient, cable loop number and the like, and each influence factor corresponds to a plurality of influence factor data, for example, influence factor data corresponding to the cable laying mode includes, but is not limited to, delta laying, line laying, double-row laying and the like. And the terminal determines the characteristic data of the cable unbalance corresponding to each influence factor based on the influence factor data of each influence factor. The specific determination process will be described in detail later. The terminal obtains a plurality of feature matrixes by means of randomly arranging and combining the feature data corresponding to each influence factor. Wherein each feature matrix includes one of the feature data of all influencing factors.
Step S102, based on each feature matrix, a feature map corresponding to each influence factor is established, the feature map is input into a sensitivity analysis network, and sub-sensitivity of the cable unbalance corresponding to each influence factor is calculated.
In this embodiment, the terminal extracts key feature data of each influencing factor in each feature matrix, and establishes a feature map corresponding to each influencing factor based on the key feature data of each influencing factor. The key feature data are feature data corresponding to the key degree with the key degree larger than a preset key degree threshold value. The specific criticality determination process will be described in detail later. And then, the terminal inputs the feature patterns corresponding to the key feature data of each influence factor into a sensitivity analysis network, and calculates the sub-sensitivity of the cable unbalance corresponding to each influence factor. Wherein the sensitivity analysis network is a classification neural network based on deep reinforcement learning. The classified neural network includes a plurality of convolutional layers, a plurality of pooling layers, a plurality of fully connected layers, and a gradient back propagation computation layer.
Step S103, taking the sub-sensitivity corresponding to all the influencing factors as the sensitivity of the unbalance degree of the cable.
In this embodiment, the terminal combines the sub-sensitivities corresponding to all the influencing factors to obtain the sensitivity of the cable imbalance of the in-phase cable.
Based on the scheme, the feature matrix of the arrangement combination of the plurality of influence factor data is established by acquiring the influence factor data of the unbalance degree of the cables in the same phase cable, so that the data comprehensiveness in the process of identifying the sub-sensitivity corresponding to each influence factor is improved. Then, by establishing the feature patterns corresponding to the influence factors based on the feature matrices, the feature data of all the influence factors can be ensured to synchronously perform sensitivity analysis, and by converting the feature matrices into the feature patterns, the operation data quantity is reduced, the operation efficiency is improved, the key feature data in the feature patterns is extracted, and the accuracy of calculating the sub-sensitivity corresponding to each influence factor is improved. And finally, calculating the sub-sensitivity of the cable unbalance corresponding to each influence factor through a sensitivity analysis network, so as to obtain the sensitivity of the cable unbalance, comprehensively considering the influence weights of different influence factors on the cable unbalance, and improving the accuracy of the sensitivity of the analyzed cable unbalance.
Optionally, obtaining each feature data of the cable unbalance corresponding to each influencing factor includes: acquiring influence factor data corresponding to each influence factor of the unbalance of the cable in the same-phase cable, and establishing a cable simulation model based on the influence factor data; and carrying out simulation processing on the cable simulation model to obtain unbalance degree data corresponding to the cable simulation model, and respectively adjusting the influence factor data corresponding to each influence factor through a single variable method strategy to obtain the characteristic data corresponding to each influence factor.
In this embodiment, the terminal obtains influence factor data corresponding to each influence factor of the cable unbalance in the in-phase cable, and establishes a cable simulation model based on each influence factor data. Wherein the cable simulation model may be, but is not limited to being, constructed by a finite element simulation model. And then, the terminal carries out simulation current transmission process treatment on the cable simulation model to obtain current carrying information of the cable simulation model. And finally, the terminal calculates unbalance degree data corresponding to the cable simulation model through a three-phase current carrying unbalance degree algorithm based on current carrying information of the cable simulation model.
And then, the terminal respectively replaces the cable simulation model with the influence factor data of each influence factor through a single variable method strategy, so as to obtain the characteristic data corresponding to each influence factor. The specific process of determining the respective feature data will be described in detail later.
Based on the scheme, through a single variable method, each piece of characteristic data corresponding to each influence factor is determined, and the accuracy of determining each piece of characteristic data is improved.
Optionally, the method includes respectively adjusting each influence factor data corresponding to each influence factor by a single variable method policy to obtain each feature data corresponding to each influence factor, including: for each influence factor, acquiring a plurality of influence factor data of the influence factor, replacing the influence factor data of the influence factor based on the influence factor data and a single variable method strategy to obtain new influence factor data corresponding to the influence factor, and updating the cable simulation model based on the new influence factor data to obtain a new cable simulation model corresponding to the new influence factor data; respectively carrying out simulation processing on each new cable simulation model to obtain new unbalance degree data corresponding to each new cable simulation model, and respectively calculating data variables between the unbalance degree data and each new unbalance degree data; and respectively carrying out characterization processing on each data variable to obtain each characteristic data corresponding to the influence factors.
In this embodiment, the terminal acquires, for each influence factor, a plurality of influence factor data of the influence factor. And then the terminal respectively replaces the influence factor data of the influence factors based on the influence factor data and the single variable method strategy to obtain new influence factor data corresponding to the influence factors. And finally, updating the cable simulation model by the terminal based on the new influence factor data to obtain a new cable simulation model corresponding to the new influence factor data.
And the terminal respectively carries out simulation current transmission process treatment on each new cable simulation model of the influence factors to obtain current carrying information of each new cable simulation model. And then the terminal calculates new unbalance data corresponding to each new cable simulation model through a three-phase current-carrying unbalance algorithm based on current-carrying information of each new cable simulation model. And finally, the terminal calculates data variables between the unbalance degree data and each new unbalance degree data respectively, and performs characterization processing on each data variable respectively to obtain each characteristic data corresponding to the influence factors. And the terminal obtains the characteristic data corresponding to each influence factor through the processing process.
Based on the scheme, the feature data corresponding to the plurality of influence factor data of each influence factor obtained through simulation improves the accuracy of the obtained feature data.
Optionally, constructing a plurality of feature matrices based on the feature data corresponding to the influence factors includes: randomly screening target feature data in the feature data corresponding to each influence factor, and constructing a first feature matrix of each influence factor based on the target feature data of each influence factor; based on the characteristic data corresponding to each influence factor, randomly adjusting the target characteristic data of any influence factor in the first characteristic matrix by a single variable method to obtain each second characteristic matrix; and taking the first feature matrix and each second feature matrix as each feature matrix corresponding to all influence factors.
In this embodiment, the terminal randomly screens the target feature data in the feature data corresponding to each influence factor, and constructs the first feature matrix of each influence factor based on the target feature data of each influence factor. Then, the terminal randomly adjusts the target characteristic data of any one influence factor in the first characteristic matrix through a single variable method based on the characteristic data corresponding to each influence factor to obtain each second characteristic matrix. The specific adjustment process is to select one characteristic data from the characteristic data except the characteristic data of the established characteristic matrix in the characteristic data, replace the characteristic data of the influencing factors in the first characteristic matrix and obtain a second characteristic matrix. And finally, the first characteristic matrix and the second characteristic matrices of the terminal are used as characteristic matrices corresponding to all influencing factors. For example, by replacing the characteristic data corresponding to the cable laying mode, a plurality of samples are obtained, and a characteristic matrix is established based on each sample, and the characteristic data corresponding to the samples are shown in the following table
In the table, X is characteristic data corresponding to the inverted V-shaped laying, Y is characteristic data corresponding to the in-line laying, and Z is characteristic data corresponding to the double-row laying.
Based on the scheme, the feature matrixes are determined through a single variable method, so that the comprehensiveness of the combination mode of the feature data of each influence factor contained in each feature matrix is improved.
Optionally, based on each feature matrix, a feature map corresponding to each influence factor is established, including: based on the data variable corresponding to each feature data in each feature matrix, the criticality of each feature data in each feature matrix is respectively identified through a convolution layer of the feature graph neural network, and based on the criticality of each feature data in each feature matrix, the critical feature data in each feature matrix is extracted through a pooling layer of the feature graph neural network; and carrying out data connection processing on each key characteristic data according to the influence factors corresponding to each key characteristic data through a full connection layer of the characteristic map neural network to obtain a characteristic map corresponding to each influence factor.
In this embodiment, the terminal identifies the criticality of each feature data in each feature matrix through the convolutional layer of the feature map neural network based on the data variable corresponding to each feature data in each feature matrix. Wherein the criticality is used to characterize the extent to which the characteristic data of each influencing factor affects the cable balance. And then, the terminal extracts the feature data corresponding to the maximum criticality in each feature matrix through a feature extraction block diagram corresponding to the pooling layer of the feature map neural network based on the criticality of the feature data in each feature matrix to obtain the key feature data in each feature matrix. As shown in fig. 2, the extraction range of the feature extraction block diagram includes two or more feature data.
And then, the terminal performs data connection processing on each key characteristic data according to the influence factors corresponding to each key characteristic data through the full-connection layer of the characteristic map neural network to obtain a characteristic map corresponding to each influence factor. Wherein the feature map neural network is based on a deep convolutional neural network (SINCTION-CNN), and comprises 3 modules of a convolutional layer, a pooling layer and a full-connection layer.
Based on the scheme, the terminal constructs the feature map corresponding to each key feature data by extracting the key feature data in each feature matrix, reduces the operation data amount, improves the operation efficiency, refines the key feature data in each feature map, and improves the accuracy of calculating the sub-sensitivity corresponding to each influencing factor
Optionally, inputting the characteristic spectrum into a sensitivity analysis network, and calculating the sub-sensitivity of the cable unbalance corresponding to each influence factor, including: inputting the key feature data of the same influence factors in the feature map into a sensitivity analysis model, and analyzing the influence sensitivity of the key feature data of each influence factor on the unbalance degree of the cable; for each influencing factor, determining the sub-sensitivity of the cable unbalance corresponding to the influencing factor based on the influence sensitivity of the key characteristic data of the influencing factor to the cable unbalance.
In the embodiment, a terminal inputs key feature data of the same influence factors in a feature map into a sensitivity analysis model to analyze influence sensitivity of the key feature data of each influence factor on the unbalance degree of the cable; for each influencing factor, determining the sub-sensitivity of the cable unbalance corresponding to the influencing factor based on the influence sensitivity of the key characteristic data of the influencing factor to the cable unbalance.
Specifically, the sensitivity analysis model comprises a full connection layer, a convolution layer and a pooling layer, and the calculation formulas corresponding to the layers are as follows:
the calculation formula of the sensitivity of the full connection layer input neuron to the model output E is as follows:
the calculation formula of the sensitivity of the convolutional layer input neuron to the model output E is:
the calculation formula of the sensitivity of the pooling layer input neurons to the model output E is:
in the above-mentioned formulae, the first and second light-emitting elements,for the next layer x out For model output E (influence sensitivity of each key characteristic data on cable unbalance), rot180 is to flip the convolution parameter matrix by 180 degrees; σl is the derivative matrix of the activation function of the first convolutional layer. Z is the key characteristic data of each influencing factor in the characteristic map input by the full connection layer, and x in The key feature data of each influencing factor in the feature map input for the convolution layer, C in Key feature data, ω, for each influencing factor in the feature map input to the pooling layer 1 、δ 1 、ω 2 、δ 2 Delta are function normalization parameters.
Based on the scheme, the sub-sensitivity of the cable unbalance corresponding to each influence factor is calculated through the sensitivity analysis network, so that the sensitivity of the cable unbalance is obtained, the influence weights of different influence factors on the cable unbalance are comprehensively considered, and the accuracy of the sensitivity of the analyzed cable unbalance is improved.
The application also provides a sensitivity determination example of the unbalance degree of the cable, as shown in fig. 3, and the specific processing procedure comprises the following steps:
in step S301, each influencing factor of the cable unbalance in the in-phase cable is obtained.
Step S302, obtaining influence factor data corresponding to each influence factor of the unbalance of the cables in the same-phase cables, and establishing a cable simulation model based on the influence factor data.
Step S303, performing simulation processing on the cable simulation model to obtain unbalance degree data corresponding to the cable simulation model.
Step S304, for each influence factor, a plurality of influence factor data of the influence factor are obtained, the influence factor data of the influence factor are replaced based on the influence factor data and the single variable method strategy, new influence factor data corresponding to the influence factor are obtained, and the cable simulation model is updated based on the new influence factor data, so that a new cable simulation model corresponding to the new influence factor data is obtained.
Step S305, respectively performing simulation processing on each new cable simulation model to obtain new unbalance degree data corresponding to each new cable simulation model, and respectively calculating data variables between the unbalance degree data and each new unbalance degree data.
And step S306, performing characterization processing on each data variable to obtain each characteristic data corresponding to the influence factors.
Step S307, randomly screening target feature data from the feature data corresponding to each influence factor, and constructing a first feature matrix of each influence factor based on the target feature data of each influence factor.
Step S308, based on the feature data corresponding to each influence factor, randomly adjusting the target feature data of any influence factor in the first feature matrix by a single variable method to obtain each second feature matrix.
Step S309, using the first feature matrix and each second feature matrix as each feature matrix corresponding to all influencing factors.
Step S310, based on the data variable corresponding to each feature data in each feature matrix, the criticality of each feature data in each feature matrix is respectively identified through the convolution layer of the feature map neural network, and based on the criticality of each feature data in each feature matrix, the critical feature data in each feature matrix is extracted through the pooling layer of the feature map neural network.
And step S311, carrying out data connection processing on each key characteristic data according to the influence factors corresponding to each key characteristic data through the full connection layer of the characteristic map neural network, and obtaining the characteristic map corresponding to each influence factor.
Step S312, inputting the key feature data of the same influencing factors in the feature map into a sensitivity analysis model, and analyzing the influence sensitivity of the key feature data of each influencing factor on the unbalance degree of the cable.
Step S313, for each influencing factor, determining a sub-sensitivity of the cable unbalance corresponding to the influencing factor based on the influence sensitivity of each key feature data of the influencing factor to the cable unbalance.
In step S314, the sub-sensitivities corresponding to all the influencing factors are used as the sensitivity of the cable unbalance.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a cable unbalance sensitivity determining device for implementing the cable unbalance sensitivity determining method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the sensitivity determination device for the unbalance degree of one or more cables provided below may be referred to the limitation of the sensitivity determination method for the unbalance degree of a cable hereinabove, and will not be repeated here.
In one embodiment, as shown in fig. 4, there is provided a sensitivity determining apparatus of a cable unbalance degree, including: an acquisition module 410, a calculation module 420, and a determination module 430, wherein:
an obtaining module 410, configured to obtain each influencing factor of the cable unbalance in the in-phase cable and each feature data of the cable unbalance corresponding to each influencing factor, and construct a plurality of feature matrices based on each feature data corresponding to each influencing factor;
the calculation module 420 is configured to establish a feature map corresponding to each influence factor based on each feature matrix, input the feature map into a sensitivity analysis network, and calculate a sub-sensitivity of the cable imbalance corresponding to each influence factor;
And the determining module 430 is configured to use the sub-sensitivities corresponding to all the influencing factors as the sensitivity of the cable unbalance.
Optionally, the acquiring module 410 is specifically configured to:
acquiring influence factor data corresponding to each influence factor of the unbalance of the cable in the same-phase cable, and establishing a cable simulation model based on each influence factor data;
and carrying out simulation processing on the cable simulation model to obtain unbalance degree data corresponding to the cable simulation model, and respectively adjusting each influence factor data corresponding to each influence factor through a single variable method strategy to obtain each characteristic data corresponding to each influence factor.
Optionally, the acquiring module 410 is specifically configured to:
for each influence factor, acquiring a plurality of influence factor data of the influence factor, replacing the influence factor data of the influence factor based on the influence factor data and a single variable method strategy to obtain new influence factor data corresponding to the influence factor, and updating the cable simulation model based on the new influence factor data to obtain a new cable simulation model corresponding to the new influence factor data;
Respectively carrying out simulation processing on each new cable simulation model to obtain new unbalance degree data corresponding to each new cable simulation model, and respectively calculating data variables between the unbalance degree data and each new unbalance degree data;
and respectively carrying out characterization processing on each data variable to obtain each characteristic data corresponding to the influence factors.
Optionally, the acquiring module 410 is specifically configured to:
randomly screening target feature data in the feature data corresponding to each influence factor, and constructing a first feature matrix of each influence factor based on the target feature data of each influence factor;
based on the characteristic data corresponding to each influence factor, randomly adjusting the target characteristic data of any influence factor in the first characteristic matrix by a single variable method to obtain each second characteristic matrix;
and taking the first feature matrix and each second feature matrix as feature matrices corresponding to all influencing factors.
Optionally, the calculating module 420 is specifically configured to:
based on the data variable corresponding to each feature data in each feature matrix, respectively identifying the criticality of each feature data in each feature matrix through a convolution layer of a feature map neural network, and extracting the critical feature data in each feature matrix through a pooling layer of the feature map neural network based on the criticality of each feature data in each feature matrix;
And carrying out data connection processing on each key characteristic data according to the influence factors corresponding to each key characteristic data through the full connection layer of the characteristic map neural network to obtain a characteristic map corresponding to each influence factor.
Optionally, the calculating module 420 is specifically configured to:
inputting the key feature data of the same influence factors in the feature map into a sensitivity analysis model, and analyzing the influence sensitivity of the key feature data of each influence factor on the unbalance degree of the cable;
for each influence factor, determining the sub-sensitivity of the cable unbalance corresponding to the influence factor based on the influence sensitivity of the key characteristic data of the influence factor to the cable unbalance.
The respective modules in the above-described sensitivity determination device for the cable unbalance may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a method of sensitivity determination of a cable imbalance. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in FIG. 5 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In an embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method of any of the first aspects when the computer program is executed.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, implements the steps of the method of any of the first aspects.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method of any of the first aspects.
The user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.
Claims (10)
1. A method of sensitivity determination of cable unbalance, the method comprising:
acquiring each influence factor of the unbalance of the cable in the in-phase cable and each characteristic data of the unbalance of the cable corresponding to each influence factor, and constructing a plurality of characteristic matrixes based on each characteristic data corresponding to each influence factor;
based on the feature matrixes, building a feature map corresponding to each influence factor, inputting the feature map into a sensitivity analysis network, and calculating the sub-sensitivity of the cable unbalance corresponding to each influence factor;
And taking the sub sensitivity corresponding to all the influencing factors as the sensitivity of the unbalance degree of the cable.
2. The method according to claim 1, wherein the obtaining the characteristic data of the cable unbalance degree corresponding to each influencing factor includes:
acquiring influence factor data corresponding to each influence factor of the unbalance of the cable in the same-phase cable, and establishing a cable simulation model based on each influence factor data;
and carrying out simulation processing on the cable simulation model to obtain unbalance degree data corresponding to the cable simulation model, and respectively adjusting each influence factor data corresponding to each influence factor through a single variable method strategy to obtain each characteristic data corresponding to each influence factor.
3. The method according to claim 2, wherein the step of respectively adjusting the influence factor data corresponding to each influence factor by using a single variable method policy to obtain the feature data corresponding to each influence factor includes:
for each influence factor, acquiring a plurality of influence factor data of the influence factor, replacing the influence factor data of the influence factor based on the influence factor data and a single variable method strategy to obtain new influence factor data corresponding to the influence factor, and updating the cable simulation model based on the new influence factor data to obtain a new cable simulation model corresponding to the new influence factor data;
Respectively carrying out simulation processing on each new cable simulation model to obtain new unbalance degree data corresponding to each new cable simulation model, and respectively calculating data variables between the unbalance degree data and each new unbalance degree data;
and respectively carrying out characterization processing on each data variable to obtain each characteristic data corresponding to the influence factors.
4. A method according to claim 3, wherein said constructing a plurality of feature matrices based on the feature data corresponding to each of the influencing factors comprises:
randomly screening target feature data in the feature data corresponding to each influence factor, and constructing a first feature matrix of each influence factor based on the target feature data of each influence factor;
based on the characteristic data corresponding to each influence factor, randomly adjusting the target characteristic data of any influence factor in the first characteristic matrix by a single variable method to obtain each second characteristic matrix;
and taking the first feature matrix and each second feature matrix as feature matrices corresponding to all influencing factors.
5. The method of claim 3, wherein the establishing a feature map corresponding to each influencing factor based on each feature matrix comprises:
Based on the data variable corresponding to each feature data in each feature matrix, respectively identifying the criticality of each feature data in each feature matrix through a convolution layer of a feature map neural network, and extracting the critical feature data in each feature matrix through a pooling layer of the feature map neural network based on the criticality of each feature data in each feature matrix;
and carrying out data connection processing on each key characteristic data according to the influence factors corresponding to each key characteristic data through the full connection layer of the characteristic map neural network to obtain a characteristic map corresponding to each influence factor.
6. The method of claim 5, wherein inputting the characteristic spectrum into a sensitivity analysis network, calculating a sub-sensitivity of the cable imbalance corresponding to each of the influencing factors, comprises:
inputting the key feature data of the same influence factors in the feature map into a sensitivity analysis model, and analyzing the influence sensitivity of the key feature data of each influence factor on the unbalance degree of the cable;
for each influence factor, determining the sub-sensitivity of the cable unbalance corresponding to the influence factor based on the influence sensitivity of the key characteristic data of the influence factor to the cable unbalance.
7. A sensitivity determination device for cable unbalance, the device comprising:
the acquisition module is used for acquiring each influence factor of the cable unbalance degree in the in-phase cable and each characteristic data of the cable unbalance degree corresponding to each influence factor, and constructing a plurality of characteristic matrixes based on each characteristic data corresponding to each influence factor;
the computing module is used for building a characteristic map corresponding to each influence factor based on each characteristic matrix, inputting the characteristic map into a sensitivity analysis network and computing the sub-sensitivity of the cable unbalance corresponding to each influence factor;
and the determining module is used for taking the sub-sensitivity corresponding to all the influencing factors as the sensitivity of the unbalance degree of the cable.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311018664.6A CN117216649A (en) | 2023-08-11 | 2023-08-11 | Sensitivity determination method and device for unbalance degree of cable and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311018664.6A CN117216649A (en) | 2023-08-11 | 2023-08-11 | Sensitivity determination method and device for unbalance degree of cable and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117216649A true CN117216649A (en) | 2023-12-12 |
Family
ID=89041564
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311018664.6A Pending CN117216649A (en) | 2023-08-11 | 2023-08-11 | Sensitivity determination method and device for unbalance degree of cable and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117216649A (en) |
-
2023
- 2023-08-11 CN CN202311018664.6A patent/CN117216649A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116167289B (en) | Power grid operation scene generation method and device, computer equipment and storage medium | |
| CN113887845A (en) | Extreme event prediction method, apparatus, device, medium, and computer program product | |
| CN115689018A (en) | Material demand prediction method, device, equipment, storage medium and program product | |
| CN117195691A (en) | Method and device for determining current-carrying unbalance degree of cable and computer equipment | |
| CN115392594B (en) | Electrical load model training method based on neural network and feature screening | |
| CN116894721A (en) | Index prediction method and device and computer equipment | |
| CN117216649A (en) | Sensitivity determination method and device for unbalance degree of cable and computer equipment | |
| CN116191398A (en) | Load prediction method, load prediction device, computer equipment and storage medium | |
| CN116258923A (en) | Image recognition model training method, device, computer equipment and storage medium | |
| CN108229572A (en) | A kind of parameter optimization method and computing device | |
| CN115577259A (en) | Fault pole selection method and device for high-voltage direct-current transmission system and computer equipment | |
| CN114118858A (en) | Power security intelligent evaluation method, apparatus, device, medium, and program product | |
| CN117034772A (en) | Current-carrying unbalance degree determining method and device and computer equipment | |
| CN117147986A (en) | Method, device, computer equipment and storage medium for determining unbalance degree of cable | |
| CN117195492A (en) | Simulation model determination method and device for cable joint structure and computer equipment | |
| CN117235584B (en) | Picture data classification method, device, electronic device and storage medium | |
| CN117172107A (en) | Method and device for determining cable interval positioning model and computer equipment | |
| CN117195491A (en) | Cable structure model determination method, device, computer equipment and storage medium | |
| CN117852224A (en) | Cable trench heat dissipation test method and device, computer equipment and storage medium | |
| CN117993130A (en) | Path planning method, device, computer equipment, medium and product of power distribution network | |
| CN116359653A (en) | Cable current-carrying capacity determining method, device, computer equipment and storage medium | |
| CN118035889A (en) | Method, device, equipment, storage medium and product for fault classification of rotary equipment | |
| CN116881297A (en) | Cache content ordering method, device, computer equipment and storage medium | |
| CN116862673A (en) | Processing result prediction method, device, computer equipment and storage medium | |
| CN117992061A (en) | Program conversion method, program conversion device, computer device, and computer-readable storage medium |
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 |