CN113887626A - Method and device for generating portrait of power equipment - Google Patents
Method and device for generating portrait of power equipment Download PDFInfo
- Publication number
- CN113887626A CN113887626A CN202111163557.3A CN202111163557A CN113887626A CN 113887626 A CN113887626 A CN 113887626A CN 202111163557 A CN202111163557 A CN 202111163557A CN 113887626 A CN113887626 A CN 113887626A
- Authority
- CN
- China
- Prior art keywords
- equipment
- label
- data information
- target
- model
- 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 44
- 238000012423 maintenance Methods 0.000 claims abstract description 24
- 230000002776 aggregation Effects 0.000 claims abstract description 17
- 238000004220 aggregation Methods 0.000 claims abstract description 17
- 238000013079 data visualisation Methods 0.000 claims abstract description 11
- 238000003066 decision tree Methods 0.000 claims description 26
- 238000013145 classification model Methods 0.000 claims description 25
- 230000009466 transformation Effects 0.000 claims description 24
- 125000004122 cyclic group Chemical group 0.000 claims description 23
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000012512 characterization method Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 11
- 238000012544 monitoring process Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 230000036541 health Effects 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 4
- 230000004927 fusion Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000000366 juvenile effect Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 231100000331 toxic Toxicity 0.000 description 1
- 230000002588 toxic effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a method and a device for generating an image of power equipment, wherein the method comprises the following steps: acquiring data information of all types of equipment; performing homotype aggregation on the data information of all types of equipment to obtain an effective data information set of the same type of equipment for distinguishing different states; determining the type of target equipment of the portrait equipment to be generated, and matching all the effective equipment data information sets according to the type of the target equipment to obtain an effective data information set of the target equipment; inputting the target equipment effective data information set into a pre-constructed network model to obtain a corresponding equipment label; and distributing the equipment label for the portrait equipment to be generated, and generating the equipment portrait by combining a data visualization method. Therefore, the corresponding equipment label is obtained under the condition that irrelevant data interference is eliminated, and the equipment image is generated based on the equipment label, so that accurate information is provided for operation and maintenance personnel to know the equipment state.
Description
Technical Field
The present invention relates to the technical field of device information processing, and in particular, to a method and an apparatus for generating a representation of a power device.
Background
With the advance of power grid construction, the number of transformer substations and equipment thereof is increasing day by day, and the task of equipment management and control is becoming harder and harder. Most of the current equipment management and control are realized by monitoring and displaying equipment through an equipment state monitoring system, but because monitored data are too trivial, people cannot feel intuitive and global to the current running state of the equipment.
In order to visually reflect the running state of equipment, the prior art provides a method for generating an equipment portrait, and specifically, a series of basic labels are generated according to data collected by an equipment state monitoring system, and various attributes of the equipment are described in a labeling manner. However, the equipment state monitoring system at the present stage is generally insufficient in equipment data mining and analysis, and most of generated basic tags are trivial static tags, so that operation and maintenance personnel can know the current state of the equipment through the static tags, but cannot comprehensively and intuitively master the various states of the equipment, so that the potential risks of the equipment are difficult to find in time, and effective operation and maintenance management measures are made.
Disclosure of Invention
The invention provides a method and a device for generating an image of power equipment, which are used for obtaining a corresponding equipment label under the condition of eliminating irrelevant data interference and generating the image of the equipment based on the equipment label, thereby providing accurate information for operation and maintenance personnel to know the comprehensive state of the equipment.
In a first aspect, the present invention provides a method for generating a representation of a power device, including:
acquiring data information of all types of equipment;
performing homotype aggregation on the data information of all types of equipment to obtain an effective data information set of the same type of equipment for distinguishing different states;
determining the type of target equipment of the portrait equipment to be generated, and matching all the effective equipment data information sets according to the type of the target equipment to obtain an effective data information set of the target equipment;
inputting the target equipment effective data information set into a pre-constructed network model to obtain a corresponding equipment label;
and distributing the equipment label for the portrait equipment to be generated, and generating the equipment portrait by combining a data visualization method.
Optionally, the network model comprises: the device comprises an equipment characteristic model, a decision tree classification model and a cyclic classification prediction model; the device tag includes: the device comprises a device attribute label, a device fault label and a state prediction label; inputting the target device valid data information set into a pre-constructed network model to obtain a corresponding device tag, wherein the method comprises the following steps:
respectively inputting the target equipment effective data information set into the equipment characteristic model and the decision tree classification model to obtain corresponding equipment fault labels and equipment attribute labels;
screening device state data related to a time sequence from the target device valid data information set;
and inputting the equipment state data into the cyclic classification prediction model to obtain a corresponding state prediction label.
Optionally, the device attribute tag includes: the equipment operation label and the equipment operation label; respectively inputting the target equipment valid data information set into the equipment feature model and the decision tree classification model to obtain corresponding equipment fault labels and equipment attribute labels, specifically:
inputting the target equipment effective data information set into the decision tree classification model to obtain corresponding equipment operation and maintenance labels and equipment operation labels;
the step of inputting the device state data into the cyclic classification prediction model to obtain a corresponding label prediction result specifically comprises:
and inputting the equipment state data into the cyclic classification prediction model to obtain a corresponding equipment operation label prediction result and an equipment fault label prediction result and form a state prediction label.
Optionally, the step of inputting the target device valid data information set into the device feature model and the decision tree classification model respectively to obtain corresponding device fault tags and device attribute tags includes:
performing mathematical transformation on the signal type of the target equipment effective data information set to obtain a transformed target data set with the signal type being a transform domain signal;
and inputting the transformed target data set information into the equipment characteristic model to obtain a corresponding equipment fault label.
Optionally, before inputting the transformed target data set information into the device feature model and obtaining a corresponding device fault label, the method further includes:
and carrying out preprocessing including wavelet transformation, Fourier transformation and fuzzy function calculation on the transformed target data in sequence.
In a second aspect, the present invention provides an apparatus for generating an image of an electrical device, including:
the acquisition module is used for acquiring data information of all types of equipment;
the homotype aggregation module is used for carrying out homotype aggregation on the data information of all types of equipment to obtain an effective data information set of the same type of equipment for distinguishing different states;
the matching module is used for determining the type of target equipment of the portrait equipment to be generated and matching all the effective equipment data information sets according to the type of the target equipment to obtain an effective data information set of the target equipment;
the label generation module is used for inputting the target equipment effective data information set into a pre-constructed network model to obtain a corresponding equipment label;
and the equipment image generation module is used for distributing the equipment label for the equipment to be generated and generating the equipment portrait by combining a data visualization method.
Optionally, the network model comprises: the device comprises an equipment characteristic model, a decision tree classification model and a cyclic classification prediction model; the device tag includes: the device comprises a device attribute label, a device fault label and a state prediction label; the tag generation module includes:
the first input submodule is used for respectively inputting the effective data information set of the target equipment into the equipment characteristic model and the decision tree classification model to obtain a corresponding equipment fault label and an equipment attribute label;
the screening submodule is used for screening the device state data related to the time sequence from the target device effective data information set;
and the second input submodule is used for inputting the equipment state data into the cyclic classification prediction model to obtain a corresponding state prediction label.
Optionally, the device attribute tag includes: the equipment operation label and the equipment operation label; the input first input submodule is specifically configured to:
inputting the target equipment effective data information set into the decision tree classification model to obtain corresponding equipment operation and maintenance labels and equipment operation labels;
the second input submodule is specifically configured to:
and inputting the equipment state data into the cyclic classification prediction model to obtain a corresponding equipment operation label prediction result and an equipment fault label prediction result and form a state prediction label.
Optionally, the first input submodule includes:
the transformation unit is used for carrying out mathematical transformation on the signal type of the target equipment effective data information set to obtain a transformed target data set with the signal type being a transform domain signal;
and the input unit is used for inputting the transformed target data set information into the equipment characteristic model to obtain a corresponding equipment fault label.
Optionally, the method further comprises:
and the preprocessing unit is used for sequentially carrying out preprocessing including wavelet transformation, Fourier transformation and fuzzy function calculation on the transformed target data.
According to the technical scheme, the invention has the following advantages:
the method comprises the steps of acquiring data information of all types of equipment; performing homotype aggregation on the data information of all types of equipment to obtain an effective data information set of the same type of equipment for distinguishing different states; determining the type of target equipment of the portrait equipment to be generated, and matching all the effective equipment data information sets according to the type of the target equipment to obtain an effective data information set of the target equipment; inputting the target equipment effective data information set into a pre-constructed network model to obtain a corresponding equipment label; and distributing the equipment label for the portrait equipment to be generated, and generating the equipment portrait by combining a data visualization method. The data information of the type equipment is subjected to homotypic aggregation, then the type of the target equipment is extracted to determine a valid data information set of the target equipment, and the valid data information set of the target equipment is input into a network model, so that a corresponding equipment label is obtained under the condition that irrelevant data interference is eliminated, an equipment image is generated based on the equipment label, and accurate information is provided for operation and maintenance personnel to know the equipment state.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts;
FIG. 1 is a flowchart illustrating a first step of a method for generating a representation of a power device according to a first embodiment of the present invention;
FIG. 2 is a flowchart illustrating steps of a second method for generating an image of a power device according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating a convolutional layer structure of a device feature model according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a super-resolution feature generation module FRCN of the device feature model in the embodiment of the present invention;
FIG. 5 is a schematic structural diagram of an adaptive feature fusion module of an apparatus feature model in an implementation of the present invention;
FIG. 6 is a schematic diagram of a decision tree classification model for a random forest in accordance with an embodiment of the present invention;
FIG. 7 is a circular classification prediction model architecture in an implementation of the present invention;
FIG. 8 is a block diagram of an embodiment of an image generator for power equipment according to the present invention.
Detailed Description
The embodiment of the invention provides a method and a device for generating an image of power equipment, which are used for obtaining a corresponding equipment label under the condition of eliminating irrelevant data interference and generating the image of the equipment based on the equipment label, so that accurate information is provided for operation and maintenance personnel to know the state of the equipment.
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, fig. 1 is a flowchart illustrating a first step of a method for generating an image of an electrical device according to a first embodiment of the present invention, which may specifically include the following steps:
step S101, acquiring data information of all types of equipment;
step S102, carrying out homotype aggregation on the data information of all types of equipment to obtain an effective data information set for distinguishing different states of the same type of equipment;
step S103, determining the type of target equipment of the portrait equipment to be generated, and matching all the effective equipment data information sets according to the type of the target equipment to obtain an effective data information set of the target equipment;
step S104, inputting the target equipment effective data information set into a pre-constructed network model to obtain a corresponding equipment label;
and S105, distributing the equipment label for the equipment to be generated to generate the equipment portrait and generating the equipment portrait by combining a data visualization method.
The embodiment of the invention obtains data information of all types of equipment; performing homotype aggregation on the data information of all types of equipment to obtain an effective data information set of the same type of equipment for distinguishing different states; determining the type of target equipment of the portrait equipment to be generated, and matching all the effective equipment data information sets according to the type of the target equipment to obtain an effective data information set of the target equipment; inputting the target equipment effective data information set into a pre-constructed network model to obtain a corresponding equipment label; and distributing the equipment label for the portrait equipment to be generated, and generating the equipment portrait by combining a data visualization method. The data information of the type equipment is subjected to homotypic aggregation, then the type of the target equipment is extracted to determine a valid data information set of the target equipment, and the valid data information set of the target equipment is input into a network model, so that a corresponding equipment label is obtained under the condition that irrelevant data interference is eliminated, an equipment image is generated based on the equipment label, and accurate information is provided for operation and maintenance personnel to know the equipment state.
Referring to fig. 2, a flowchart of a second step of a method for generating an image of an electrical device according to an embodiment of the present invention includes:
step S201, acquiring data information of all types of equipment;
in the embodiment of the invention, the enterprise external historical equipment fault data, the operation and maintenance historical data information of all the power equipment, the experimental inspection data and the historical label data in the process of inspection are obtained, and the historical and real-time data information of all types of equipment is obtained in the monitoring system.
Step S202, carrying out homotype aggregation on the data information of all types of equipment to obtain an effective data information set for distinguishing different states of the same type of equipment;
in the embodiment of the invention, because the differences of different types of equipment are large, and the commonalities of the same type of equipment are high, the equipment data information sets of the same type of equipment can be obtained by dividing all the obtained data according to the equipment types, namely, the data of various types of equipment are uniformly classified to obtain the equipment data information sets of the same type of equipment, so that the interference of irrelevant data is eliminated, and the convergence effect of a network model is improved.
Step S203, determining the type of target equipment of the portrait equipment to be generated, and matching all the effective equipment data information sets to obtain an effective data information set of the target equipment according to the type of the target equipment;
in the embodiment of the invention, the identified to-be-generated portrait equipment required by operation and maintenance personnel is obtained, and the type of the target equipment of the to-be-generated portrait equipment is determined, so that the effective data information set of the target equipment is determined from the effective data information set according to the type of the target equipment.
Step S204, respectively presetting an input equipment characteristic model and a decision tree classification model for the effective data information set of the target equipment to obtain a corresponding equipment fault label and an equipment attribute label;
it should be noted that the device tag system is defined to embody the overall state of the device in an all-round, visualized and real-time manner.
Specifically, the device attribute tag includes: the equipment operation label and the equipment operation label; respectively inputting the target equipment valid data information set into the equipment feature model and the decision tree classification model to obtain corresponding equipment fault labels and equipment attribute labels, specifically:
and inputting the target equipment effective data information set into the decision tree classification model to obtain a corresponding equipment operation and maintenance label and an equipment operation label.
In the embodiment of the present invention, the device operation and maintenance label includes: condition label and equipment maintenance condition label are patrolled and examined to equipment, and wherein equipment patrols and examines the condition label and include: patrol and examine the label on schedule, patrol and examine label less than a few and lack and patrol and examine the label, equipment maintenance condition label includes: scheduled maintenance label and lack of maintenance label; the device operation tag includes: equipment running state label, equipment load state label, equipment health state label and equipment life label, wherein equipment running state label includes: normal operating label, maintenance label and retreat transportation label, equipment load state label includes: light load label, moderate load label, heavy load label and continuous heavy load label, equipment health state label includes: a health label, a sub-health label, a mild condition label, a toxic condition label, and a severe condition label, the device life status label comprising: juvenile tags, youth tags, middle-aged tags, and elderly tags; the equipment failure tag includes: transformer fault state label and circuit breaker fault state label etc. wherein the transformer fault state label includes: the circuit breaker fault state label comprises a circuit breaker partial discharge abnormal label, a stroke abnormal label and a contact abnormal label.
In an optional embodiment, the step of inputting the target device valid data information set into the device feature model and the decision tree classification model respectively to obtain a corresponding device fault tag and a corresponding device attribute tag includes:
performing mathematical transformation on the signal type of the target equipment effective data information set to obtain a transformed target data set with the signal type being a transform domain signal;
and inputting the transformed target data set information into the equipment characteristic model to obtain a corresponding equipment fault label.
In an embodiment of the present invention, a convolutional neural network for monitoring device defects and faults is established and trained, specifically, a device feature model shown in fig. 3 to 5 is obtained by using sample data learning feature pattern training, where fig. 3 is a schematic diagram of a convolutional layer structure of the device feature model in the embodiment of the present invention, fig. 4 is a schematic diagram of a super-resolution feature generation module FRCN of the device feature model in the embodiment of the present invention, and fig. 5 is a schematic diagram of a structure of an adaptive feature fusion module of the device feature model in the embodiment of the present invention, and in a specific implementation, a network structure of the device feature model includes: the device comprises a convolutional layer, a super-resolution feature generation module FRCN, an adaptive feature fusion module and an SSD monitoring module, and under the cooperation of the modules, the discovery of equipment faults and hidden dangers of data monitoring based on a transform domain is realized.
It should be noted that the convolutional neural network may be a one-dimensional convolutional neural network or a two-dimensional convolutional neural network, and the present invention is not limited herein.
In the embodiment of the invention, because data information of all types of equipment is complex, the acquired discrete data, the classified data and the monitored fault label data exist, and the structural schematic diagram of the decision tree classification model of the random forest in the implementation shown in fig. 6 is designed according to the characteristics of the influence factors of the states of the equipment, such as the service life, the health, the maintenance, the load and the like, different calculation modes of different types of data are integrated on different nodes of the decision tree, and the effective classification and identification of the running state of the equipment are realized.
In addition, a schematic structural diagram of a cyclic classification prediction model shown in fig. 7 is designed for the device state data related to the time series, in the cyclic classification prediction model, two branches exist after the cyclic feature extraction module, one branch is connected with the dense layer Softmax and the Softmax loss to realize prediction of the time series data, and the other branch is connected with the fully connected layer to realize state classification prediction by using the Softmax loss and taking the time series data as features. Therefore, the technical effect that the label prediction result of the equipment state is obtained by using historical operation and maintenance data, real-time data, fault monitoring data and health state feedback data of equipment of the same type as input and by reasoning operation of the cyclic classification prediction network is achieved.
In an optional embodiment, before inputting the transformed target data set information into the device feature model and obtaining a corresponding device fault label, the method further includes:
and carrying out preprocessing including wavelet transformation, Fourier transformation and fuzzy function calculation on the transformed target data in sequence.
It should be noted that the fourier transform is a conversion between a time domain and a frequency domain, and is divided into a continuous fourier transform and a discrete fourier transform, and since the apparatus in the embodiment of the present invention collects signals as discrete points, the discrete fourier transform is used here.
The wavelet transform is to select an appropriate basic wavelet or mother wavelet, form a series of wavelets by shifting and scaling the wavelets or mother wavelets, form a series of nested (signal) subspaces as the cluster of wavelets or mother wavelets, and project the signal (e.g., image) to be analyzed into each of the different-sized (signal) subspaces to observe the corresponding characteristics. Thus, it is equivalent to using different focal lengths to observe an object, from macro to micro, and from overview to detail. The wavelet or mother wavelet transform is also referred to as a "mathematical microscope".
It should be noted that "wavelet" is a waveform with a small area, a limited length and an average value of 0; translation and expansion are a characteristic of wavelet transformation, so that various analyses can be carried out on signals in different frequency ranges and different time (space) positions, and through the multi-resolution analysis, a good time resolution and a poor frequency resolution are obtained in high-frequency signals, a good frequency resolution and a high time resolution are obtained in low-frequency signals, and the defects of Fourier transformation application and non-stationary signals are overcome. Wavelet transformation provides time-frequency mixed representation of signals, and has very efficient application in numerous fields, such as denoising, edge monitoring, compression coding, image fusion and the like of images.
Fuzzy function: and respectively counting and calculating the signal intensity of each time period and frequency band of the time sequence signal by taking the time period as a horizontal axis and the frequency band as a vertical axis to form a two-dimensional fuzzy function graph.
Take the signal expression u (t), andif u (t) is 0, then the blurring function of the signal is defined as the positive of the blurring function:
in a digital system, sampling a signal, namely discretizing a received signal and a reference signal, can be expressed as:
if the signal sampling frequency is assumed to be fsAt time, there is τ1=l/fs,vm=mfsThe total number of signal sampling points is N, and the calculated frequency domain range vmThere is a total of M points, where the amount of x (l, M) needed is calculated to be 2N (2N-1) M.
Step S205, screening the device state data related to the time sequence from the target device valid data information set;
step S206, inputting the equipment state data into the cyclic classification prediction model to obtain a corresponding label prediction result;
the method specifically comprises the following steps:
and inputting the equipment state data into the cyclic classification prediction model to obtain a corresponding equipment operation label prediction result and an equipment fault label prediction result and form a state prediction label.
And step S207, distributing the equipment label for the equipment to be generated to generate the equipment portrait and generating the equipment portrait by combining a data visualization method.
It should be noted that, because the network model uses the same type aggregated data as the sample input, when the type device data information acquired in step S201 changes, the input data for reasoning the current device status label also changes, and the device label of the target device type also needs to update the prediction again.
Under a special condition, the historical database can be re-input by regularly feeding back data of the same type of equipment state, so that the equipment state label is continuously updated and reasoned, and the multi-angle and omnibearing visualized real-time portrait of the equipment is realized.
In the method for generating the portrait of the power equipment provided by the embodiment of the invention, all types of equipment data information are acquired; performing homotype aggregation on the data information of all types of equipment to obtain an effective data information set of the same type of equipment for distinguishing different states; determining the type of target equipment of the portrait equipment to be generated, and matching all the effective equipment data information sets according to the type of the target equipment to obtain an effective data information set of the target equipment; inputting the target equipment effective data information set into a pre-constructed network model to obtain a corresponding equipment label; and distributing the equipment label for the portrait equipment to be generated, and generating the equipment portrait by combining a data visualization method. The data information of the type equipment is subjected to homotypic aggregation, then the type of the target equipment is extracted to determine a valid data information set of the target equipment, and the valid data information set of the target equipment is input into a network model, so that a corresponding equipment label is obtained under the condition that irrelevant data interference is eliminated, an equipment image is generated based on the equipment label, and accurate information is provided for operation and maintenance personnel to know the equipment state.
Referring to fig. 8, a block diagram of an embodiment of an apparatus for generating a representation of a power device is shown, which includes the following modules:
an obtaining module 401, configured to obtain data information of all types of devices;
a homotype aggregation module 402, configured to perform homotype aggregation on the data information of all types of devices to obtain an effective data information set of the same type of device for distinguishing different states;
a matching module 403, configured to determine a target device type of the portrait device to be generated, and match, according to the target device type, the valid data information set of the target device from all valid device data information sets to obtain a valid data information set of the target device;
a tag generation module 404, configured to input the target device valid data information set into a pre-constructed network model to obtain a corresponding device tag;
and the device image generation module 405 is configured to assign the device tag to the to-be-generated portrait device, and generate a device portrait by using a data visualization method.
In an optional embodiment, the network model comprises: the device comprises an equipment characteristic model, a decision tree classification model and a cyclic classification prediction model; the device tag includes: the device comprises a device attribute label, a device fault label and a state prediction label; the tag generation module 404 includes:
the first input submodule is used for respectively inputting the effective data information set of the target equipment into the equipment characteristic model and the decision tree classification model to obtain a corresponding equipment fault label and an equipment attribute label;
the screening submodule is used for screening the device state data related to the time sequence from the target device effective data information set;
and the second input submodule is used for inputting the equipment state data into the cyclic classification prediction model to obtain a corresponding state prediction label.
In an alternative embodiment, the device attribute tag comprises: the equipment operation label and the equipment operation label; the input first input submodule is specifically configured to:
inputting the target equipment effective data information set into the decision tree classification model to obtain corresponding equipment operation and maintenance labels and equipment operation labels;
the second input submodule is specifically configured to:
and inputting the equipment state data into the cyclic classification prediction model to obtain a corresponding equipment operation label prediction result and an equipment fault label prediction result and form a state prediction label.
In an alternative embodiment, the first input submodule comprises:
the transformation unit is used for carrying out mathematical transformation on the signal type of the target equipment effective data information set to obtain a transformed target data set with the signal type being a transform domain signal;
and the input unit is used for inputting the transformed target data set information into the equipment characteristic model to obtain a corresponding equipment fault label.
In an optional embodiment, further comprising:
and the preprocessing unit is used for sequentially carrying out preprocessing including wavelet transformation, Fourier transformation and fuzzy function calculation on the transformed target data.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working process of the apparatus described above may refer to the corresponding process in the foregoing method embodiment, and is not described herein again.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for generating a representation of a power device, comprising:
acquiring data information of all types of equipment;
performing homotype aggregation on the data information of all types of equipment to obtain an effective data information set of the same type of equipment for distinguishing different states;
determining the type of target equipment of the portrait equipment to be generated, and matching all the effective equipment data information sets according to the type of the target equipment to obtain an effective data information set of the target equipment;
inputting the target equipment effective data information set into a pre-constructed network model to obtain a corresponding equipment label;
and distributing the equipment label for the portrait equipment to be generated, and generating the equipment portrait by combining a data visualization method.
2. The power device representation generation method of claim 1, wherein the network model comprises: the device comprises an equipment characteristic model, a decision tree classification model and a cyclic classification prediction model; the device tag includes: the device comprises a device attribute label, a device fault label and a state prediction label; inputting the target device valid data information set into a pre-constructed network model to obtain a corresponding device tag, wherein the method comprises the following steps:
respectively inputting the target equipment effective data information set into the equipment characteristic model and the decision tree classification model to obtain corresponding equipment fault labels and equipment attribute labels;
screening device state data related to a time sequence from the target device valid data information set;
and inputting the equipment state data into the cyclic classification prediction model to obtain a corresponding state prediction label.
3. The power device representation generation method of claim 2, wherein the device attribute tag comprises: the equipment operation label and the equipment operation label; respectively inputting the target equipment valid data information set into the equipment feature model and the decision tree classification model to obtain corresponding equipment fault labels and equipment attribute labels, specifically:
inputting the target equipment effective data information set into the decision tree classification model to obtain corresponding equipment operation and maintenance labels and equipment operation labels;
the step of inputting the device state data into the cyclic classification prediction model to obtain a corresponding label prediction result specifically comprises:
and inputting the equipment state data into the cyclic classification prediction model to obtain a corresponding equipment operation label prediction result and an equipment fault label prediction result and form a state prediction label.
4. The method for generating a representation of a power device as claimed in claim 3, wherein inputting the set of valid data information of the target device into the device feature model and the decision tree classification model respectively to obtain a corresponding device failure tag and a corresponding device attribute tag comprises:
performing mathematical transformation on the signal type of the target equipment effective data information set to obtain a transformed target data set with the signal type being a transform domain signal;
and inputting the transformed target data set information into the equipment characteristic model to obtain a corresponding equipment fault label.
5. The method for generating a representation of a power device as defined in claim 4, further comprising, prior to inputting the transformed target data set information into the device characterization model and obtaining a corresponding device failure label:
and carrying out preprocessing including wavelet transformation, Fourier transformation and fuzzy function calculation on the transformed target data in sequence.
6. An apparatus for generating a representation of an electric power device, comprising:
the acquisition module is used for acquiring data information of all types of equipment;
the homotype aggregation module is used for carrying out homotype aggregation on the data information of all types of equipment to obtain an effective data information set of the same type of equipment for distinguishing different states;
the matching module is used for determining the type of target equipment of the portrait equipment to be generated and matching all the effective equipment data information sets according to the type of the target equipment to obtain an effective data information set of the target equipment;
the label generation module is used for inputting the target equipment effective data information set into a pre-constructed network model to obtain a corresponding equipment label;
and the equipment image generation module is used for distributing the equipment label for the equipment to be generated and generating the equipment portrait by combining a data visualization method.
7. The power device representation generation apparatus of claim 6, wherein the network model comprises: the device comprises an equipment characteristic model, a decision tree classification model and a cyclic classification prediction model; the device tag includes: the device comprises a device attribute label, a device fault label and a state prediction label; the tag generation module includes:
the first input submodule is used for respectively inputting the effective data information set of the target equipment into the equipment characteristic model and the decision tree classification model to obtain a corresponding equipment fault label and an equipment attribute label;
the screening submodule is used for screening the device state data related to the time sequence from the target device effective data information set;
and the second input submodule is used for inputting the equipment state data into the cyclic classification prediction model to obtain a corresponding state prediction label.
8. The power device representation generation apparatus of claim 7, wherein the device attribute tag comprises: the equipment operation label and the equipment operation label; the input first input submodule is specifically configured to:
inputting the target equipment effective data information set into the decision tree classification model to obtain corresponding equipment operation and maintenance labels and equipment operation labels;
the second input submodule is specifically configured to:
and inputting the equipment state data into the cyclic classification prediction model to obtain a corresponding equipment operation label prediction result and an equipment fault label prediction result and form a state prediction label.
9. The power device representation generation apparatus of claim 8, wherein the first input submodule comprises:
the transformation unit is used for carrying out mathematical transformation on the signal type of the target equipment effective data information set to obtain a transformed target data set with the signal type being a transform domain signal;
and the input unit is used for inputting the transformed target data set information into the equipment characteristic model to obtain a corresponding equipment fault label.
10. The power device representation generation method of claim 9, further comprising:
and the preprocessing unit is used for sequentially carrying out preprocessing including wavelet transformation, Fourier transformation and fuzzy function calculation on the transformed target data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111163557.3A CN113887626A (en) | 2021-09-30 | 2021-09-30 | Method and device for generating portrait of power equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111163557.3A CN113887626A (en) | 2021-09-30 | 2021-09-30 | Method and device for generating portrait of power equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113887626A true CN113887626A (en) | 2022-01-04 |
Family
ID=79005140
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111163557.3A Pending CN113887626A (en) | 2021-09-30 | 2021-09-30 | Method and device for generating portrait of power equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113887626A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115271277A (en) * | 2022-10-08 | 2022-11-01 | 中国电力科学研究院有限公司 | Power equipment portrait construction method and system, computer equipment and storage medium |
CN116049700A (en) * | 2023-04-03 | 2023-05-02 | 佰聆数据股份有限公司 | Multi-mode-based operation and inspection team portrait generation method and device |
-
2021
- 2021-09-30 CN CN202111163557.3A patent/CN113887626A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115271277A (en) * | 2022-10-08 | 2022-11-01 | 中国电力科学研究院有限公司 | Power equipment portrait construction method and system, computer equipment and storage medium |
CN116049700A (en) * | 2023-04-03 | 2023-05-02 | 佰聆数据股份有限公司 | Multi-mode-based operation and inspection team portrait generation method and device |
CN116049700B (en) * | 2023-04-03 | 2023-06-20 | 佰聆数据股份有限公司 | Multi-mode-based operation and inspection team portrait generation method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Avila et al. | NTL detection in electric distribution systems using the maximal overlap discrete wavelet-packet transform and random undersampling boosting | |
Murthy et al. | Insulator condition analysis for overhead distribution lines using combined wavelet support vector machine (SVM) | |
Wang et al. | A robust combination approach for short-term wind speed forecasting and analysis–Combination of the ARIMA (Autoregressive Integrated Moving Average), ELM (Extreme Learning Machine), SVM (Support Vector Machine) and LSSVM (Least Square SVM) forecasts using a GPR (Gaussian Process Regression) model | |
Wu et al. | A visual analytics approach for equipment condition monitoring in smart factories of process industry | |
CN111368089B (en) | Business processing method and device based on knowledge graph | |
CN113887626A (en) | Method and device for generating portrait of power equipment | |
Zhang et al. | Deep learning-driven data curation and model interpretation for smart manufacturing | |
CN105677791A (en) | Method and system used for analyzing operating data of wind generating set | |
Han et al. | An efficient algorithm for atomic decomposition of power quality disturbance signals using convolutional neural network | |
Chen et al. | A patent time series processing component for technology intelligence by trend identification functionality | |
CN106682835A (en) | Data-driven complex electromechanical system service quality state evaluation method | |
Su et al. | Nonlinear compensation algorithm for multidimensional temporal data: A missing value imputation for the power grid applications | |
CN111999591B (en) | Method for identifying abnormal state of primary equipment of power distribution network | |
Mitiche et al. | An expert system for EMI data classification based on complex Bispectrum representation and deep learning methods | |
Xiao et al. | Design and implementation of a data-driven approach to visualizing power quality | |
Jandan et al. | Recognition and classification of power quality disturbances by DWT-MRA and SVM classifier | |
Moradzadeh et al. | A novel cyber-Resilient solar power forecasting model based on secure federated deep learning and data visualization | |
Turović et al. | Training an LSTM voltage sags classificator on a synthetic dataset | |
CN117421994A (en) | Edge application health monitoring method and system | |
CN116070140A (en) | Power distribution substation safe operation state monitoring system and method | |
CN109450567A (en) | Frequency range degree Tendency Prediction method and apparatus | |
Sima et al. | A framework for automatically cleansing overvoltage data measured from transmission and distribution systems | |
Rosenlund et al. | Clustering and dimensionality-reduction techniques applied on power quality measurement data | |
Yin et al. | Spatio-temporal graph convolutional networks driven by data-physical fusion for parameter prediction of natural gas dehydration system | |
Chen et al. | An analytical method of data mining on voltage sag based on gray target theory and cloud model |
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 |