CN112418202A - MaskRCNN-based power transformation equipment abnormity identification and positioning method and system - Google Patents
MaskRCNN-based power transformation equipment abnormity identification and positioning method and system Download PDFInfo
- Publication number
- CN112418202A CN112418202A CN202011060711.XA CN202011060711A CN112418202A CN 112418202 A CN112418202 A CN 112418202A CN 202011060711 A CN202011060711 A CN 202011060711A CN 112418202 A CN112418202 A CN 112418202A
- Authority
- CN
- China
- Prior art keywords
- positioning
- data
- power transformation
- identification
- 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 60
- 230000009466 transformation Effects 0.000 title claims abstract description 32
- 230000002159 abnormal effect Effects 0.000 claims abstract description 34
- 238000012549 training Methods 0.000 claims abstract description 15
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 11
- 238000003064 k means clustering Methods 0.000 claims abstract description 9
- 238000005457 optimization Methods 0.000 claims abstract description 6
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 4
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 230000005856 abnormality Effects 0.000 claims description 23
- 238000012360 testing method Methods 0.000 claims description 17
- 238000011176 pooling Methods 0.000 claims description 14
- 239000011159 matrix material Substances 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 10
- 239000013598 vector Substances 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 230000004807 localization Effects 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims 3
- 239000002994 raw material Substances 0.000 claims 3
- 238000004458 analytical method Methods 0.000 claims 1
- 238000003860 storage Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000007796 conventional method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000013095 identification testing Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
- 230000000007 visual effect Effects 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
- G06F18/21—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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a transformer equipment abnormity identification and positioning method and system based on MarkRCNN, which comprises the steps of collecting real-time data of electric equipment for preprocessing; identifying abnormal values of the preprocessed operation data by using an iForest algorithm, and combining the abnormal values marked by a K-means clustering strategy; constructing a Mask RCNN target recognition network model based on a convolutional neural network; inputting the marked abnormal value into the Mask RCNN target recognition network model for primary recognition, and outputting a target recognition result; training and parameter optimization are carried out on the LSSVM, accuracy requirements and threshold values are set, and a positioning model is output after training is finished; and importing the target identification result into the positioning model to obtain abnormal position information of the electric power equipment. According to the invention, the accuracy of image recognition of the power transformation equipment is greatly improved, the positioning recognition of the abnormal position of the equipment is improved, and the fault-tolerant capability, the positioning efficiency and the accuracy of fault positioning information are improved.
Description
Technical Field
The invention relates to the technical field of electric power systems and image recognition, in particular to a transformer equipment abnormity recognition and positioning method and system based on MarkRCNN.
Background
The traditional image identification method is better in performance on a large sample data set, but at present, the image samples of the power equipment are few, the accuracy of the traditional identification method is low, the traditional identification method cannot reach the industrial application level, but the power transformation equipment has abundant correlation, the probability of simultaneous occurrence of specific types of equipment is high, and if the correlation is introduced during image identification, the identification accuracy can be greatly improved, so that the industrial application becomes possible.
The method for positioning fault information based on field device collection mainly comprises the following 2 types, a, matrix method: a unified matrix algorithm is proposed in the literature, and the basic process is that a network description matrix is constructed according to the topological structure of a power distribution network, a fault information matrix is generated according to overcurrent information, and therefore a fault judgment matrix is obtained, and a fault section is accurately judged; b. an artificial intelligence method: the method can still accurately position faults under the conditions that the network structure is changed, the uploaded real-time information is distorted or incomplete and the like, and mainly comprises algorithms such as an artificial neural network, a genetic algorithm, a rough set theory, data mining, a Petri network and an electromagnetism imitation algorithm.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The present invention has been made in view of the above-mentioned conventional problems.
Therefore, the invention provides a transformer equipment abnormity identification and positioning method and system based on MarkRCNN, which can solve the problems of weak fault tolerance, low positioning efficiency and low accuracy of fault positioning information.
In order to solve the technical problems, the invention provides the following technical scheme: the method comprises the steps of collecting real-time data of the power equipment for preprocessing; identifying abnormal values of the preprocessed operation data by using an iForest algorithm, and combining the abnormal values marked by a K-means clustering strategy; constructing a Mask RCNN target recognition network model based on a convolutional neural network; inputting the marked abnormal value into the Mask RCNN target recognition network model for primary recognition, and outputting a target recognition result; training and parameter optimization are carried out on the LSSVM, accuracy requirements and threshold values are set, and a positioning model is output after training is finished; and importing the target identification result into the positioning model to obtain abnormal position information of the electric power equipment.
As a preferred scheme of the transformer equipment abnormality identification and positioning method based on MarkRCNN of the present invention, wherein: comprises selecting a radial basis function as an objective function of the localization model, as follows,
wherein x ═ { x ═ x1；x2；…；x14}: a frequency characteristic matrix formed by frequency characteristic vectors of real-time operation data of the power transformation equipment, y: frequency characteristic vector of historical operation related data of the power transformation equipment, sigma: nuclear width, distribution of response training, range characteristics.
As a preferred scheme of the transformer equipment abnormality identification and positioning method based on MarkRCNN of the present invention, wherein: outputting the positioning model comprises initializing punishment parameters C and sigma, and training and testing the LSSVM by utilizing a preprocessed data set; setting the precision requirement, and if the precision of the LSSVM model does not meet the requirement, carrying out assignment optimization on the C and the sigma according to errors until the precision of test data meets the precision requirement; and setting the threshold value and outputting the positioning model.
As a preferred scheme of the transformer equipment abnormality identification and positioning method based on MarkRCNN of the present invention, wherein: positioning by using the positioning model, wherein the positioning comprises the step of importing the preprocessed running data into the positioning model; and if the operation data of one equipment in the power transformation equipment exceeds the threshold value, the position of the equipment component is abnormal.
As a preferred scheme of the transformer equipment abnormality identification and positioning method based on MarkRCNN of the present invention, wherein: constructing the Mask RCNN target recognition network model comprises the steps of superposing a plurality of residual error networks ResNet, wherein y is F (x) + x; establishing a regionally generated network, Pi＝FC2[FC1[Pooling(f,Ri)]]Setting the threshold value to 0.5 if PiIf it exceeds 0.5, the candidate area is reserved, if P isiIf the content is less than 0.5, the content is discarded; generating a classification branch, Pc i＝FC4[FC3[Pooling(f,Ri′)]](ii) a Generating a masked branch, Mi＝FC6[FC5[Pooling(f,Ri′)]](ii) a Wherein, y: output of residual network, x: input to the residual network, F: convolution operation function, f: image features of the residual network output, Ri: candidate region, Pooling: pooling operation, FC1、FC2Respectively, a first layer and a second layer of full-link layer operation, Pi: candidate region RiProbability of belonging to the foreground (i.e. containing the object to be identified), Ri': reserved candidate area, FC3、FC4Respectively for third and fourth layer full-link layer operations, Pc i: candidate region Ri' probability of object to be recognized, C5、FC6Respectively a fifth layer full-connection layer operation and a sixth layer full-connection layer operation, and a matrix MiAnd the candidate region Ri' Pixel size is uniform, MiEach position in the candidate area represents the probability that the pixel point in the candidate area belongs to the identified object.
As a preferred scheme of the transformer equipment abnormality identification and positioning method based on MarkRCNN of the present invention, wherein: the preliminary identification comprises extracting image features by using the residual error network; the area generation network positions an object to be identified by using the image characteristics and respectively sends the characteristics of a positioning area into the classification branch and the mask branch; the classification branch identifies the kind of the object to be identified; and the mask branch positions pixel points of the object to be recognized in the image.
As a preferred scheme of the transformer equipment abnormality identification and positioning method based on MarkRCNN of the present invention, wherein: the target recognition result comprises a type, an orientation and a size.
As a preferred scheme of the transformer equipment abnormality identification and positioning method based on MarkRCNN of the present invention, wherein: identifying the marked outliers includes randomly sampling the operational data; defining division dimensions, and placing the operation data smaller than a division point in the dimensions on the left side of a current node and placing the operation data larger than the division point on the right side; loop iteration is carried out until the running data is not separable; selecting K points as an initial centroid by using the K-means clustering strategy and calculating Euclidean distances between all the other points and the centroid; dividing all points with the distance value from the centroid point smaller than the threshold value into a cluster; and recalculating the central point of the cluster and defining the label.
As a preferred scheme of the transformer equipment abnormality identification and positioning system based on MarkRCNN of the present invention, wherein: the identification and acquisition module is used for acquiring the picture information and the correlation information among the power transformation equipment and acquiring historical operation data and real-time operation data of the power transformation equipment; the data processing center module is connected with the acquisition module, is used for receiving, calculating, storing and outputting data information to be processed, and comprises an operation unit, a database and an input/output management unit, wherein the operation unit is connected with the acquisition module, is used for receiving the data information acquired by the information acquisition module to perform identification, positioning, operation processing and normalization processing, and calculates the type, size and position data; the positioning module is connected with the data processing center module and used for receiving the operation result of the operation unit, analyzing and judging whether the size exceeds a threshold value and the position is in an area through the calling decoding body, comprehensively judging whether the target identification and the data matching correspond to each other or not, and positioning the abnormal position.
The invention has the beneficial effects that: according to the method, the abnormal value of the preprocessed operation data is recognized through the iForest algorithm, the abnormal value marked by the K-means clustering strategy is combined, the Mask RCNN target recognition network model is used for preliminary recognition, the positioning model of the LSSVM is added, the positioning recognition of the abnormal position of the equipment is improved while the image recognition accuracy of the power transformation equipment is greatly improved, and the fault-tolerant capability, the positioning efficiency and the accuracy of fault positioning information are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise. Wherein:
fig. 1 is a schematic flowchart of a transformer equipment abnormality identification and positioning method based on MarkRCNN according to a first embodiment of the method of the present invention;
fig. 2 is a schematic diagram of a MarkRCNN algorithm framework of a transformer equipment abnormality identification and positioning method based on MarkRCNN according to a first embodiment of the method of the present invention;
fig. 3 is a schematic diagram of a distribution of a module structure of a transformer equipment abnormality identification and positioning system based on MarkRCNN according to a second embodiment of the method of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, specific embodiments accompanied with figures are described in detail below, and it is apparent that the described embodiments are a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention, shall fall within the protection scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Furthermore, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
The present invention will be described in detail with reference to the drawings, wherein the cross-sectional views illustrating the structure of the device are not enlarged partially in general scale for convenience of illustration, and the drawings are only exemplary and should not be construed as limiting the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
Meanwhile, in the description of the present invention, it should be noted that the terms "upper, lower, inner and outer" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation and operate, and thus, cannot be construed as limiting the present invention. Furthermore, the terms first, second, or third are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected and connected" in the present invention are to be understood broadly, unless otherwise explicitly specified or limited, for example: can be fixedly connected, detachably connected or integrally connected; they may be mechanically, electrically, or directly connected, or indirectly connected through intervening media, or may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1
Referring to fig. 1 and 2, a transformer equipment abnormality identification and positioning method based on MarkRCNN is provided as a first embodiment of the present invention, and includes:
s1: and acquiring real-time data of the power equipment for preprocessing.
S2: and identifying abnormal values of the preprocessed running data by using an iForest algorithm, and marking the abnormal values by combining a K-means clustering strategy. It should be noted that, in this step, identifying the abnormal value of the marker includes:
randomly sampling operation data;
defining division dimensionality and placing operation data smaller than a division point in the dimensionality on the left side of a current node and placing operation data larger than the division point on the right side;
iteration is carried out circularly until the running data is not separable;
selecting K points as an initial centroid by using a K-means clustering strategy and calculating Euclidean distances between all the other points and the centroid;
dividing all points with the distance value from the centroid point smaller than a threshold into a cluster;
and recalculating the central point of the cluster and defining the label.
S3: and constructing a Mask RCNN target recognition network model based on the convolutional neural network. It should be further noted that the constructing the Mask RCNN target recognition network model includes:
superimposing a plurality of residual networks ResNet, y ═ f (x) + x;
establishing a regionally generated network, Pi＝FC2[FC1[Pooling(f,Ri)]]Setting the threshold value to 0.5 if PiIf it exceeds 0.5, the candidate area is reserved, if P isiIf the content is less than 0.5, the content is discarded;
generating a classification branch, Pc i＝FC4[FC3[Pooling(f,Ri′)]]；
Generating a masked branch, Mi＝FC6[FC5[Pooling(f,Ri′)]]；
Wherein, y: output of residual network, x: input to the residual network, F: convolution operation function, f: image features of the residual network output, Ri: candidate region, Pooling: pooling operation, FC1、FC2Respectively, a first layer and a second layer of full-link layer operation, Pi: candidate region RiProbability of belonging to the foreground (i.e. containing the object to be identified), Ri': reserved candidate area, FC3、FC4Respectively for third and fourth layer full-link layer operations, Pc i: candidate region Ri' probability of object to be recognized, C5、FC6Respectively a fifth layer full-connection layer operation and a sixth layer full-connection layer operation, and a matrix MiAnd the candidate region Ri' Pixel size is uniform, MiEach position in the candidate area represents the probability that the pixel point in the candidate area belongs to the identified object.
S4: and inputting the marked abnormal value into a Mask RCNN target recognition network model for primary recognition, and outputting a target recognition result. It should be further noted that the preliminary identification includes:
extracting image features by using a residual error network;
the area generation network positions the object to be identified by utilizing the image characteristics and respectively sends the characteristics of the positioned area into the classification branch and the mask branch;
the classification branch identifies the type of the object to be identified;
the mask branch locates the pixel points of the object to be identified in the image.
Specifically, the target recognition result includes:
category, orientation and size.
S5: and training and optimizing parameters of the LSSVM, setting precision requirements and thresholds, and outputting a positioning model after training. Wherein again to be noted are:
the radial basis functions are chosen as the target functions of the localization model, as follows,
wherein x ═ { x ═ x1；x2；…；x14}: a frequency characteristic matrix formed by frequency characteristic vectors of real-time operation data of the power transformation equipment, y: frequency characteristic vector of historical operation related data of the power transformation equipment, sigma: nuclear width, distribution of response training, range characteristics.
Further, outputting the localization model includes:
initializing punishment parameters C and sigma, and training and testing the LSSVM by utilizing the preprocessed data set;
setting a precision requirement, and if the precision of the LSSVM model does not meet the requirement, carrying out assignment optimization on C and sigma according to errors until the precision of the test data meets the precision requirement;
and setting a threshold value and outputting a positioning model.
S6: and importing the target identification result into a positioning model to obtain abnormal position information of the power equipment. It should be noted again that in this step, the positioning is performed by using a positioning model, which includes:
importing the preprocessed operation data into a positioning model;
and if the operation data of one equipment in the power transformation equipment exceeds a threshold value, the position of the equipment component is abnormal.
Preferably, in this embodiment, it should be further explained that, in the conventional method for identifying and positioning an abnormality of an electrical device, an infrared thermometer is used to measure a hotspot temperature of the electrical device and an environmental reference body temperature of a non-fault phase thermometer, a relative temperature difference is calculated through a temperature difference value, and a PC is used to identify different abnormalities according to different electrical devices, so that how to conveniently determine an abnormal position of a heating device to perform troubleshooting is a main problem to be solved; compared with the traditional method, the abnormal value of the preprocessed operation data is identified through the iForest algorithm, the abnormal value marked by the K-means clustering strategy is combined, the Mask RCNN target identification network model is used for preliminary identification, the positioning model of the LSSVM is added, the image identification accuracy of the power transformation equipment is greatly improved, meanwhile, the positioning identification of the abnormal position of the equipment is improved, and the fault-tolerant capability, the positioning efficiency and the accuracy of fault positioning information are improved.
Preferably, in order to better verify and explain the technical effects adopted in the method of the present invention, the embodiment selects the conventional power equipment abnormality identification and positioning method and adopts the method to perform a comparison test, and compares the test results by means of scientific demonstration to verify the real effects of the method.
In order to verify that the method has higher fault tolerance, more comprehensive applicability, and higher positioning efficiency and accuracy compared with the conventional method, the conventional method and the method of the present invention are adopted to perform positioning identification test on the abnormal position of the power transformation equipment respectively.
And (3) testing environment: (1) shooting related pictures of one hundred groups of equipment to be tested, collecting historical operating data and full-time real-time operating data of the related equipment, and inputting the processed data into simulation software;
(2) the transformation equipment types comprise a transformer, a GIS, a sleeve, an insulator, a switch, a breaker, a mutual inductor and a capacitor;
(3) the method of the invention and the traditional method respectively train on the training set and test on the test set, and start the automatic test equipment and utilize MATLB simulation.
The test results are shown below:
table 1: the two methods test and compare the result table of the fault tolerance rate of the abnormal positioning of the equipment.
Referring to table 1, it can be seen visually that, in the presence of the same test data and test equipment, the fault tolerance of the recognition and positioning result processed by the method of the present invention is higher, i.e., the accuracy is higher, compared with the recognition and positioning result processed by the conventional method, and the real effect of the method of the present invention is verified.
Example 2
Referring to fig. 3, a second embodiment of the present invention, which is different from the first embodiment, provides a MarkRCNN-based power transformation equipment abnormality recognition and positioning system, including:
and the identification acquisition module 100 is used for acquiring the picture information and the correlation information between the power transformation devices, and acquiring historical operation data and real-time operation data of the power transformation devices.
The data processing center module 200 is connected to the acquisition module 100, and is configured to receive, calculate, store, and output data information to be processed, and includes an arithmetic unit 201, a database 202, and an input/output management unit 203, where the arithmetic unit 201 is connected to the acquisition module 100, and is configured to receive the data information acquired by the information acquisition module 100 to perform identification, positioning, arithmetic processing, and normalization processing, calculate type, size, and position data, the database 202 is connected to each module, and is configured to store all received data information, and provide a provisioning service for the data processing center module 200, and the input/output management unit 203 is configured to receive information of each module and output an arithmetic result of the arithmetic unit 201.
The positioning module 300 is connected to the data processing center module 200, and is configured to receive the operation result of the operation unit 201, analyze and determine whether the size exceeds the threshold and the position is within the area by retrieving the decoding body, and comprehensively determine whether the target identification and the data matching correspond to each other, so as to position the abnormal position.
In popular terms, the data processing center module 200 is mainly divided into three layers, including a control layer, an operation layer and a storage layer, wherein the control layer is a command control center of the data processing center module 200 and is composed of an instruction register IR, an instruction decoder ID and an operation controller OC, the control layer can sequentially take out various instructions from a memory according to a program which is pre-programmed by a user, place the instructions in the instruction register IR, analyze and determine the instructions through the instruction decoder, inform the operation controller OC of operation, and send micro-operation control signals to corresponding components according to a determined time sequence; the operation layer is the core of the calculation unit 201, can execute arithmetic operation (such as addition, subtraction, multiplication, division and addition operation thereof) and logic operation (such as shift, logic test or two-value comparison), is connected to the control layer, and performs operation by receiving a control signal of the control layer; the storage layer is a database of the data processing center module 200, and can store data (data to be processed and data already processed).
It should be recognized that embodiments of the present invention can be realized and implemented by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer readable memory. The methods may be implemented in a computer program using standard programming techniques, including a non-transitory computer-readable storage medium configured with the computer program, where the storage medium so configured causes a computer to operate in a specific and predefined manner, according to the methods and figures described in the detailed description. Each program may be implemented in a high level procedural or object oriented programming language to communicate with a computer system. However, the program(s) can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.
Further, the operations of processes described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and/or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) collectively executed on one or more processors, by hardware, or combinations thereof. The computer program includes a plurality of instructions executable by one or more processors.
Further, the method may be implemented in any type of computing platform operatively connected to a suitable interface, including but not limited to a personal computer, mini computer, mainframe, workstation, networked or distributed computing environment, separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, and the like. Aspects of the invention may be embodied in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optically read and/or write storage medium, RAM, ROM, or the like, such that it may be read by a programmable computer, which when read by the storage medium or device, is operative to configure and operate the computer to perform the procedures described herein. Further, the machine-readable code, or portions thereof, may be transmitted over a wired or wireless network. The invention described herein includes these and other different types of non-transitory computer-readable storage media when such media include instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor. The invention also includes the computer itself when programmed according to the methods and techniques described herein. A computer program can be applied to input data to perform the functions described herein to transform the input data to generate output data that is stored to non-volatile memory. The output information may also be applied to one or more output devices, such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including particular visual depictions of physical and tangible objects produced on a display.
As used in this application, the terms "component," "module," "system," and the like are intended to refer to a computer-related entity, either hardware, firmware, a combination of hardware and software, or software in execution. For example, a component may be, but is not limited to being: a process running on a processor, an object, an executable, a thread of execution, a program, and/or a computer. By way of example, both an application running on a computing device and the computing device can be a component. One or more components can reside within a process and/or thread of execution and a component can be localized on one computer and/or distributed between two or more computers. In addition, these components can execute from various computer readable media having various data structures thereon. The components may communicate by way of local and/or remote processes such as in accordance with a signal having one or more data packets (e.g., data from one component interacting with another component in a local system, distributed system, and/or across a network such as the internet with other systems by way of the signal).
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (9)
1. A transformer equipment abnormity identification and positioning method based on MarkRCNN is characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
collecting real-time data of the power transformation equipment for preprocessing;
identifying abnormal values of the preprocessed operation data by using an iForest algorithm, and combining the abnormal values marked by a K-means clustering strategy;
constructing a Mask RCNN target recognition network model based on a convolutional neural network;
inputting the marked abnormal value into the Mask RCNN target recognition network model for primary recognition, and outputting a target recognition result;
training and parameter optimization are carried out on the LSSVM, accuracy requirements and threshold values are set, and a positioning model is output after training is finished;
and importing the target identification result into the positioning model to obtain abnormal position information of the electric power equipment.
2. The MarkRCNN-based power transformation equipment abnormality identification and positioning method according to claim 1, wherein: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
the radial basis functions are chosen as the objective functions of the localization model, as follows,
wherein x ═ { x ═ x1；x2；…；x14}: a frequency characteristic matrix formed by frequency characteristic vectors of real-time operation data of the power transformation equipment, y: frequency characteristic vector of historical operation related data of the power transformation equipment, sigma: nuclear width, distribution of response training, range characteristics.
3. The MarkRCNN-based power transformation equipment abnormality identification and positioning method according to claim 2, wherein: outputting the location model may include outputting the location model,
initializing punishment parameters C and sigma, and training and testing the LSSVM by utilizing a preprocessed data set;
setting the precision requirement, and if the precision of the LSSVM model does not meet the requirement, carrying out assignment optimization on the C and the sigma according to errors until the precision of test data meets the precision requirement;
and setting the threshold value and outputting the positioning model.
4. The MarkRCNN-based power transformation equipment abnormality identification and positioning method according to claim 3, wherein: and positioning by using the positioning model, including,
importing the preprocessed running data into the positioning model;
and if the operation data of one equipment in the power transformation equipment exceeds the threshold value, the position of the equipment component is abnormal.
5. The MarkRCNN-based power transformation equipment abnormality identification and positioning method as claimed in any one of claims 1 to 4, wherein: constructing the Mask RCNN target recognition network model comprises,
superimposing a plurality of residual networks ResNet, y ═ f (x) + x;
establishing a regionally generated network, Pi＝FC2[FC1[Pooling(f,Ri)]]Setting the threshold value to 0.5 if PiIf it exceeds 0.5, the candidate area is reserved, if P isiIf the content is less than 0.5, the content is discarded;
a classification branch is generated and,
generating a masked branch, Mi＝FC6[FC5[Pooling(f,Ri′)]]；
Wherein, y: output of residual network, x: input to the residual network, F: convolution operation function, f: image features of the residual network output, Ri: candidate region, Pooling: pooling operation, FC1、FC2Respectively, a first layer and a second layer of full-link layer operation, Pi: candidate region RiProbability of belonging to the foreground (i.e. containing the object to be identified), Ri': reserved candidate area, FC3、FC4Respectively the third layer and the fourth layer full connection layer operation,
candidate region Ri' probability of object to be recognized, C5、FC6Respectively a fifth layer full-connection layer operation and a sixth layer full-connection layer operation, and a matrix MiWaiting time and dateSelect region Ri' Pixel size is uniform, MiEach position in the candidate area represents the probability that the pixel point in the candidate area belongs to the identified object.
6. The MarkRCNN-based power transformation equipment abnormality identification and positioning method according to claim 5, wherein: the preliminary identification may include one or more of,
extracting image features by using the residual error network;
the area generation network positions an object to be identified by using the image characteristics and respectively sends the characteristics of a positioning area into the classification branch and the mask branch;
the classification branch identifies the kind of the object to be identified;
and the mask branch positions pixel points of the object to be recognized in the image.
7. The MarkRCNN-based power transformation equipment abnormality identification and positioning method according to claim 6, wherein: the target recognition result comprises a type, an orientation and a size.
8. The MarkRCNN-based power transformation equipment abnormality identification and positioning method according to claim 7, wherein: identifying the outlier that is flagged includes identifying a location of the outlier,
randomly sampling the operational data;
defining division dimensions, and placing the operation data smaller than a division point in the dimensions on the left side of a current node and placing the operation data larger than the division point on the right side;
loop iteration is carried out until the running data is not separable;
selecting K points as an initial centroid by using the K-means clustering strategy and calculating Euclidean distances between all the other points and the centroid;
dividing all points with the distance value from the centroid point smaller than the threshold value into a cluster;
and recalculating the central point of the cluster and defining the label.
9. The utility model provides a transformer equipment abnormal recognition positioning system based on markRCNN which characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
the identification acquisition module (100) is used for acquiring the picture information and the correlation information among the power transformation equipment and acquiring historical operation data and real-time operation data of the power transformation equipment;
the data processing center module (200) is connected to the acquisition module (100) and used for receiving, calculating, storing and outputting data information to be processed, and comprises an operation unit (201), a database (202) and an input and output management unit (203), wherein the operation unit (201) is connected to the acquisition module (100) and used for receiving the data information acquired by the information acquisition module (100) to perform identification, positioning, operation and normalization processing and calculating the type, size and position data, the database (202) is connected to each module and used for storing all the received data information and providing allocation and supply services for the data processing center module (200), and the input and output management unit (203) is used for receiving the information of each module and outputting the operation result of the operation unit (201);
the positioning module (300) is connected with the data processing center module (200) and is used for receiving the operation result of the operation unit (201), judging whether the size exceeds a threshold value and the position is in an area through analysis of a calling decoding body, comprehensively judging whether target identification and data matching correspond to each other and positioning an abnormal position.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011060711.XA CN112418202A (en) | 2021-01-11 | 2021-01-11 | MaskRCNN-based power transformation equipment abnormity identification and positioning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011060711.XA CN112418202A (en) | 2021-01-11 | 2021-01-11 | MaskRCNN-based power transformation equipment abnormity identification and positioning method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112418202A true CN112418202A (en) | 2021-02-26 |
Family
ID=74855074
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011060711.XA Pending CN112418202A (en) | 2021-01-11 | 2021-01-11 | MaskRCNN-based power transformation equipment abnormity identification and positioning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112418202A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113075498A (en) * | 2021-03-09 | 2021-07-06 | 华中科技大学 | Power distribution network traveling wave fault positioning method and system based on residual error clustering |
| CN113222429A (en) * | 2021-05-20 | 2021-08-06 | 国网山东省电力公司潍坊供电公司 | Power grid power consumption demand supervision method based on geographic information consistency verification |
| CN113486965A (en) * | 2021-07-14 | 2021-10-08 | 西南交通大学 | Training method for abnormity identification model of vehicle network electric coupling data |
| CN113762163A (en) * | 2021-09-09 | 2021-12-07 | 杭州澳亚生物技术股份有限公司 | GMP workshop intelligent monitoring management method and system |
| CN116433226A (en) * | 2023-06-14 | 2023-07-14 | 浙江亿视电子技术有限公司 | Alternating current power supply equipment management method and system based on electrical parameter AI analysis |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150279052A1 (en) * | 2014-03-31 | 2015-10-01 | National Taipei University Of Technology | Method and apparatus for moving object detection using principal component analysis based radial basis function network |
| US20190057507A1 (en) * | 2017-08-18 | 2019-02-21 | Samsung Electronics Co., Ltd. | System and method for semantic segmentation of images |
| CN109712118A (en) * | 2018-12-11 | 2019-05-03 | 武汉三江中电科技有限责任公司 | A kind of substation isolating-switch detection recognition method based on Mask RCNN |
| CN111209864A (en) * | 2020-01-07 | 2020-05-29 | 上海交通大学 | Target identification method for power equipment |
| CN111579936A (en) * | 2020-06-30 | 2020-08-25 | 上海交通大学 | Positioning method and system suitable for arc light grounding fault |
| CN112101359A (en) * | 2020-11-11 | 2020-12-18 | 广州华多网络科技有限公司 | Text formula positioning method, model training method and related device |
-
2021
- 2021-01-11 CN CN202011060711.XA patent/CN112418202A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150279052A1 (en) * | 2014-03-31 | 2015-10-01 | National Taipei University Of Technology | Method and apparatus for moving object detection using principal component analysis based radial basis function network |
| US20190057507A1 (en) * | 2017-08-18 | 2019-02-21 | Samsung Electronics Co., Ltd. | System and method for semantic segmentation of images |
| CN109712118A (en) * | 2018-12-11 | 2019-05-03 | 武汉三江中电科技有限责任公司 | A kind of substation isolating-switch detection recognition method based on Mask RCNN |
| CN111209864A (en) * | 2020-01-07 | 2020-05-29 | 上海交通大学 | Target identification method for power equipment |
| CN111579936A (en) * | 2020-06-30 | 2020-08-25 | 上海交通大学 | Positioning method and system suitable for arc light grounding fault |
| CN112101359A (en) * | 2020-11-11 | 2020-12-18 | 广州华多网络科技有限公司 | Text formula positioning method, model training method and related device |
Non-Patent Citations (2)
| Title |
|---|
| 李画;李明晶;李凯;赵雪竹;: "Mask RCNN模型在路面缺陷检测中的应用", 科学技术创新, no. 29, 25 September 2020 (2020-09-25) * |
| 王宪保等: "基于Ｍａｓｋ ＲＣＮＮ的滤袋开口检测方法", 计算机测量与控制, vol. 28, no. 12, 25 December 2020 (2020-12-25), pages 21 - 25 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113075498A (en) * | 2021-03-09 | 2021-07-06 | 华中科技大学 | Power distribution network traveling wave fault positioning method and system based on residual error clustering |
| CN113222429A (en) * | 2021-05-20 | 2021-08-06 | 国网山东省电力公司潍坊供电公司 | Power grid power consumption demand supervision method based on geographic information consistency verification |
| CN113222429B (en) * | 2021-05-20 | 2022-11-29 | 国网山东省电力公司潍坊供电公司 | Power grid power consumption demand supervision method based on geographic information consistency verification |
| CN113486965A (en) * | 2021-07-14 | 2021-10-08 | 西南交通大学 | Training method for abnormity identification model of vehicle network electric coupling data |
| CN113762163A (en) * | 2021-09-09 | 2021-12-07 | 杭州澳亚生物技术股份有限公司 | GMP workshop intelligent monitoring management method and system |
| CN116433226A (en) * | 2023-06-14 | 2023-07-14 | 浙江亿视电子技术有限公司 | Alternating current power supply equipment management method and system based on electrical parameter AI analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112418202A (en) | MaskRCNN-based power transformation equipment abnormity identification and positioning method and system | |
| CN112699913A (en) | Transformer area household variable relation abnormity diagnosis method and device | |
| CN111832468A (en) | Gesture recognition method and device based on biological recognition, computer equipment and medium | |
| JP2021532434A (en) | Face feature extraction model Training method, face feature extraction method, device, equipment and storage medium | |
| CN111650453A (en) | Power equipment diagnosis method and system based on windowing characteristic Hilbert imaging | |
| CN111914813A (en) | Power transmission line inspection image naming method and system based on image classification | |
| WO2021248269A1 (en) | High-precision identification method and system for transformer device | |
| Liao et al. | Fusion of infrared-visible images in UE-IoT for fault point detection based on GAN | |
| CN113191253A (en) | Non-invasive load identification method based on feature fusion under edge machine learning | |
| CN116188543B (en) | Point cloud registration method and system based on deep learning unsupervised | |
| CN111537884A (en) | Method and device for acquiring service life data of power battery, computer equipment and medium | |
| CN111553176B (en) | Wireless transmission checking method and system suitable for wiring of substation screen cabinet | |
| CN114219855A (en) | Point cloud normal vector estimation method and device, computer equipment and storage medium | |
| CN111537831B (en) | Power distribution network line fault positioning method and device | |
| CN111598123A (en) | Power distribution network line vectorization method and device based on neural network | |
| CN112595918A (en) | Low-voltage meter reading fault detection method and device | |
| CN112083275A (en) | Distribution network fault type identification method and system | |
| CN115115919B (en) | Power grid equipment thermal defect identification method and device | |
| CN115830342A (en) | Method and device for determining detection frame, storage medium and electronic device | |
| CN114596487A (en) | Switch on-off state identification method based on self-attention mechanism | |
| CN112579721B (en) | Method and system for constructing crowd distribution map, terminal equipment and storage medium | |
| Li et al. | Automatic infrared image recognition method for substation equipment based on a deep self-attention network and multi-factor similarity calculation | |
| CN114581761A (en) | Remote sensing image recognition method, device, equipment and computer readable storage medium | |
| CN112308421A (en) | RFID-based terminal asset information safety management method and system | |
| CN111859370A (en) | Method, apparatus, electronic device and computer-readable storage medium for identifying service |
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 |