CN116740687A - Dam leakage electrical anomaly identification method and system and electronic equipment - Google Patents

Dam leakage electrical anomaly identification method and system and electronic equipment Download PDF

Info

Publication number
CN116740687A
CN116740687A CN202310724771.4A CN202310724771A CN116740687A CN 116740687 A CN116740687 A CN 116740687A CN 202310724771 A CN202310724771 A CN 202310724771A CN 116740687 A CN116740687 A CN 116740687A
Authority
CN
China
Prior art keywords
dam
leakage
abnormal
leakage electrical
electrical
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
Application number
CN202310724771.4A
Other languages
Chinese (zh)
Inventor
张平松
汪椰伶
席超强
谭磊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Anhui University of Science and Technology
Original Assignee
Anhui University of Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Anhui University of Science and Technology filed Critical Anhui University of Science and Technology
Priority to CN202310724771.4A priority Critical patent/CN116740687A/en
Publication of CN116740687A publication Critical patent/CN116740687A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • 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
    • G06N3/0455—Auto-encoder networks; Encoder-decoder networks
    • 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
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • 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
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/08—Construction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G06V10/765—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks

Abstract

The invention provides a dam leakage electrical anomaly identification method, a dam leakage electrical anomaly identification system and electronic equipment, and relates to the technical field of dam leakage electrical anomaly identification. The method comprises the steps of obtaining a apparent resistivity image of a dam to be tested; inputting the apparent resistivity image of the dam to be tested into a dam leakage electrical anomaly identification model, and determining the position and the anomaly constant of a leakage electrical anomaly area in the dam to be tested; the dam leakage electrical anomaly identification model is obtained by training an end-to-end deep learning model by using the marked apparent resistivity image. The method can improve the identification precision and efficiency of the dam leakage electrical anomaly area by constructing and training the end-to-end deep learning model.

Description

Dam leakage electrical anomaly identification method and system and electronic equipment
Technical Field
The invention relates to the technical field of dam leakage electrical anomaly identification, in particular to a dam leakage electrical anomaly identification method, a dam leakage electrical anomaly identification system and electronic equipment.
Background
Along with the development of hydraulic engineering construction, the number of reservoir dams is increased year by year, and correspondingly, the problem of reservoir dam leakage is also increasingly outstanding. On one hand, leakage problems occur when old reservoir dams are lost over time; on the other hand, the newly-built reservoir dam also has hidden leakage trouble due to the problems of construction, materials and the like. The leakage problem seriously threatens the safety operation and maintenance of the dam, so that the deep research on the dam leakage diagnosis technology and the safety evaluation has important significance for guaranteeing the safety and stable operation of the dam. The high-density electrical method is widely applied to detection of dam leakage abnormality as a nondestructive detection method with high precision, good reliability and low cost. In the conventional low-resistance anomaly identification work of a dam, researchers mainly observe inversion apparent resistivity according to naked eyes, so that the range of a target area with low resistance anomaly is judged, but the method is too dependent on experience, takes long time, has higher professional requirements, is easily influenced by subjective factors, leads to relatively lower precision and accuracy, and is accompanied by the increase of the detection scale of the dam and the rapid increase of the acquired data quantity, so that the rapid and accurate positioning of the electric anomaly area of the leakage of the dam is also a problem to be solved.
Disclosure of Invention
The invention aims to provide a dam leakage electrical anomaly identification method, a system and electronic equipment, which can improve identification precision and efficiency of a dam leakage electrical anomaly area.
In order to achieve the above object, the present invention provides the following solutions:
a dam leakage electrical anomaly identification method comprises the following steps:
acquiring a apparent resistivity image of a dam to be tested;
inputting the apparent resistivity image of the dam to be tested into a dam leakage electrical anomaly identification model, and determining the leakage electrical anomaly condition in the dam to be tested; the dam leakage electrical anomaly identification model is obtained by training an end-to-end deep learning model by using the marked apparent resistivity image; the leaky electrical anomaly condition includes a number of leaky electrical anomaly regions and a location of each leaky electrical anomaly region.
Optionally, the end-to-end deep learning model includes: the front end, the rear end and the post-processing module are sequentially connected;
the front end includes an encoder; the encoder is obtained by removing a full connection layer in the VGG16 deep convolutional neural network;
the back end comprises a split branch decoder and an embedded branch decoder; the input end of the split branch decoder and the input end of the embedded branch decoder are connected with the output end of the encoder; the output end of the split branch decoder and the output end of the embedded branch decoder are connected with the input end of the post-processing module;
the split branch decoder is used for outputting a leakage electrical abnormal region identification result;
the embedded branch decoder is used for outputting mask images of leakage electrical abnormal areas;
the post-processing module is used for carrying out clustering processing on the mask images of the leakage electrical abnormal region, combining the clustering result with the images output by the segmentation branch decoder to obtain a classification result of the leakage electrical abnormal region, and determining whether the leakage abnormal resistivity is the same according to the visual characteristics of the abnormal region; extracting leakage electrical abnormal characteristics and combining the leakage electrical abnormal area mask image to determine leakage electrical abnormal conditions.
Optionally, before acquiring the apparent resistivity image of the dam to be measured, the method further includes:
constructing the end-to-end deep learning model;
acquiring a plurality of apparent resistivity historical images of the dam;
marking leakage electrical property abnormal areas and marking types of the leakage electrical property abnormal areas in the plurality of visual resistivity historical images to obtain a plurality of visual resistivity historical marking images;
and training the end-to-end deep learning model by taking the apparent resistivity historical image as input and taking a plurality of apparent resistivity historical labeling images as output to obtain the dam leakage electrical anomaly identification model.
Optionally, the label type is an oval frame or a square frame.
A dam leakage electrical anomaly identification system, comprising:
the apparent resistivity image acquisition module is used for acquiring an apparent resistivity image of the dam to be tested;
the leakage electrical property abnormal region identification module is used for inputting the apparent resistivity image of the dam to be tested into a dam leakage electrical property abnormal identification model to determine the leakage electrical property abnormal condition in the dam to be tested; the dam leakage electrical anomaly identification model is obtained by training an end-to-end deep learning model by using the marked apparent resistivity image; the leaky electrical anomaly condition includes a number of leaky electrical anomaly regions and a location of each leaky electrical anomaly region.
An electronic device comprising a memory for storing a computer program and a processor that runs the computer program to cause the electronic device to perform the method of identifying dam leakage electrical anomalies.
Optionally, the memory is a readable storage medium.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention provides a dam leakage electrical anomaly identification method, a dam leakage electrical anomaly identification system and electronic equipment, wherein a apparent resistivity image of a dam to be tested is obtained; inputting the apparent resistivity image of the dam to be tested into a dam leakage electrical anomaly identification model, and determining a leakage electrical anomaly area in the dam to be tested; the dam leakage electrical anomaly identification model is obtained by training an end-to-end deep learning model by using the marked apparent resistivity image. The method can improve the identification precision and efficiency of the dam leakage electrical anomaly area by constructing and training the end-to-end deep learning model.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for identifying electrical anomalies in dam leakage in embodiment 1 of the present invention;
FIG. 2 is a diagram showing the thinking of the method for identifying electrical anomalies of dam leakage based on end-to-end deep learning in embodiment 1 of the present invention;
FIG. 3 is a diagram of a dataset according to example 1 of the present invention;
FIG. 4 is a schematic diagram of ARNet model structure in embodiment 1 of the present invention;
FIG. 5 is a schematic diagram of the clustering effect of the partition branch in embodiment 1 of the present invention;
FIG. 6 is a schematic diagram of the cross-correlation of network training in embodiment 1 of the present invention;
FIG. 7 is a diagram showing the network training loss value in embodiment 1 of the present invention;
FIG. 8 shows the ARNet model test recognition effect in example 1 of the present invention;
FIG. 9 is a schematic diagram of the predicted abnormal position of ARNet model in embodiment 1 of the present invention;
FIG. 10 is a schematic diagram of the inversion results of Res2Dinv inversion software in example 1 of the present invention;
FIG. 11 is a schematic diagram of a drilling pattern of ARNet in example 1 of the present invention at abnormal locations and areas of investigation delineated by apparent resistivity images.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention aims to provide a dam leakage electrical anomaly identification method, a system and electronic equipment, which can improve identification precision and efficiency of a dam leakage electrical anomaly area.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
Example 1
As shown in fig. 1-2, the present embodiment provides a method for identifying an electrical anomaly of a dam leakage, including:
step 101: and acquiring a apparent resistivity image of the dam to be tested.
Step 102: inputting the apparent resistivity image of the dam to be tested into a dam leakage electrical anomaly identification model, and determining the leakage electrical anomaly condition in the dam to be tested; the dam leakage electrical anomaly identification model is obtained by training an end-to-end deep learning model by using the marked apparent resistivity image; the leaky electrical anomaly condition includes a number of leaky electrical anomaly regions and a location of each leaky electrical anomaly region.
Wherein the end-to-end deep learning model comprises: the front end, the rear end and the post-processing module are sequentially connected; the front end includes an encoder; the encoder is obtained by removing a full connection layer in the VGG16 deep convolutional neural network; the back end comprises a split branch decoder and an embedded branch decoder; the input end of the split branch decoder and the input end of the embedded branch decoder are connected with the output end of the encoder; the output end of the split branch decoder and the output end of the embedded branch decoder are connected with the input end of the post-processing module; the split branch decoder is used for outputting the identification result of the leakage electrical abnormal region.
The embedded branch decoder is used for outputting mask images of leakage electrical abnormal areas.
The post-processing module is used for carrying out clustering processing on the mask images of the leakage electrical abnormal region, combining the clustering result with the images output by the segmentation branch decoder to obtain a classification result of the leakage electrical abnormal region, and determining whether the leakage abnormal resistivity is the same according to the visual characteristics of the abnormal region; extracting leakage electrical abnormal characteristics and combining the leakage electrical abnormal area mask image to determine leakage electrical abnormal conditions.
Prior to step 101, further comprising:
step 103: and constructing an end-to-end deep learning model.
Step 104: a plurality of apparent resistivity history images of the dam are acquired.
Step 105: marking leakage electrical property abnormal areas and marking types of the leakage electrical property abnormal areas in the plurality of visual resistivity historical images to obtain a plurality of visual resistivity historical marking images; the labeling type is an oval frame or a square frame. Reservoir seepage monitoring information is collected, data are analyzed, and the relative size and shape of a dam seepage abnormal region, a surrounding rock resistivity value range, a background value resistivity value, a seepage target region and the like are summarized. Referring to the actual measurement data characteristics of dam leakage, respectively establishing resistivity models of a single abnormal body and a double abnormal body in batches by an open source forward modeling program (as shown in figure 3); and extracting the apparent resistivity value rho generated in the resistivity model, determining the position coordinates (X, Z) of the measuring point of the corresponding set electric device, carrying out interpolation visualization processing on the position coordinates (X, Z, rho) by using a programming language to generate an apparent resistivity image dataset in batches, extracting sample data from the model data at random in proportion in order to enable the trained model to have wider performance, and finally forming the sample dataset which is respectively used as a training set, a verification set and a test set in proportion for network training, verification and test. And setting a preset model of the model as a training label, and corresponding to the abnormal characteristic information of the dam model.
Step 106: and training the end-to-end deep learning model by taking the visual resistivity historical image as input and taking a plurality of visual resistivity historical labeling images as output to obtain the dam leakage electrical anomaly identification model.
Training the apparent resistivity image dataset by adopting an end-to-end-based deep learning algorithm, and performing super-parameter optimization to obtain an optimal training learning classifier. The specific flow is as follows:
1) End-to-end based deep learning algorithms are directed to learning the mapping from input (apparent resistivity data) to output (abnormal resistivity model) through convolutional neural networks. The network structure mainly comprises three parts: the method comprises a front end, a rear end and a post-processing part, wherein the front end is used for coding and decoding the input apparent resistivity characteristic, the rear end is used for updating model parameters by using a loss function and a gradient decreasing function so as to continuously evolve towards an expected direction, and the post-processing part adopts a communication and clustering algorithm to circle all anomalies in an apparent resistivity image, as shown in fig. 4.
a. The front end of the model is composed of a multi-layer convolutional neural network, and the structure is divided into two parts of coding and decoding. The encoder uses a VGG16 depth convolutional neural network with full-connection layer removed as a shared feature extractor, which contains 13 convolutional hidden layers, extracting feature maps of different sizes in 5 stages.
b. The backend contains configuration optimization functions of the network model. The partition branch uses a bisectional cross entropy loss function L 1 It can classify different classes of anomaly regions, the predicted probabilities of the target anomaly and the background are y and 1-y, respectively. The cross entropy loss function representation is shown in formula (1):
wherein y represents the label of the target abnormal body, the positive class is 1, and the negative class is 0;representing the probability of the target abnormality being predicted as positive class,/-> Probability of all positive class items in the tag being predicted to be true, < >>The probability that all items in the tag that are negative classes are predicted to be true, the more the product of the probabilities of the twoThe smaller the loss value, the more the predicted result is matched with the actual.
The embedded branch uses a discriminant (discriminant) loss function L emb The specific form is shown in the formula (2):
wherein II is the two norms, []+＝max(0,*)；L var For the variance term component, m c Cluster centers representing individual outliers, namely: average value of all pixel points in abnormal region, and radius of cluster is delta v C is the number of abnormal regions, N c For the number of pixels in the c-th anomaly region, m c -x i And I represents the Euclidean distance from the pixel point to the center of the abnormal body cluster. If the distance between the pixel point and the center of the cluster is larger than the radius delta of the cluster v Pixels are not considered to be within a cluster and vice versa. The smaller the variance term component, the closer the pixel point is to the cluster center, namely, the smaller the difference of pixel values of the abnormal region is, and the color of the abnormal region is similar in visual aspect. L (L) dist As a component of the distance term, representing Euclidean distance between centers of different abnormal clusters, if the distance between centers of two clusters is less than 2 delta d When two clusters are considered as the same class, otherwise, two clusters are considered as different classes. The smaller the distance item component, the larger the distance between the unnecessary abnormal body clusters, and the color phase difference of different abnormal areas is obvious in visual aspect. L (L) reg For regularization term, it constrains all cluster centers, preventing cluster centers from being too large, exceeding the pixel threshold. L (L) emb For the weighted summation of the first three components, α, β, γ are used to balance the magnitudes of the three.
Model training aims at minimizing the loss function value to improve the performance of the model. In order to realize efficient calculation of the model, a random gradient descent algorithm is adopted, the algorithm can rapidly optimize parameters of the model in a large-scale data set, and a gradient value is calculated through a back propagation algorithm and iterative updating of weights is carried out so as to effectively find a global optimal solution.
c. Post-treatment part: in order to distinguish between different abnormal body areas in dam leakage, the model adds a post-treatment method. The method comprises the steps of firstly taking the output of a segmentation branch as a Mask (Mask), and extracting a corresponding abnormal region from the result of embedding the branch. And then dividing the abnormal region into different clusters through a DBSCAN clustering algorithm, and returning the clustering result to the segmentation branch for output, thereby further optimizing the segmented image. In the figure, the surrounding rock area is represented in black, other abnormal bodies are represented in a differentiated mode, the resistivity of the abnormal bodies is different, and the colors of the abnormal bodies are different, as shown in fig. 5.
2) The network model parameters initially set Batch Size (Batch Size), learning Rate (Learning Rate), weight attenuation value (weight decay), momentum coefficient (Momentum), etc. The model uses the intersection ratio and the loss value as evaluation indexes of network training, wherein the intersection ratio represents the overlapping rate of the expected result and the label, namely the ratio of intersection and union of the expected result and the label. The loss value is mainly used for measuring the difference between the model predicted value and the true value. After each round of training, the intersection ratio and loss value of the model are recorded and plotted as a change curve, as shown in fig. 6-7.
The trained classifier firstly carries out recognition test on the test set of the forward model, and the test result is compared with the prediction model to check the accuracy of the test result, as shown in figure 8. The validity and robustness of the network are then demonstrated by application testing of the dam measured data, as shown in fig. 9-11.
Example 2
In order to execute the method corresponding to the embodiment 1 to achieve the corresponding functions and technical effects, the following provides a dam leakage electrical anomaly identification system, which includes:
and the apparent resistivity image acquisition module is used for acquiring an apparent resistivity image of the dam to be tested.
The leakage electrical property abnormal region identification module is used for inputting the apparent resistivity image of the dam to be tested into a dam leakage electrical property abnormal identification model to determine the leakage electrical property abnormal condition in the dam to be tested; the dam leakage electrical anomaly identification model is obtained by training an end-to-end deep learning model by using the marked apparent resistivity image; the leaky electrical anomaly condition includes a number of leaky electrical anomaly regions and a location of each leaky electrical anomaly region.
Example 3
The embodiment provides an electronic device, including a memory and a processor, where the memory is configured to store a computer program, and the processor is configured to run the computer program to enable the electronic device to execute a dam leakage electrical anomaly identification method described in embodiment 1. Wherein the memory is a readable storage medium
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present invention and the core ideas thereof; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the invention.

Claims (7)

1. The dam leakage electrical anomaly identification method is characterized by comprising the following steps:
acquiring a apparent resistivity image of a dam to be tested;
inputting the apparent resistivity image of the dam to be tested into a dam leakage electrical anomaly identification model, and determining the leakage electrical anomaly condition in the dam to be tested; the dam leakage electrical anomaly identification model is obtained by training an end-to-end deep learning model by using the marked apparent resistivity image; the leaky electrical anomaly condition includes a number of leaky electrical anomaly regions and a location of each leaky electrical anomaly region.
2. The method of claim 1, wherein the end-to-end deep learning model comprises: the front end, the rear end and the post-processing module are sequentially connected;
the front end includes an encoder; the encoder is obtained by removing a full connection layer in the VGG16 deep convolutional neural network;
the back end comprises a split branch decoder and an embedded branch decoder; the input end of the split branch decoder and the input end of the embedded branch decoder are connected with the output end of the encoder; the output end of the split branch decoder and the output end of the embedded branch decoder are connected with the input end of the post-processing module;
the split branch decoder is used for outputting a leakage electrical abnormal region identification result;
the embedded branch decoder is used for outputting mask images of leakage electrical abnormal areas;
the post-processing module is used for carrying out clustering processing on the mask images of the leakage electrical abnormal region, combining the clustering result with the images output by the segmentation branch decoder to obtain a classification result of the leakage electrical abnormal region, and determining whether the leakage abnormal resistivity is the same according to the visual characteristics of the abnormal region; extracting leakage electrical abnormal characteristics and combining the leakage electrical abnormal area mask image to determine leakage electrical abnormal conditions.
3. The method for identifying electrical anomalies in dam leakage according to claim 2, further comprising, prior to acquiring the apparent resistivity image of the dam under test:
constructing the end-to-end deep learning model;
acquiring a plurality of apparent resistivity historical images of the dam;
marking leakage electrical property abnormal areas and marking types of the leakage electrical property abnormal areas in the plurality of visual resistivity historical images to obtain a plurality of visual resistivity historical marking images;
and training the end-to-end deep learning model by taking the apparent resistivity historical image as input and taking a plurality of apparent resistivity historical labeling images as output to obtain the dam leakage electrical anomaly identification model.
4. A method for identifying an electrical anomaly of a dam leakage according to claim 3, wherein the label is an oval frame or a square frame.
5. A dam leakage electrical anomaly identification system, comprising:
the apparent resistivity image acquisition module is used for acquiring an apparent resistivity image of the dam to be tested;
the leakage electrical property abnormal region identification module is used for inputting the apparent resistivity image of the dam to be tested into a dam leakage electrical property abnormal identification model to determine the leakage electrical property abnormal condition in the dam to be tested; the dam leakage electrical anomaly identification model is obtained by training an end-to-end deep learning model by using the marked apparent resistivity image; the leaky electrical anomaly condition includes a number of leaky electrical anomaly regions and a location of each leaky electrical anomaly region.
6. An electronic device comprising a memory for storing a computer program and a processor that runs the computer program to cause the electronic device to perform a dam leakage electrical anomaly identification method according to any one of claims 1 to 4.
7. The electronic device of claim 6, wherein the memory is a readable storage medium.
CN202310724771.4A 2023-06-16 2023-06-16 Dam leakage electrical anomaly identification method and system and electronic equipment Pending CN116740687A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310724771.4A CN116740687A (en) 2023-06-16 2023-06-16 Dam leakage electrical anomaly identification method and system and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310724771.4A CN116740687A (en) 2023-06-16 2023-06-16 Dam leakage electrical anomaly identification method and system and electronic equipment

Publications (1)

Publication Number Publication Date
CN116740687A true CN116740687A (en) 2023-09-12

Family

ID=87914674

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310724771.4A Pending CN116740687A (en) 2023-06-16 2023-06-16 Dam leakage electrical anomaly identification method and system and electronic equipment

Country Status (1)

Country Link
CN (1) CN116740687A (en)

Similar Documents

Publication Publication Date Title
CN108447057B (en) SAR image change detection method based on significance and depth convolution network
CN111562108A (en) Rolling bearing intelligent fault diagnosis method based on CNN and FCMC
CN109214349A (en) A kind of object detecting method based on semantic segmentation enhancing
CN108399430B (en) A kind of SAR image Ship Target Detection method based on super-pixel and random forest
CN108171119B (en) SAR image change detection method based on residual error network
CN111709465A (en) Intelligent identification method for rough difference of dam safety monitoring data
CN112766301B (en) Oil extraction machine indicator diagram similarity judging method
CN112395382A (en) Ship abnormal track data detection method and device based on variational self-encoder
Bai et al. An intelligent water level monitoring method based on SSD algorithm
CN114694178A (en) Method and system for monitoring safety helmet in power operation based on fast-RCNN algorithm
CN112149597A (en) River surface flow velocity detection method based on deep learning
CN112906816A (en) Target detection method and device based on optical differential and two-channel neural network
CN115935139A (en) Space field interpolation method for ocean observation data
CN114387332B (en) Pipeline thickness measuring method and device
CN115654381A (en) Water supply pipeline leakage detection method based on graph neural network
CN113627257A (en) Detection method, detection system, device and storage medium
Chou et al. SHM data anomaly classification using machine learning strategies: A comparative study
CN111242028A (en) Remote sensing image ground object segmentation method based on U-Net
CN117372854A (en) Real-time detection method for hidden danger diseases of deep water structure of dam
CN117041972A (en) Channel-space-time attention self-coding based anomaly detection method for vehicle networking sensor
CN115184054B (en) Mechanical equipment semi-supervised fault detection and analysis method, device, terminal and medium
CN116912240A (en) Mutation TP53 immunology detection method based on semi-supervised learning
CN111814696A (en) Video ship target detection method based on improved YOLOv3
CN116740687A (en) Dam leakage electrical anomaly identification method and system and electronic equipment
CN116129327A (en) Infrared vehicle detection method based on improved YOLOv7 algorithm

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