CN110929618B - Potential safety hazard detection and assessment method for power distribution network crossing type building - Google Patents

Potential safety hazard detection and assessment method for power distribution network crossing type building Download PDF

Info

Publication number
CN110929618B
CN110929618B CN201911118585.6A CN201911118585A CN110929618B CN 110929618 B CN110929618 B CN 110929618B CN 201911118585 A CN201911118585 A CN 201911118585A CN 110929618 B CN110929618 B CN 110929618B
Authority
CN
China
Prior art keywords
potential safety
model
power distribution
distribution network
tower
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.)
Active
Application number
CN201911118585.6A
Other languages
Chinese (zh)
Other versions
CN110929618A (en
Inventor
刘蓓
安义
杜敏
刘珣
陈世金
尚银辉
戚沁雅
周求宽
欧阳文华
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.)
State Grid Corp of China SGCC
Electric Power Research Institute of State Grid Jiangxi Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
Electric Power Research Institute of State Grid Jiangxi Electric Power Co Ltd
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 State Grid Corp of China SGCC, Electric Power Research Institute of State Grid Jiangxi Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN201911118585.6A priority Critical patent/CN110929618B/en
Publication of CN110929618A publication Critical patent/CN110929618A/en
Application granted granted Critical
Publication of CN110929618B publication Critical patent/CN110929618B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/176—Urban or other man-made structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • 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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Data Mining & Analysis (AREA)
  • Strategic Management (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • Computational Linguistics (AREA)
  • Tourism & Hospitality (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Software Systems (AREA)
  • Biophysics (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Game Theory and Decision Science (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Operations Research (AREA)
  • Evolutionary Biology (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Primary Health Care (AREA)
  • Multimedia (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses a potential safety hazard detection and assessment method for a power distribution network crossing type building, which comprises the following steps of: obtaining a remote sensing image data set by establishing a channel environment remote sensing image block set based on Faster-RCNN; extracting characteristic data from channel environment remote sensing image information by establishing a potential safety hazard detection model based on Faster-RCNN power distribution network tower pole construction, and determining a possibility candidate target area; training a potential safety hazard detection model based on Faster-RCNN power distribution network tower pole construction to obtain a learning model, inputting the characteristic data into the learning model, and generating a model output result; the intelligent detection and evaluation method for the potential safety hazards of the power distribution tower pole construction based on the Faster-RCNN is established to detect and risk evaluate the output result and output the evaluation result.

Description

Potential safety hazard detection and assessment method for power distribution network crossing type building
Technical Field
The invention relates to the field of artificial intelligence and ubiquitous power Internet of things, in particular to a potential safety hazard detection and assessment method for a power distribution network crossing type building.
Background
The power distribution network is the last kilometer of the power system for transmitting the electric energy to the users, and potential safety hazards caused by the distribution in the crowd-intensive area cannot be ignored. In recent years, the national power grid company issues and checks and manages the notification of potential safety hazards of a power distribution network, such as three spans (spans of highways, railways and bridges), a fish pond and the like, but the checking modes adopted in the current industry are all manual on-site checking modes, and the problems of large workload, incomplete checking, inaccurate position and the like exist.
With the rapid development of artificial intelligence technology, remote sensing image recognition technology has been widely applied to the fields of satellite transmission, address investigation, city planning and construction, earthquake relief and the like. The potential safety hazards such as three spans and a fish pond are closely related to geographic information, so that if the remote sensing image recognition technology can be applied to the investigation of the potential safety hazards such as three spans and the fish pond, the manual workload can be effectively reduced, and the comprehensiveness and the accuracy of the potential safety hazard investigation can be improved.
Disclosure of Invention
In order to solve the problems, the invention discloses a potential safety hazard detection and assessment method for a crossing building of a power distribution network, which is applied to detection and assessment of potential safety hazards of three-span and cross-fishponds of the power distribution network, and comprises the following steps:
s1: obtaining a remote sensing image dataset by establishing a channel environment remote sensing image block set based on a Faster-RCNN network detection model;
s2: extracting characteristic data from the remote sensing image data set obtained in the step S1 by establishing a power distribution network tower pole construction potential safety hazard detection model based on a Faster-RCNN network detection model, and determining a possibility candidate target area;
s3: training a potential safety hazard detection model based on a Faster-RCNN network detection model power distribution network tower pole construction to obtain a learning model, inputting the characteristic data in the step S2 into the learning model, and generating a model output result;
s4: and detecting and evaluating the output result by establishing an intelligent detection and evaluation method for potential safety hazards of power distribution pole construction based on a Faster-RCNN network detection model, and outputting an evaluation result.
Further, the step S1 further includes the following steps:
classifying and labeling the remote sensing image data set, generating a corresponding class label by the remote sensing image data set, and dividing the remote sensing image data set into a training set and a verification set according to a certain proportion or step length;
the remote sensing image data set contains potential safety hazards of crossing construction of the power distribution network tower poles to be detected;
the potential safety hazards include one or more of railways, highways, and fish ponds.
Further, step S2 further includes the steps of:
s21: sequentially constructing a tower three-span feature extraction sub-model, an RPN (reactive power network) region suggestion framework sub-model and a classification detection position correction sub-model;
s22: and adopting a training set and a verification set to simulate the effects of the tower three-span feature extraction sub-model, the RPN region suggestion framework sub-model and the classification detection position correction sub-model.
Further, the simulation effect of the tower three-span feature extraction sub-model is that the tower three-span feature extraction sub-model is used for extracting features of a training set and a verification set;
the tower three-span feature extraction sub-model adopts at least 13 convolution layers, at least 13 Relu layers and at least 4 pooling layers;
and setting parameters of the convolution layer, and reducing the size of the picture after the feature extraction.
Further, the RPN region suggestion framework sub-model adopts a full convolution network to realize a candidate target region with the possibility of recommendation;
the RPN region proposal framework sub-model comprises a CNN model framework and a convolution layer and a two-layer structure connected behind the CNN model framework; the two-layer structure comprises a classification structure and a target detection positioning structure, wherein the classification structure is used for classifying targets, and the target detection positioning structure is used for accurately positioning possible candidate target areas;
the ROI-Pooling layer in the Faster-RCNN network detection model is used for collecting the extracted characteristic data and calculating a characteristic diagram.
Further, the simulation effect of the classification detection position correction sub-model is to calculate the specific attribution category of each abstract feature by adopting a full connection layer and Softmax and realize regression adjustment of the target detection frame.
Further, in the step S2, a potential safety hazard detection model for constructing a Faster-RCNN power distribution network tower pole is calculated by adopting a potential safety hazard detection model loss function, and the formula is as follows:
Figure BDA0002274775760000021
wherein i represents a candidate frame index, p i Representing the probability that the candidate box is predicted as the target,
Figure BDA0002274775760000022
a calibration value representing a candidate box,/>
Figure BDA0002274775760000031
Representing log losses of two classes, N reg Represent the number of anchor points, N cls Represents the minimum lot size, lambda represents the balance parameter, L reg Represents a smooth L1 loss function, t represents an offset of a prediction candidate frame, t * Representing the actual offset of the calibration frame corresponding to the candidate frame;
Figure BDA0002274775760000032
Figure BDA0002274775760000033
Figure BDA0002274775760000034
further, step S3 further includes the steps of:
s31: selecting a VGG16 weight initialization fast-RCNN network detection model;
performing feature extraction by adopting a VGG16 convolutional neural network based on training on ImageNet, and discarding a full connection layer aiming at classification; performing fast-RCNN network detection model training initialization by adopting the trained VGG16 weight, and continuously training the fast-RCNN network detection model by using the distribution network channel environment remote sensing image set;
s32: and setting parameters of a Faster-RCNN network detection model.
Further, the potential safety hazard detection model loss function is optimized by adopting a random gradient descent method.
Further, step S4 further includes the steps of:
s41: selecting a target area: performing target area detection on the power distribution network channel environment based on a Faster-RCNN network detection model trained by Faster-RCNN, wherein the target area is divided into a starting point and an ending point of highway, railway, fish pond and tower construction thereof; if the starting point and the ending point of the tower construction are not on the same side of the target area, judging that the tower is constructed in a crossing mode, and having potential safety hazards;
s42: detection and evaluation: if one side of the target area contains a starting point and an ending point of tower construction at the same time, judging that the potential safety hazard is a low potential safety hazard;
if the starting point and the ending point of the tower pole construction are respectively distributed on the two sides of the target area, judging the potential safety hazard as a moderate potential hazard;
and if different detection targets contain a specific starting point and a specific ending point of tower pole construction, judging that potential safety hazards existing in the tower pole construction in the power distribution network are high-risk potential hazards.
The invention has the beneficial effects that: according to the intelligent power distribution network tower pole crossing construction remote sensing image multi-potential safety hazard detection model based on the Faster-RCNN, the recall ratio and the precision are effectively improved; and the multi-potential-hazard rapid detection network for the tower pole crossing construction in the power distribution network channel environment is realized, and the potential-hazard detection network is trained by utilizing the intelligent power distribution network channel environment remote sensing image which is independently constructed on the premise of maximum safety, robustness and accuracy. Therefore, the generalization capability of the Faster-RCNN network detection model is trained and improved by utilizing the multi-scale remote sensing image set and the batch regularization method. Aiming at potential safety hazards existing in the crossing construction of the intelligent power distribution network system tower poles, a multi-potential safety hazard detection model based on a Faster-RCNN network detection model is provided, the multi-potential safety hazard detection of the power distribution network tower pole construction is realized, and effective guarantee is provided for the construction safety of the intelligent power distribution network system tower poles.
Drawings
FIG. 1 is a block diagram of a technical route in a preferred embodiment of the present invention;
FIG. 2 is a block diagram of a three-span potential safety hazard detection model for power distribution network tower construction in a preferred embodiment of the invention;
FIG. 3 is a block diagram of detection and evaluation of potential safety hazards of spanning construction of a power distribution network tower in a preferred embodiment of the invention;
FIG. 4 is a feature extraction network of a detection model in a preferred embodiment of the invention;
fig. 5 is a diagram of the RPN network structure in the preferred embodiment of the present invention;
FIG. 6 is a classification and detection model in a preferred embodiment of the invention;
FIG. 7 is a Faster-RCNN network detection model in a preferred embodiment of the invention.
Detailed Description
It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other.
Specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
Referring to fig. 1 to 7, the method for detecting and evaluating potential safety hazards of a crossing building of a power distribution network is applied to detection and evaluation of potential safety hazards of three-span and cross-fishponds of the power distribution network, and is shown in fig. 1 to 3 when the method is applied specifically: the method is applied to a power distribution tower pole construction potential safety hazard assessment system, the system comprises a power distribution channel remote sensing image block set and a power distribution tower pole construction potential safety hazard detection model, and the method comprises the following steps:
s1: obtaining a remote sensing image dataset by establishing a channel environment remote sensing image block set based on a Faster-RCNN network detection model;
s2: extracting characteristic data from the remote sensing image set obtained in the step S1 by establishing a power distribution network tower pole construction potential safety hazard detection model based on a Faster-RCNN network detection model, and determining a possibility candidate target area;
s3: training a potential safety hazard detection model based on a Faster-RCNN network detection model for power distribution network tower pole construction to obtain a learning model, inputting characteristic data into the learning model, and generating a model output result;
s4: and detecting and evaluating the output result by establishing an intelligent detection and evaluation method for potential safety hazards of power distribution pole construction based on a Faster-RCNN network detection model, and outputting an evaluation result.
Specifically, step S1 further includes the steps of:
classifying and labeling the remote sensing image data set, generating a corresponding class label by the remote sensing image data set, and dividing the remote sensing image data set into a training set and a verification set according to step sizes; the training set is train, and the verification set is valid;
train＝[I 1 ,I 2 ,...,I n ]
valid＝[I n+1 ,I n+2 ,...,I N ]
the remote sensing image data set contains potential safety hazards of crossing construction of the power distribution network tower poles to be detected;
the potential safety hazards comprise railways, highways and fishponds, and other potential safety hazards can be added in specific applications.
Specifically, as shown in fig. 5-7, step S2 further includes the steps of:
s21: sequentially constructing a tower three-span feature extraction sub-model, an RPN (reactive power network) region suggestion framework sub-model and a classification detection position correction sub-model;
s22: and adopting a training set and a verification set to simulate the effects of the tower three-span feature extraction sub-model, the RPN region suggestion framework sub-model and the classification detection position correction sub-model.
Specifically, the simulation effect of the tower three-span feature extraction submodel is as follows:
the tower three-span feature extraction sub-model is adopted for extracting features of a training set and a verification set;
the tower three-span feature extraction sub-model adopts 13 convolution layers, 13 Relu layers and 4 pooling layers;
and setting parameters of the convolution layer, and reducing the size of the picture after the feature extraction.
In specific application, the parameters are set as follows:
the configuration of the convolution layer in the feature extraction network is as follows: keenel_size=3, pad=1, stride=1; the setting of the pooling layer is as follows: keenel_size=2, stride=2; the size of the picture after passing through the feature extraction network is reduced to 16 times of the original size
Specifically, the RPN region suggestion framework sub-model adopts a full convolution network to realize a candidate target region of the possibility of recommendation;
the RPN region proposal framework sub-model comprises a CNN model framework and a convolution layer and a two-layer structure connected behind the CNN model framework; the two-layer structure comprises a classification structure and a target detection positioning structure, wherein the classification structure is used for classifying targets, and the target detection positioning structure is used for accurately positioning possible candidate target areas;
the ROI-Pooling layer in the Faster-RCNN network detection model is used for collecting the extracted characteristic data and calculating a characteristic diagram.
Specifically, the simulation effect of the classification detection position correction sub-model is to calculate the specific attribution category of each abstract feature by adopting a full connection layer and Softmax and realize regression adjustment of the target detection frame.
Specifically, in step S2, a potential safety hazard detection model for constructing a tower pole of the fast-RCNN power distribution network is calculated by adopting a loss function of the potential safety hazard detection model, and the formula is as follows:
Figure BDA0002274775760000061
wherein i represents a candidate frame index, p i Representing the probability that the candidate box is predicted as the target,
Figure BDA0002274775760000062
a calibration value representing a candidate box,/>
Figure BDA0002274775760000063
Representing log losses of two classes, N reg Represent the number of anchor points, N cls Represents the minimum lot size, lambda represents the balance parameter, L reg Represents a smooth L1 loss function, t represents an offset of a prediction candidate frame, t * Representing the actual offset of the calibration frame corresponding to the candidate frame;
Figure BDA0002274775760000064
Figure BDA0002274775760000065
Figure BDA0002274775760000066
specifically, step S3 further includes the steps of:
s31: selecting a VGG16 weight initialization fast-RCNN network detection model;
performing feature extraction by adopting a VGG16 convolutional neural network based on training on ImageNet, and discarding a full connection layer aiming at classification; performing fast-RCNN network detection model training initialization by adopting the trained VGG16 weight, and continuously training the fast-RCNN network detection model by using the distribution network channel environment remote sensing image set;
s32: and setting parameters of a Faster-RCNN network detection model.
Specifically, the loss function of the potential safety hazard detection model is optimized by adopting a random gradient descent method, and specific parameters are set: max_iters=10000; learning_rate=0.001; batch_size=64; step_size=4000; momentum=0.9, weight_decay=0.0005.
Specifically, step S4 further includes the steps of:
s41: selecting a target area: performing target area detection on the power distribution network channel environment based on a Faster-RCNN network detection model trained by Faster-RCNN, wherein the target area comprises a highway, a railway or a fish pond; if the starting point and the ending point of the tower construction are not on the same side of the target area, judging that the tower is constructed in a crossing mode, and having potential safety hazards;
s42: detection and evaluation: if one side of the target area contains a starting point and an ending point of tower construction at the same time, judging that the potential safety hazard is a low potential safety hazard;
if the starting point and the ending point of the tower pole construction are respectively distributed on the two sides of the target area, judging the potential safety hazard as a moderate potential hazard;
and if different detection targets contain a specific starting point and a specific ending point of tower pole construction, judging that potential safety hazards existing in the tower pole construction in the power distribution network are high-risk potential hazards.
The above embodiments only describe the optimal use manner of the existing device, and similar common means are used to replace elements in the present embodiment, which all fall into the protection scope.

Claims (7)

1. A potential safety hazard detection and assessment method for a power distribution network crossing type building is characterized by comprising the following steps of: the method comprises the following steps:
s1: obtaining a remote sensing image dataset by establishing a channel environment remote sensing image block set based on a Faster-RCNN network detection model;
s2: extracting characteristic data from the remote sensing image data set obtained in the step S1 by establishing a power distribution network tower pole construction potential safety hazard detection model based on a Faster-RCNN network detection model, and determining a possibility candidate target area;
s3: training a potential safety hazard detection model based on a Faster-RCNN network detection model power distribution network tower pole construction to obtain a learning model, inputting the characteristic data in the step S2 into the learning model, and generating a model output result;
s4: the output result is detected and risk assessed by establishing an intelligent detection and assessment method for potential safety hazards of power distribution pole construction based on a Faster-RCNN network detection model, and an assessment result is output; the step S1 also comprises the following steps:
classifying and labeling the remote sensing image data set, generating a corresponding class label by the remote sensing image data set, and dividing the remote sensing image data set into a training set and a verification set according to a certain proportion or step length;
the remote sensing image data set contains potential safety hazards of crossing construction of the power distribution network tower poles to be detected;
the potential safety hazards comprise one or more of railways, highways and fishponds;
step S2 further comprises the steps of:
s21: sequentially constructing a tower three-span feature extraction sub-model, an RPN (reactive power network) region suggestion framework sub-model and a classification detection position correction sub-model;
s22: performing effect simulation on the tower three-span feature extraction sub-model, the RPN region suggestion framework sub-model and the classification detection position correction sub-model by adopting a training set and a verification set;
step S4 further comprises the steps of:
s41: selecting a target area: the trained Faster-RCNN network detection model detects a target area of the power distribution network channel environment, wherein the target area comprises a highway, a railway or a fish pond; if the starting point and the ending point of the tower construction are not on the same side of the target area, judging that the tower is constructed in a crossing mode, and having potential safety hazards;
s42: detection and evaluation: if one side of the target area contains a starting point and an ending point of tower construction at the same time, judging that the potential safety hazard is a low potential safety hazard;
if the starting point and the ending point of the tower pole construction are respectively distributed on the two sides of the target area, judging the potential safety hazard as a moderate potential hazard;
and if different detection targets contain a specific starting point and a specific ending point of tower pole construction, judging that potential safety hazards existing in the tower pole construction in the power distribution network are high-risk potential hazards.
2. The method for detecting and evaluating potential safety hazards of a power distribution network spanning structure according to claim 1, wherein the method comprises the following steps: the simulation effect of the tower three-span feature extraction sub-model is that the tower three-span feature extraction sub-model is adopted to extract features of a training set and a verification set;
the tower three-span feature extraction sub-model adopts at least 13 convolution layers, at least 13 Relu layers and at least 4 pooling layers;
and setting parameters of the convolution layer, and reducing the size of the picture after the feature extraction.
3. The method for detecting and evaluating potential safety hazards of a power distribution network spanning structure according to claim 1, wherein the method comprises the following steps: the RPN region proposal framework sub-model adopts a full convolution network;
the RPN region proposal framework sub-model comprises a CNN model framework and a convolution layer and a two-layer structure connected behind the CNN model framework; the two-layer structure comprises a classification structure and a target detection positioning structure, wherein the classification structure is used for classifying targets, and the target detection positioning structure is used for accurately positioning a possible candidate target area;
the model of the ROI-Pooling layer in the Faster-RCNN network detection model is used for collecting the extracted characteristic data and calculating a characteristic diagram.
4. A method for detecting and evaluating potential safety hazards of a power distribution network spanning structure according to claim 3, characterized by: the simulation effect of the classification detection position correction sub-model is to calculate the specific attribution category of each abstract feature by adopting a full connection layer and a Softmax classification function and realize regression adjustment of a target detection frame.
5. The method for detecting and evaluating potential safety hazards of a power distribution network spanning structure according to any one of claims 1-4, wherein the method comprises the following steps:
in the step S2, a potential safety hazard detection model for constructing a tower pole of the Faster-RCNN power distribution network is calculated by adopting a potential safety hazard detection model loss function, and the formula is as follows:
Figure QLYQS_1
wherein i represents a candidate frame index, p i Representing the probability that the candidate box is predicted as the target,
Figure QLYQS_2
the calibration values representing the candidate boxes are presented,
Figure QLYQS_3
representing log losses of two classes, N reg Represent the number of anchor points, N cls Represents the minimum lot size, lambda represents the balance parameter, L reg Represents a smooth L1 loss function, t represents an offset of a prediction candidate frame, t * Representing the actual offset of the calibration frame corresponding to the candidate frame;
Figure QLYQS_4
Figure QLYQS_5
Figure QLYQS_6
Figure QLYQS_7
6. the method for detecting and evaluating potential safety hazards of a spanning structure of a power distribution network according to claim 5, wherein the method comprises the following steps:
the step S3 further comprises the following steps:
s31: selecting a VGG16 weight initialization fast-RCNN network detection model, adopting a VGG16 convolutional neural network trained on an ImageNet to perform feature extraction, and discarding a full connection layer aiming at classification; performing fast-RCNN network detection model training initialization by adopting the trained VGG16 weight, and continuously training the fast-RCNN network detection model by using the distribution network channel environment remote sensing image set;
s32: and setting parameters of a Faster-RCNN network detection model.
7. The method for detecting and evaluating potential safety hazards of a spanning structure of a power distribution network according to claim 5, wherein the method comprises the following steps: and the loss function of the potential safety hazard detection model is optimized by adopting a random gradient descent method.
CN201911118585.6A 2019-11-15 2019-11-15 Potential safety hazard detection and assessment method for power distribution network crossing type building Active CN110929618B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911118585.6A CN110929618B (en) 2019-11-15 2019-11-15 Potential safety hazard detection and assessment method for power distribution network crossing type building

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911118585.6A CN110929618B (en) 2019-11-15 2019-11-15 Potential safety hazard detection and assessment method for power distribution network crossing type building

Publications (2)

Publication Number Publication Date
CN110929618A CN110929618A (en) 2020-03-27
CN110929618B true CN110929618B (en) 2023-06-20

Family

ID=69854044

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911118585.6A Active CN110929618B (en) 2019-11-15 2019-11-15 Potential safety hazard detection and assessment method for power distribution network crossing type building

Country Status (1)

Country Link
CN (1) CN110929618B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111950488B (en) * 2020-08-18 2022-07-19 山西大学 Improved Faster-RCNN remote sensing image target detection method

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2009129013A1 (en) * 2008-04-18 2009-10-22 The Boeing Company Assessing conditions of aircraft wiring
WO2014101636A1 (en) * 2012-12-31 2014-07-03 北京邮电大学 Method for evaluating risk in electric power communications network
TW201434004A (en) * 2013-02-19 2014-09-01 Univ Nat Kaohsiung Marine Distribution network enhanced decision-making system with increased distributed generation grid connection safety
CN105787501A (en) * 2015-12-17 2016-07-20 武汉大学 Vegetation classification method capable of automatically selecting features in power transmission line corridor area
CN108564109A (en) * 2018-03-21 2018-09-21 天津大学 A kind of Remote Sensing Target detection method based on deep learning
CN109765462A (en) * 2019-03-05 2019-05-17 国家电网有限公司 Fault detection method, device and the terminal device of transmission line of electricity
CN109977921A (en) * 2019-04-11 2019-07-05 广东电网有限责任公司 A kind of transmission line of electricity perils detecting method
CN110222641A (en) * 2019-06-06 2019-09-10 北京百度网讯科技有限公司 The method and apparatus of image for identification

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2009129013A1 (en) * 2008-04-18 2009-10-22 The Boeing Company Assessing conditions of aircraft wiring
WO2014101636A1 (en) * 2012-12-31 2014-07-03 北京邮电大学 Method for evaluating risk in electric power communications network
TW201434004A (en) * 2013-02-19 2014-09-01 Univ Nat Kaohsiung Marine Distribution network enhanced decision-making system with increased distributed generation grid connection safety
CN105787501A (en) * 2015-12-17 2016-07-20 武汉大学 Vegetation classification method capable of automatically selecting features in power transmission line corridor area
CN108564109A (en) * 2018-03-21 2018-09-21 天津大学 A kind of Remote Sensing Target detection method based on deep learning
CN109765462A (en) * 2019-03-05 2019-05-17 国家电网有限公司 Fault detection method, device and the terminal device of transmission line of electricity
CN109977921A (en) * 2019-04-11 2019-07-05 广东电网有限责任公司 A kind of transmission line of electricity perils detecting method
CN110222641A (en) * 2019-06-06 2019-09-10 北京百度网讯科技有限公司 The method and apparatus of image for identification

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
刘宁.高压输电线路智能检测技术研究与应用.《中国优秀硕士学位论文全文数据库（电子期刊）工程科技Ⅱ辑》.2019,全文. *
基于深度卷积神经网络的遥感影像目标检测;孙梓超 等;《上海航天》;20181025;第35卷(第5期);全文 *

Also Published As

Publication number Publication date
CN110929618A (en) 2020-03-27

Similar Documents

Publication Publication Date Title
Miao et al. Application of LSTM for short term fog forecasting based on meteorological elements
CN106127204A (en) A kind of multi-direction meter reading Region detection algorithms of full convolutional neural networks
Ma et al. A real-time crack detection algorithm for pavement based on CNN with multiple feature layers
CN105493109A (en) Air quality inference using multiple data sources
CN111667101A (en) Personalized electric power field operation path planning method and system integrating high-resolution remote sensing image and terrain
US20210263957A1 (en) Method and apparatus for dividing region, storage medium, and electronic device
CN110910440B (en) Power transmission line length determination method and system based on power image data
CN109492756B (en) Multi-element wire galloping early warning method based on deep learning and related device
CN106849353B (en) Project of transmitting and converting electricity environment monitoring and sensitizing range forecasting system and method
CN112668375B (en) Tourist distribution analysis system and method in scenic spot
CN112801399B (en) Path generation method and device, terminal equipment and storage medium
CN109118020A (en) A kind of subway station energy consumption short term prediction method and its forecasting system
CN111382330A (en) Land property identification method and device, electronic equipment and storage medium
CN112149887A (en) PM2.5 concentration prediction method based on data space-time characteristics
CN110929618B (en) Potential safety hazard detection and assessment method for power distribution network crossing type building
CN116046008A (en) Situation awareness-based route planning method, system and efficiency evaluation device
CN116737857A (en) Road data processing method, related device and medium
Lu et al. An integrated damage modeling and assessment framework for overhead power distribution systems considering tree-failure risks
CN115272656A (en) Environment detection alarm method and device, computer equipment and storage medium
Wang et al. Hybrid model for prediction of carbon monoxide and fine particulate matter concentrations near a road intersection
CN116884222B (en) Short-time traffic flow prediction method for bayonet nodes
CN115511280A (en) Urban flood toughness evaluation method based on multi-mode data fusion
CN115564174A (en) Method, system, computer device and medium for measuring living street space quality
CN113849976B (en) Method, device and equipment for evaluating development intensity of planning land
CN113689053B (en) Strong convection weather overhead line power failure prediction method based on random forest

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
GR01 Patent grant
GR01 Patent grant