CN116862712A - Electric power construction potential safety risk detection method and system based on thunder fusion - Google Patents
Electric power construction potential safety risk detection method and system based on thunder fusion Download PDFInfo
- Publication number
- CN116862712A CN116862712A CN202310836848.7A CN202310836848A CN116862712A CN 116862712 A CN116862712 A CN 116862712A CN 202310836848 A CN202310836848 A CN 202310836848A CN 116862712 A CN116862712 A CN 116862712A
- Authority
- CN
- China
- Prior art keywords
- fusion
- data
- point cloud
- information
- site
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 122
- 230000004927 fusion Effects 0.000 title claims abstract description 67
- 238000001514 detection method Methods 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 claims abstract description 27
- 238000004422 calculation algorithm Methods 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 16
- 238000010801 machine learning Methods 0.000 claims description 15
- 238000013527 convolutional neural network Methods 0.000 claims description 11
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 238000012706 support-vector machine Methods 0.000 claims description 9
- 230000006399 behavior Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- 238000009434 installation Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000002203 pretreatment Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 7
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000007689 inspection Methods 0.000 abstract description 5
- 238000004458 analytical method Methods 0.000 description 8
- 238000012502 risk assessment Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 239000004035 construction material Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000009440 infrastructure construction Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- 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
- Image Analysis (AREA)
Abstract
The application discloses a method and a system for detecting potential safety risk of electric power construction based on thunder fusion, wherein the system comprises the following steps: the laser radar control subsystem is used for acquiring site three-dimensional point cloud data of power grid construction; the vision subsystem is used for acquiring high-definition image information of a power grid construction site; the data fusion subsystem is used for carrying out data fusion on the site three-dimensional point cloud data and the high-definition image information to construct a three-dimensional model of the power grid construction site; the safety risk detection subsystem is used for carrying out safety risk detection according to the three-dimensional model of the power grid construction site; the alarm subsystem is used for carrying out early warning prompt when the safety risk occurs; according to the application, the lightning fusion technology is used for power grid construction safety monitoring, so that the detected target has space information, the risk identification rate is greatly improved, the power grid constructor is helped to find and solve the potential safety risk problem in time, the workload of manual inspection is greatly reduced, the construction efficiency is improved, and the cost is reduced.
Description
Technical Field
The application belongs to the technical field of construction safety risk detection, and particularly relates to a lightning fusion-based electric power construction potential safety risk detection method and system.
Background
Currently, in actual operation of observing and identifying unsafe behaviors of workers on construction sites, the traditional manual inspection method is mainly used for observing, recording and judging whether the workers are safely executing construction work tasks. The technical scheme of identifying and analyzing unsafe behaviors of workers based on computer vision has been developed in a few parts, but the following defects still exist:
the prior art mainly focuses on intelligent recognition of unsafe behaviors of a single type of workers on a construction site, and mostly analyzes unsafe behaviors of the workers by processing single-mode data (such as images), so that analysis and processing of multi-source data cannot be realized.
Disclosure of Invention
The application aims to provide a lightning fusion-based electric power construction potential safety risk detection method and system, which are used for solving the problems existing in the prior art.
In order to achieve the above object, the present application provides a method for detecting potential safety risk of electric power construction based on lightning fusion, comprising the following steps:
scanning a power grid construction site based on a laser radar to acquire site three-dimensional point cloud data;
shooting a power grid construction site based on a high-definition camera to acquire high-definition image information of the power grid construction site;
preprocessing the site three-dimensional point cloud data and the high-definition image information; the pretreatment method comprises denoising, filtering and registering;
carrying out data fusion on the preprocessed site three-dimensional point cloud data and the high-definition image information to obtain fusion data;
performing image classification and target identification on the fusion data based on a machine learning algorithm to acquire target information;
based on the target information, detecting potential safety risks according to safety regulations of the power construction site, generating detection information, classifying and grading the detection information, and obtaining risk grades;
generating early warning information based on the risk level to carry out early warning prompt; and generating and storing a report based on the detection information and the early warning information.
Optionally, the process of performing data fusion on the preprocessed on-site three-dimensional point cloud data and the high-definition image information includes:
mapping each point in the point cloud to a corresponding image pixel position, aligning the site three-dimensional point cloud data with the high-definition image information, and ensuring that the site three-dimensional point cloud data and the high-definition image information represent the same scene under the same coordinate system;
acquiring a corresponding relation between the point cloud and the image based on a feature matching algorithm, and carrying out data registration;
projecting the registered point cloud data onto an image plane to enable the point cloud to be compared and fused with the image;
and fusing the depth information of the point cloud with the color information of the image at each pixel position to form fused data with three-dimensional geometric information and texture information.
Optionally, the machine learning algorithm includes a deep neural network, a convolutional neural network, and a support vector machine, and the process of performing image classification and target recognition on the fused data based on the machine learning algorithm includes:
taking the preprocessed fusion data as input, and training and testing a machine learning model;
performing feature extraction on the fusion data based on a deep neural network or a convolutional neural network;
identifying the target in the fusion data by using the trained model, and outputting the label or the category of the target;
and carrying out image classification according to the labels or the categories of the output targets based on the support vector machine.
Optionally, the process of detecting potential safety risk according to the safety regulations of the electric power construction site comprises:
matching the extracted target information with the safety regulations of the power construction site;
acquiring potential safety risks based on the matching result; the potential safety risk is target information which does not accord with safety regulations, and the target information comprises equipment installation which does not accord with regulations, improper placement of construction objects and illegal behaviors of workers.
Optionally, the classifying and grading the detection information includes:
ranking the detected potential security risks based on the importance and severity of the security provisions;
the detected potential safety risk information is tidied and generalized;
carrying out quantitative or qualitative assessment on each detected potential safety risk according to relevant standards and guidelines, and determining the severity;
setting a grading standard according to the evaluation result;
each potential security risk is determined as a corresponding risk level according to the ranking criteria.
In order to achieve the above purpose, the application provides a lightning fusion-based electric power construction potential safety risk detection system, which comprises a laser radar control subsystem, a vision subsystem, a data fusion subsystem, a safety risk detection subsystem and an alarm subsystem;
the laser radar control subsystem is used for acquiring site three-dimensional point cloud data of power grid construction;
the vision subsystem is used for acquiring high-definition image information of a power grid construction site;
the data fusion subsystem is used for carrying out data fusion on the field three-dimensional point cloud data and the high-definition image information to construct a three-dimensional model of the power grid construction field;
the safety risk detection subsystem is used for carrying out safety risk detection according to the three-dimensional model of the power grid construction site;
the alarm subsystem is used for carrying out early warning prompt when the safety risk occurs.
Optionally, the laser radar control subsystem scans the power grid construction site by using a laser radar, acquires site three-dimensional point cloud data, and transmits the site three-dimensional point cloud data to the data fusion subsystem in real time for processing.
Optionally, the vision subsystem comprises a high-definition camera, the high-definition camera is used for shooting the power grid construction site, high-definition image information of the power grid construction site is obtained, the image information is converted into a digital signal through a vision algorithm, and the digital signal is transmitted to the data fusion subsystem for processing.
Optionally, the data fusion subsystem maps each point in the point cloud to a corresponding image pixel position, so that the on-site three-dimensional point cloud data is aligned with the high-definition image information, and the on-site three-dimensional point cloud data and the high-definition image information are ensured to represent the same scene under the same coordinate system;
acquiring a corresponding relation between the point cloud and the image based on a feature matching algorithm, and carrying out data registration;
projecting the registered point cloud data onto an image plane to enable the point cloud to be compared and fused with the image;
and fusing the depth information of the point cloud with the color information of the image at each pixel position to form fused data with three-dimensional geometric information and texture information, and constructing a three-dimensional model of the power grid construction site.
Optionally, the safety risk detection subsystem adopts a machine learning algorithm to analyze the three-dimensional model of the power grid construction site, and detects potential safety risks existing in the power grid construction site; the machine learning algorithm comprises a deep neural network, a convolutional neural network and a support vector machine.
The application has the technical effects that:
according to the application, the lightning fusion technology is used for power grid construction safety monitoring, so that the detected target has space information, the risk identification rate is greatly improved, the power grid constructor is helped to find and solve the potential safety risk problem in time, the potential safety risk is avoided, the construction safety is greatly improved, the manual inspection workload is greatly reduced, the construction efficiency is improved, and the cost is reduced.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:
fig. 1 is a schematic flow chart of a method for detecting potential safety risks in electric power construction based on radar fusion in an embodiment of the application.
Detailed Description
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.
Example 1
As shown in fig. 1, the embodiment provides a method for detecting potential safety risk in electric power construction based on radar fusion, which includes the following steps:
scanning a power grid construction site based on a laser radar to acquire site three-dimensional point cloud data;
shooting a power grid construction site based on a high-definition camera to acquire high-definition image information of the power grid construction site;
preprocessing the site three-dimensional point cloud data and the high-definition image information; the pretreatment method comprises denoising, filtering and registering;
carrying out data fusion on the preprocessed site three-dimensional point cloud data and the high-definition image information to obtain fusion data;
performing image classification and target identification on the fusion data based on a machine learning algorithm to acquire target information;
based on the target information, detecting potential safety risks according to safety regulations of the power construction site, generating detection information, classifying and grading the detection information, and obtaining risk grades;
generating early warning information based on the risk level to carry out early warning prompt; and generating and storing a report based on the detection information and the early warning information.
In this embodiment, the data collected by the laser radar and the vision system are analyzed and processed by data fusion, where the laser radar can accurately measure the position, size, shape, etc. of the target object, and the vision system can distinguish and classify the appearance features of the target object.
The specific process of data fusion comprises the following steps: registering the point cloud with the image: the point cloud data is aligned with the image information, ensuring that they represent the same scene in the same coordinate system. This may be registered by using feature matching algorithms (e.g., SIFT, SURF, etc.) to find the correspondence between the point cloud and the image.
Projection of point cloud and image: the registered point cloud data is projected onto an image plane for comparison and fusion with the image. Alignment of the point cloud with the image may be achieved by mapping each point in the point cloud to a corresponding pixel location.
Data fusion: and fusing the projected point cloud data with the image information to generate fusion data. And fusing the depth information of the point cloud with the color information of the image at each pixel position to form fused data with three-dimensional geometric information and texture information.
In the process of target detection and recognition, training and optimizing data by adopting a deep learning algorithm to improve the accuracy and the efficiency of recognition, and specifically comprises the following steps:
data preparation: and taking the preprocessed fusion data as input, wherein the fusion data comprises fusion representation of the point cloud and the image information. These data will be used to train and test the machine learning model.
Feature extraction: feature extraction is performed on the fused data using a deep neural network or Convolutional Neural Network (CNN). Deep neural networks and CNNs have the ability to learn advanced features, and can automatically extract useful features from the data.
Target identification: and identifying the target in the fusion data by using the trained model. The deep neural network or CNN can be utilized to classify the target and output the label or class of the target.
Image classification: the entire image is classified using a Support Vector Machine (SVM) or other classification algorithm. This may help identify safety conditions throughout the job site, such as determining if there is a potential safety risk.
In the risk assessment and early warning process, potential safety risks can be assessed according to safety regulations and standards of the power construction site, and corresponding early warning information and suggested measures are given. The specific process comprises the following steps:
extracting target information: and performing image classification and target recognition on the preprocessed fusion data by using a machine learning algorithm, and extracting target information. Such target information may include power equipment, construction objects, workers, and the like.
Safety regulation matching: and matching the extracted target information with the safety regulations of the power construction site. Safety regulations are established according to relevant regulations and standards, including potential safety risks and requirements. By comparing the extracted target information with security specifications, potential security risks can be identified.
Potential security risk detection: based on the matching result, target information which is not in compliance with the security regulations, namely potential security risks, are identified. These security risks may involve improper installation of equipment, improper placement of construction objects, worker violations, and the like.
Generating detection information according to potential safety risks, classifying and grading the detection information, acquiring risk grades, and carrying out early warning prompt according to the risk grades, wherein the steps comprise:
risk classification: the potential security risk detected is ranked according to the importance and severity of the security regulations. The risk may be rated according to the likelihood and degree of impact of the risk, and may be classified into various classes, such as high, medium, low, etc.
And (3) detecting information arrangement: the detected potential safety risk information is collated and summarized, and the potential safety risk information comprises the identified target information which does not accord with the safety regulations and corresponding risk description.
Risk assessment: each detected potential security risk is evaluated, taking into account its likelihood and extent of impact. The risk is quantitatively or qualitatively assessed to determine its severity according to relevant criteria and guidelines.
Grading: the potential security risk is classified into different levels according to the result of the risk assessment. Risk may be generally classified as high, medium, low or using a hierarchy of more sub-divisions to reflect its severity and urgency.
Risk level determination: and determining each potential safety risk as a corresponding risk level according to the set grading standard. This may involve comparing the risk assessment with a predefined threshold to determine the risk level to which it belongs.
Risk level notification: the risk level of each potential security risk is notified to the relevant personnel. The risk level can be visually represented by means of symbols, colors or words, so that a person can quickly understand and take corresponding measures.
The embodiment achieves the following technical effects:
risk classification and ranking: classifying and grading the data collected on the power construction site, giving corresponding early warning information and recommended measures according to different risk grades, helping constructors to know the nature and severity of potential risks more clearly, and taking countermeasures.
And (3) high-precision detection: the laser radar can provide high-precision three-dimensional space data, can more accurately detect information such as objects, equipment, personnel and the like on an electric power construction site, and can identify potential safety hazards.
Historical data analysis and optimization: through analysis and optimization of the historical data, the detection precision and efficiency of the application can be further improved, so that the system can more accurately identify potential risks, and the possibility of misjudgment is reduced.
All-weather detection: compared with a vision-based method, the detection of the laser radar is not affected by weather, illumination and other environments, and all-weather safety detection can be realized in various complex environments.
Multimodal data processing: in the implementation of the method, a plurality of different data modes can be adopted, the laser radar can provide three-dimensional point cloud data, and more comprehensive and rich information can be obtained after the laser radar is fused with image data, so that the accuracy and reliability of safety detection are improved.
Real-time monitoring and early warning: the method can realize real-time monitoring and early warning of the power construction site, discover potential safety risks in time and take corresponding measures for processing, so that potential safety accidents are avoided.
And (3) automatic control: the method can realize automatic control on the electric power construction site, feed back detection and identification results to a control system in real time, and automatically adjust construction equipment and construction flow, thereby avoiding the influence of human factors on safety risk and improving the accuracy and efficiency of construction.
Data sharing and analysis: the method can realize sharing and analysis of the data of a plurality of construction sites, and compare and analyze the data of each construction site to obtain more comprehensive and accurate risk early warning and control measures, thereby realizing safety management and monitoring of the whole electric power construction field.
In this embodiment, various suitable algorithms and models may be employed to process the data, such as deep neural networks, convolutional neural networks, support vector machines, and the like. The potential safety risk is rapidly and accurately identified through data processing and analysis, and early warning information and suggested measures are timely given, so that accidents are avoided.
In practical application, the application can be widely applied to various power construction scenes, such as construction of a power transmission line, construction of a transformer substation and the like. By implementing the method, the safety and efficiency of the electric power construction site can be effectively improved, potential safety risks are avoided, the workload of manual inspection can be greatly reduced, the construction efficiency is improved, and the cost is reduced. The technical innovation point of the application is that the laser radar and the vision system are effectively fused, and comprehensive analysis is performed by utilizing a plurality of data modes, so that the accuracy and reliability of safety risk identification and early warning are improved.
The embodiment adopts the data fusion technology, combines the advantages of a laser radar and a vision system, can monitor and identify the electric power construction site in an omnibearing and multi-angle manner, improves the precision and efficiency of safety risk detection and early warning, reduces the occurrence of safety accidents, and is beneficial to improving the safety and efficiency of electric power construction.
In practical application, the application can be widely applied to various power construction scenes, such as construction of a power transmission line, construction of a transformer substation and the like. By implementing the method, the safety and efficiency of the electric power construction site can be effectively improved, potential safety risks are avoided, the workload of manual inspection can be greatly reduced, the construction efficiency is improved, and the cost is reduced. The technical innovation point of the application is that the laser radar and the vision system are effectively fused, and comprehensive analysis is performed by utilizing a plurality of data modes, so that the accuracy and reliability of safety risk identification and early warning are improved, and the application has great application prospect and market value.
Example two
The embodiment provides a detection system for potential safety risk in electric power construction based on lightning fusion, which comprises:
laser radar control subsystem: and scanning a power grid construction site by adopting a laser radar technology, acquiring site three-dimensional point cloud data, and transmitting the point cloud data to a computer for processing in real time through a control system. By adopting the laser radar technology, efficient and accurate three-dimensional point cloud data acquisition can be realized on the power grid construction site.
Vision subsystem: shooting the power grid construction site through a high-definition camera, converting image information into digital signals through a visual algorithm, and transmitting the digital signals to a computer for processing. By adopting the visual system, high-definition image information of the power grid construction site can be obtained, and a foundation is provided for subsequent data processing.
And a data fusion subsystem: and fusing the point cloud data acquired by the laser radar system and the image information acquired by the vision system to form a complete three-dimensional model of the power grid construction site, and analyzing and processing the three-dimensional model through an algorithm. Through the data fusion technology, the point cloud data acquired by the laser radar system and the image information acquired by the vision system can be fused to form a complete three-dimensional model of the power grid construction site, and the accuracy and reliability of data processing are greatly improved.
Security risk detection subsystem: by analyzing the three-dimensional model of the power grid construction site, the potential safety risk existing in the power grid construction site, such as problems of construction equipment, construction materials, worker operation and the like, is detected, and timely repair is performed through system prompt. Through the safety risk detection system, potential safety hazards existing in the power grid construction site can be found in time, and construction safety is guaranteed.
And an alarm subsystem: when a major potential safety hazard exists in the power grid construction site, an alarm signal is timely sent out so as to remind workers to take measures in time and ensure construction safety. By adopting the alarm system, an alarm signal can be sent out in time when major potential safety hazards are found, workers are reminded to take measures, and construction safety is guaranteed.
The laser radar imaging equipment and the visual camera collect data of a construction site at the same time and transmit the data to the data acquisition system for processing and storage. The image processing analysis system analyzes and identifies potential safety hazards existing in the construction site through an algorithm, and real-time monitoring and early warning of the construction site are achieved. When the potential safety risk is detected, the alarm system can immediately give an alarm to remind constructors to take measures in time, so that construction safety is guaranteed.
The embodiment provides a high-efficient, accurate, automatic electric wire netting construction safety risk detecting system, through behind the electric wire netting construction safety monitoring with the thunder vision integration technique for the target that detects has spatial information, improves risk recognition rate greatly to help electric wire netting constructor in time discover and solve potential safe risk problem. The power grid construction safety identification system provided by the system greatly improves the construction safety, and is suitable for advanced concepts such as future digital construction, intelligent construction sites and the like.
The application can automatically monitor and detect the power grid construction site, avoids the problems of error and missing detection existing in manual detection, and improves the working efficiency and the detection accuracy.
The system has wide application range, is suitable for various power grid infrastructure construction sites including power transmission lines, substations, distribution lines and the like, and can provide omnibearing safety guarantee for power grid constructors.
The present application is not limited to the above-mentioned embodiments, and any changes or substitutions that can be easily understood by those skilled in the art within the technical scope of the present application are intended to be included in the scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.
Claims (10)
1. The electric power construction potential safety risk detection method based on the thunder fusion is characterized by comprising the following steps of:
scanning a power grid construction site based on a laser radar to acquire site three-dimensional point cloud data;
shooting a power grid construction site based on a high-definition camera to acquire high-definition image information of the power grid construction site;
preprocessing the site three-dimensional point cloud data and the high-definition image information; the pretreatment method comprises denoising, filtering and registering;
carrying out data fusion on the preprocessed site three-dimensional point cloud data and the high-definition image information to obtain fusion data;
performing image classification and target identification on the fusion data based on a machine learning algorithm to acquire target information;
based on the target information, detecting potential safety risks according to safety regulations of the power construction site, generating detection information, classifying and grading the detection information, and obtaining risk grades;
generating early warning information based on the risk level to carry out early warning prompt; and generating and storing a report based on the detection information and the early warning information.
2. The lightning fusion-based power construction potential safety risk detection method according to claim 1, wherein the process of carrying out data fusion on the preprocessed on-site three-dimensional point cloud data and the high-definition image information comprises the following steps:
mapping each point in the point cloud to a corresponding image pixel position, aligning the site three-dimensional point cloud data with the high-definition image information, and ensuring that the site three-dimensional point cloud data and the high-definition image information represent the same scene under the same coordinate system;
acquiring a corresponding relation between the point cloud and the image based on a feature matching algorithm, and carrying out data registration;
projecting the registered point cloud data onto an image plane to enable the point cloud to be compared and fused with the image;
and fusing the depth information of the point cloud with the color information of the image at each pixel position to form fused data with three-dimensional geometric information and texture information.
3. The method for detecting potential safety risk of electric power construction based on the thunder fusion according to claim 1, wherein the machine learning algorithm comprises a deep neural network, a convolutional neural network and a support vector machine, and the process of performing image classification and target recognition on the fusion data based on the machine learning algorithm comprises the following steps:
taking the preprocessed fusion data as input, and training and testing a machine learning model;
performing feature extraction on the fusion data based on a deep neural network or a convolutional neural network;
identifying the target in the fusion data by using the trained model, and outputting the label or the category of the target;
and carrying out image classification according to the labels or the categories of the output targets based on the support vector machine.
4. The lightning fusion-based power construction potential safety risk detection method according to claim 1, wherein the process of performing potential safety risk detection according to safety regulations of a power construction site comprises:
matching the extracted target information with the safety regulations of the power construction site;
acquiring potential safety risks based on the matching result; the potential safety risk is target information which does not accord with safety regulations, and the target information comprises equipment installation which does not accord with regulations, improper placement of construction objects and illegal behaviors of workers.
5. The method for detecting potential safety risk of power construction based on the thunder fusion according to claim 1, wherein the process of classifying and grading the detection information comprises:
ranking the detected potential security risks based on the importance and severity of the security provisions;
the detected potential safety risk information is tidied and generalized;
carrying out quantitative or qualitative assessment on each detected potential safety risk according to relevant standards and guidelines, and determining the severity;
setting a grading standard according to the evaluation result;
each potential security risk is determined as a corresponding risk level according to the ranking criteria.
6. The electric power construction potential safety risk detection system based on the thunder fusion is characterized by comprising a laser radar control subsystem, a vision subsystem, a data fusion subsystem, a safety risk detection subsystem and an alarm subsystem;
the laser radar control subsystem is used for acquiring site three-dimensional point cloud data of power grid construction;
the vision subsystem is used for acquiring high-definition image information of a power grid construction site;
the data fusion subsystem is used for carrying out data fusion on the field three-dimensional point cloud data and the high-definition image information to construct a three-dimensional model of the power grid construction field;
the safety risk detection subsystem is used for carrying out safety risk detection according to the three-dimensional model of the power grid construction site;
the alarm subsystem is used for carrying out early warning prompt when the safety risk occurs.
7. The lightning fusion-based power construction potential safety risk detection system according to claim 6, wherein the laser radar control subsystem scans a power grid construction site by using a laser radar, acquires site three-dimensional point cloud data, and transmits the site three-dimensional point cloud data to the data fusion subsystem for processing in real time.
8. The lightning fusion-based power construction potential safety risk detection system according to claim 6, wherein the vision subsystem comprises a high-definition camera, the high-definition camera is used for shooting a power grid construction site, high-definition image information of the power grid construction site is obtained, the image information is converted into a digital signal through a vision algorithm, and the digital signal is transmitted to the data fusion subsystem for processing.
9. The system for detecting potential safety risk of electric power construction based on the thunder fusion according to claim 6, wherein the data fusion subsystem maps each point in the point cloud to a corresponding image pixel position, so that the on-site three-dimensional point cloud data is aligned with the high-definition image information, and the on-site three-dimensional point cloud data and the high-definition image information represent the same scene in the same coordinate system;
acquiring a corresponding relation between the point cloud and the image based on a feature matching algorithm, and carrying out data registration;
projecting the registered point cloud data onto an image plane to enable the point cloud to be compared and fused with the image;
and fusing the depth information of the point cloud with the color information of the image at each pixel position to form fused data with three-dimensional geometric information and texture information, and constructing a three-dimensional model of the power grid construction site.
10. The lightning fusion-based power construction potential safety risk detection system according to claim 6, wherein the safety risk detection subsystem analyzes the three-dimensional model of the power grid construction site by adopting a machine learning algorithm to detect potential safety risks existing in the power grid construction site; the machine learning algorithm comprises a deep neural network, a convolutional neural network and a support vector machine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310836848.7A CN116862712A (en) | 2023-07-07 | 2023-07-07 | Electric power construction potential safety risk detection method and system based on thunder fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310836848.7A CN116862712A (en) | 2023-07-07 | 2023-07-07 | Electric power construction potential safety risk detection method and system based on thunder fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116862712A true CN116862712A (en) | 2023-10-10 |
Family
ID=88218725
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310836848.7A Pending CN116862712A (en) | 2023-07-07 | 2023-07-07 | Electric power construction potential safety risk detection method and system based on thunder fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116862712A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117371949A (en) * | 2023-10-24 | 2024-01-09 | 国网山东省电力公司建设公司 | Three-dimensional visual model-based power transmission line construction safety monitoring method and system |
| CN118297755A (en) * | 2024-04-01 | 2024-07-05 | 天津大学 | Building construction analysis management and control method and system based on Internet of things and big data technology |
-
2023
- 2023-07-07 CN CN202310836848.7A patent/CN116862712A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117371949A (en) * | 2023-10-24 | 2024-01-09 | 国网山东省电力公司建设公司 | Three-dimensional visual model-based power transmission line construction safety monitoring method and system |
| CN117371949B (en) * | 2023-10-24 | 2024-05-31 | 国网山东省电力公司建设公司 | Three-dimensional visual model-based power transmission line construction safety monitoring method and system |
| CN118297755A (en) * | 2024-04-01 | 2024-07-05 | 天津大学 | Building construction analysis management and control method and system based on Internet of things and big data technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116862712A (en) | Electric power construction potential safety risk detection method and system based on thunder fusion | |
| CN110850723B (en) | Fault diagnosis and positioning method based on transformer substation inspection robot system | |
| CN108537154A (en) | Transmission line of electricity Bird's Nest recognition methods based on HOG features and machine learning | |
| CN112528979B (en) | Transformer substation inspection robot obstacle distinguishing method and system | |
| CN105404867B (en) | A kind of substation isolating-switch state identification method of view-based access control model | |
| CN104994334A (en) | Automatic substation monitoring method based on real-time video | |
| CN111044149A (en) | Method and device for detecting temperature abnormal point of voltage transformer and readable storage medium | |
| CN112818806A (en) | Transformer substation inspection robot auxiliary navigation method based on deep learning | |
| CN112949457A (en) | Maintenance method, device and system based on augmented reality technology | |
| CN107657682A (en) | A kind of power transformation method for inspecting based on augmented reality | |
| CN111091104A (en) | Target object protection detection method, device, equipment and storage medium | |
| CN117723739B (en) | Quality analysis method and system for low-carbon lubricating oil | |
| CN118429282A (en) | Power cable pipeline water seepage detection method based on inspection robot | |
| CN114330477B (en) | Power equipment defect detection system and method based on mixed reality equipment | |
| CN113706721A (en) | Elevator inspection method and system based on augmented reality technology | |
| CN116363397A (en) | Equipment fault checking method, device and inspection system | |
| CN113780224A (en) | Transformer substation unmanned inspection method and system | |
| CN116579609B (en) | Illegal operation analysis method based on inspection process | |
| CN116912721B (en) | Power distribution network equipment body identification method and system based on monocular stereoscopic vision | |
| CN206546417U (en) | A kind of GIS switch fault automatic recognition systems based on picture recognition | |
| CN117726239B (en) | Engineering quality acceptance actual measurement method and system | |
| CN112907105B (en) | Early warning method and device based on service scene | |
| CN114445850B (en) | Depth image-based safety monitoring method for power producer | |
| CN118447594A (en) | Construction safety inspection method for farmland power station | |
| CN118521935A (en) | Marketing small-sized operation site behavior recognition system, method, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |