CN113705364B - Power transmission line external hidden danger early warning system and method based on artificial intelligence - Google Patents
Power transmission line external hidden danger early warning system and method based on artificial intelligence Download PDFInfo
- Publication number
- CN113705364B CN113705364B CN202110893024.4A CN202110893024A CN113705364B CN 113705364 B CN113705364 B CN 113705364B CN 202110893024 A CN202110893024 A CN 202110893024A CN 113705364 B CN113705364 B CN 113705364B
- Authority
- CN
- China
- Prior art keywords
- monitoring
- module
- video
- hidden danger
- external hidden
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The power transmission line external hidden danger early warning system and method based on artificial intelligence comprise front-end equipment and a monitoring substation host which are installed on a high-voltage power transmission line tower pole, wherein the front-end equipment is connected with the monitoring substation host, the monitoring substation host is in communication connection with a remote background monitoring system, and the monitoring substation host and the background monitoring system are connected with a neural network module. And the foreign matter detection is carried out by utilizing the lightweight network deployed in the core processing operation module, and different warning information is sent to the mobile terminal, the monitoring substation host and the warning device of the front-end equipment according to the foreign matter detection condition of the background monitoring system. The core processing operation module and the video server in the background monitoring system are all provided with intelligent detection algorithms for intelligently detecting external hidden dangers, so that two defense lines for detecting the external hidden dangers are formed, the external hidden dangers can be timely and quickly found, meanwhile, the false detection and the missing detection caused by a single intelligent detection algorithm are effectively reduced, and the efficiency and the accuracy rate of automatic monitoring are improved.
Description
Technical Field
The invention relates to the field of power transmission line safety monitoring, in particular to a power transmission line external hidden danger early warning system and method based on artificial intelligence.
Background
With the continuous increase of the demand of power transmission in China and the continuous enlargement of the scale of a power system, the safety and the stability of a power transmission line in the power system are more and more important. Most of the power transmission lines are erected in natural environments and engineering fields, and are inevitably damaged by external hidden dangers such as cranes, forklifts, mountain fires and the like. If the external hidden trouble objects cannot be found in time and correspondingly processed and removed, unexpected electric power accidents can be caused, line fault tripping is caused, and the electricity utilization of important loads such as factories and hospitals and the normal operation of the society are influenced. Therefore, it is very important and necessary to find the potential damage object caused by external force to cause line fault in time.
At present, the detection of external hidden dangers of a power transmission line is mainly manually patrolled and unmanned aerial vehicle patrolled. Traditional manual inspection is mainly used for inspecting potential areas through experienced electric power workers. The method is limited by geographical environment and weather conditions, not only has long line patrol time and low detection efficiency, but also is easy to threaten personal safety to cause accidents due to uncontrollable factors such as geological disasters and the like; although unmanned aerial vehicle patrols and examines and breaks through the restriction of factors such as geographical environment, nevertheless because current unmanned aerial vehicle does not possess the ability of the outside hidden danger thing of intelligent recognition, patrols and examines the picture of shooing back and still need screen through experienced electric power staff, and the detection flow is not only boring, need consume a large amount of time moreover, can not in time just discover outside hidden danger thing fast. In addition, longer screening times can be visually fatiguing, leading to false positives and false negatives. Compared with the two traditional detection methods, the method for detecting the external hidden danger based on the computer vision technology can greatly reduce the discrimination time and effectively improve the discrimination efficiency and the accuracy, and has become the research focus in the field of the current safety monitoring of the power transmission line. However, researchers are mainly concerned with the study of detection algorithms for external hazards, and the study of monitoring systems based on detection algorithms is rarely concerned. Therefore, it is very important and necessary to research an intelligent monitoring system for external hidden troubles of the power transmission line, which can be timely and fast.
Disclosure of Invention
The invention aims to solve the technical problem of providing a power transmission line external hidden danger early warning system and method based on artificial intelligence.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
the transmission line external hidden danger early warning system based on artificial intelligence comprises front-end equipment and a monitoring substation host which are installed on a high-voltage transmission line tower pole, wherein the front-end equipment is connected with the monitoring substation host, the monitoring substation host is in communication connection with a remote background monitoring system, the monitoring substation host and the background monitoring system are connected with a neural network module, the front-end equipment is used for collecting on-site environment images and sending collected data to the monitoring substation host, and the monitoring substation host judges whether foreign objects invade or not after preprocessing and intelligent analysis and monitoring are carried out on the images and controls the front-end equipment to carry out on-site warning.
The front-end equipment and the monitoring substation host are integrated in the host and are uniformly arranged on a tower pole of a high-voltage transmission line
The front-end equipment comprises a pan-tilt camera and an alarm, the pan-tilt camera is connected with the input end of a video acquisition module in the monitoring sub-station host, a core processing operation module and a communication and transmission module are further arranged in the monitoring sub-station host, the input end of the core processing operation module is connected with the output end of the video acquisition module, the output end of the core processing operation module is connected with the alarm, the core processing operation module is in communication connection with the communication and transmission module, and the communication and transmission module is connected with a background monitoring system.
A pan-tilt camera in the front-end equipment can respectively adopt a high-definition network gun camera and an automatic tracking ball camera according to different detection areas.
The video acquisition module in the monitoring substation host can acquire video streams of video signals of front-end equipment, acquire a video stream packet containing a certain number of frames, decode the video stream packet according to different video stream coding modes, and send the acquired current frame image as an input signal to the core processing operation module of the monitoring substation host.
The communication and transmission module in the monitoring substation host adopts a stable and reliable communication chip circuit module, is provided with a special wireless communication antenna to enlarge the signal intensity, and is used for transmitting the detection and analysis result output by the core processing operation module to the background monitoring system.
The neural network module comprises a high-precision network model, an external hidden danger data set and a light-weight network model, the external hidden danger data set is used for training the high-precision network model, the high-precision network model is deployed in a background monitoring system after being trained, the high-precision network model obtains the light-weight network model after being subjected to light-weight operation, and the light-weight network model is deployed in a core processing operation module.
The high-precision network model and the lightweight network model structure in the neural network module are composed of a backbone network, a detector neck and a detector head.
The background monitoring system comprises a database server, a Web server and a video server, wherein a communication and transmission module is in communication connection with the three servers, a trained high-precision network model is deployed in the video server, the video server is used for receiving a framing detection result image signal sent by a monitoring substation host and further analyzing the framing detection result image signal, the high-precision network model in the video server detects the image signal again through a detection algorithm, a corresponding warning grade signal is sent to the monitoring substation host according to the detection result, the monitoring substation host controls an alarm to send a corresponding audible and visual alarm signal, the Web server is used for visually displaying the detection result and sending information to a mobile phone and a personal computer of related personnel, and the database server stores the result in a data file.
The database server and the video server carry out data interaction through the Web server.
The Web server is provided with a human-computer interaction interface, and a video playing module, a data query module, a statistical analysis module and an equipment management module are arranged in the Web server.
The core processing operation module comprises a storage chip circuit unit, a power supply circuit unit, an Ethernet transceiving circuit unit, a serial port circuit unit, a wireless transceiving circuit unit and a watchdog circuit unit, a lightweight network model is stored through the storage chip circuit unit, and data transmission is carried out with the outside through the Ethernet transceiving circuit unit, the serial port circuit unit and the wireless transceiving circuit unit.
The monitoring substation host is electrically connected with the power module, the power module comprises a photovoltaic panel, a photovoltaic power management module and a storage battery pack, the photovoltaic panel and the storage battery pack are connected through the photovoltaic power management module, and the photovoltaic power management module is connected with the monitoring substation host.
The early warning method using the artificial intelligence-based power transmission line external hidden danger early warning system comprises the following steps:
the method comprises the following steps of firstly, collecting video data of the external hidden danger objects in different areas, different weather conditions, different illumination conditions and different seasons, and introducing the video data into a video server in a background monitoring system for manual marking to form an external hidden danger data set;
secondly, training an external hidden-danger object detection model by using a high-precision target detection algorithm in a deep learning platform, and storing the trained model into a video server;
thirdly, carrying out lightweight processing on the trained detection model of the external hidden danger by using a model compression and prediction library in the deep learning platform, converting the trained large model into a small model, and storing the small model into a monitoring substation host;
fourthly, according to different areas, video monitoring of the surrounding environment of the power transmission line is carried out by using the debugged front-end equipment and the monitoring substation host, and a video stream obtained by monitoring is transmitted to a video server and a database server of the background monitoring system through a communication and transmission module of the monitoring substation host, so that real-time monitoring and archiving are facilitated;
step five, a video acquisition module of the monitoring substation host machine extracts the framing images of the monitoring video stream, a core processing operation module calls a lightweight neural network model to detect the extracted framing images according to a time sequence, and when an external hidden danger is detected, the current frame image is stored and the monitoring information of the image is sent to a video server;
step six, the video server receives a current frame image of the power transmission line with the external hidden danger, calls a high-precision detection neural network model to detect the image again, sends a general level warning signal with time information to the mobile terminal if the confidence coefficient of the external hidden danger is detected to be lower than a preset threshold value, and respectively stores a video stream containing the image and a warning comparison result of the rear end of the substation in a lowest warning folder and a warning record folder of the database server according to the time sequence;
if no external hidden trouble is detected, only the video stream containing the image and the early warning comparison result of the rear end of the substation are respectively stored in a normal folder and an early warning record folder of a database server according to the time sequence;
if the confidence coefficient of the detected external hidden danger is higher than the preset threshold value, a serious grade warning signal with time information is sent to the mobile terminal, and a warning signal is sent to the monitoring substation host, the substation controls the warning device to send an audible and visual warning signal through a bus protocol, and video streams containing the images and the warning comparison results at the rear end of the substation are respectively stored in a serious warning folder and a warning recording folder of the database server according to the time sequence;
and step seven, after receiving the warning information through the mobile terminal, the monitoring personnel call the stored monitoring video from the Web server in the background monitoring system to check, and inform the inspection personnel of carrying out on-site inspection and emergency treatment.
The invention provides a power transmission line external hidden danger early warning system and method based on artificial intelligence, which have the following beneficial effects:
1. the external hidden danger which may damage the safety of the power transmission line can be quickly and timely discovered;
2. by combining the lightweight embedded network reasoning model in the monitoring substation host and the large-scale high-precision network detection model in the video server, false detection and missing detection caused by a single neural network model can be prevented, and the efficiency and the accuracy rate of automatic monitoring are effectively improved.
Drawings
The invention is further illustrated by the following examples in conjunction with the accompanying drawings:
FIG. 1 is a block diagram of a detection system in accordance with an exemplary embodiment of the present invention;
FIG. 2 is a functional block diagram of a Web server in accordance with an exemplary embodiment of the present invention;
FIG. 3 is a flow chart of a detection method in an exemplary embodiment of the invention;
FIG. 4 is a diagram of a high-accuracy neural network model architecture in accordance with an exemplary embodiment of the present invention;
FIG. 5 is a diagram of a lightweight neural network model architecture in accordance with an exemplary embodiment of the present invention.
Detailed Description
The invention will be further illustrated in detail with reference to the following specific examples:
as shown in fig. 1, the external hidden danger early warning system of the power transmission line based on artificial intelligence, including front-end equipment and a monitoring substation host installed on a high-voltage power transmission line tower pole, the front-end equipment is connected with the monitoring substation host, the monitoring substation host is in communication connection with a remote background monitoring system, the monitoring substation host, the background monitoring system is connected with a neural network module, the front-end equipment is used for collecting on-site environment images, and transmits the collected data to the monitoring substation host, the monitoring substation host judges whether foreign objects invade after preprocessing and intelligent analysis monitoring are carried out on the images, and controls the front-end equipment to carry out on-site warning.
The front-end equipment is used for detecting foreign object invasion, field alarming and transmission line field environment image information acquisition and sending acquired data to the monitoring substation host; the monitoring sub-station host is mainly used for preprocessing image information, intelligently analyzing and detecting images and communicating the sub-station host with a background monitoring system.
The front-end equipment comprises a pan-tilt camera and an alarm, the pan-tilt camera is connected with the input end of a video acquisition module in the monitoring sub-station host, a core processing operation module and a communication and transmission module are further arranged in the monitoring sub-station host, the input end of the core processing operation module is connected with the output end of the video acquisition module, the output end of the core processing operation module is connected with the alarm, the core processing operation module is in communication connection with the communication and transmission module, and the communication and transmission module is connected with a background monitoring system.
The pan-tilt camera adopts an E series 5-inch infrared 1080P coaxial high-definition intelligent ball machine produced by Hai Kangwei vision.
The Core processing operation module in the monitoring substation host adopts a Core-3399Pro-JD4 six-Core high-performance AI Core board.
The communication and transmission module adopts an ME3760 chip module based on an ARM framework of Zhongxing company, and the module supports the whole network communication frequency band.
A pan-tilt camera in the front-end equipment can respectively adopt a high-definition network gun camera and an automatic tracking ball camera according to different detection areas.
The video acquisition module in the monitoring substation host can acquire video streams of video signals of front-end equipment, acquire a video stream packet containing a certain number of frames, decode the video stream packet according to different video stream coding modes, and send the acquired current frame image as an input signal to the core processing operation module of the monitoring substation host.
The communication and transmission module in the monitoring substation host adopts a stable and reliable communication chip circuit module, is provided with a special wireless communication antenna to enlarge the signal intensity, and is used for transmitting the detection and analysis result output by the core processing operation module to the background monitoring system.
The neural network module comprises a high-precision network model, an external hidden danger data set and a light-weight network model, the external hidden danger data set is used for training the high-precision network model, the high-precision network model is deployed in a background monitoring system after being trained, the high-precision network model obtains the light-weight network model after being subjected to light-weight operation, and the light-weight network model is deployed in a core processing operation module.
The high-precision network model and the lightweight network model structure in the neural network module are composed of a backbone network, a detector neck and a detector head.
The background monitoring system comprises a database server, a Web server and a video server, wherein a communication and transmission module is in communication connection with the three servers, a trained high-precision network model is deployed in the video server, the video server is used for receiving a framing detection result image signal sent by a monitoring substation host and further analyzing the framing detection result image signal, the high-precision network model in the video server detects the image signal again through a detection algorithm, a corresponding warning grade signal is sent to the monitoring substation host according to the detection result, the monitoring substation host controls an alarm to send a corresponding audible and visual alarm signal, the Web server is used for visually displaying the detection result and sending information to a mobile phone and a personal computer of related personnel, and the database server stores the result in a data file.
The database server and the video server carry out data interaction through the Web server.
As shown in fig. 2, the Web server is provided with a human-computer interaction interface, and a video playing module, a data query module, a statistical analysis module, and an equipment management module are arranged in the Web server.
The core processing operation module comprises a storage chip circuit unit, a power supply circuit unit, an Ethernet transceiving circuit unit, a serial port circuit unit, a wireless transceiving circuit unit and a watchdog circuit unit, a lightweight network model is stored through the storage chip circuit unit, and data transmission is carried out with the outside through the Ethernet transceiving circuit unit, the serial port circuit unit and the wireless transceiving circuit unit.
The monitoring substation host is electrically connected with the power supply module, the power supply module comprises a photovoltaic panel, a photovoltaic power supply management module and a storage battery pack, the photovoltaic panel and the storage battery pack are connected through the photovoltaic power supply management module, the photovoltaic power supply management module is connected with the monitoring substation host, and the power supply module is used for ensuring normal power supply of the monitoring substation host.
As shown in fig. 3, the early warning method using the artificial intelligence-based power transmission line external hidden danger early warning system includes the following steps:
collecting video data of 5 external hidden danger objects such as engineering machinery, mountain fire, smoke and the like in different areas, different weather conditions, different illumination conditions and different seasons, and introducing the video data into a video server in a background monitoring system for manual labeling to form an external hidden danger data set;
step two, dividing a data set into a training set and a testing set according to the proportion of 8:2, inputting the training set into a PP YOLOv2 target detection algorithm in a hundred-degree PaddleDetection deep learning platform to train an external hidden-danger detection model, wherein a network structure diagram is shown in FIG. 4, and storing the trained model into a video server;
step three, using a highly integrated Paddle reference and Paddle Lite model compression and prediction library in a Baidu PaddleDetection deep learning framework to compress and quantize the trained large model, converting the trained large model into a PP-YOLO tiny model, and storing the PP-YOLO tiny model into a storage unit of a monitoring substation host, wherein a network structure diagram is shown in FIG. 5;
fourthly, according to different areas, video monitoring of the surrounding environment of the power transmission line is carried out by using the debugged front-end equipment and the monitoring substation host, and a video stream obtained by monitoring is transmitted to a video server and a database server of a rear-end server through a communication and transmission module of the monitoring substation host, so that real-time monitoring and archiving are facilitated;
step five, a video acquisition module of the monitoring substation host extracts the framing images of the monitoring video stream, a storage unit calls a depth-compressed PP-YOLO tiny lightweight neural network model to detect the extracted framing images according to a time sequence, when the external hidden danger is detected, the current frame image is stored, and the power transmission line image with the external hidden danger is sent to a video server;
step six, the video server receives a current frame image of the power transmission line with the external hidden danger, calls a high-precision detection neural network model to detect the image again, sends a general level warning signal with time information to the mobile terminal if the confidence coefficient of the external hidden danger is detected to be lower than a preset threshold value, and respectively stores a video stream containing the image and a warning comparison result of the rear end of the substation in a lowest warning folder and a warning record folder of the database server according to the time sequence;
if no external hidden trouble is detected, only the video stream containing the image and the early warning comparison result of the rear end of the substation are respectively stored in a normal folder and an early warning record folder of a database server according to the time sequence;
if the confidence coefficient of the detected external hidden danger is higher than the preset threshold value, a serious grade warning signal with time information is sent to the mobile terminal, and a warning signal is sent to the monitoring substation host, the substation controls the warning device to send an audible and visual warning signal through a bus protocol, and video streams containing the images and the warning comparison results at the rear end of the substation are respectively stored in a serious warning folder and a warning recording folder of the database server according to the time sequence;
and step seven, after receiving the severe warning information through the mobile terminal, the monitoring personnel call the stored monitoring video from the back-end server to check, and inform the inspection personnel of carrying out on-site inspection and emergency treatment.
Claims (6)
1. The power transmission line external hidden danger early warning system based on artificial intelligence is characterized by comprising front-end equipment and a monitoring substation host which are installed on a tower pole of a high-voltage power transmission line, wherein the front-end equipment is connected with the monitoring substation host, the monitoring substation host is in communication connection with a remote background monitoring system, the monitoring substation host and the background monitoring system are connected with a neural network module, the front-end equipment is used for collecting an on-site environment image and sending the collected data to the monitoring substation host, and the monitoring substation host judges whether foreign objects invade or not after preprocessing and intelligently analyzing and monitoring the image and controls the front-end equipment to alarm on site;
the front-end equipment comprises a pan-tilt camera and an alarm, the pan-tilt camera is connected with the input end of a video acquisition module in a monitoring sub-station host, a core processing operation module and a communication and transmission module are further arranged in the monitoring sub-station host, the input end of the core processing operation module is connected with the output end of the video acquisition module, the output end of the core processing operation module is connected with the alarm, the core processing operation module is in communication connection with the communication and transmission module, and the communication and transmission module is connected with a background monitoring system;
the neural network module comprises a high-precision network model, an external hidden danger data set and a light-weight network model, the external hidden danger data set is used for training the high-precision network model, the high-precision network model is deployed in a background monitoring system after being trained, the high-precision network model obtains the light-weight network model after being subjected to light-weight operation, and the light-weight network model is deployed in the core processing operation module;
the background monitoring system comprises a database server, a Web server and a video server, wherein a communication and transmission module is in communication connection with the three servers, a trained high-precision network model is deployed in the video server, the video server is used for receiving a framing detection result image signal sent by a monitoring substation host and further analyzing the framing detection result image signal, the high-precision network model in the video server detects the image signal again through a detection algorithm, a corresponding warning grade signal is sent to the monitoring substation host according to the detection result, the monitoring substation host controls an alarm to send a corresponding acousto-optic alarm signal, the Web server is used for visually displaying the detection result and sending information to a mobile phone and a personal computer of related personnel, and the database server stores the result in a data file.
2. The artificial intelligence based power transmission line external hidden danger early warning system according to claim 1, wherein the database server and the video server perform data interaction through a Web server.
3. The artificial intelligence-based power transmission line external hidden danger early warning system according to claim 2, wherein the Web server is provided with a human-computer interaction interface, and a video playing module, a data query module, a statistical analysis module and an equipment management module are arranged in the Web server.
4. The artificial intelligence-based power transmission line external hidden danger early warning system according to claim 1, wherein the core processing operation module comprises a memory chip circuit unit, a power supply circuit unit, an ethernet transceiving circuit unit, a serial port circuit unit, a wireless transceiving circuit unit and a watchdog circuit unit.
5. The artificial intelligence-based power transmission line external hidden danger early warning system according to claim 1, wherein the monitoring substation host is electrically connected with the power module, the power module comprises a photovoltaic panel, a photovoltaic power management module and a storage battery pack, the photovoltaic panel and the storage battery pack are connected through the photovoltaic power management module, and the photovoltaic power management module is connected with the monitoring substation host.
6. The early warning method of the artificial intelligence based transmission line external hidden danger early warning system according to claim 3, comprising the following steps:
the method comprises the following steps of firstly, collecting video data of the external hidden danger objects in different areas, different weather conditions, different illumination conditions and different seasons, and introducing the video data into a video server in a background monitoring system for manual marking to form an external hidden danger data set;
secondly, training an external hidden-danger object detection model by using a high-precision target detection algorithm in a deep learning platform, and storing the trained model into a video server;
thirdly, carrying out lightweight processing on the trained detection model of the external hidden danger by using a model compression and prediction library in the deep learning platform, converting the trained large model into a small model, and storing the small model into a monitoring substation host;
fourthly, according to different areas, video monitoring of the surrounding environment of the power transmission line is carried out by using the debugged front-end equipment and the monitoring substation host, and a video stream obtained by monitoring is transmitted to a video server and a database server of the background monitoring system through a communication and transmission module of the monitoring substation host, so that real-time monitoring and archiving are facilitated;
step five, a video acquisition module of the monitoring substation host machine extracts the framing images of the monitoring video stream, a core processing operation module calls a lightweight neural network model to detect the extracted framing images according to a time sequence, and when an external hidden danger is detected, the current frame image is stored and the monitoring information of the image is sent to a video server;
step six, the video server receives a current frame image of the power transmission line with the external hidden danger, calls a high-precision detection neural network model to detect the image again, sends a general level warning signal with time information to the mobile terminal if the confidence coefficient of the external hidden danger is detected to be lower than a preset threshold value, and respectively stores a video stream containing the image and a warning comparison result of the rear end of the substation in a lowest warning folder and a warning record folder of the database server according to the time sequence;
if no external hidden trouble is detected, only the video stream containing the image and the early warning comparison result of the rear end of the substation are respectively stored in a normal folder and an early warning record folder of a database server according to the time sequence;
if the confidence coefficient of the detected external hidden danger is higher than the preset threshold value, a serious grade warning signal with time information is sent to the mobile terminal, and a warning signal is sent to the monitoring substation host, the substation controls the warning device to send an audible and visual warning signal through a bus protocol, and video streams containing the images and the warning comparison results at the rear end of the substation are respectively stored in a serious warning folder and a warning recording folder of the database server according to the time sequence;
and step seven, after receiving the warning information through the mobile terminal, the monitoring personnel call the stored monitoring video from the Web server in the background monitoring system to check, and inform the inspection personnel of carrying out on-site inspection and emergency treatment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110893024.4A CN113705364B (en) | 2021-08-04 | 2021-08-04 | Power transmission line external hidden danger early warning system and method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110893024.4A CN113705364B (en) | 2021-08-04 | 2021-08-04 | Power transmission line external hidden danger early warning system and method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113705364A CN113705364A (en) | 2021-11-26 |
| CN113705364B true CN113705364B (en) | 2022-03-11 |
Family
ID=78651587
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110893024.4A Active CN113705364B (en) | 2021-08-04 | 2021-08-04 | Power transmission line external hidden danger early warning system and method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113705364B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117095359B (en) * | 2023-10-17 | 2024-02-02 | 山东和兑智能科技有限公司 | Transmission line safety monitoring and early warning method and system based on artificial intelligence |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202067379U (en) * | 2010-11-26 | 2011-12-07 | 上海电力带电作业技术开发有限公司 | Remote wireless video intelligent monitoring prewarning system for electricity transmission line |
| WO2015131462A1 (en) * | 2014-03-07 | 2015-09-11 | 国家电网公司 | Centralized monitoring system and monitoring method for unmanned aerial vehicle to patrol power transmission line |
| CN110543986A (en) * | 2019-08-27 | 2019-12-06 | 广东电网有限责任公司 | Intelligent monitoring system and monitoring method for external hidden danger of power transmission line |
| CN110689531A (en) * | 2019-09-23 | 2020-01-14 | 云南电网有限责任公司电力科学研究院 | Automatic power transmission line machine inspection image defect identification method based on yolo |
| CN110705415A (en) * | 2019-09-24 | 2020-01-17 | 智洋创新科技股份有限公司 | Power transmission line construction machinery detection method based on android system and embedded platform |
| CN112528971A (en) * | 2021-02-07 | 2021-03-19 | 北京智芯微电子科技有限公司 | Power transmission line abnormal target detection method and system based on deep learning |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112528898A (en) * | 2020-12-17 | 2021-03-19 | 长扬科技（北京）有限公司 | Alarm event aggregation method and device based on multi-target detection of surveillance videos |
-
2021
- 2021-08-04 CN CN202110893024.4A patent/CN113705364B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202067379U (en) * | 2010-11-26 | 2011-12-07 | 上海电力带电作业技术开发有限公司 | Remote wireless video intelligent monitoring prewarning system for electricity transmission line |
| WO2015131462A1 (en) * | 2014-03-07 | 2015-09-11 | 国家电网公司 | Centralized monitoring system and monitoring method for unmanned aerial vehicle to patrol power transmission line |
| CN110543986A (en) * | 2019-08-27 | 2019-12-06 | 广东电网有限责任公司 | Intelligent monitoring system and monitoring method for external hidden danger of power transmission line |
| CN110689531A (en) * | 2019-09-23 | 2020-01-14 | 云南电网有限责任公司电力科学研究院 | Automatic power transmission line machine inspection image defect identification method based on yolo |
| CN110705415A (en) * | 2019-09-24 | 2020-01-17 | 智洋创新科技股份有限公司 | Power transmission line construction machinery detection method based on android system and embedded platform |
| CN112528971A (en) * | 2021-02-07 | 2021-03-19 | 北京智芯微电子科技有限公司 | Power transmission line abnormal target detection method and system based on deep learning |
Non-Patent Citations (2)
| Title |
|---|
| Calculation and analysis of inductive coupling effects for HV transmission lines on aerial pipelines;Djekidel, R等;《 Przeglad Elektrotechniczny》;20141231;全文 * |
| 基于无人机可见光点云的输电线路树障隐患智能分析研究;曾忱 等;《电力设备管理》;20200331;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113705364A (en) | 2021-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN207820108U (en) | A kind of transmission line long-distance video monitoring system | |
| CN104537788B (en) | High voltage electric transmission line external damage-proof intelligent image pre-warning system and method | |
| CN110543986A (en) | Intelligent monitoring system and monitoring method for external hidden danger of power transmission line | |
| CN210691345U (en) | Cloud intelligence safety inspection auxiliary system based on degree of depth learning | |
| CN102446390A (en) | Method and system for safety detection and early warning of monitoring areas near power transmission lines | |
| CN115220479B (en) | Dynamic and static cooperative power transmission line refined inspection method and system | |
| CN103035104B (en) | Preposing electric transmission line long-distance intelligent preventing external loss monitoring system based on digital signal processor (DSP) | |
| CN113705364B (en) | Power transmission line external hidden danger early warning system and method based on artificial intelligence | |
| CN111681381A (en) | Intelligent recognition system for preventing external damage of power transmission line | |
| CN110853287A (en) | Flame real-time monitoring system and method based on Internet of things distributed architecture | |
| CN111274880A (en) | Video intelligent analysis auxiliary inspection and abnormity warning method | |
| CN207473032U (en) | More rotor dual systems unmanned plane inspection fault diagnosis systems | |
| CN215642796U (en) | Intelligent detection and troubleshooting system for hidden troubles of power transmission line | |
| CN205846861U (en) | A kind of 500 kv substation communication equipment intelligence regular visit systems | |
| CN115297305A (en) | Multi-video-stream security risk early warning system and method based on edge calculation | |
| CN105811578B (en) | Transmission line of electricity monitor supervision platform and its Power Supply Monitoring algorithm and image warning algorithm | |
| CN102355575A (en) | Distributed video monitoring device with pre-warning function | |
| CN203039803U (en) | Power transmission line remote monitoring system | |
| CN115967183A (en) | Power transmission line's system of patrolling and examining | |
| CN111915831A (en) | Intelligent forest grassland fire prevention and rescue method | |
| CN114445782A (en) | Power transmission line image acquisition system based on edge AI and Beidou short messages | |
| CN207573079U (en) | A kind of power circuit monitoring management device and system | |
| CN209845008U (en) | Cluster monitoring system based on system on chip | |
| CN111105395A (en) | A AI intelligence cloud platform for transmission of electricity operation monitoring | |
| CN211429409U (en) | Rural tourism platform system based on digital interaction technology |
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 |