CN114594490A - Laser external damage prevention method and device for power line - Google Patents
Laser external damage prevention method and device for power line Download PDFInfo
- Publication number
- CN114594490A CN114594490A CN202210091845.0A CN202210091845A CN114594490A CN 114594490 A CN114594490 A CN 114594490A CN 202210091845 A CN202210091845 A CN 202210091845A CN 114594490 A CN114594490 A CN 114594490A
- Authority
- CN
- China
- Prior art keywords
- sound
- target
- module
- laser
- laser radar
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
- G06N3/047—Probabilistic or stochastic 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
- G06F2218/06—Denoising by applying a scale-space analysis, e.g. using wavelet analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Evolutionary Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- Bioinformatics & Computational Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Traffic Control Systems (AREA)
- Emergency Alarm Devices (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The application discloses an electric power line laser external damage prevention method and device, comprising the following steps: starting and self-checking the laser external damage prevention device of the power line; the laser radar module and the auxiliary video image module perform scanning modeling and image recording on a monitoring environment; monitoring the sound of a monitored area, collecting and identifying the sound when the sound in a set frequency range appears in the area, and positioning the position of a target sound when an engine of the engineering machinery and related characteristic sound are identified; carrying out three-dimensional point cloud scanning on the position of a target sound, and carrying out distance calculation and target segmentation and identification; and acquiring images of the sound position of the target, calculating, further assisting in identifying the type of the target, calculating spatial position information of the target, evaluating the danger level according to the distance between the target and the power transmission line, and performing related early warning operation. The invention adopts sound recognition and positioning as conventional monitoring, and avoids the problems of high power consumption and difficult long-time work of laser radar and video monitoring.
Description
Technical Field
The invention belongs to the technical field of power line monitoring, and relates to a method and a device for preventing laser external damage of a power line.
Background
The power grid bears important facilities of national economy, and the safety of power equipment plays an important role in the reliability of power supply of power users, the stability of society and the development of economy. Most of power transmission lines are exposed in the field, the positions and the environment of the power transmission lines are complex, the pole towers are installed in many places, long distances and wide areas, faults and loss caused by external force damage are frequently seen, external force damage such as offline illegal construction, tree and bamboo obstacles is a main reason for power transmission summer rage tripping, and the external force damage caused by the illegal construction of engineering vehicles has the characteristics of high occurrence, burst and difficulty in timely finding and stopping.
In recent years, as socioeconomic development continues, urban construction in China is continuously improved, and with continuous construction of railways and highways, various large-scale engineering machines are constructed in a power line protection area, so that external force damage events caused by the construction often occur.
At present, the power system usually adopts methods such as video visualization on-line monitoring and shooting, manual inspection and the like to prevent external force damage. The manual inspection has weak real-time performance and large workload. Due to power supply limitation, video visualization online monitoring shooting can only be carried out at intervals and is not timely; moreover, because the images shot by the video do not have spatial position information, intelligent identification is easy to report by mistake or report by mistake, and the workload of manual identification is overlarge; at night, due to light interference of a construction site, the condition of the construction site is difficult to see clearly through visual monitoring; therefore, the visual monitoring is difficult to better undertake prevention in the work of preventing external force damage.
With the development of laser technology and laser radar technology, the research of adopting laser radar to solve the problem of preventing the outer damage of the power line appears at present, but because the power consumption of the laser radar during working is large and even exceeds the power consumption of a visual monitoring system, the system is difficult to keep the working state for a long time, and the practicability is low.
Disclosure of Invention
In order to overcome the defects in the prior art, the application provides a method and a device for preventing the laser of a power line from being broken.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a laser external damage prevention method for a power line comprises the following steps:
step 1: starting the laser external damage prevention device of the power line and carrying out self-checking on the equipment;
step 2: the laser radar module and the auxiliary video image module enter a dormant state after monitoring environment scanning modeling and image recording are carried out;
and step 3: monitoring sound in a monitored area, triggering an audio monitoring module to collect and identify the sound when the sound in a set frequency range appears in the area, and judging whether a dormant laser radar module and an auxiliary video image module need to be awakened or not;
and 4, step 4: when the engineering machinery engine and the related characteristic sound are identified, positioning the target sound position and awakening the laser radar module and the auxiliary video image module;
and 5: the laser radar module carries out three-dimensional point cloud scanning on the target sound position, and then distance calculation and target segmentation and identification are carried out on the basis of point cloud data; the auxiliary video image module collects images of the target sound position and carries out calculation processing, further assists in identifying the target type and records video image information for a user to check;
step 6: and after the target is segmented and identified, calculating the spatial position information of the target, evaluating the danger level according to the distance between the target and the power transmission line and performing related early warning operation.
The invention further comprises the following preferred embodiments:
preferably, step 2 specifically comprises:
step 2.1: the laser radar module is combined with the auxiliary video camera module, and a current environment image and laser radar point cloud data are collected in a monitoring range;
step 2.2: collecting or synthesizing a laser point cloud data set of engineering vehicles and engineering equipment in the power transmission line environment in advance, training the data set by adopting a large-scale point cloud semantic segmentation network RandLA-Net, and generating an AI algorithm model based on RandLA-Net;
step 2.3: inputting the point cloud data acquired by the laser radar module in the step 2.1 into an AI algorithm model for calculation, identifying various different target objects by RandLA-Net segmentation, storing calculation results, and completing monitoring environment scanning modeling;
the target objects include transmission lines, towers, trees and house buildings.
Preferably, the audio monitoring module in step 3 collects and identifies sound, and specifically includes:
1) the microphone array collects sound signals in a monitoring area range;
2) windowing the collected sound signal;
3) denoising the sound signal by adopting a wavelet threshold denoising method;
4) extracting characteristic values of the sound signals based on 1/3 octaves and Bark scale wavelet packet characteristic fusion algorithm;
5) and identifying the type of the engineering vehicle and the type of the engineering machinery based on the characteristic value of the step 4).
4. The power line laser anti-external-damage method according to claim 3, characterized in that:
in the step 2), the window length is 5-1000 ms;
and 5), adopting a probabilistic neural network or a support vector machine algorithm to identify the types of the engineering vehicle and the engineering machinery.
Preferably, in step 4, when the engineering machinery engine and the related characteristic sound are identified, sound data of a full monitoring area are collected in real time, background noise and sound signals of a non-target frequency band are directly removed through digital filtering, and only target sound is reserved as an effective input sound signal;
time delay between each microphone sensor pair in the audio monitoring module is estimated through a GCC algorithm, azimuth angles of sounds are calculated, the azimuth angles are calculated through a circular clustering method, a search area is defined by taking the azimuth as a center, accurate search is carried out in the defined area through a controllable response power phase weighting algorithm, and the sound source position, namely the positioning target sound position, is obtained.
Preferably, step 5 specifically includes:
step 5.1: according to the sound positioning result, cutting weak related image information far away from the target sound position and the power line position in the video image, then utilizing a background image stored in the system, removing unchanged background image information in the image by using a background difference method, and only keeping changed image information;
step 5.2: training the engineering vehicle and engineering machinery target video images in advance by using a YOLO algorithm, and carrying out target identification on the images subjected to background difference processing in the step 5.1 by using the trained model;
step 5.3: for the laser radar point cloud data, firstly removing the point cloud data far away from the target sound position and the power transmission line position, then removing fixed and uncertain point cloud data by a background difference method, and reserving a part inconsistent with the stored background;
step 5.4: and (3) inputting the laser point cloud data obtained in the step (5.3) into an AI (artificial intelligence) algorithm model based on RandLA-Net, performing semantic segmentation and target identification on the laser point cloud, identifying the engineering vehicle and the engineering machinery target, and recording related video image information for a user to check by combining the identification result in the step (5.2).
Preferably, in step 6, if the target is in a medium-high risk state, an alarm is immediately reported; if the target is in a safe position and is in a low-risk state, the laser radar module and the auxiliary video camera module enter the dormant state, the safety is checked and confirmed by timing awakening, and the sound monitoring module continuously monitors the working state and position change of the target.
The invention also discloses a laser anti-external-damage device for the power line, which comprises a laser radar module, an audio monitoring module consisting of a microphone array, an auxiliary video camera module, a main control module and a holder;
the laser radar module and the auxiliary video camera module are fixedly arranged, and the normal line of a laser window of the laser radar is parallel to the normal line of a lens of the auxiliary video camera module and is respectively used for collecting current environment images and point cloud data of the laser radar;
the laser radar module is fixed on the holder and can be driven by the holder to rotate in the vertical and horizontal directions;
the audio monitoring module is used for monitoring the acquisition of regional sound signals and the conversion of sound and electricity signals, when the regional sound signals are discontinuously acquired, part of microphones in the microphone array are electrified to work, and when an engineering machinery engine and related characteristic sounds are identified, all microphones in the microphone array are electrified to work;
the main control module is used for controlling the external damage prevention device and comprises a control laser radar module, an auxiliary video camera module, an audio monitoring module and a tripod head self-checking and working state; modeling a three-dimensional model of a monitoring environment based on a current environment image and laser radar point cloud data; performing sound identification and positioning based on the sound signals of the monitoring area; performing image calculation and three-dimensional point cloud calculation based on three-dimensional point cloud scanning and a target sound position image, and identifying a target; and when the target is the engineering machine, calculating the danger level of the engineering machine and performing related early warning operation.
Preferably, the microphone array adopts a cross-shaped, T-shaped or circular two-dimensional array, or adopts a three-dimensional array; in the microphone array, the number of microphone elements is 8 or more.
Preferably, the main control module is connected with the laser radar module, the audio monitoring module, the auxiliary video camera module and the holder through cables.
The beneficial effect that this application reached:
1. the invention adopts sound recognition and positioning as conventional monitoring, thereby avoiding the problems of high power consumption and difficult long-time work of laser radar and video monitoring;
2. the laser radar is used as the main monitoring equipment, so that accurate spatial position information is provided, the false alarm rate is greatly reduced, the accuracy rate is improved, and the subsequent manual judgment of the risk level by a user is facilitated;
3. the invention solves the night monitoring problem of conventional video visual monitoring, the sound is not influenced by day and night, the effect of timely finding the construction at night can be achieved, the laser radar does not influence the work at night, and the problem of accurately mastering the construction condition at night is solved.
Drawings
FIG. 1 is a flow chart of a laser anti-external damage method for a power line according to the present invention;
FIG. 2 is a structural diagram of a laser anti-external-damage device for power lines according to the present invention;
the reference signs are: the system comprises a laser radar module, a 2-audio monitoring module, a 3-auxiliary video camera module, a 4-main control module and a 5-tripod head.
Detailed Description
The present application is further described below with reference to the accompanying drawings. The following examples are only used to illustrate the technical solutions of the present invention more clearly, and the protection scope of the present application is not limited thereby.
As shown in fig. 1, the laser external damage prevention method for the power line of the invention comprises the following steps:
step 1: starting the laser external damage prevention device of the power line and carrying out equipment self-inspection;
step 2: the laser radar module and the auxiliary video image module enter a dormant state after monitoring environment scanning modeling and image recording, and the method specifically comprises the following steps:
step 2.1: the laser radar module is combined with the auxiliary video camera module, and a current environment image and laser radar point cloud data are collected in a monitoring range;
step 2.2: collecting or synthesizing a laser point cloud data set of engineering vehicles and engineering equipment in the power transmission line environment in advance, training the data set by adopting a large-scale point cloud semantic segmentation network RandLA-Net, and generating an AI algorithm model based on RandLA-Net;
step 2.3: inputting the point cloud data acquired by the laser radar module in the step 2.1 into an AI algorithm model for calculation, identifying various different target objects by RandLA-Net segmentation, storing calculation results, and completing monitoring environment scanning modeling;
the target objects include transmission lines, towers, trees and house buildings.
And step 3: monitoring sound in a monitored area, triggering an audio monitoring module to collect and identify the sound when the sound in a set frequency range appears in the area, and judging whether a dormant laser radar module and an auxiliary video image module need to be awakened or not;
during specific implementation, sound signals of a monitoring area are collected discontinuously (interval time is set by a user), the sound signals are converted into electric signals, the electric signals are conditioned and filtered, then analog-to-digital conversion is carried out on the electric signals into digital signals, and finally recognition is carried out by adopting a sound recognition algorithm.
The audio monitoring module collects and identifies sound, and specifically comprises:
1) the microphone array collects sound signals in a monitoring area range;
2) windowing the collected sound signals, wherein the window length is 5-1000 ms;
3) denoising the sound signal by adopting a wavelet threshold denoising method;
4) extracting characteristic values of the sound signals based on 1/3 octaves and Bark scale wavelet packet characteristic fusion algorithm;
5) and (4) identifying the types of the engineering vehicles and the engineering machinery by adopting a Probabilistic Neural Network (PNN) or Support Vector Machine (SVM) algorithm based on the characteristic values in the step 4).
And 4, step 4: when the engineering machinery engine and the related characteristic sound are identified, positioning the target sound position and awakening the laser radar module and the auxiliary video image module;
when an engineering machinery engine and related characteristic sounds are identified, sound data of a full monitoring area are collected in real time, background noise and sound signals of a non-target frequency range are directly removed through digital filtering, and only target sounds are reserved as effective input sound signals;
time delay between each microphone sensor pair in the audio monitoring module is estimated through a Generalized Cross Correlation (GCC) algorithm, the azimuth angle of sound is calculated, a circular clustering method is used for combining and calculating the azimuth angle, a search area is defined by taking the azimuth as the center, accurate search is carried out in the defined area by using a controllable response power phase weighting (SRP-PHAT) algorithm, and the position of a sound source, namely the position of positioning target sound, is obtained and is a space position coordinate (X1, Y1, Z1) of relative sound collection equipment.
And 5: the laser radar module carries out three-dimensional point cloud scanning on the target sound position, and then distance calculation and target segmentation and identification are carried out on the basis of point cloud data; the auxiliary video image module collects images of target sound positions and carries out calculation processing, further assists in identifying target types, records video image information for users to check, and specifically comprises the following steps:
step 5.1: according to the sound positioning result, cutting weak related image information far away from the target sound position and the power line position in the video image, then utilizing a background image stored in the system, removing unchanged background image information in the image by using a background difference method, only keeping changed image information, reducing the calculated amount and quickening the calculation time;
step 5.2: training the engineering vehicle and engineering machinery target video images in advance by using AI algorithms such as YOLO (auto-regressive optical modeling) and the like, embedding the trained model into an external damage prevention system, and performing target identification on the image subjected to background difference processing in the step 5.1;
step 5.3: for the similar video image processing of the laser radar point cloud data processing, firstly removing point cloud data far away from a target sound position and a power transmission line position, wherein the data are irrelevant or extremely weak with event detection, then removing fixed and uncertain point cloud data by a background difference method, and reserving a part inconsistent with the stored background;
step 5.4: and (4) inputting the laser point cloud data obtained in the step (5.3) into an AI (artificial intelligence) algorithm model based on RandLA-Net, performing semantic segmentation and target identification on the laser point cloud, identifying targets such as engineering vehicles, and recording related video image information for a user to check by combining the identification result in the step (5.2).
Step 6: and after the target is segmented and identified, calculating the spatial position information of the target, evaluating the danger level according to the distance between the target and the power transmission line and performing related early warning operation.
If the target is in a medium and high risk state, immediately reporting an alarm; if the target is temporarily at a safe position and is in a low-risk state, the laser radar module and the auxiliary video camera module enter the sleep state, and wake up for checking and confirming safety at regular time, and the sound monitoring module is used for continuously monitoring the working state and position change of the target under the conventional condition.
The danger level can be specified and set by the user.
For example, a laser radar is used as a coordinate origin, the lowest point in laser point cloud obtained by scanning is used as a reference point, the highest height of the laser point cloud of the engineering vehicle is H1, the ground height below a power transmission line is H2, when an excavator works near the power transmission line, the excavator is likely to open to the lower part of the power transmission line, the total height is H1+ H2, the height of the power transmission line is H, the safety distance is L, if H- (H1+ H2) < L, medium and high risks exist, otherwise, low risks exist.
The spatial position information comprises spatial information such as the height and the size of the target, the height of the ground below the line and the like.
As shown in fig. 2, the laser external damage prevention device for the power line of the invention comprises a laser radar module 1, an audio monitoring module 2 consisting of a microphone array, an auxiliary video camera module 3, a main control module 4 and a holder 5;
the laser radar module 1 and the auxiliary video camera module 3 are fixedly arranged, and the normal line of a laser window of the laser radar is parallel to the normal line (optical axis) of a lens of the auxiliary video camera module 3 and is respectively used for collecting current environment images and point cloud data of the laser radar;
the laser radar module 1 is fixed on the holder 5 and can be driven by the holder 5 to rotate in the vertical and horizontal directions;
the audio monitoring module 2 is used for monitoring the acquisition of regional sound signals and the conversion of sound and electricity signals, when the sound signals of the monitored region are intermittently acquired, part of microphones in the microphone array are electrified to work, and when an engineering machinery engine and related characteristic sounds are identified, all microphones in the microphone array are electrified to work;
the microphone array adopts a cross-shaped, T-shaped or circular two-dimensional array or a three-dimensional array; in the microphone array, the number of microphone elements is 8 or more.
The microphone array and the laser radar can be independently placed or fixed together;
the main control module 4 is used for controlling the external damage prevention device and comprises a control laser radar module 1, an auxiliary video camera module 3, an audio monitoring module 2 and a cradle head 5 for self-checking and working states; modeling a three-dimensional model of a monitoring environment based on a current environment image and laser radar point cloud data; performing sound identification and positioning based on the sound signals of the monitoring area; performing image calculation and three-dimensional point cloud calculation based on three-dimensional point cloud scanning and a target sound position image, and identifying a target; and when the target is the engineering machine, calculating the danger level of the engineering machine and performing related early warning operation.
The main control module 4 comprises communication, calculation and control functions and adopts an embedded processor;
the main control module 4 is connected with the laser radar module 1, the audio monitoring module 2, the auxiliary video camera module 3 and the holder 5 through cables.
Referring to fig. 1, the laser external damage prevention device for the power line comprises a laser radar module 1, an audio monitoring module 2, an auxiliary video camera module 3, a main control module 4 and a holder 5.
The laser radar module 1 and the auxiliary video camera module 3 are fixedly arranged, and the normal line of a laser window of the laser radar is parallel to the normal line (optical axis) of a lens of the auxiliary video camera module 3;
the laser radar module 1 is fixed on the holder and can be driven by the holder to rotate in the vertical and horizontal directions;
the audio monitoring module 2 can adopt two-dimensional arrays such as cross, T-shaped and round arrays, and can also adopt three-dimensional arrays; the number of microphone elements is 8 or more;
the audio monitoring module 2 and the laser radar can be independently placed or fixed together;
the main control module 4 has communication, calculation and control functions and adopts an embedded processor;
the main control module 4 is connected with the laser radar module 1, the audio monitoring module 2, the auxiliary video camera module 3 and the holder 5 through cables;
the laser anti-external-damage power line laser anti-external-damage method is adopted for realizing the laser anti-external-damage of the power line, and the method works according to the following steps:
step 1: the system is started, and the main control module 4 controls the laser radar module 1, the auxiliary video camera module 3, the audio monitoring module 2 and the cradle head 5 to perform self-checking;
step 2: the cloud deck 5 drives the laser radar module 1 and the auxiliary video camera module 3 to rotate, and collects a current environment image and laser radar point cloud data within a monitoring range set by a user;
the main control module 4 receives the images and the laser radar point cloud data, establishes a three-dimensional model of the monitoring environment, and fuses and matches the three-dimensional model with image information; the internal algorithm classifies and identifies targets such as power transmission lines, towers, trees, house buildings and the like, and stores calculation results;
the laser radar module 1, the auxiliary video camera module 3 and the holder 5 enter a sleep mode and operate with extremely low power consumption;
the main control module 4 shuts down or sleeps unnecessary power supply modules, such as communication, GPU computing modules, etc.;
and step 3: the audio monitoring module 2 works by only starting 1 or a few microphones to electrify, discontinuously collecting sound signals in a monitoring area (interval time is set by a user), converting the sound signals into electric signals, conditioning and filtering the sound electric signals by the main control module 4, performing analog-to-digital conversion on the sound electric signals into digital signals, and then adopting a sound identification algorithm to identify;
and 4, step 4: when the engineering machinery engine and the related characteristic sound are identified, starting the electrical operation on all microphone arrays, collecting sound data, and carrying out calculation and positioning by a positioning algorithm in the main control module 4 to obtain a spatial position coordinate (X1, Y1, Z1) relative to the center of the microphone arrays;
and 5: the main control module 4 starts up and awakens the laser radar module 1 and the auxiliary video camera module 3, and controls the holder 5 to rotate, so that the laser radar module 1 and the auxiliary video camera module 3 face to a space coordinate (X1, Y1, Z1);
the laser radar module 1 scans a three-dimensional point cloud of a target position, the auxiliary video camera module 3 shoots the target position, and the main control module 4 performs image calculation and three-dimensional point cloud calculation after acquiring data to identify the target;
step 6: when the target is identified to be engineering machinery, automatically calculating spatial information such as the height, the size and the ground height below the line of the target, evaluating various possibilities of the distance between the target and the line and the height change, and finally calculating the danger level.
Thereafter, the user manually checks in the field or remotely, and the user selects whether to enter a low power monitoring state or continue to maintain a high level of attention.
In conclusion, the voice recognition and positioning are adopted as conventional monitoring, so that the problems that the power consumption of a laser radar and a video monitoring camera is high and the laser radar and the video monitoring camera are difficult to work for a long time are solved; the laser radar is used as the main monitoring equipment, so that accurate spatial position information is provided, the false alarm rate is greatly reduced, the accuracy rate is improved, and the subsequent manual judgment of the risk level by a user is facilitated; the invention solves the night monitoring problem of conventional video visual monitoring, the sound is not influenced by day and night, the effect of timely finding the construction at night can be achieved, the laser radar does not influence the work at night, and the problem of accurately mastering the construction condition at night is solved.
The present applicant has described and illustrated embodiments of the present invention in detail with reference to the accompanying drawings, but it should be understood by those skilled in the art that the above embodiments are merely preferred embodiments of the present invention, and the detailed description is only for the purpose of helping the reader to better understand the spirit of the present invention, and not for limiting the scope of the present invention, and on the contrary, any improvement or modification made based on the spirit of the present invention should fall within the scope of the present invention.
Claims (10)
1. A laser external damage prevention method for a power line is characterized by comprising the following steps:
the method comprises the following steps:
step 1: starting the laser external damage prevention device of the power line and carrying out self-checking on the equipment;
step 2: the laser radar module and the auxiliary video image module enter a dormant state after monitoring environment scanning modeling and image recording are carried out;
and step 3: monitoring sound in a monitored area, and triggering an audio monitoring module to collect and identify the sound when the sound in a set frequency range appears in the area;
and 4, step 4: when the engineering mechanical engine and the related characteristic sound are identified in the step 3, positioning the target sound position and awakening the laser radar module and the auxiliary video image module;
and 5: the laser radar module carries out three-dimensional point cloud scanning on the target sound position, and then distance calculation and target segmentation and identification are carried out on the basis of point cloud data; the auxiliary video image module collects images of the target sound position and carries out calculation processing, further assists in identifying the target type and records video image information for a user to check;
step 6: and after the target is segmented and identified, calculating spatial position information of the target, evaluating a danger level according to the distance between the target and the power transmission line, and performing related early warning operation.
2. The laser outward-breaking prevention method for the power line according to claim 1, characterized by comprising the following steps:
the step 2 specifically comprises the following steps:
step 2.1: the laser radar module is combined with the auxiliary video camera module, and a current environment image and laser radar point cloud data are collected in a monitoring range;
step 2.2: collecting or synthesizing a laser point cloud data set of engineering vehicles and engineering equipment in the power transmission line environment in advance, training the data set by adopting a large-scale point cloud semantic segmentation network RandLA-Net, and generating an AI algorithm model based on RandLA-Net;
step 2.3: inputting the point cloud data acquired by the laser radar module in the step 2.1 into an AI algorithm model for calculation, identifying various different target objects by RandLA-Net segmentation, storing calculation results, and completing monitoring environment scanning modeling;
the target objects include transmission lines, towers, trees and house buildings.
3. The laser outward-breaking prevention method for the power line according to claim 1, characterized by comprising the following steps:
step 3, the audio monitoring module collects and identifies sound, and specifically comprises:
1) the microphone array collects sound signals in a monitoring area range;
2) windowing the collected sound signal;
3) denoising the sound signal by adopting a wavelet threshold denoising method;
4) extracting characteristic values of the sound signals based on 1/3 octaves and Bark scale wavelet packet characteristic fusion algorithm;
5) and identifying the type of the engineering vehicle and the type of the engineering machinery based on the characteristic value of the step 4).
4. The power line laser anti-external-damage method according to claim 3, characterized in that:
in the step 2), the window length is 5-1000 ms;
and 5) identifying the types of the engineering vehicle and the engineering machinery by adopting a probabilistic neural network or a support vector machine algorithm.
5. The laser outward-breaking prevention method for the power line according to claim 1, characterized by comprising the following steps:
step 4, when the engineering machinery engine and the related characteristic sound are identified, collecting sound data of a full monitoring area in real time, directly removing background noise and sound signals of a non-target frequency band through digital filtering, and only reserving target sound as an effective input sound signal;
time delay between each microphone sensor pair in the audio monitoring module is estimated through a GCC algorithm, azimuth angles of sounds are calculated, the azimuth angles are calculated through a circular clustering method, a search area is defined by taking the azimuth as a center, accurate search is carried out in the defined area through a controllable response power phase weighting algorithm, and the sound source position, namely the positioning target sound position, is obtained.
6. The laser outward-breaking prevention method for the power line according to claim 1, characterized by comprising the following steps:
the step 5 specifically comprises the following steps:
step 5.1: according to the sound positioning result, cutting weak related image information far away from the target sound position and the power line position in the video image, then utilizing a background image stored in the system, removing unchanged background image information in the image by using a background difference method, and only keeping changed image information;
step 5.2: training the engineering vehicle and engineering machinery target video images in advance by using a YOLO algorithm, and carrying out target identification on the images subjected to background difference processing in the step 5.1 by using the trained model;
step 5.3: for the laser radar point cloud data, firstly removing the point cloud data far away from the target sound position and the power transmission line position, then removing fixed and uncertain point cloud data by a background difference method, and reserving a part inconsistent with the stored background;
step 5.4: and (3) inputting the laser point cloud data obtained in the step (5.3) into an AI (artificial intelligence) algorithm model based on RandLA-Net, performing semantic segmentation and target identification on the laser point cloud, identifying the engineering vehicle and the engineering machinery target, and recording related video image information for a user to check by combining the identification result in the step (5.2).
7. The laser outward-breaking prevention method for the power line according to claim 1, characterized by comprising the following steps:
in step 6, if the target is in a high risk state, immediately reporting an alarm; if the target is in a safe position and is in a low-risk state, the laser radar module and the auxiliary video camera module enter the dormant state, the safety is checked and confirmed by timing awakening, and the sound monitoring module continuously monitors the working state and position change of the target.
8. A power line laser anti-external-damage device for implementing the power line laser anti-external-damage method according to any one of claims 1 to 7, characterized in that:
the device comprises a laser radar module, an audio monitoring module consisting of a microphone array, an auxiliary video camera module, a main control module and a holder;
the laser radar module and the auxiliary video camera module are fixedly arranged, and the normal line of a laser window of the laser radar is parallel to the normal line of a lens of the auxiliary video camera module and is respectively used for collecting current environment images and point cloud data of the laser radar;
the laser radar module is fixed on the holder and can be driven by the holder to rotate in the vertical and horizontal directions;
the audio monitoring module is used for monitoring the acquisition of regional sound signals and the conversion of sound and electricity signals, when the regional sound signals are discontinuously acquired, part of microphones in the microphone array are electrified to work, and when an engineering machinery engine and related characteristic sounds are identified, all microphones in the microphone array are electrified to work;
the main control module is used for controlling the external damage prevention device and comprises a control laser radar module, an auxiliary video camera module, an audio monitoring module and a tripod head self-checking and working state; modeling a three-dimensional model of a monitoring environment based on a current environment image and laser radar point cloud data; performing sound identification and positioning based on the sound signals of the monitoring area; performing image calculation and three-dimensional point cloud calculation based on three-dimensional point cloud scanning and a target sound position image, and identifying a target; and when the target is the engineering machine, calculating the danger level of the engineering machine and performing related early warning operation.
9. The laser external damage prevention device for the power line according to claim 8, wherein:
the microphone array adopts a cross-shaped, T-shaped or circular two-dimensional array or a three-dimensional array; in the microphone array, the number of microphone elements is 8 or more.
10. The laser external damage prevention device for the power line according to claim 8, wherein:
the main control module is connected with the laser radar module, the audio monitoring module, the auxiliary video camera module and the holder through cables.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210091845.0A CN114594490A (en) | 2022-01-26 | 2022-01-26 | Laser external damage prevention method and device for power line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210091845.0A CN114594490A (en) | 2022-01-26 | 2022-01-26 | Laser external damage prevention method and device for power line |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114594490A true CN114594490A (en) | 2022-06-07 |
Family
ID=81806249
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210091845.0A Pending CN114594490A (en) | 2022-01-26 | 2022-01-26 | Laser external damage prevention method and device for power line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114594490A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115547003A (en) * | 2022-11-24 | 2022-12-30 | 北京数字绿土科技股份有限公司 | External damage prevention alarm method and system for power transmission line |
| CN115620239A (en) * | 2022-11-08 | 2023-01-17 | 国网湖北省电力有限公司荆州供电公司 | Point cloud and video combined power transmission line online monitoring method and system |
| CN115762529A (en) * | 2022-10-17 | 2023-03-07 | 国网青海省电力公司海北供电公司 | Method for preventing cable from being broken outside by using voice recognition perception algorithm |
| CN116668645A (en) * | 2023-08-01 | 2023-08-29 | 成都汉度科技有限公司 | Substation moving ring monitoring method and equipment |
| CN117346751A (en) * | 2023-10-10 | 2024-01-05 | 广东省核工业地质局测绘院 | Mine mapping system based on unmanned aerial vehicle airborne laser radar and oblique photogrammetry |
-
2022
- 2022-01-26 CN CN202210091845.0A patent/CN114594490A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115762529A (en) * | 2022-10-17 | 2023-03-07 | 国网青海省电力公司海北供电公司 | Method for preventing cable from being broken outside by using voice recognition perception algorithm |
| CN115762529B (en) * | 2022-10-17 | 2024-09-10 | 国网青海省电力公司海北供电公司 | Method for preventing cable from being broken outwards by utilizing voice recognition sensing algorithm |
| CN115620239A (en) * | 2022-11-08 | 2023-01-17 | 国网湖北省电力有限公司荆州供电公司 | Point cloud and video combined power transmission line online monitoring method and system |
| CN115620239B (en) * | 2022-11-08 | 2024-01-30 | 国网湖北省电力有限公司荆州供电公司 | Point cloud and video combined power transmission line online monitoring method and system |
| CN115547003A (en) * | 2022-11-24 | 2022-12-30 | 北京数字绿土科技股份有限公司 | External damage prevention alarm method and system for power transmission line |
| CN116668645A (en) * | 2023-08-01 | 2023-08-29 | 成都汉度科技有限公司 | Substation moving ring monitoring method and equipment |
| CN116668645B (en) * | 2023-08-01 | 2023-09-29 | 成都汉度科技有限公司 | Substation moving ring monitoring method and equipment |
| CN117346751A (en) * | 2023-10-10 | 2024-01-05 | 广东省核工业地质局测绘院 | Mine mapping system based on unmanned aerial vehicle airborne laser radar and oblique photogrammetry |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114594490A (en) | Laser external damage prevention method and device for power line | |
| CN110321853B (en) | Distributed cable external-damage-prevention system based on video intelligent detection | |
| CN102013147B (en) | High voltage power transmission tower intelligent anti-theft method for supervising and device | |
| CN103280059B (en) | A kind of intelligent monitor system for subsea cable operation maintenance | |
| WO2022116763A1 (en) | Device and method for underwater intelligent monitoring of sand dredger | |
| CN104394361A (en) | Pedestrian crossing intelligent monitoring device and detection method | |
| CN115603466B (en) | Ship shore power system based on artificial intelligence visual identification | |
| CN102446390A (en) | Method and system for safety detection and early warning of monitoring areas near power transmission lines | |
| CN111461078B (en) | Fishing preventing and monitoring method based on computer vision technology | |
| CN103366516A (en) | Intelligent power transmission line monitoring system and method | |
| CN112904328A (en) | Radar photoelectric tracking early warning system and early warning method for offshore wind farm | |
| CN113287597B (en) | Transmission line initiative bird repellent device based on video is studied and judged | |
| CN110691224A (en) | Transformer substation perimeter video intelligent detection system | |
| CN112530144B (en) | Method and system for warning violation behaviors of thermal power plant based on neural network | |
| CN106205000B (en) | A kind of mobile electric line external force damage prevention monitoring method based on miniradar | |
| CN112702570A (en) | Security protection management system based on multi-dimensional behavior recognition | |
| CN113591574A (en) | Power transmission line inspection method and device based on laser radar | |
| CN108806144A (en) | A kind of community alarm system based on 5G networks | |
| CN115761644A (en) | Transmission line foreign matter detection method based on deep learning and frame difference method | |
| CN208298351U (en) | A kind of radar monitoring early warning system based on unmanned plane | |
| CN213844302U (en) | Coupling monitoring system of laser radar, laser lamp and monitoring camera | |
| CN117789386A (en) | Side border protection intrusion alarm system and method | |
| CN110481600B (en) | Unmanned autonomous comprehensive alarm system | |
| CN103561245A (en) | Space information monitoring device and technology like human brain | |
| CN112382051A (en) | Wisdom house security protection system based on block chain |
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 |