CN115457599A - Power transmission maintenance safety early warning method based on inference machine and power transmission line maintenance platform - Google Patents

Power transmission maintenance safety early warning method based on inference machine and power transmission line maintenance platform Download PDF

Info

Publication number
CN115457599A
CN115457599A CN202211212449.5A CN202211212449A CN115457599A CN 115457599 A CN115457599 A CN 115457599A CN 202211212449 A CN202211212449 A CN 202211212449A CN 115457599 A CN115457599 A CN 115457599A
Authority
CN
China
Prior art keywords
behavior
power transmission
base
transmission line
safety
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202211212449.5A
Other languages
Chinese (zh)
Inventor
尹国伟
董元发
赵永锋
吴维
曹昌畅
彭巍
潘顺
周克来
任杰
宿仕明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Anhui Hongyuan Electric Power Construction Investment Co ltd
China Three Gorges University CTGU
Anhui Power Transmission and Transformation Engineering Co Ltd
Original Assignee
Anhui Hongyuan Electric Power Construction Investment Co ltd
China Three Gorges University CTGU
Anhui Power Transmission and Transformation Engineering Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Anhui Hongyuan Electric Power Construction Investment Co ltd, China Three Gorges University CTGU, Anhui Power Transmission and Transformation Engineering Co Ltd filed Critical Anhui Hongyuan Electric Power Construction Investment Co ltd
Priority to CN202211212449.5A priority Critical patent/CN115457599A/en
Publication of CN115457599A publication Critical patent/CN115457599A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20—Movements or behaviour, e.g. gesture recognition
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02—Alarms for ensuring the safety of persons
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Software Systems (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Artificial Intelligence (AREA)
  • Databases & Information Systems (AREA)
  • Emergency Management (AREA)
  • Medical Informatics (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • Human Computer Interaction (AREA)
  • General Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Quality & Reliability (AREA)
  • Signal Processing (AREA)
  • Operations Research (AREA)
  • Psychiatry (AREA)
  • Social Psychology (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Primary Health Care (AREA)
  • Component Parts Of Construction Machinery (AREA)

Abstract

The invention relates to a power transmission overhaul safety early warning method based on an inference engine, which is characterized in that after behaviors and scenes of maintainers are obtained by using an image recognition method based on the inference engine, an operation behavior knowledge base, an operation environment knowledge base and a safety early warning knowledge base, rule matching is carried out according to the operation behaviors and scenes of the maintainers, and behavior types are obtained by inference; carrying out rule matching on the environmental characteristics to obtain the danger type of the working environment; then, the safety type of the behavior is obtained through reasoning by combining the behavior type and the danger type of the environment; and judging the safety type of the behavior of the maintainers, and if the judgment result is dangerous behavior, sending warning information. The invention also discloses a maintenance platform for the power transmission line. The method and the system analyze the working environment and the behavior danger degree of the maintenance personnel in real time to obtain the feedback information of the working data, have good accuracy, can be widely applied to the maintenance of the power transmission line in various environments, and have the advantages of high reliability, time and labor saving and cost saving.

Description

Power transmission maintenance safety early warning method based on inference machine and power transmission line maintenance platform
Technical Field
The invention belongs to the field of maintenance of power transmission and transformation facilities, and particularly relates to a power transmission line maintenance platform with danger early warning based on an inference engine and a use method.
Background
At present, the demand of regions in China for electric power is continuously increased, because the line fault conditions caused by natural weather environment and various human factors are endless, a typical circuit maintenance machine is an insulating bucket arm vehicle. Bear insulating bucket arm car and remove near transmission line through large-scale freight train, in maintenance personal got into insulating work fill, removed insulating work fill and maintenance personal and moved to trouble circuit region and carry out work through insulating bucket arm car bucket arm's removal. However, the working environment to which the above-mentioned maintenance machine is adapted and the functions it provides have certain limitations. For example, when the fault line is located near a narrow highway, a large truck cannot enter, which affects the development of maintenance work to some extent.
Most of the existing transmission line maintenance devices are single in function and cannot adapt to increasingly complex working environments. For example, when an insulating bucket arm vehicle is used to help maintenance personnel to perform maintenance work, due to the lack of real-time sensing components and monitoring units, the maintenance personnel can only judge dangerous environments through self experiences; because the size of insulating boom car itself is great for whole device is comparatively heavy, and cost and use cost are high, and this type of device can't satisfy maintenance personal's circuit maintenance demand under the different environment, has certain potential safety hazard.
Disclosure of Invention
The invention has the technical problem that the power transmission line maintenance device in the prior art is lack of a monitoring and early warning function for dangerous scenes or dangerous behaviors which may appear in the line maintenance operation process.
The invention aims to provide a power transmission overhaul safety early warning method and system based on an inference engine, which are based on the inference engine, an operation behavior knowledge base, an operation environment knowledge base and a safety early warning knowledge base, and are used for carrying out rule matching and reasoning to obtain a behavior type according to operation behaviors and scenes of maintainers after the behaviors and scenes of the maintainers are obtained by an image recognition method; carrying out rule matching on the environmental characteristics to obtain the danger type of the working environment; then, the safety type of the behavior is obtained through reasoning by combining the behavior type and the danger type of the environment; and the dangerous behaviors of maintenance personnel are warned in time so as to improve the safety of power transmission maintenance operation.
The technical scheme of the invention is a power transmission overhaul safety early warning method based on an inference machine, which comprises the following steps:
step 1: acquiring an image of a maintainer on a maintenance operation platform, and identifying by adopting an ST-GCN action identification network to obtain the operation behavior of the maintainer; identifying the scene of the maintainer by using a YoLo v4 model;
and 2, step: based on the operation behavior knowledge base, reasoning and obtaining the behavior type of the maintainers according to the operation behaviors and the operation scenes obtained in the step 1;
and step 3: acquiring environmental characteristics and electric field intensity of the operation environment, and reasoning to obtain a danger type of the operation environment based on an operation environment knowledge base;
and 4, step 4: based on a safety early warning knowledge base, reasoning to obtain the safety type of the behavior of the maintainers according to the behavior type of the maintainers and the danger type of the operation environment;
and 5: judging the safety type of the behavior of the maintainer obtained in the step 4, and if the judgment result is dangerous behavior, sending warning information; and if the judgment result is abnormal behavior, sending out prompt information.
Preferably, in step 1, an Alphapose model is used for detecting and identifying the personnel posture in the image of the overhaul personnel, and then the ST-GCN action recognition network is used for determining the action coordinate of the overhaul personnel according to the personnel posture and determining the limb action of the personnel.
Further, the alphaposition model includes a spatial transformation network STN, a single-person pose estimation network SPPE, an inverse spatial transformation network SDTN, and a pose non-maximum suppressor PPNMS.
Further, the ST-GCN action recognition network comprises a normalization layer, a plurality of ST-GCN units, a pooling layer and a full connection layer, wherein the ST-GCN units comprise an attention layer ATT, a graph convolution network GCN and a time convolution network TCN.
Preferably, the inference engine employs a Drools rules engine.
The power transmission line maintenance platform adopting the safety early warning method comprises a working bucket, a base, a lifting mechanism and an embedded system, wherein a memory of the embedded system stores a computer program, the computer program is executed by a processor of the embedded system to realize the safety early warning method, the bottom of the working bucket is connected with the base through the lifting mechanism, the lifting mechanism comprises a first telescopic frame and a second telescopic frame which are driven by a hydraulic telescopic column, and the top ends of the first telescopic frame and the second telescopic frame are respectively connected with the front edge and the rear edge of the bottom of the working bucket; the base is equipped with a plurality of landing legs, and the landing leg bottom joint support dish. The base is provided with a first wheel set and a second wheel set, and a connecting shaft of a wheel center of the first wheel set is rotatably connected with the base through a steering column; the axle center of the second wheel set is fixedly connected with the base.
One upper end point of the X-shaped rod at the top of the first telescopic frame is hinged with the bottom of the working bucket, the other upper end point of the X-shaped rod is connected with a sliding block of a sliding block mechanism at the bottom of the working bucket, and the second telescopic frame is connected with the working bucket in the same way as the first telescopic frame and is symmetrical to the first telescopic frame; the hydraulic telescopic columns are arranged in the diagonal direction of two adjacent X-shaped rods in the first telescopic frame, and the structure of the second telescopic frame is the same as that of the first telescopic frame and is symmetrical to that of the first telescopic frame;
the base is also provided with a sliding block mechanism corresponding to the sliding block mechanism at the bottom of the working bucket, and the end parts of the X-shaped rods at the bottoms of the first telescopic frame and the second telescopic frame, which are close to the sliding block mechanism of the base, are connected with the sliding block of the sliding block mechanism; when the lifting mechanism is lifted upwards under the action of the hydraulic telescopic column, the sliding block of the sliding block mechanism slides adaptively along with the movement of the end part of the lifting mechanism connected with the sliding block mechanism.
The working bucket is provided with a sensor unit and a camera, and the output ends of the sensor unit and the camera are respectively electrically connected with the embedded system; a first operating platform electrically connected with the embedded system is arranged in the working hopper; the base is provided with a second operating platform electrically connected with the embedded system.
Preferably, the sensor unit includes an electric field strength sensor and a wind speed sensor.
Preferably, the hinged parts of the X-shaped rods at the two sides of the first telescopic frame are respectively connected with the hinged parts of the corresponding rod bodies on the second telescopic frame through the cross rods.
Preferably, a hydraulic rod is arranged on the base, and a rod head of the hydraulic rod is connected with a slide block of the slide block mechanism of the base.
Furthermore, a hydraulic pump is arranged on the base, and the hydraulic telescopic column and the hydraulic rod are respectively connected with the hydraulic pump through oil pipelines; the pump shaft of the hydraulic pump is connected with the rotating shaft of the motor, and the control end of the motor is connected with the control signal output end of the embedded system.
Compared with the prior art, the invention has the beneficial effects that:
1) According to the power transmission overhaul safety early warning method, the behavior classification is carried out in a mode of establishing the knowledge base to be matched with the characteristics of the collected images and the collected environment information, and the accuracy of behavior identification is improved by utilizing the knowledge bases of three different types.
2) The method provided by the invention can be used for analyzing the working environment and the behavior action danger degree of maintenance personnel in real time to obtain the feedback information of the working data, has good accuracy, can be widely applied to the maintenance of the power transmission line under various environments, and has the advantages of high reliability, time and labor saving and cost saving.
3) The power transmission line maintenance platform provided by the invention can be used for acquiring physical states of temperature, humidity, electric field intensity and the like of a working environment in real time, and acquiring the working state of maintenance personnel in real time, so that the dangerous behaviors of the maintenance personnel can be warned in time, and the personal safety of the maintenance personnel can be guaranteed.
4) The power transmission line maintenance platform disclosed by the invention can adapt to various power transmission line maintenance environments, and is low in manufacturing cost.
Drawings
The invention is further illustrated by the following examples in conjunction with the drawings.
Fig. 1 is a schematic diagram of real-time human body posture estimation according to an embodiment of the present invention.
FIG. 2 is a flow chart of ST-CGN based action recognition according to an embodiment of the present invention.
FIG. 3 is a block diagram of an ST-CGN model according to an embodiment of the present invention.
Fig. 4 is a schematic diagram of the operation of the rules engine Drools according to the embodiment of the present invention.
Fig. 5 is a flowchart of a security early warning method according to an embodiment of the present invention.
FIG. 6 is a schematic diagram of a neural network model of an embedded system according to an embodiment of the present invention.
Fig. 7 is a schematic diagram of an embedded system implementing security early warning according to an embodiment of the present invention.
Fig. 8 is a front view of the power transmission line maintenance platform according to the embodiment of the present invention.
Fig. 9 is a left side view of the power transmission line maintenance platform according to the embodiment of the present invention.
Fig. 10 is a left side view partially enlarged view of the power transmission line maintenance platform according to the embodiment of the present invention.
Fig. 11 is an overall structural view of the power transmission line maintenance platform according to the embodiment of the present invention.
FIG. 12 is a schematic diagram of rules of a knowledge base according to an embodiment of the invention.
Description of reference numerals: the system comprises an embedded system 1, a base 2, a supporting leg 201, a supporting disc 202, a first operating platform 3, a lifting mechanism 4, a first telescopic frame 401, a second telescopic frame 402, an X-shaped rod 403, a working bucket 5, a second operating platform 6, a slider mechanism 7, a hydraulic pump 8, a motor 9, a hydraulic telescopic column 10, a hydraulic rod 11, a sensor unit 12, a camera 13, a traction rod 14, a cross rod 15, a first wheel set 16, a second wheel set 17 and a steering column 18.
Detailed Description
As shown in fig. 8 to 11, the power transmission line maintenance platform of the embodiment includes a working bucket 5, a base 2, a lifting mechanism 4, and an embedded system 1, where a memory of the embedded system 1 stores a computer program, and the computer program is executed by a processor of the embedded system to implement the safety warning method according to claim 1, where the bottom of the working bucket 5 is connected to the base 2 through the lifting mechanism 4, the lifting mechanism 4 includes a first telescopic frame 401 and a second telescopic frame 402 driven by a hydraulic telescopic column, and top ends of the first telescopic frame and the second telescopic frame are connected to a front edge and a rear edge of the bottom of the working bucket 5, respectively; one upper end point of a first X-shaped rod 403 on the top of the first telescopic frame is hinged with the bottom of the working bucket 5, the other upper end point is connected with a slide block of a slide block mechanism 7 on the bottom of the working bucket 5, and the second telescopic frame is connected with the working bucket in the same way as the first telescopic frame and is symmetrical with the first telescopic frame; the hydraulic telescopic columns 10 are arranged in the diagonal directions of two adjacent X-shaped rods 403 in the first telescopic frame, and the structure of the second telescopic frame is the same as that of the first telescopic frame; the hinged parts of the X-shaped rods at the two sides of the first telescopic frame 401 are connected with the corresponding hinged parts of the rod body on the second telescopic frame through the cross rod 15. The base 2 is provided with a plurality of supporting legs 201, and the bottoms of the supporting legs 201 are connected with a supporting plate 202; the base 2 is provided with a first wheel set 16 and a second wheel set 17, and a connecting shaft of the wheel center of the first wheel set 16 is rotatably connected with the base through a steering column 18; the axle center of the second wheel set 17 is fixedly connected with the base.
The base is also provided with a sliding block mechanism 7 corresponding to the sliding block mechanism 7 at the bottom of the working bucket 5, and the end parts of the X-shaped rods at the bottoms of the first telescopic frame and the second telescopic frame, which are close to the sliding block mechanism 7 of the base, are connected with the sliding block of the sliding block mechanism 7; when the lifting mechanism is lifted upwards under the action of the hydraulic telescopic column, the sliding block of the sliding block mechanism 7 slides adaptively along with the movement of the end part of the lifting mechanism connected with the sliding block mechanism. The base 2 is provided with a hydraulic rod 11, and the rod head of the hydraulic rod 11 is connected with the slide block of the slide block mechanism 7 of the base. A hydraulic pump 8 is arranged on the base 2, and a hydraulic telescopic column 10 and a hydraulic rod 11 are respectively connected with the hydraulic pump 8 through oil pipelines; the pump shaft of the hydraulic pump 8 is connected with the rotating shaft of the motor 9, and the control end of the motor 9 is connected with the control signal output end of the embedded system.
The working bucket 5 is provided with a sensor unit 12 and a camera 13, and the output ends of the sensor unit 12 and the camera 13 are respectively electrically connected with the embedded system 1; the sensor unit 12 includes an electric field strength sensor and a wind speed sensor, and the respective sensors can be installed as required. The working bucket 5 is internally provided with a first operating platform 3 which is electrically connected with the embedded system 1. In the embodiment, the sensor unit 12 and the camera 13 are respectively installed on the frame above the insulating working bucket 5, so that the monitoring height of the sensor unit is consistent with the head shoulder of a maintenance worker, the physical data of the working environment can be accurately monitored, and meanwhile, the action behavior of the maintenance worker can be completely monitored by the camera. The electric field intensity sensor of the embodiment adopts a 620A electromagnetic radiation detector and adopts a 485 type wind speed sensor.
The first operating platform 3 is provided with a lifting button, a descending button and a stopping button and is used for controlling a hydraulic telescopic column of the lifting mechanism, when the hydraulic telescopic column is extended, the first telescopic frame and the second telescopic frame are unfolded, and the working bucket is lifted; when the hydraulic telescopic column contracts, the first telescopic frame and the second telescopic frame are folded along with the hydraulic telescopic column, and the working bucket descends.
As shown in fig. 10, the base 2 is provided with a second console 6 electrically connected to the embedded system 1, and the function of the second console 6 is the same as that of the first console 3.
In the embodiment, the working bucket 5 is an insulating working bucket, the size data of the working bucket is 3.3m × 2.1m × 3.5m, and the maximum working height of the power transmission line maintenance platform is 15 m. In the embodiment, the processor of the embedded system 1 is made of Jetson Nano of NVIDIA. The embedded system comprises a knowledge base, an inference engine, an image processing module and an alarm module.
When a maintainer carries out maintenance operation on a power transmission line maintenance platform, after the behavior and scene of the maintainer are obtained by using an image recognition method, rule matching is carried out according to the operation behavior and scene of the maintainer, and the behavior type is obtained by reasoning, as shown in FIG. 4; carrying out rule matching on the environmental characteristics to obtain the danger type of the operation environment; and deducing to obtain the safety type of the behavior by combining the behavior type and the danger type of the environment. The inference engine employs a Drools rules engine, the rules of the knowledge base being shown in fig. 12.
The process of real-time monitoring and early warning of the overhaul operation behavior by the embedded system according to the image of the overhaul personnel acquired by the camera in real time is shown in fig. 7.
As shown in fig. 5, the power transmission overhaul safety early warning method based on the inference engine includes the following steps:
step 1: according to the image of the maintainer collected by the camera, the operation behavior of the maintainer is obtained by adopting ST-GCN model identification; identifying the scene of the maintainer by using a YoLo v4 model;
firstly, detecting and identifying the personnel posture in the image of the maintainer by using an Alphapose model, as shown in figure 1; and then, determining the action coordinate of the maintainer and the limb action of the maintainer according to the posture of the maintainer by using an ST-GCN action recognition network, as shown in figure 2.
The ST-GCN action recognition network comprises a normalization layer, a plurality of ST-GCN units, a pooling layer and a full connection layer, wherein the ST-GCN units comprise an attention layer ATT, a graph convolution network GCN and a time convolution network TCN, and is shown in figure 3.
And 2, step: based on the operation behavior knowledge base, reasoning and obtaining the behavior type of the maintainers according to the operation behaviors and the operation scenes obtained in the step 1;
and 3, step 3: and acquiring environmental characteristics by using an electric field intensity sensor and a wind speed sensor, and reasoning to obtain the danger type of the operation environment based on an operation environment knowledge base.
And 4, step 4: and deducing to obtain the safety type of the behavior of the maintainer based on the safety early warning knowledge base according to the behavior type of the maintainer and the danger type of the operation environment.
And 5: and 4, judging the safety type of the behavior of the maintainer obtained in the step 4, if the behavior of the maintainer has risks, sending out prompt or warning information, and if the behavior of the maintainer has no risks, normally working.
The image processing module of the embedded system adopts a neural network model, which comprises an Alphapos model, an ST-GCN model and a YoLo v4 model, and the training and using principle of the neural network model is shown in FIG. 6.
The judgment basis of the safety early warning method is that the influence of the extreme bad weather such as the electric field intensity higher than the safety working intensity, the too fast wind speed, the rain and the snow, and the like on the maintenance work comes from the change of the environment. And the other is the potential safety hazard caused by the continuous change of actions of maintenance personnel, such as the body of the maintenance personnel excessively extends out of the working bucket, the limbs of the maintenance personnel may directly contact with the live line, and the like.
The slide block mechanism 7 of the embodiment refers to the slide block mechanism disclosed in the 'design of a scissor-fork type lifting platform for passengers in the amusement industry' paper of Thanksgang, meng, leshuai and the like published in Metallurgical devices 1 st stage 2021.
In the embodiment, a YoLo v4 model is a YoLo v4 target detection network disclosed in a thesis of a dungeon, a strict warrior and the like published in "computer integrated network" at 2 nd year 2022, "a man-machine cooperation assembly scene recognition method based on multi-scale target detection".

Claims (10)

1. The safety early warning method for the power transmission maintenance operation based on the inference engine is characterized in that the safety early warning method is based on the inference engine, an operation behavior knowledge base, an operation environment knowledge base and a safety early warning knowledge base, after behaviors and scenes of maintenance personnel are obtained by an image recognition method, rule matching is carried out according to the operation behaviors and scenes of the maintenance personnel, and behavior types are obtained by inference; carrying out rule matching on the environmental characteristics to obtain the danger type of the operation environment; then, the safety type of the behavior is obtained through reasoning by combining the behavior type and the danger type of the environment;
the safety early warning method comprises the following steps:
step 1: acquiring an image of a maintainer on a maintenance operation platform, and identifying by adopting an ST-GCN action identification network to obtain the operation behavior of the maintainer; identifying the scene of the maintainer by using a YoLo v4 model;
step 2: based on the operation behavior knowledge base, reasoning and obtaining the behavior type of the maintainers according to the operation behaviors and the operation scenes obtained in the step 1;
and step 3: acquiring environmental characteristics and electric field intensity of the operation environment, and reasoning to obtain the danger type of the operation environment based on an operation environment knowledge base;
and 4, step 4: based on a safety early warning knowledge base, reasoning to obtain the safety type of the behavior of the maintainer according to the behavior type of the maintainer and the danger type of the operation environment;
and 5: judging the safety type of the behavior of the maintainer obtained in the step 4, and if the judgment result is dangerous behavior, sending warning information; and if the judgment result is abnormal behavior, sending out prompt information.
2. The power transmission overhaul safety early warning method according to claim 1, wherein in step 1, an Alphaose model is used for detecting and identifying the posture of a person in an image of the overhaul person, then an ST-GCN action recognition network is used for determining the action coordinate of the overhaul person according to the posture of the person and determining the limb action of the person;
the Alphapose model comprises a space transformation network STN, a single posture estimation network SPPE, a space inverse transformation network SDTN and a posture non-maximum suppressor PPNMS.
3. The power transmission overhaul safety precaution method of claim 2, wherein the ST-GCN action identification network comprises a normalization layer, a plurality of ST-GCN units, a pooling layer, and a full connectivity layer, the ST-GCN units comprising an attention layer ATT, a graph convolution network GCN, and a time convolution network TCN.
4. The transmission overhaul safety precaution method of claim 2, characterized in that the inference engine employs a Drools rule engine.
5. The transmission line maintenance platform of the transmission line overhaul safety pre-warning method according to any one of claims 1 to 4, wherein the transmission line maintenance platform comprises a working bucket (5), a base (2), a lifting mechanism (4) and an embedded system (1), a computer program is stored in a memory of the embedded system (1), and when the computer program is executed by a processor of the embedded system, the safety pre-warning method according to claim 1 is realized, wherein the bottom of the working bucket (5) is connected with the base (2) through the lifting mechanism (4), the lifting mechanism (4) comprises a first expansion bracket (401) and a second expansion bracket (402) driven by a hydraulic expansion column, and the top ends of the first expansion bracket and the second expansion bracket are respectively connected with the front edge and the rear edge of the bottom of the working bucket (5);
one upper end point of an X-shaped rod (403) at the top of the first telescopic frame is hinged with the bottom of the working bucket (5), the other upper end point is connected with a slide block of a slide block mechanism (7) at the bottom of the working bucket (5), and the connection mode of the second telescopic frame and the working bucket is the same as that of the first telescopic frame;
the hydraulic telescopic columns (10) are arranged in the diagonal directions of two adjacent X-shaped rods (403) in the first telescopic frame, and the structure of the second telescopic frame is the same as that of the first telescopic frame;
the base is also provided with a sliding block mechanism (7) corresponding to the sliding block mechanism (7) at the bottom of the working bucket (5), and the ends of the X-shaped rods at the bottoms of the first telescopic frame and the second telescopic frame, which are close to the sliding block mechanism (7) of the base, are connected with the sliding block of the sliding block mechanism (7); when the lifting mechanism is lifted upwards under the action of the hydraulic telescopic column, the sliding block of the sliding block mechanism (7) slides left and right along with the movement of the end part of the lifting mechanism connected with the sliding block mechanism;
the working bucket (5) is provided with a sensor unit (12) and a camera (13), and the output ends of the sensor unit (12) and the camera (13) are respectively electrically connected with the embedded system;
the working bucket (5) is internally provided with a first operating platform (3) which is electrically connected with the embedded system.
6. The power transmission line maintenance platform as claimed in claim 5, wherein the base (2) is provided with a plurality of support legs (201), and the bottoms of the support legs (201) are connected with the support plate (202).
7. The power transmission line maintenance platform as claimed in claim 6, wherein the hinged ends of the X-shaped rods on both sides of the first expansion bracket (401) are connected with the hinged ends of the corresponding rod bodies on the second expansion bracket through cross rods (15) respectively.
8. The power transmission line maintenance platform as claimed in claim 7, wherein the base (2) is provided with a first wheel set (16) and a second wheel set (17), and a connecting shaft of the shaft center of the first wheel set (16) is rotatably connected with the base through a steering column (18); the axle center of the second wheel set (17) is fixedly connected with the base.
9. The power transmission line maintenance platform according to claim 8, wherein a hydraulic rod (11) is arranged on the base (2), and a rod head of the hydraulic rod (11) is connected with a sliding block of the sliding block mechanism (7) of the base.
10. The power transmission line maintenance platform of claim 9, wherein the base (2) is provided with a hydraulic pump (8), and the hydraulic telescopic column (10) and the hydraulic rod (11) are respectively connected with the hydraulic pump (8) through an oil pipeline; the pump shaft of the hydraulic pump (8) is connected with the rotating shaft of the motor (9), and the control end of the motor (9) is connected with the control signal output end of the embedded system.
CN202211212449.5A 2022-09-30 2022-09-30 Power transmission maintenance safety early warning method based on inference machine and power transmission line maintenance platform Pending CN115457599A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211212449.5A CN115457599A (en) 2022-09-30 2022-09-30 Power transmission maintenance safety early warning method based on inference machine and power transmission line maintenance platform

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211212449.5A CN115457599A (en) 2022-09-30 2022-09-30 Power transmission maintenance safety early warning method based on inference machine and power transmission line maintenance platform

Publications (1)

Publication Number Publication Date
CN115457599A true CN115457599A (en) 2022-12-09

Family

ID=84308613

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211212449.5A Pending CN115457599A (en) 2022-09-30 2022-09-30 Power transmission maintenance safety early warning method based on inference machine and power transmission line maintenance platform

Country Status (1)

Country Link
CN (1) CN115457599A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116205921A (en) * 2023-05-05 2023-06-02 南京航空航天大学 Pipeline disease identification method based on Yolov5 and Drools
TWI830617B (en) * 2023-03-06 2024-01-21 友達光電股份有限公司 Machine unintentional action prediction method

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI830617B (en) * 2023-03-06 2024-01-21 友達光電股份有限公司 Machine unintentional action prediction method
CN116205921A (en) * 2023-05-05 2023-06-02 南京航空航天大学 Pipeline disease identification method based on Yolov5 and Drools
CN116205921B (en) * 2023-05-05 2023-09-26 南京航空航天大学 Pipeline disease identification method based on Yolov5 and Drools

Similar Documents

Publication Publication Date Title
CN115457599A (en) Power transmission maintenance safety early warning method based on inference machine and power transmission line maintenance platform
CN109901546B (en) Hardware-in-loop simulation test method and system for auxiliary driving vehicle
CN111016932B (en) Track inspection vehicle and detection method of energy-saving air rail system
CN107653775A (en) Suspension type monorail traffic track beam external smart maintenance and inspection car
CN105967066B (en) A kind of pre-alarming control system for ocean platform crane
CN107526329A (en) Robot management system based on artificial intelligence design
CN207828776U (en) Suspension type monorail traffic track beam external smart maintenance and inspection vehicle
CN107315410A (en) A kind of automatic troubleshooting method of robot
CN205766107U (en) A kind of parallel robot controller
CN108520133A (en) Automobile storage battery installing bracket strength analysis method
CN114132842A (en) Real-time monitoring system and monitoring method for operation state of container gantry crane storage yard
CN114169036A (en) Wind vibration response early warning system and method for large-span bridge
DE102019200407A1 (en) PARTIAL DETECTION AND DAMAGE CHARACTERIZATION BY DEEP-LEARNING
CN101477339A (en) Recreation facility intelligent monitoring apparatus based on multi-AGENT technology
CN113779734A (en) Straddle type single-track turnout monitoring and maintaining system based on artificial intelligence
CN206069222U (en) Ocean platform crane on-site control device
CN109443789A (en) The processing method and processing system of rolling stock health
CN210591921U (en) Dynamic image detection system for whole-body operation faults of motor train unit
CN105484211B (en) A kind of door machine security monitoring management system
CN107146493A (en) A kind of mechanical operating personnel's test system of universal crane
CN116062622B (en) Ship unloader grab bucket real-time position and posture monitoring system based on multiple laser sensors
CN114707576B (en) Railway contact line state detection system based on digital twinning
CN217278922U (en) Liftable three-dimensional ground penetrating radar detects car
CN113650648B (en) Operation monitoring and maintenance system of straddle type monorail turnout
CN114314347B (en) Safety monitoring and management system for hoisting machinery

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