CN112343657A - Mine underground air door identification and abnormal state monitoring method - Google Patents
Mine underground air door identification and abnormal state monitoring method Download PDFInfo
- Publication number
- CN112343657A CN112343657A CN202011216352.2A CN202011216352A CN112343657A CN 112343657 A CN112343657 A CN 112343657A CN 202011216352 A CN202011216352 A CN 202011216352A CN 112343657 A CN112343657 A CN 112343657A
- Authority
- CN
- China
- Prior art keywords
- air door
- time
- algorithm
- alarm information
- video
- 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.)
- Granted
Links
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21F—SAFETY DEVICES, TRANSPORT, FILLING-UP, RESCUE, VENTILATION, OR DRAINING IN OR OF MINES OR TUNNELS
- E21F17/00—Methods or devices for use in mines or tunnels, not covered elsewhere
- E21F17/18—Special adaptations of signalling or alarm devices
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21F—SAFETY DEVICES, TRANSPORT, FILLING-UP, RESCUE, VENTILATION, OR DRAINING IN OR OF MINES OR TUNNELS
- E21F1/00—Ventilation of mines or tunnels; Distribution of ventilating currents
- E21F1/10—Air doors
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Mining & Mineral Resources (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Alarm Systems (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention discloses a method for identifying and monitoring abnormal states of an underground mine air door, which comprises the following steps: configuring an algorithm model for a camera in a system; the system automatically sends the camera information to an algorithm service; the algorithm service carries out calculation analysis on the real-time monitoring video of the camera; sending air door damage information after the air door is found to be damaged; the invention has the following beneficial effects: the system has obvious and strong alarm prompt, so that the manager cannot omit each alarm message, and each alarm message can be ensured to be concerned by the manager, thereby avoiding the occurrence of accidents.
Description
Technical Field
The invention relates to the technical field of monitoring methods, in particular to a method for identifying and monitoring abnormal states of an underground mine air door.
Background
The underground mine air door has the following functions:
1. and enough fresh air is supplied to the underground to meet the requirement of personnel on oxygen.
2. Dilute the poisonous and harmful gas and dust in the well and ensure the safe production.
3. The underground climate is adjusted, and a good working environment is created.
4. And controlling the air flow. The mine ventilation system consists of two parts, namely a ventilator and a ventilation network. After entering a mine from an air inlet wellhead, the air flow passes through various underground air fields and then enters an air return shaft, and is discharged out of the mine from the air return shaft, and the whole route through which the air flow passes is called a mine ventilation system.
If the air door is not closed for a long time, the air flow can not operate according to the design scheme of the mine, the conditions of insufficient air pressure and no air exist in other places, and underground workers can not obtain enough oxygen to cause accidents such as anoxic shock and death.
At present, an underground air door uses a sensor to monitor the on-off state, so that the on-off signal of the air door can be obtained, but the sensor can only transmit the on-off signal and can not obtain a picture, so that the situation of misinformation can exist, if the air door is closed, but the data obtained by the sensor is still in an open state, the alarm can not be realized, video data can not be provided for a manager, after the on-off signal sent by the sensor is seen, the manager needs to call video monitoring or go into the well to check, and troubles are brought to the manager.
No other project has proposed a solution to this.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method for identifying an underground mine air door and monitoring an abnormal state of the underground mine air door.
In order to solve the technical problems, the invention provides the following technical scheme:
the invention preferably comprises the following steps:
(1) the underground air door damage monitoring method comprises the following steps:
s11, configuring an algorithm model for the camera in the system;
s12, the system automatically issues the camera information to an algorithm service;
s13, performing calculation analysis on the real-time monitoring video of the camera by using algorithm service;
s14, after the camera finds that the air door is damaged, sending air door damage information;
s15, recording the video from the latest normal time of the air door to 15 seconds after the damage is found, and combining the video into the 4 th alarm information;
and S16, the alarm information can be continuously sent until the air door is repaired.
(2) The monitoring of the overlong opening time of the underground air door comprises the following steps:
s21, configuring an algorithm model and an allowable starting duration for the camera in the system;
s22, the system automatically issues the camera information to an algorithm service;
s23, performing calculation analysis on the real-time monitoring video of the camera by using algorithm service;
s24, after the camera finds that the air door is opened, timing the opening state of the air door;
s25, if the air door is closed, stopping timing, and returning to the step 3;
s26, if the opening time of the air door exceeds the allowable duration, sending alarm information, and firstly sending the alarm information that the air door without the video is damaged for the timeliness of the alarm information;
s27, recording the real-time state video of the air door, and combining the video into the 6 th alarm information;
s28, the alarm information can be continuously sent until the air door is closed;
s29, a user can combine alarm information with the same position and the same type in a period of time by using system configuration, so that visual interference to the user is reduced;
s210, if the system has false alarm, the system automatically records the event record into a false alarm database.
Preferably, in step S15, when the damage to the damper is abnormal, a video from the time when the damper is normal to 15 seconds after the damage is found is recorded and incorporated into the warning message of item S14.
Preferably, the algorithm in step (2) is embedded into a front-end camera to monitor the opening and closing state of the damper.
Preferably, S14 in step (1) sends alarm information that the damper without video is damaged, so as to ensure timeliness of the alarm information.
Preferably, in step s14, the algorithm service starts timing the open state of the damper after detecting that the damper is opened, and when the timing duration exceeds the allowable open duration of the damper, it is determined that the damper is opened abnormally for too long, and then an abnormality warning message is sent.
Preferably, in step S14, the algorithm service starts to time the open state of the damper after detecting that the damper is opened, and determines that the damper is normally opened and does not send an abnormal alarm message if the time length of the time does not exceed the allowable open time length.
Preferably, in step S16, the user may combine the same location and the same type of alarm information for a period of time using the system configuration, so as to reduce the visual interference to the user, and if a system false alarm occurs, the system automatically records the event in the false alarm database.
Preferably, the alarm message in step S27 continues until the damper is closed, and the user can use the system configuration to combine the same type of alarm messages at the same location over a period of time, to reduce the visual interference to the user, and if a system false alarm occurs, the system automatically records the event in a false alarm database.
Preferably, the steps of the downhole damper and damper status identification algorithm are as follows:
and S31, establishing corresponding algorithm models including a target detection model of the air door and a classification model of the air door according to the normal situation and the abnormal situation in the air door monitoring video.
S32, preparing a data set corresponding to an algorithm according to the content of the monitoring video; the air door detection algorithm marks specific position information of the air door in the image, and the air door classification algorithm captures an image of the air door and marks whether the current state of the air door is open or closed.
And S33, acquiring an anchor point of the air door in the image through the labeling condition in the data set, taking the position coordinates of the air door in the image as label information, extracting air door characteristic information of different scales from the input image through a plurality of multilayer convolutional neural networks, combining to obtain overall characteristics, and outputting the position coordinates and the probability value of the air door through a full connection layer. When the probability value is greater than 0.5, the current prediction is retained.
S34, judging whether the prediction effect is good or not through the IoU ratio of the sitting prediction frame to the labeling data frame, wherein the loss function of the whole model is as follows:
s5, classifying the detected air door by using a classification algorithm, dividing the state of the air door into a closed state and an open state for data labeling, extracting characteristic output 0 or 1 through a residual error network, respectively representing the closed state and the open state, comparing the characteristic output with the labeled state, comparing a cross entropy loss function for comparison,
the invention has the following beneficial effects:
1. the underground air door state can be monitored in real time, the longest opening time of the air door can be set according to actual needs, once the opening time of the air door exceeds a set value, alarm information is sent out immediately, information such as the position of the air door, the state of the air door and videos in the alarm information can be avoided, managers can check the videos directly to carry out manual judgment after the alarm information is obtained, and whether the alarm information is real effective information is judged. The manpower for checking the monitoring picture is saved, and meanwhile, the monitoring picture can be checked without going into the well, so that the safety of management personnel is improved. Meanwhile, damage monitoring of the air door can be achieved, for example, the air door is knocked away by a rubber-tyred vehicle, the process and the result of knocking of the air door can be recorded, and when the safety is improved, responsibility pursuit can also be achieved.
2. The system has obvious and strong alarm prompt, so that the manager cannot omit each alarm message, and each alarm message can be ensured to be concerned by the manager, thereby avoiding the occurrence of accidents.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic flow chart of the downhole damper damage monitoring steps of the present invention;
FIG. 2 is a schematic flow chart of the downhole damper open time overlength monitoring process of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
Examples
As shown in fig. 1-2, the present invention provides, among other things, a method comprising the steps of:
(1) the underground air door damage monitoring method comprises the following steps:
s11, configuring an algorithm model for the camera in the system;
s12, the system automatically issues the camera information to an algorithm service;
s13, performing calculation analysis on the real-time monitoring video of the camera by using algorithm service;
s14, after the camera finds that the air door is damaged, sending air door damage information;
s15, recording the video from the latest normal time of the air door to 15 seconds after the damage is found, and combining the video into the 4 th alarm information;
and S16, the alarm information can be continuously sent until the air door is repaired.
(2) The monitoring of the overlong opening time of the underground air door comprises the following steps:
s21, configuring an algorithm model and an allowable starting duration for the camera in the system;
s22, the system automatically issues the camera information to an algorithm service;
s23, performing calculation analysis on the real-time monitoring video of the camera by using algorithm service;
s24, after the camera finds that the air door is opened, timing the opening state of the air door;
s25, if the air door is closed, stopping timing, and returning to the step 3;
s26, if the opening time of the air door exceeds the allowable duration, sending alarm information, and firstly sending the alarm information that the air door without the video is damaged for the timeliness of the alarm information;
s27, recording the real-time state video of the air door, and combining the video into the 6 th alarm information;
s28, the alarm information can be continuously sent until the air door is closed;
s29, a user can combine alarm information with the same position and the same type in a period of time by using system configuration, so that visual interference to the user is reduced;
s210, if the system has false alarm, the system automatically records the event record into a false alarm database.
In step S15, when the air door is damaged abnormally, the video from the latest time when the air door is normal to 15 seconds after the damage is found is recorded and incorporated into the alarm information of item S14.
And (3) embedding the algorithm in the step (2) into a front-end camera, and monitoring the opening and closing state of the air door.
Wherein, the step (1) of S14 sends alarm information that the air door without video is damaged, so as to ensure the timeliness of the alarm information.
In step s14, after detecting that the air door is opened, the algorithm service starts timing the opening state of the air door, and when the timing duration exceeds the allowable opening duration of the air door, it is determined that the air door is opened abnormally for too long, and at this time, an abnormal alarm message is sent.
In step S14, after detecting that the air door is opened, the algorithm service starts to time the opening state of the air door, and if the time length of the time does not exceed the allowable opening time length of the air door, it is determined that the air door is normally opened, and no abnormal alarm information is sent.
In step S16, the user may combine the same position and type of alarm information within a period of time using the system configuration, so as to reduce the visual interference to the user, and if a system false alarm occurs, the system automatically records the event record into a false alarm database.
The alarm information in step S27 continues until the damper is closed, and the user can use the system configuration to combine the same position and type of alarm information in a period of time, so as to reduce the visual interference to the user.
The steps of the downhole damper and damper state identification algorithm are as follows:
and S31, establishing corresponding algorithm models including a target detection model of the air door and a classification model of the air door according to the normal situation and the abnormal situation in the air door monitoring video.
S32, preparing a data set corresponding to an algorithm according to the content of the monitoring video; the air door detection algorithm marks specific position information of the air door in the image, and the air door classification algorithm captures an image of the air door and marks whether the current state of the air door is open or closed.
And S33, acquiring an anchor point of the air door in the image through the labeling condition in the data set, taking the position coordinates of the air door in the image as label information, extracting air door characteristic information of different scales from the input image through a plurality of multilayer convolutional neural networks, combining to obtain overall characteristics, and outputting the position coordinates and the probability value of the air door through a full connection layer. When the probability value is greater than 0.5, the current prediction is retained.
S34, judging whether the prediction effect is good or not through the IoU ratio of the sitting prediction frame to the labeling data frame, wherein the loss function of the whole model is as follows:
s5, classifying the detected air door by using a classification algorithm, dividing the state of the air door into a closed state and an open state for data labeling, extracting characteristic output 0 or 1 through a residual error network, respectively representing the closed state and the open state, comparing the characteristic output with the labeled state, comparing a cross entropy loss function for comparison,
finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. The method for identifying the underground mine air door and monitoring the abnormal state of the underground mine air door is characterized by comprising the following steps of:
(1) the underground air door damage monitoring method comprises the following steps:
s11, configuring an algorithm model for the camera in the system;
s12, the system automatically issues the camera information to an algorithm service;
s13, performing calculation analysis on the real-time monitoring video of the camera by using algorithm service;
s14, after the camera finds that the air door is damaged, sending air door damage information;
s15, recording the video from the latest normal time of the air door to 15 seconds after the damage is found, and combining the video into the 4 th alarm information;
and S16, the alarm information can be continuously sent until the air door is repaired.
(2) The monitoring of the overlong opening time of the underground air door comprises the following steps:
s21, configuring an algorithm model and an allowable starting duration for the camera in the system;
s22, the system automatically issues the camera information to an algorithm service;
s23, performing calculation analysis on the real-time monitoring video of the camera by using algorithm service;
s24, after the camera finds that the air door is opened, timing the opening state of the air door;
s25, if the air door is closed, stopping timing, and returning to the step 3;
s26, if the opening time of the air door exceeds the allowable duration, sending alarm information, and firstly sending the alarm information that the air door without the video is damaged for the timeliness of the alarm information;
s27, recording the real-time state video of the air door, and combining the video into the 6 th alarm information;
s28, the alarm information can be continuously sent until the air door is closed;
s29, a user can combine alarm information with the same position and the same type in a period of time by using system configuration, so that visual interference to the user is reduced;
s210, if the system has false alarm, the system automatically records the event record into a false alarm database.
2. The mine down-hole damper identification and abnormal state monitoring method according to claim 1, characterized in that: in the step S15, when the air door is damaged abnormally, the video from the latest time when the air door is normal to 15 seconds after the damage is found is recorded and combined into the alarm information of the step S14.
3. The mine down-hole damper identification and abnormal state monitoring method according to claim 1, characterized in that: and (3) embedding the algorithm in the step (2) into a front-end camera to monitor the opening and closing state of the air door.
4. The mine down-hole damper identification and abnormal state monitoring method according to claim 1, characterized in that: s14 in the step (1) sends alarm information that the air door without the video is damaged, so that timeliness of the alarm information is ensured.
5. The mine down-hole damper identification and abnormal state monitoring method according to claim 1, characterized in that: in step s14, the algorithm service starts timing the open state of the air door after detecting that the air door is opened, and determines that the air door is opened abnormally for a long time when the timing time exceeds the allowable open time of the air door, and sends an abnormal alarm message at this time.
6. The mine down-hole damper identification and abnormal state monitoring method according to claim 1, characterized in that: in step S14, after the algorithm service detects that the air door is opened, it starts to time the opening state of the air door, and if the time length of the time does not exceed the allowable opening time length, it is determined that the air door is normally opened, and no abnormal alarm information is sent.
7. The mine down-hole damper identification and abnormal state monitoring method according to claim 1, characterized in that: in step S16, the user may use the system configuration to combine the same position and type of alarm information within a period of time, so as to reduce the visual interference to the user, and if there is a system false alarm, the system automatically records the event in a false alarm database.
8. The mine down-hole damper identification and abnormal state monitoring method according to claim 1, characterized in that: the alarm information in step S27 continues until the damper is closed, and the user can use the system configuration to combine the same position and type of alarm information over a period of time, so as to reduce the visual interference to the user.
9. The mine down-hole damper identification and abnormal state monitoring method according to claim 1, characterized in that the steps of the down-hole damper and damper state identification algorithm are as follows:
and S31, establishing corresponding algorithm models including a target detection model of the air door and a classification model of the air door according to the normal situation and the abnormal situation in the air door monitoring video.
S32, preparing a data set corresponding to an algorithm according to the content of the monitoring video; the air door detection algorithm marks specific position information of the air door in the image, and the air door classification algorithm captures an image of the air door and marks whether the current state of the air door is open or closed.
And S33, acquiring an anchor point of the air door in the image through the labeling condition in the data set, taking the position coordinates of the air door in the image as label information, extracting air door characteristic information of different scales from the input image through a plurality of multilayer convolutional neural networks, combining to obtain overall characteristics, and outputting the position coordinates and the probability value of the air door through a full connection layer. When the probability value is greater than 0.5, the current prediction is retained.
S34, judging whether the prediction effect is good or not through the IoU ratio of the sitting prediction frame to the labeling data frame, wherein the loss function of the whole model is as follows:
s5, classifying the detected air door by using a classification algorithm, dividing the state of the air door into a closed state and an open state for data labeling, extracting characteristic output 0 or 1 through a residual error network, respectively representing the closed state and the open state, comparing the characteristic output with the labeled state, comparing a cross entropy loss function for comparison,
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011216352.2A CN112343657B (en) | 2020-11-04 | 2020-11-04 | Method for identifying mine underground air door and monitoring abnormal state of mine underground air door |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011216352.2A CN112343657B (en) | 2020-11-04 | 2020-11-04 | Method for identifying mine underground air door and monitoring abnormal state of mine underground air door |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112343657A true CN112343657A (en) | 2021-02-09 |
CN112343657B CN112343657B (en) | 2022-11-08 |
Family
ID=74428234
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011216352.2A Active CN112343657B (en) | 2020-11-04 | 2020-11-04 | Method for identifying mine underground air door and monitoring abnormal state of mine underground air door |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112343657B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114036465A (en) * | 2021-11-26 | 2022-02-11 | 辽宁工程技术大学 | Air door opening and closing disturbance identification method based on wind speed monitoring |
CN117422991A (en) * | 2023-10-07 | 2024-01-19 | 中色地科蓝天矿产(北京)有限公司 | Intelligent mine detection system and method based on big data and readable storage medium |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101581932A (en) * | 2009-06-23 | 2009-11-18 | 北京旺斯达科技有限公司 | Coal mine safety monitoring system |
CN102979555A (en) * | 2011-09-13 | 2013-03-20 | 杜志刚 | Stope face roadway full-automatic safety equipment |
CN203547781U (en) * | 2013-09-22 | 2014-04-16 | 济南嘉宏科技有限责任公司 | Remote-monitoring full-automatic mining damper system |
CN103883351A (en) * | 2014-03-28 | 2014-06-25 | 山东中盾电气设备有限公司 | Mine comprehensive on-line monitoring system |
CN103953381A (en) * | 2014-05-26 | 2014-07-30 | 蓝小玲 | Full-automatic intelligent security interlocking air door system |
CN203796304U (en) * | 2014-04-25 | 2014-08-27 | 南通神华电气有限公司 | Automatic monitoring device for mine disaster relief air doors |
CN105370310A (en) * | 2015-12-16 | 2016-03-02 | 北京天地华泰矿业管理股份有限公司 | Self-lock device and method for outburst prevention air door |
CN106168141A (en) * | 2016-09-08 | 2016-11-30 | 山东科技大学 | A kind of mine working air door intelligence control system and control method thereof |
CN110284928A (en) * | 2019-07-03 | 2019-09-27 | 济南嘉宏科技有限责任公司 | A kind of mining multitask intelligence air door management system |
CN111828076A (en) * | 2020-08-18 | 2020-10-27 | 福州大学 | Automatic ventilation system for underground mine |
-
2020
- 2020-11-04 CN CN202011216352.2A patent/CN112343657B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101581932A (en) * | 2009-06-23 | 2009-11-18 | 北京旺斯达科技有限公司 | Coal mine safety monitoring system |
CN102979555A (en) * | 2011-09-13 | 2013-03-20 | 杜志刚 | Stope face roadway full-automatic safety equipment |
CN203547781U (en) * | 2013-09-22 | 2014-04-16 | 济南嘉宏科技有限责任公司 | Remote-monitoring full-automatic mining damper system |
CN103883351A (en) * | 2014-03-28 | 2014-06-25 | 山东中盾电气设备有限公司 | Mine comprehensive on-line monitoring system |
CN203796304U (en) * | 2014-04-25 | 2014-08-27 | 南通神华电气有限公司 | Automatic monitoring device for mine disaster relief air doors |
CN103953381A (en) * | 2014-05-26 | 2014-07-30 | 蓝小玲 | Full-automatic intelligent security interlocking air door system |
CN105370310A (en) * | 2015-12-16 | 2016-03-02 | 北京天地华泰矿业管理股份有限公司 | Self-lock device and method for outburst prevention air door |
CN106168141A (en) * | 2016-09-08 | 2016-11-30 | 山东科技大学 | A kind of mine working air door intelligence control system and control method thereof |
CN110284928A (en) * | 2019-07-03 | 2019-09-27 | 济南嘉宏科技有限责任公司 | A kind of mining multitask intelligence air door management system |
CN111828076A (en) * | 2020-08-18 | 2020-10-27 | 福州大学 | Automatic ventilation system for underground mine |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114036465A (en) * | 2021-11-26 | 2022-02-11 | 辽宁工程技术大学 | Air door opening and closing disturbance identification method based on wind speed monitoring |
CN114036465B (en) * | 2021-11-26 | 2024-04-12 | 辽宁工程技术大学 | Wind door opening and closing disturbance identification method based on wind speed monitoring |
CN117422991A (en) * | 2023-10-07 | 2024-01-19 | 中色地科蓝天矿产(北京)有限公司 | Intelligent mine detection system and method based on big data and readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN112343657B (en) | 2022-11-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112343657B (en) | Method for identifying mine underground air door and monitoring abnormal state of mine underground air door | |
CN105540377A (en) | Internet of things remote elevator monitoring system with human face matching function | |
CN210691345U (en) | Cloud intelligence safety inspection auxiliary system based on degree of depth learning | |
CN111932709A (en) | Method for realizing violation safety supervision of inspection operation of gas station based on AI identification | |
CN110147762A (en) | A kind of embedded type fire control wrong report elimination system | |
CN117119175B (en) | Underground coal mine air door AI video safety management control system | |
CN108039020A (en) | A kind of warehouse safety monitoring alarming system | |
CN110287917A (en) | The security management and control system and method in capital construction building site | |
CN113393625A (en) | Anti-theft alarm evidence obtaining method and system for intelligent lamp pole | |
CN111516708A (en) | Subway platform door obstacle detection early warning system based on machine vision technology | |
CN110928305B (en) | Patrol method and system for patrol robot of railway passenger station | |
CN116993265A (en) | Intelligent warehouse safety management system based on Internet of things | |
CN111062932A (en) | Monitoring method of network service program | |
CN114413055B (en) | Operation and maintenance device and method for interlocking air valve of subway tunnel fan | |
CN115359416A (en) | Intelligent early warning system for railway freight yard sky eye | |
CN112184496B (en) | Elevator cloud platform management system | |
CN114943481A (en) | Intelligent operation and maintenance management system for urban tunnel based on BIM | |
CN113762783A (en) | Online detection platform for digital industrial products | |
CN107516079A (en) | A kind of demographic using recognition of face and warning system and its method | |
CN113721564A (en) | Intelligent workshop safety management system | |
CN210405509U (en) | Efficient community security center | |
CN108961661B (en) | Three-dimensional security intelligent alarm linkage system | |
CN112666911A (en) | Cooperative control system | |
KR20200078736A (en) | Method for safely managing and monitoring railroad station and the periphery zone | |
KR102555938B1 (en) | Video monitoring system using artificial intelligence |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |