CN111696320B - Intelligent visual early warning system for early gas leakage - Google Patents
Intelligent visual early warning system for early gas leakage Download PDFInfo
- Publication number
- CN111696320B CN111696320B CN202010543068.XA CN202010543068A CN111696320B CN 111696320 B CN111696320 B CN 111696320B CN 202010543068 A CN202010543068 A CN 202010543068A CN 111696320 B CN111696320 B CN 111696320B
- Authority
- CN
- China
- Prior art keywords
- gas leakage
- organic gas
- model
- detection
- monitoring 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.)
- Expired - Fee Related
Links
- 230000000007 visual effect Effects 0.000 title claims abstract description 20
- 238000012544 monitoring process Methods 0.000 claims abstract description 80
- 238000001514 detection method Methods 0.000 claims abstract description 58
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000012549 training Methods 0.000 claims abstract description 9
- 238000013135 deep learning Methods 0.000 claims abstract description 7
- 238000013461 design Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 description 10
- 230000018109 developmental process Effects 0.000 description 10
- 238000000034 method Methods 0.000 description 5
- 230000007547 defect Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000009432 framing Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 231100000572 poisoning Toxicity 0.000 description 1
- 230000000607 poisoning effect Effects 0.000 description 1
- 239000007858 starting material Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
- G08B21/12—Alarms for ensuring the safety of persons responsive to undesired emission of substances, e.g. pollution alarms
-
- 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
- G06N3/045—Combinations of 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/30—Transforming light or analogous information into electric information
- H04N5/33—Transforming infrared radiation
-
- 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
- H04N7/183—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Toxicology (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The invention relates to an intelligent visual early warning system for early gas leakage, which comprises a detected area, a data collecting and processing module and a central control room; the data collecting and processing module is responsible for monitoring video real-time storage and leakage detection positioning, and the central control room is responsible for organic gas leakage display and early warning; the organic gas leakage detection positioning module adopted by the invention belongs to a deep learning hybrid model, and the trained module is embedded into the embedded information processor to realize automatic detection of organic gas leakage in the monitoring video. The model adopted by the invention comprises an unsupervised self-coding model and a supervised target identification model, the former avoids the problem that the supervised model training is difficult to collect and label the data set, the latter only aims at the data set at the leakage source, the data set is easy to collect and label, the high detection rate and the low false alarm rate of the detection and positioning of the organic gas are ensured, and the safety guarantee is provided for the field of petrochemical industry.
Description
Technical Field
The invention relates to an intelligent visual early warning system for early gas leakage, and belongs to the technical field of organic gas leakage monitoring.
Background
In the petrochemical industry and other process industries, the organic gas leakage can cause safety accidents such as burning explosion, poisoning, environmental pollution and the like. Therefore, on-site organic gas leaks should be monitored early. In the aspect of organic gas leakage monitoring, the conventional sensor has high gas leakage detection false alarm rate, is greatly influenced by the field environment, and cannot accurately determine the leakage position, so that higher risk exists. Compare sensor monitoring mode, infrared monitoring mode of making a video recording can realize organic gas leakage visual monitoring, but needs the artifical real-time supervision video of observing, and whether the artificial judgement takes place organic gas leakage, and this kind of monitoring mode receives artificial subjective influence, consumes the manpower and appears failing to report, the wrong report condition easily. In recent years, the early-stage gas leakage characteristics are intelligently and automatically learned based on a deep learning supervised anomaly recognition algorithm, and a trained model can replace a human monitoring video. However, the network model constructed by the deep learning needs a large amount of abnormal labeled data for training, organic gas leakage belongs to rare events, and it is difficult to collect and obtain a large amount of labeled data representing abnormal characteristics of organic gas leakage in reality, so that the model based on the deep supervised learning is easy to detect data similar to the abnormal leaked gas as the abnormal leaked gas, and abnormal false alarm occurs in the system. The network model based on the unsupervised deep learning theory can represent abnormal space-time characteristics of non-leakage gas without a large amount of abnormal marking data so as to overcome the defect of a deep supervised learning detection model, but the model cannot visually give the abnormal position of the leakage gas. In view of the harm of organic gas leakage and the defects of an intelligent monitoring technology, the early-stage gas leakage intelligent visual early warning system needs to be invented urgently, the high detection rate and the low false alarm rate are guaranteed, meanwhile, the early-stage gas leakage abnormal position is intelligently determined on line in real time, and safety guarantee is provided for the field of petrochemical industry.
Disclosure of Invention
The invention provides an intelligent visual early warning system for early gas leakage, which is used for overcoming the defects in the prior art.
The invention is realized by the following technical scheme:
an intelligent visual early warning system for early gas leakage comprises a monitored area, a data collecting and processing module, a detection and positioning module and a central control room; the monitored area is distributed with storage tanks for storing materials, and organic gas leakage can occur due to human factors, aging corrosion and the like; the data acquisition and processing system comprises an infrared camera, a data line, an embedded information processor and a display control terminal, wherein a plurality of infrared cameras are arranged at the infrared camera, and the infrared cameras can carry out secondary development of SDK; the detection positioning module comprises an organic gas leakage detection model and an organic gas leakage positioning model, the two models are embedded into the embedded information processor, and the SDK secondary development program can call the infrared monitoring video in real time and transmit the infrared monitoring video to the detection positioning module; the central control room adopts an explosion-proof design and is provided with an embedded information processor and a display control terminal; the organic gas leakage detection and positioning working steps are as follows: the monitoring system comprises an infrared camera end monitoring tank area, monitoring videos are transmitted to an embedded information processor in real time, the embedded information processor stores and calls the monitoring videos, a detection positioning module processes the called monitoring videos and outputs a scene normal curve in real time, when the scene normal curve value is lower than a set threshold value, the system can determine that organic gas leakage occurs in the monitoring area, then a gas leakage positioning model of a starter is started, the organic gas leakage positioning model detects organic gas leakage sources and marks the leakage sources, and a display control terminal displays the monitoring videos with organic gas leakage marks and positioning marks.
According to the early-stage gas leakage intelligent visual early warning system, the embedded information processor is embedded with the SDK secondary development program and the detection positioning module, and the SDK secondary development program is responsible for monitoring video storage and real-time calling.
As mentioned above, the detection positioning module comprises an organic gas leakage monitoring model and an organic gas leakage positioning model, and belongs to a mixed deep learning algorithm model, the organic gas leakage detection model firstly determines whether organic gas leakage occurs in a monitored area, and if organic gas leakage occurs, the system can start the organic gas leakage positioning device to perform leakage source positioning and marking.
According to the early-stage gas leakage intelligent visual early warning system, the organic gas leakage detection model adopts a Conv-LSTM layer to encode time and space information, the trained Conv-LSTMConv2D self-encoding model can reconstruct an original input monitoring video frame, and the organic gas leakage detection steps are as follows:
step S1, data call: adopting an SDK secondary development program to call a real-time monitoring video, and performing framing processing on the monitoring video to obtain monitoring images according to a time sequence;
step S2, reconstructing output: selecting n frames of monitoring images according to a time sequence by adopting a sliding window technology, inputting the monitoring images into a Conv-LSTMConv2D self-coding model, and outputting reconstructed monitoring images;
step S3, reconstruction error: calculating the reconstruction error of the n frames of monitoring images, calculating normal scores and outputting a normal score curve of the corresponding frame number;
step S4, abnormality detection: when the normal score is lower than a certain threshold value, the organic gas leakage can be judged, and a machine leakage positioning model is available.
According to the early-stage gas leakage intelligent visual early warning system, the scene normal curve is used for judging whether organic gas leakage occurs or not, representing the normal degree of the monitoring video scene, and related to the reconstruction error of the sequence monitoring image, the pixel intensity value I (x, y, t) of the (x, y) position of the t-frame initial monitoring image and the reconstructed monitoring image fwThe reconstruction error of (I (x, y, t)) is:
e(x,y,t)＝||I(x,y,t)-fw(I(x,y,t))||2 (1)
and accumulating the reconstruction errors in all pixel directions to obtain the reconstruction errors of the t frames of monitoring images:
starting from t frames, the reconstruction error of the monitoring image of n frame sequences is:
the normal score of the scene of the n frame sequence monitoring video is as follows:
according to the early-stage gas leakage intelligent visual early warning system, the organic gas leakage positioning model is obtained by training an organic gas leakage source video data set through fast RCNN, and when the normal score of a monitoring video sequence is lower than a set threshold value, the organic gas leakage positioning model can position the leakage source of the sequence monitoring video.
The invention has the advantages that: the method divides the organic gas leakage early warning into two steps of organic gas leakage detection and positioning, and realizes real-time and intelligent online determination of the abnormal position of early-stage leaked gas under the condition of simultaneously ensuring high detection rate and low false alarm rate; the core part of the invention is a deep learning mixed algorithm model, which is realized by mixing two models of unsupervised leakage detection and supervised leakage source positioning; the unsupervised leakage detection model avoids the problems that a training data set is difficult to obtain and label, and the model detection precision is high; the leakage positioning model is started after the oil gas leakage is confirmed, and the model only collects a leakage source training data set for training, so that the leakage label is easy to obtain and label.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic structural diagram of an early-stage gas leakage intelligent visual early warning system; FIG. 2 is a plot of normal fraction for an organic gas leak scenario; fig. 3 is an organic gas leak detection and localization flow.
Reference numerals: the system comprises a monitored area 1, an infrared camera shooting end 2, a data line 3, a central control room 4, an embedded information processor 5, a detection positioning module 6 and a display control terminal 7.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
An intelligent visual early warning system for early gas leakage is shown in the figure and comprises a monitored area 1, a data collecting and processing module, a detection and positioning module 6 and a central control room 4; the monitored area 1 is provided with a storage tank for storing materials; the data collecting and processing module comprises an infrared camera 2, a data line 3, an embedded information processor 5 and a display control terminal 7, wherein the infrared camera 2 consists of an infrared camera with SDK secondary development; the detection positioning module 6 comprises an organic gas leakage detection model and an organic gas leakage positioning model, the two models are embedded into the embedded information processor 5, and the monitoring video is called and processed through an SDK development program; the central control room 4 is provided with an embedded information processor 5 and a display control terminal 7, and the central control room 4 adopts an explosion-proof design; the organic gas leakage detection and positioning work steps are as follows: the infrared camera end 2 monitors the monitored area 1 in real time, the data line 3 is responsible for monitoring video transmission to the embedded information processor 5, the embedded information processor 5 stores and calls the monitoring video, the detection positioning module 6 processes the monitoring video, the organic gas leakage detection model processes the monitoring video in real time, the normal fractional curve of a monitoring video scene is output, when the normal fractional curve of the scene is lower than a set threshold value, the system judges that organic gas leakage occurs and starts the organic gas leakage positioning model, the organic gas leakage positioning model detects an organic gas leakage source and marks the leakage source, and the display control terminal 7 displays the monitoring video of the organic gas leakage mark and the positioning mark.
Specifically, the embedded information processor 5 according to this embodiment embeds the detection positioning module 6 and the SDK development program, and the detection positioning module 6 calls the real-time monitoring video through the SDK secondary development program.
Specifically, the detection positioning module described in this embodiment includes an organic gas leakage detection model and an organic gas leakage positioning model, where the organic gas leakage detection model is responsible for detecting whether organic gas leakage occurs in a monitoring video scene, and the organic gas leakage positioning model is responsible for finding out an organic gas leakage source.
Specifically, the organic gas leakage detection model described in this embodiment is a Conv-LSTMConv2D self-encoding model formed by training a normal scene monitoring video, and the model is composed of a space encoder, a time encoder, a Bottleneck Layer (bottle Layer), a time decoder, and a space decoder, and can reconstruct and output an original monitoring video, and the detection steps of the organic gas leakage detection model are as follows:
step S1, data retrieval: an SDK secondary development program in the embedded information processor 6 calls a monitoring video in real time and performs framing processing on the monitoring video to obtain time sequence monitoring video frames;
step S2, reconstructing a video: the sliding window algorithm in the embedded information processor 6 selects n frames of monitoring images as the original input of the organic gas leakage detection model, and the organic gas leakage detection model outputs a reconstructed sequence image;
step S4, reconstruction error: calculating the reconstruction error of the n frames of monitoring images, calculating the normal score of the scene and outputting a normal score curve of the corresponding frame number;
step S4, abnormality detection: and when the normal score is lower than a set threshold value, judging that organic gas leakage occurs, and starting an organic gas leakage positioning model.
Specifically, the scene normal curve described in this embodiment is used to determine whether organic gas leakage occurs, and represents the normal degree of the scene of the monitoring video, where a high value of the normal curve indicates that the monitoring video is normal, and a value of the normal curve lower than a set threshold indicates that organic gas leakage occurs.
Specifically, the organic gas leakage positioning model described in this embodiment is a fast RCNN model trained by a collected organic gas leakage source video data set, and when a normal score of a sequence scene of a monitoring video is lower than a set threshold, the organic gas leakage positioning model performs leakage source positioning on the sequence monitoring video.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (6)
1. The utility model provides an early visual early warning system of gas leakage intelligence which characterized in that: comprises a monitored area (1), a data collecting and processing module, a detection positioning module (6) and a central control room (4); a material storage tank is arranged in the monitored area (1), and infrared camera ends (2) are distributed above the area; the data collecting and processing module comprises an infrared camera (2), a data line (3), an embedded information processor (5) and a display control terminal (7), wherein the infrared camera is composed of an infrared camera with SDK secondary development; the detection positioning module (6) comprises an organic gas leakage detection model and an organic gas leakage positioning model, the detection positioning module (6) is embedded into the embedded information processor (5), and the detection positioning module (6) is used for calling a monitoring video by an SDK development program; the central control room (4) is provided with an embedded information processor (5) and a display control terminal (7), and the central control room (4) adopts an explosion-proof design; the organic gas leakage detection and positioning working steps are as follows: the monitoring of infrared camera end (2) real-time supervision is monitored the district, the monitoring video is transmitted to embedded information processor (5) through data line (3), embedded information processor (5) storage and call monitoring video, detect the monitoring video that positioning module (6) processing called, organic gas leaks the detection video of detection model input, the normal fraction curve of scene of monitoring video is rebuild in output and monitoring video is exported and rebuild, when the normal fraction of scene of monitoring video is less than the settlement threshold value, the system judges that organic gas leaks and starts organic gas and reveals the location model, organic gas leaks the location model and detects organic gas and leaks the source and marks and leaks the source, display control terminal (7) show organic gas and leak the monitoring video of location mark.
2. The intelligent visual early warning system for early gas leakage according to claim 1, wherein: the embedded information processor (5) is embedded with a detection positioning module (6) and an SDK development program, and the detection positioning module 6 calls a real-time monitoring video through the SDK development program.
3. The intelligent visual early warning system for early gas leakage according to claim 1, wherein: the detection positioning module belongs to a mixed deep learning algorithm model and comprises an organic gas leakage detection model and an organic gas leakage positioning model, wherein the organic gas leakage detection model is responsible for detecting whether organic gas leakage occurs in a monitoring video scene, and the organic gas leakage positioning model is responsible for finding out an organic gas leakage source.
4. The intelligent visual early warning system for early gas leakage according to claim 1, wherein: the organic gas leakage detection model is a Conv-LSTMConv2D self-coding model formed by training normal scene monitoring videos, the model consists of a space encoder, a time encoder, a Bottleneck Layer (Bottleneck Layer), a time decoder and a space decoder, the Conv-LSTM Layer is used for realizing time and space information encoding, and the model outputs and reconstructs original monitoring videos.
5. The intelligent visual early warning system for early gas leakage according to claim 1, wherein: the scene normal curve is used for judging whether organic gas leakage occurs or not, the curve value is related to reconstruction errors, and the pixel intensity value I (x, y, t) of the position of the monitoring image (x, y) of the initial t frames and the reconstructed monitoring image fwThe reconstruction error of (I (x, y, t)) is:
e(x,y,t)＝||I(x,y,t)-fw(I(x,y,t))||2 (1)
and accumulating the reconstruction errors in all pixel directions to obtain the reconstruction errors of the t frames of monitoring images:
starting from t frames, the reconstruction error of the monitoring image of n frame sequences is:
the normal score of the scene of the n frame sequence monitoring video is as follows:
the scene normal score represents the normal degree of the scene of the monitoring video, the high value represents that the monitoring video is normal, and the scene normal curve value is lower than the set threshold value and represents that organic gas leakage occurs.
6. The intelligent visual early warning system for early gas leakage according to claim 1, wherein: the organic gas leakage positioning model is obtained by training an organic gas leakage video data set through fast RCNN, and when the normal score of a certain sequence of the monitoring video is lower than a set threshold value, the organic gas leakage positioning model can perform leakage source positioning on the sequence of the monitoring video.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010543068.XA CN111696320B (en) | 2020-06-15 | 2020-06-15 | Intelligent visual early warning system for early gas leakage |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010543068.XA CN111696320B (en) | 2020-06-15 | 2020-06-15 | Intelligent visual early warning system for early gas leakage |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111696320A CN111696320A (en) | 2020-09-22 |
| CN111696320B true CN111696320B (en) | 2021-11-26 |
Family
ID=72481074
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010543068.XA Expired - Fee Related CN111696320B (en) | 2020-06-15 | 2020-06-15 | Intelligent visual early warning system for early gas leakage |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111696320B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113469098B (en) * | 2021-07-13 | 2022-08-26 | 中国石油大学(华东) | Intelligent visual monitoring device for organic hazardous chemical leakage |
| CN115206063A (en) * | 2022-07-21 | 2022-10-18 | 因士(上海)科技有限公司 | Oil gas leakage visual monitoring system and method |
| US11953161B1 (en) | 2023-04-18 | 2024-04-09 | Intelcon System C.A. | Monitoring and detecting pipeline leaks and spills |
| CN116682070B (en) * | 2023-08-03 | 2024-05-28 | 武汉工程大学 | Infrared video detection method and system for dangerous gas leakage under complex scene |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3270134A1 (en) * | 2015-03-09 | 2018-01-17 | Konica Minolta, Inc. | Gas leak location estimating device, gas leak location estimating system, gas leak location estimating method and gas leak location estimating program |
| CN109191796A (en) * | 2018-11-12 | 2019-01-11 | 南京工程学院 | A kind of natural gas leaking detection device and method based on infrared image |
| WO2019138873A1 (en) * | 2018-01-09 | 2019-07-18 | コニカミノルタ株式会社 | Gas detection-use image processing device, and gas detection-use image processing method |
| CN110136210A (en) * | 2018-02-07 | 2019-08-16 | 中国石油化工股份有限公司 | A kind of intelligent early-warning system of monitoring device leakage |
| CN110414478A (en) * | 2019-08-08 | 2019-11-05 | 东莞德福得精密五金制品有限公司 | The contingency liquefied gas leak supervision method of the non-Application inductor of artificial intelligence cloud computing |
-
2020
- 2020-06-15 CN CN202010543068.XA patent/CN111696320B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3270134A1 (en) * | 2015-03-09 | 2018-01-17 | Konica Minolta, Inc. | Gas leak location estimating device, gas leak location estimating system, gas leak location estimating method and gas leak location estimating program |
| WO2019138873A1 (en) * | 2018-01-09 | 2019-07-18 | コニカミノルタ株式会社 | Gas detection-use image processing device, and gas detection-use image processing method |
| CN110136210A (en) * | 2018-02-07 | 2019-08-16 | 中国石油化工股份有限公司 | A kind of intelligent early-warning system of monitoring device leakage |
| CN109191796A (en) * | 2018-11-12 | 2019-01-11 | 南京工程学院 | A kind of natural gas leaking detection device and method based on infrared image |
| CN110414478A (en) * | 2019-08-08 | 2019-11-05 | 东莞德福得精密五金制品有限公司 | The contingency liquefied gas leak supervision method of the non-Application inductor of artificial intelligence cloud computing |
Non-Patent Citations (1)
| Title |
|---|
| Machine vision for natural gas methane emissions detection using an infrared camera;Jingfan Wang 等;《Applied Energy》;20191031;第1-9页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111696320A (en) | 2020-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111696320B (en) | Intelligent visual early warning system for early gas leakage | |
| LU502731B1 (en) | Method for monitoring abnormality of power production, apparatus, computer device, and storage medium therefor | |
| CN112287816B (en) | Dangerous work area accident automatic detection and alarm method based on deep learning | |
| CN112487356B (en) | Structural health monitoring data enhancement method | |
| CN111723720A (en) | Intelligent visual real-time online monitoring system for organic gas leakage | |
| US20240346461A1 (en) | Methods and internet of things systems for managing robots in pipeline corridor of gas based on regulatory internet of things | |
| CN113343998A (en) | Reading monitoring system and method for electric power mechanical meter, computer equipment and application | |
| CN118172693A (en) | Method for intelligently identifying illegal filling of liquefied gas cylinder through video | |
| CN118197027A (en) | Unmanned aerial vehicle scheduling checking method based on pipeline early warning and related device | |
| CN113114987B (en) | Hadoop-based power system inspection method and system | |
| CN110779077A (en) | Intelligent geothermal operation and maintenance system | |
| CN117274697A (en) | Method and system for automatically identifying pipeline thermal leakage based on image | |
| CN117113255A (en) | Liquefied natural gas safety monitoring system based on status monitoring and automatic content identification | |
| CN110232769A (en) | Distributed retail terminal modularization method for early warning based on big data statistics | |
| CN112784706B (en) | Oil testing test operation area safety control method based on image intelligent identification | |
| CN113065416B (en) | Leakage monitoring device integrated in transformer substation video monitoring device, leakage monitoring method and medium | |
| JPH1042274A (en) | Abnormality monitoring method and device | |
| CN117539674B (en) | Exception handling method, device, equipment and storage medium | |
| CN118211840B (en) | Regional pipe network safety assessment method and system for intelligent pipe network | |
| CN113362563B (en) | Method and device for determining abnormal condition of power tunnel | |
| KR102686245B1 (en) | Method for Diagnosing Heat Pipelines | |
| CN118570990B (en) | Intelligent quay crane operation monitoring large screen system and visual management method thereof | |
| CN117875946B (en) | Man-machine collaborative autonomous infrared inspection method for operation and maintenance of transformer substation equipment | |
| CN114140896A (en) | Voice broadcast panoramic intelligent inspection system | |
| CN117876717A (en) | Hydrogen micro-leakage intelligent identification method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20211126 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |