CN111582016A - Intelligent maintenance-free power grid monitoring method and system based on cloud edge collaborative deep learning - Google Patents
Intelligent maintenance-free power grid monitoring method and system based on cloud edge collaborative deep learning Download PDFInfo
- Publication number
- CN111582016A CN111582016A CN202010191686.2A CN202010191686A CN111582016A CN 111582016 A CN111582016 A CN 111582016A CN 202010191686 A CN202010191686 A CN 202010191686A CN 111582016 A CN111582016 A CN 111582016A
- Authority
- CN
- China
- Prior art keywords
- power grid
- monitoring
- image
- edge
- deep learning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 176
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000013135 deep learning Methods 0.000 title claims abstract description 32
- 238000001514 detection method Methods 0.000 claims abstract description 92
- 238000012549 training Methods 0.000 claims abstract description 71
- 238000013136 deep learning model Methods 0.000 claims abstract description 27
- 230000002159 abnormal effect Effects 0.000 claims description 41
- 230000005856 abnormality Effects 0.000 claims description 31
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 230000003993 interaction Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/086—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution networks, i.e. with interconnected conductors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Economics (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an intelligent maintenance-free power grid monitoring method and system based on cloud edge collaborative deep learning, wherein the method comprises the following steps: the sensing equipment collects the monitoring image and gives an alarm according to the alarm information; the edge computing node identifies the monitoring image based on the monitoring image and a power grid abnormity detection model issued by the cloud computing center, and sends alarm information to the sensing equipment when determining that the power grid abnormity exists; transmitting the identified monitoring image to a cloud computing center; the cloud computing center generates a power grid abnormity detection model according to the stored training set image training deep learning model, updates the power grid abnormity detection model according to the recognized monitoring image training, and issues the power grid abnormity detection model to the edge computing node; the invention also discloses a corresponding power grid monitoring system; by adopting the method and the system, the operation burden of the cloud computing center can be reduced.
Description
Technical Field
The invention belongs to the field of power grid safety protection, and particularly relates to an intelligent maintenance-free power grid monitoring method and system based on cloud edge collaborative deep learning.
Background
The application of intelligent video monitoring in an electric power system is particularly important, the traditional video monitoring is not enough in the aspects of timely processing, evidence obtaining after the fact and the like, massive videos need a large amount of manpower to identify and analyze the abnormity existing in video images, the intelligent monitoring video gradually becomes a development trend along with the development of artificial intelligence, deep learning and the like, the video images are subjected to uninterrupted analysis by adopting an artificial intelligence algorithm, and once abnormity is found, early warning information is immediately sent to a worker, the workload of equipment maintenance of the worker can be reduced, and the efficiency and the effect of the whole monitoring management are improved.
The cloud-based video monitoring technology reduces the construction and maintenance cost of users, and the centralized computing and storing mode of the cloud improves the safety and reliability of video data; however, video data has two characteristics, namely, data generated by video monitoring is mainly unstructured data, and video data has an explosive growth trend, so that the cloud-based video monitoring technology has the following problems:
images obtained by mass video streams are transmitted to a cloud computing center, so that a large amount of network bandwidth is consumed, and further problems of service interruption, network delay and the like can be caused, so that the real-time performance cannot be guaranteed;
the image processing task is centralized in the cloud computing center, a large amount of computing resources are needed, and the operation burden of the cloud computing center is increased.
Disclosure of Invention
The invention aims to solve one of the problems in the prior art, and provides an intelligent maintenance-free power grid monitoring method and system based on cloud edge collaborative deep learning, so that the operation burden of a cloud computing center is reduced.
In order to achieve the purpose, the intelligent maintenance-free power grid monitoring method based on cloud edge collaborative deep learning is used for a power grid monitoring system, the power grid monitoring system comprises sensing equipment, edge computing nodes and a cloud computing center, and the method comprises the following steps:
the sensing equipment collects a monitoring image;
the edge computing node acquires a monitoring image acquired by the sensing equipment;
the edge computing node identifies the monitoring image to determine whether the power grid abnormality exists or not based on the monitoring image and a power grid abnormality detection model issued by the cloud computing center, and sends alarm information to the sensing equipment when the power grid abnormality exists;
the sensing equipment receives alarm information of the edge computing node and gives an alarm according to the alarm information;
the edge computing node transmits the identified monitoring image to a cloud computing center;
the cloud computing center trains a deep learning model according to the stored training set images to generate a power grid abnormity detection model, and the power grid abnormity detection model is updated according to the recognized monitoring image training transmitted by the edge computing node;
and the cloud computing center issues the power grid abnormity detection model to the edge computing node.
Optionally, the method further includes:
the edge computing node carries out preprocessing operation on the monitoring image;
the edge computing node performs duplicate removal operation on the monitoring images acquired within the interval time;
the monitoring image is identified to determine whether the power grid abnormity exists based on the monitoring image and a power grid abnormity detection model issued by a cloud computing center: and identifying the preprocessed and deduplicated monitoring image according to the power grid abnormality detection model so as to determine whether the power grid abnormality exists in the monitoring image.
Optionally, transmitting the identified monitoring image to the cloud computing center includes:
temporarily storing the identified monitoring image in an edge computing node;
and transmitting the temporarily stored monitoring images to the cloud computing center in a unified manner in a time period when the network bandwidth flow is smaller than a preset value.
Optionally, the generating a power grid anomaly detection model according to the stored training set image training deep learning model includes:
adjusting the training set image to 320 x 320;
constructing a lightweight target detection network ThunderNet as a deep learning model;
and training the deep learning model according to the adjusted training set image to generate a power grid abnormity detection model.
Optionally, the method further includes:
the cloud computing center builds and trains an abnormal flow monitoring model;
the cloud computing center issues the trained abnormal flow monitoring model to the edge computing node;
monitoring the flow of the edge by the edge computing node according to the abnormal flow monitoring model, and if the abnormal flow exists in the edge, sending a flow abnormal signal to the cloud computing center;
and when the cloud computing center receives the flow abnormal signal, the cloud computing center blocks the abnormal flow.
In another aspect of the disclosure, an intelligent maintenance-free power grid monitoring system based on cloud-edge collaborative deep learning comprises a sensing device, an edge computing node and a cloud computing center;
the sensing device includes:
the image acquisition component is used for acquiring a monitoring image;
the alarm device is used for receiving the alarm information of the edge computing node and giving an alarm according to the alarm information;
the edge computing node comprises:
the image processing module is used for acquiring a monitoring image acquired by the sensing equipment;
the image detection module is used for identifying the monitoring image and determining whether the power grid is abnormal or not based on the monitoring image and a power grid abnormity detection model issued by the cloud computing center;
the alarm module is used for sending alarm information to the sensing equipment when the power grid abnormity exists;
the first transmission module is used for transmitting the identified monitoring image to the cloud computing center;
the cloud computing center includes:
the power grid anomaly detection model training module is used for training the deep learning model according to the stored training set images to generate a power grid anomaly detection model, and training and updating the power grid anomaly detection model according to the identified monitoring images transmitted by the edge computing nodes;
and the second transmission module is used for transmitting the power grid abnormity detection model to the edge computing node.
Optionally, the image acquisition assembly is connected to a camera for shooting the power monitoring video, and is used for acquiring the monitoring image from a video stream shot by the camera.
Optionally, the edge computing node further includes a repeat filtering module;
the image processing module is also used for carrying out preprocessing operation on the monitoring image;
the repeated filtering module is used for carrying out duplicate removal operation on the monitoring images collected within the interval time;
the monitoring image is identified and whether the power grid abnormity exists is determined based on the monitoring image and a power grid abnormity detection model issued by a cloud computing center: and identifying the preprocessed and deduplicated monitoring image according to the power grid abnormality detection model so as to determine whether the power grid abnormality exists in the monitoring image.
Optionally, transmitting the identified monitoring image to the cloud computing center includes: and temporarily storing the identified monitoring images in the edge computing nodes, and uniformly transmitting the temporarily stored monitoring images to the cloud computing center in a time period when the network bandwidth flow is less than a preset value.
Optionally, the generating a power grid anomaly detection model according to the stored training set image training deep learning model includes:
adjusting the training set image to 320 x 320;
constructing a lightweight target detection network ThunderNet as a deep learning model;
and training the deep learning model according to the adjusted training set image to generate a power grid abnormity detection model.
The technical scheme of the present disclosure can be implemented to obtain the following beneficial technical effects:
the cloud computing center is used for training and updating the power grid abnormity detection model; the power grid abnormity detection model trained and updated by the edge computing node judges whether power grid abnormity exists or not based on the monitoring image, the power grid abnormity detection model issued by the cloud computing center and the monitoring image acquired by the sensing equipment, sends alarm information to the corresponding sensing equipment when the power grid is abnormal, and alarms by the sensing equipment, so that a worker can know the power grid abnormity in time and take effective measures for the power grid abnormity in time.
The cloud computing center is mainly used for training and updating the power grid abnormity detection model, and the recognition work is distributed to each edge computing node, so that the operation amount of the cloud computing center is greatly reduced, and the operation burden of the cloud computing center is reduced.
Massive video image data are directly uploaded to a cloud computing center, network bandwidth pressure is high, network time delay is often generated, the edge computing nodes process the image data nearby a data source and make judgment in real time, the problems of interaction delay and the like are effectively solved, and bandwidth cost is reduced
Drawings
Fig. 1 is a flowchart of an intelligent maintenance-free power grid monitoring method based on cloud-edge collaborative deep learning in an embodiment of the present disclosure;
fig. 2 is a block diagram of an intelligent maintenance-free power grid monitoring system based on cloud-edge collaborative deep learning according to an embodiment of the present disclosure;
fig. 3 is another block diagram of an intelligent maintenance-free power grid monitoring system based on cloud-edge collaborative deep learning in an embodiment of the present disclosure;
fig. 4 is another block diagram of an intelligent maintenance-free power grid monitoring system based on cloud-edge collaborative deep learning in an embodiment of the present disclosure;
fig. 5 is another block diagram of an intelligent maintenance-free power grid monitoring system based on cloud-edge collaborative deep learning in an embodiment of the present disclosure.
Detailed Description
To facilitate understanding of those skilled in the art, the present invention will be further described with reference to specific examples:
referring to fig. 1 and 2, the intelligent maintenance-free power grid monitoring method based on cloud edge collaborative deep learning is used for a power grid monitoring system, the power grid monitoring system comprises a sensing device 1, an edge computing node 2 and a cloud computing center 3, and the method comprises the following steps:
s1: the sensing equipment collects a monitoring image;
s2: the edge computing node acquires a monitoring image acquired by the sensing equipment;
s3: the edge computing node identifies the monitoring image to determine whether the power grid abnormality exists or not based on the monitoring image and a power grid abnormality detection model issued by the cloud computing center, and sends alarm information to the sensing equipment when the power grid abnormality exists;
s4: the sensing equipment receives alarm information of the edge computing node and gives an alarm according to the alarm information;
s5: the edge computing node transmits the identified monitoring image to a cloud computing center;
s6: the cloud computing center trains a deep learning model according to the stored training set images to generate a power grid abnormity detection model, and the power grid abnormity detection model is updated according to the recognized monitoring image training transmitted by the edge computing node;
s7: and the cloud computing center issues the power grid abnormity detection model to the edge computing node.
It is to be appreciated that the edge computing node 2 may be in communication with a plurality of sensing devices 1, and the cloud computing center 3 may be in communication with a plurality of sensing devices.
Note that the above numbers S1 to S6 do not represent the execution order relationship of the steps S1 to S6.
In the intelligent maintenance-free power grid monitoring method based on cloud-edge collaborative deep learning, a cloud computing center is used for training and updating a power grid abnormity detection model; the power grid abnormity detection model trained and updated by the edge computing node judges whether power grid abnormity exists or not based on the monitoring image, the power grid abnormity detection model issued by the cloud computing center and the monitoring image acquired by the sensing equipment, sends alarm information to the corresponding sensing equipment when the power grid is abnormal, and alarms by the sensing equipment, so that a worker can know the power grid abnormity in time and take effective measures for the power grid abnormity in time.
Massive video image data are directly uploaded to a cloud computing center, network bandwidth pressure is high, network delay is often generated, edge computing nodes process the image data nearby a data source and make judgment in real time, the problems of interaction delay and the like are effectively solved, and bandwidth cost is reduced;
the deep learning calculation is completed by the cooperation of a cloud calculation center and an edge side, the cloud calculation center is responsible for basic model training of historical data with large calculation amount, model optimization is completed based on calculation and storage capacity, the model optimization is issued to the edge side, the inference process of the training model is completed, namely the detection of real-time images, and the intelligent cooperation of the cloud side is realized;
the cloud computing center is mainly used for training and updating the power grid abnormity detection model, and recognition work is distributed to each edge computing node, so that the operation amount of the cloud computing center is greatly reduced, and the operation burden of the cloud computing center is reduced.
The cloud computing center trains and updates the power grid anomaly detection model according to the identified monitoring images uploaded by the edge computing nodes, so that the power grid anomaly detection model is more complete, and the identification rate of the power grid anomaly detection model is improved; when the monitoring image is identified and the power grid is abnormal, the staff can carry out further manual verification, and the verified monitoring image is trained and the power grid abnormality detection model is updated.
In one embodiment, the intelligent maintenance-free power grid monitoring method based on cloud edge collaborative deep learning further includes:
the edge computing node carries out preprocessing operation on the monitoring image;
the edge computing node performs duplicate removal operation on the monitoring images acquired within the interval time;
the monitoring image is identified and whether the power grid abnormity exists is determined based on the monitoring image and a power grid abnormity detection model issued by a cloud computing center: and identifying the preprocessed and de-duplicated monitoring image according to the power grid abnormality detection model so as to determine whether the monitoring image judges whether the power grid abnormality exists.
In the embodiment of the present disclosure, the main purpose of the preprocessing is to eliminate irrelevant information in the image, which includes removing the image of the mashup, and adjusting the size of the image to 320 × 320 pixels, and performing a normalization operation on the image. Because a large number of repeated pictures exist in the interval time due to the fact that images in the video stream are obtained, the identification operation which is unnecessary to repeat can be reduced through the duplication removing operation, and the identification efficiency is greatly improved.
In one embodiment, the grid anomaly detection model may identify and locate grid anomalies.
In one embodiment, when the power grid abnormality is identified, the corresponding label text is used as alarm information; meanwhile, if the images of the continuous frame number in the preset interval time are the same alarm information, the alarm information is sent to the alarm device only once, and frequent repeated alarm is avoided.
In one embodiment, transmitting the identified monitoring image to the cloud computing center comprises:
temporarily storing the identified monitoring image in an edge computing node;
and transmitting the temporarily stored monitoring images to the cloud computing center in a unified manner in a time period when the network bandwidth flow is smaller than a preset value.
By selecting a time period with small network agent flow and sending the monitoring image, the occupation of the loan can be reduced.
In one embodiment, training the deep learning model to generate a grid anomaly detection model from the stored training set images comprises:
resizing the training set images to 320 x 320;
constructing a lightweight target detection network ThunderNet as a deep learning model;
and training the deep learning model according to the adjusted training set image to generate a power grid abnormity detection model.
ThunderNet includes two parts: the system comprises a backbone network and a detection network, wherein the backbone network is SNet, and the detection network adopts a Light-Head R-CNN network architecture. In the process of training the deep learning model according to the adjusted training set image, the AP can be used as a performance evaluation index, and when the accuracy of the model on each class reaches a preset threshold value, the training is stopped; and the cloud computing center optimizes the trained model based on the computing and storage capacity of the application nodes required by the deployment of the model, and generates a thunderNet power grid abnormality detection model required by the edge computing nodes.
When the size of the training set image is adjusted, the image data can be cleaned, redundant images with mixed mashups are removed, and normalization processing is carried out on the images. So as to keep consistent with the preprocessing operation of the monitoring image by the edge computing node.
In one embodiment, the intelligent maintenance-free power grid monitoring method based on cloud edge collaborative deep learning further includes:
the method comprises the steps that a cloud computing center builds and trains an abnormal flow monitoring model DAE-RNN, the built model is trained by using historical flow data stored on the cloud, and the internal difference between normal flow and abnormal flow is mined;
the cloud computing center issues the trained abnormal flow monitoring model to the edge computing node;
monitoring the flow of the edge by the edge computing node according to the abnormal flow monitoring model, and if the abnormal flow exists in the edge, sending a flow abnormal signal to the cloud computing center;
and when the cloud computing center receives the flow abnormal signal, the cloud computing center blocks the abnormal flow.
The computing center provides safety guarantee for the edge side, and when the edge side detects abnormal flow, the cloud computing center is informed to block the abnormal flow, so that the safety cooperation of the cloud edge is realized.
Example 2:
referring to fig. 2 to 5, the intelligent maintenance-free power grid monitoring system based on cloud edge collaborative deep learning includes a sensing device 1, an edge computing node 2 and a cloud computing center 3;
sensing device 1, comprising:
the image acquisition component 11 is used for acquiring monitoring images;
the alarm device 12 is used for receiving alarm information of the edge computing node and giving an alarm according to the alarm information;
an edge compute node 2, comprising:
the image processing module 21 is configured to obtain a monitoring image acquired by the sensing device;
the image detection module 22 is configured to identify the monitoring image and determine whether a power grid abnormality exists based on the monitoring image and a power grid abnormality detection model issued by the cloud computing center;
the warning module 23 is configured to send warning information to the sensing device when there is a power grid abnormality;
a first transmission module 24, configured to transmit the identified monitoring image to the cloud computing center;
the cloud computing center 3 includes:
the model training module 31 is used for training the deep learning model according to the stored training set images to generate a power grid abnormity detection model, and training and updating the power grid abnormity detection model according to the identified monitoring images transmitted by the edge computing nodes;
and the second transmission module 32 is configured to issue the power grid abnormality detection model to the edge computing node.
In the intelligent maintenance-free power grid monitoring system based on cloud-edge collaborative deep learning, a cloud computing center is used for training and updating a power grid abnormity detection model; the power grid abnormity detection model trained and updated by the edge computing node judges whether power grid abnormity exists or not based on the monitoring image, the power grid abnormity detection model issued by the cloud computing center and the monitoring image acquired by the sensing equipment, sends alarm information to the corresponding sensing equipment when the power grid is abnormal, and alarms by the sensing equipment, so that a worker can know the power grid abnormity in time and take effective measures for the power grid abnormity in time.
Massive video image data are directly uploaded to a cloud computing center, network bandwidth pressure is high, network delay is often generated, edge computing nodes process the image data nearby a data source and make judgment in real time, the problems of interaction delay and the like are effectively solved, and bandwidth cost is reduced;
the deep learning calculation is completed by the cooperation of a cloud calculation center and an edge side, the cloud calculation center is responsible for basic model training of historical data with large calculation amount, model optimization is completed based on calculation and storage capacity, the model optimization is issued to the edge side, the inference process of the training model is completed, namely the detection of real-time images, and the intelligent cooperation of the cloud side is realized;
the cloud computing center is mainly used for training and updating the power grid abnormity detection model, and recognition work is distributed to each edge computing node, so that the operation amount of the cloud computing center is greatly reduced, and the operation burden of the cloud computing center is reduced.
The cloud computing center trains and updates the power grid anomaly detection model according to the identified monitoring images uploaded by the edge computing nodes, so that the power grid anomaly detection model is more complete, and the identification rate of the power grid anomaly detection model is improved; when the monitoring image is identified and the power grid is abnormal, the staff can carry out further manual verification, and the verified monitoring image is trained and the power grid abnormality detection model is updated.
In one embodiment, referring to fig. 3, the image capturing assembly 11 is connected to a camera for capturing power surveillance video for obtaining surveillance images from a video stream captured by the camera.
In one embodiment, referring to fig. 4, the edge compute node further includes a repeat filter module 25;
the image processing module 21 is further configured to perform a preprocessing operation on the monitoring image;
the repeated filtering module 25 is used for carrying out duplicate removal operation on the monitoring images collected within the interval time;
based on the monitoring image and a power grid abnormity detection model issued by the cloud computing center, identifying the monitoring image to determine whether the power grid abnormity exists comprises the following steps: and identifying the preprocessed and de-duplicated monitoring image according to the power grid abnormality detection model so as to determine whether the monitoring image judges whether the power grid abnormality exists.
In the embodiment of the present disclosure, the main purpose of the preprocessing is to eliminate irrelevant information in the image, which includes removing the image of the mashup, and adjusting the size of the image to 320 × 320, and performing a normalization operation on the image. Because a large number of repeated pictures exist in the interval time due to the fact that images in the video stream are obtained, the identification operation which is unnecessary to repeat can be reduced through the duplication removing operation, and the identification efficiency is greatly improved.
In one embodiment, when the power grid abnormality is identified, the corresponding label text is used as alarm information; meanwhile, if the images of the continuous frame number in the preset interval time are the same alarm information, the alarm information is sent to the alarm device only once, and frequent repeated alarm is avoided.
In one embodiment, transmitting the identified monitoring image to the cloud computing center comprises: and temporarily storing the identified monitoring images in the edge computing nodes, and uniformly transmitting the temporarily stored monitoring images to the cloud computing center in a time period when the network bandwidth flow is less than a preset value. By selecting a time period with small network agent flow and sending the monitoring image, the occupation of the loan can be reduced.
In one embodiment, training the deep learning model to generate a grid anomaly detection model from the stored training set images comprises:
adjusting the training set image to 320 x 320;
constructing a lightweight target detection network ThunderNet as a deep learning model;
and training the deep learning model according to the adjusted training set image to generate a power grid abnormity detection model.
ThunderNet includes two parts: the system comprises a backbone network and a detection network, wherein the backbone network is SNet, and the detection network adopts a Light-Head R-CNN network architecture. In the process of training the deep learning model according to the adjusted training set image, the AP can be used as a performance evaluation index, and when the accuracy of the model on each class reaches a preset threshold value, the training is stopped; and the cloud computing center optimizes the trained model based on the computing and storage capacity of the application nodes required by the deployment of the model, and generates a thunderNet power grid abnormality detection model required by the edge computing nodes.
When the size of the training set image is adjusted, the image data can be cleaned, redundant images with mixed mashups are removed, and normalization processing is carried out on the images. So as to keep consistent with the preprocessing operation of the monitoring image by the edge computing node.
The intelligent maintenance-free power grid monitoring system based on cloud edge collaborative deep learning further comprises a flow monitoring module, and the flow monitoring module is used for:
building and training an abnormal flow monitoring model DAE-RNN, training the built model by using historical flow data stored on the cloud, and mining the internal difference between normal flow and abnormal flow;
issuing the trained abnormal flow monitoring model to an edge computing node;
and when the flow abnormal signal is received, the abnormal flow is blocked.
The edge computing node is further used for monitoring the edge traffic according to the abnormal traffic monitoring model, and if the edge is found to have abnormal traffic, sending a traffic abnormal signal to the cloud computing center.
The computing center provides safety guarantee for the edge side, and when the edge side detects abnormal flow, the cloud computing center is informed to block the abnormal flow, so that the safety cooperation of the cloud edge is realized.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above description is only an embodiment of the present invention, but the technical features of the present invention are not limited thereto, and any changes or modifications within the technical field of the present invention by those skilled in the art are covered by the claims of the present invention.
Claims (10)
1. The intelligent maintenance-free power grid monitoring method based on cloud edge collaborative deep learning is characterized by being used for a power grid monitoring system, wherein the power grid monitoring system comprises sensing equipment, edge computing nodes and a cloud computing center, and the method comprises the following steps:
the sensing equipment collects a monitoring image;
the edge computing node acquires a monitoring image acquired by the sensing equipment;
the edge computing node identifies the monitoring image to determine whether the power grid abnormality exists or not based on the monitoring image and a power grid abnormality detection model issued by the cloud computing center, and sends alarm information to the sensing equipment when the power grid abnormality exists;
the sensing equipment receives alarm information of the edge computing node and gives an alarm according to the alarm information;
the edge computing node transmits the identified monitoring image to a cloud computing center;
the cloud computing center trains a deep learning model according to the stored training set images to generate a power grid abnormity detection model, and the power grid abnormity detection model is updated according to the recognized monitoring image training transmitted by the edge computing node;
and the cloud computing center issues the power grid abnormity detection model to the edge computing node.
2. The intelligent maintenance-free power grid monitoring method based on cloud edge collaborative deep learning according to claim 1,
the method further comprises the following steps:
the edge computing node carries out preprocessing operation on the monitoring image;
the edge computing node performs duplicate removal operation on the monitoring images acquired within the interval time;
the monitoring image is identified and whether the power grid abnormity exists is determined based on the monitoring image and a power grid abnormity detection model issued by a cloud computing center: and identifying the preprocessed and deduplicated monitoring image according to the power grid abnormality detection model so as to determine whether the power grid abnormality exists in the monitoring image.
3. The intelligent maintenance-free power grid monitoring method based on cloud edge collaborative deep learning according to claim 2, wherein transmitting the identified monitoring image to a cloud computing center comprises:
temporarily storing the identified monitoring image in an edge computing node;
and transmitting the temporarily stored monitoring images to the cloud computing center in a unified manner in a time period when the network bandwidth flow is smaller than a preset value.
4. The intelligent maintenance-free power grid monitoring method based on cloud edge collaborative deep learning as claimed in claim 3, wherein training the deep learning model to generate the power grid anomaly detection model according to the stored training set image comprises:
adjusting the training set image to 320 x 320;
constructing a lightweight target detection network ThunderNet as a deep learning model;
and training the deep learning model according to the adjusted training set image to generate a power grid abnormity detection model.
5. The intelligent maintenance-free power grid monitoring method based on cloud edge collaborative deep learning according to claim 4, wherein the method further comprises:
the cloud computing center builds and trains an abnormal flow monitoring model;
the cloud computing center issues the trained abnormal flow monitoring model to the edge computing node;
monitoring the flow of the edge by the edge computing node according to the abnormal flow monitoring model, and if the abnormal flow exists in the edge, sending a flow abnormal signal to the cloud computing center;
and when the cloud computing center receives the flow abnormal signal, the cloud computing center blocks the abnormal flow.
6. The intelligent maintenance-free power grid monitoring system based on cloud edge collaborative deep learning is characterized by comprising sensing equipment, edge computing nodes and a cloud computing center;
the sensing device includes:
the image acquisition component is used for acquiring a monitoring image;
the alarm device is used for receiving the alarm information of the edge computing node and giving an alarm according to the alarm information;
the edge computing node comprises:
the image processing module is used for acquiring a monitoring image acquired by the sensing equipment;
the image detection module is used for identifying the monitoring image and determining whether the power grid is abnormal or not based on the monitoring image and a power grid abnormity detection model issued by the cloud computing center;
the alarm module is used for sending alarm information to the sensing equipment when the power grid abnormity exists;
the first transmission module is used for transmitting the identified monitoring image to the cloud computing center;
the cloud computing center includes:
the power grid anomaly detection model training module is used for training the deep learning model according to the stored training set images to generate a power grid anomaly detection model, and training and updating the power grid anomaly detection model according to the identified monitoring images transmitted by the edge computing nodes;
and the second transmission module is used for transmitting the power grid abnormity detection model to the edge computing node.
7. The intelligent maintenance-free power grid monitoring system based on cloud edge collaborative deep learning according to claim 6, wherein the image acquisition component is connected with a camera for shooting power monitoring video and is used for acquiring monitoring images from a video stream shot by the camera.
8. The intelligent maintenance-free power grid monitoring system based on cloud edge collaborative deep learning according to claim 7, wherein the edge computing node further comprises a repeat filtering module;
the image processing module is also used for carrying out preprocessing operation on the monitoring image;
the repeated filtering module is used for carrying out duplicate removal operation on the monitoring images collected within the interval time;
the monitoring image is identified and whether the power grid abnormity exists is determined based on the monitoring image and a power grid abnormity detection model issued by a cloud computing center: and identifying the preprocessed and deduplicated monitoring image according to the power grid abnormality detection model so as to determine whether the power grid abnormality exists in the monitoring image.
9. The intelligent maintenance-free power grid monitoring system based on cloud edge collaborative deep learning according to claim 8, wherein transmitting the identified monitoring image to a cloud computing center comprises: and temporarily storing the identified monitoring images in the edge computing nodes, and uniformly transmitting the temporarily stored monitoring images to the cloud computing center in a time period when the network bandwidth flow is less than a preset value.
10. The intelligent maintenance-free power grid monitoring system based on cloud edge collaborative deep learning as claimed in claim 9, wherein training the deep learning model to generate the power grid anomaly detection model according to the stored training set image comprises:
adjusting the training set image to 320 x 320;
constructing a lightweight target detection network ThunderNet as a deep learning model;
and training the deep learning model according to the adjusted training set image to generate a power grid abnormity detection model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010191686.2A CN111582016A (en) | 2020-03-18 | 2020-03-18 | Intelligent maintenance-free power grid monitoring method and system based on cloud edge collaborative deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010191686.2A CN111582016A (en) | 2020-03-18 | 2020-03-18 | Intelligent maintenance-free power grid monitoring method and system based on cloud edge collaborative deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111582016A true CN111582016A (en) | 2020-08-25 |
Family
ID=72120521
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010191686.2A Pending CN111582016A (en) | 2020-03-18 | 2020-03-18 | Intelligent maintenance-free power grid monitoring method and system based on cloud edge collaborative deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111582016A (en) |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112187932A (en) * | 2020-09-29 | 2021-01-05 | 长江勘测规划设计研究有限责任公司 | Intelligent monitoring and early warning method for small and medium reservoir dam based on edge calculation |
| CN112183498A (en) * | 2020-11-11 | 2021-01-05 | 成都摘果子科技有限公司 | Edge calculation system based on animal identification |
| CN112188502A (en) * | 2020-09-16 | 2021-01-05 | 中国南方电网有限责任公司超高压输电公司 | Resource allocation method for front-end and back-end cooperative communication in transformer substation monitoring |
| CN112286691A (en) * | 2020-11-12 | 2021-01-29 | 济南浪潮高新科技投资发展有限公司 | Cloud edge-side cooperation method based on heterogeneous decision model generation technology |
| CN112506673A (en) * | 2021-02-04 | 2021-03-16 | 国网江苏省电力有限公司信息通信分公司 | Intelligent edge calculation-oriented collaborative model training task configuration method |
| CN112565438A (en) * | 2020-12-07 | 2021-03-26 | 厦门博海中天信息科技有限公司 | Edge-side cooperative intelligent identification method and system |
| CN112666911A (en) * | 2020-12-29 | 2021-04-16 | 煤炭科学研究总院 | Cooperative control system |
| CN112769796A (en) * | 2020-12-30 | 2021-05-07 | 华北电力大学 | Cloud network side collaborative defense method and system based on end side edge computing |
| CN112950400A (en) * | 2021-03-30 | 2021-06-11 | 煤炭科学研究总院 | Data processing platform |
| CN112947585A (en) * | 2021-04-09 | 2021-06-11 | 广东电网有限责任公司电力调度控制中心 | Power grid unmanned aerial vehicle inspection method, device and system based on 5G cloud edge-end cooperation |
| CN112988327A (en) * | 2021-03-04 | 2021-06-18 | 杭州谐云科技有限公司 | Container safety management method and system based on cloud edge cooperation |
| CN113033355A (en) * | 2021-03-11 | 2021-06-25 | 中北大学 | Abnormal target identification method and device based on intensive power transmission channel |
| CN113079530A (en) * | 2021-03-31 | 2021-07-06 | 广东电网有限责任公司电力调度控制中心 | Cloud edge collaborative operation and maintenance support system based on 5G slice |
| CN113139945A (en) * | 2021-02-26 | 2021-07-20 | 山东大学 | Intelligent image detection method, equipment and medium for air conditioner outdoor unit based on Attention + YOLOv3 |
| CN113155197A (en) * | 2021-05-07 | 2021-07-23 | 南京邮电大学 | Intelligent water Internet of things system |
| CN113221981A (en) * | 2021-04-28 | 2021-08-06 | 之江实验室 | Edge deep learning-oriented data cooperative processing optimization method |
| CN113452961A (en) * | 2021-06-21 | 2021-09-28 | 上海鹰觉科技有限公司 | Water surface monitoring alarm system, method and medium based on edge calculation |
| CN113596390A (en) * | 2021-06-16 | 2021-11-02 | 国网浙江省电力有限公司电力科学研究院 | Transformer substation video monitoring abnormity early warning system based on three-layer architecture and implementation method |
| CN113778686A (en) * | 2021-09-16 | 2021-12-10 | 上海电信科技发展有限公司 | Distributed image recognition cloud service platform system |
| CN113783862A (en) * | 2021-09-02 | 2021-12-10 | 付腾瑶 | Method and device for data verification in edge cloud cooperation process |
| CN113867263A (en) * | 2021-08-27 | 2021-12-31 | 大唐互联科技(武汉)有限公司 | Intelligent cutter management system based on cloud edge cooperation and machine learning |
| CN114127814A (en) * | 2021-06-25 | 2022-03-01 | 商汤国际私人有限公司 | Scene detection method and device, electronic equipment and computer storage medium |
| CN114140447A (en) * | 2021-12-06 | 2022-03-04 | 国网新疆电力有限公司信息通信公司 | Cloud edge cooperation technology-based power equipment image identification method and system |
| CN114202738A (en) * | 2021-12-02 | 2022-03-18 | 广西电网有限责任公司钦州供电局 | Power grid monitoring method, device and equipment based on edge calculation and artificial intelligence |
| CN114359781A (en) * | 2021-12-02 | 2022-04-15 | 国家石油天然气管网集团有限公司 | Intelligent recognition system for cloud-side collaborative autonomous learning |
| WO2022096959A1 (en) * | 2021-06-25 | 2022-05-12 | Sensetime International Pte. Ltd. | Scene detection method and apparatus, electronic device and computer storage medium |
| CN115052130A (en) * | 2022-05-27 | 2022-09-13 | 合肥富煌君达高科信息技术有限公司 | High low temperature experiment unmanned on duty bug information wireless transmission system |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170060574A1 (en) * | 2015-08-27 | 2017-03-02 | FogHorn Systems, Inc. | Edge Intelligence Platform, and Internet of Things Sensor Streams System |
| CN107766889A (en) * | 2017-10-26 | 2018-03-06 | 济南浪潮高新科技投资发展有限公司 | A kind of the deep learning computing system and method for the fusion of high in the clouds edge calculations |
| US20180330238A1 (en) * | 2017-05-09 | 2018-11-15 | Neurala, Inc. | Systems and methods to enable continual, memory-bounded learning in artificial intelligence and deep learning continuously operating applications across networked compute edges |
| CN108828409A (en) * | 2018-08-03 | 2018-11-16 | 南方电网科学研究院有限责任公司 | Fault detection system based on edge calculation |
| CN108845885A (en) * | 2018-07-04 | 2018-11-20 | 济南浪潮高新科技投资发展有限公司 | A kind of edge calculations method for managing resource towards automatic Pilot |
| CN109728939A (en) * | 2018-12-13 | 2019-05-07 | 杭州迪普科技股份有限公司 | A kind of network flow detection method and device |
| CN110084165A (en) * | 2019-04-19 | 2019-08-02 | 山东大学 | The intelligent recognition and method for early warning of anomalous event under the open scene of power domain based on edge calculations |
| CN110135564A (en) * | 2019-05-15 | 2019-08-16 | 深圳朴生智能科技有限公司 | Coal mine gas sensing data method for detecting abnormality based on edge calculations |
| CN110278416A (en) * | 2019-07-12 | 2019-09-24 | 山东智洋电气股份有限公司 | Power transmission line intelligent prison based on artificial intelligence claps device |
| CN110287945A (en) * | 2019-07-04 | 2019-09-27 | 山东浪潮人工智能研究院有限公司 | Unmanned plane target detection method under a kind of 5G environment |
| CN110363735A (en) * | 2019-07-22 | 2019-10-22 | 广东工业大学 | A kind of car networking image data fusing method and relevant apparatus |
| CN110414373A (en) * | 2019-07-08 | 2019-11-05 | 武汉大学 | A kind of deep learning palm vein identification system and method based on cloud side end cooperated computing |
| CN110516837A (en) * | 2019-07-10 | 2019-11-29 | 马欣 | A kind of Intelligence Diagnosis method, system and device based on AI |
| CN209895464U (en) * | 2019-07-01 | 2020-01-03 | 深圳江行联加智能科技有限公司 | Transformer substation abnormity monitoring and alarming system |
| CN110719210A (en) * | 2019-12-05 | 2020-01-21 | 赣江新区智慧物联研究院有限公司 | Industrial equipment predictive maintenance method based on cloud edge cooperation |
-
2020
- 2020-03-18 CN CN202010191686.2A patent/CN111582016A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170060574A1 (en) * | 2015-08-27 | 2017-03-02 | FogHorn Systems, Inc. | Edge Intelligence Platform, and Internet of Things Sensor Streams System |
| US20180330238A1 (en) * | 2017-05-09 | 2018-11-15 | Neurala, Inc. | Systems and methods to enable continual, memory-bounded learning in artificial intelligence and deep learning continuously operating applications across networked compute edges |
| CN107766889A (en) * | 2017-10-26 | 2018-03-06 | 济南浪潮高新科技投资发展有限公司 | A kind of the deep learning computing system and method for the fusion of high in the clouds edge calculations |
| CN108845885A (en) * | 2018-07-04 | 2018-11-20 | 济南浪潮高新科技投资发展有限公司 | A kind of edge calculations method for managing resource towards automatic Pilot |
| CN108828409A (en) * | 2018-08-03 | 2018-11-16 | 南方电网科学研究院有限责任公司 | Fault detection system based on edge calculation |
| CN109728939A (en) * | 2018-12-13 | 2019-05-07 | 杭州迪普科技股份有限公司 | A kind of network flow detection method and device |
| CN110084165A (en) * | 2019-04-19 | 2019-08-02 | 山东大学 | The intelligent recognition and method for early warning of anomalous event under the open scene of power domain based on edge calculations |
| CN110135564A (en) * | 2019-05-15 | 2019-08-16 | 深圳朴生智能科技有限公司 | Coal mine gas sensing data method for detecting abnormality based on edge calculations |
| CN209895464U (en) * | 2019-07-01 | 2020-01-03 | 深圳江行联加智能科技有限公司 | Transformer substation abnormity monitoring and alarming system |
| CN110287945A (en) * | 2019-07-04 | 2019-09-27 | 山东浪潮人工智能研究院有限公司 | Unmanned plane target detection method under a kind of 5G environment |
| CN110414373A (en) * | 2019-07-08 | 2019-11-05 | 武汉大学 | A kind of deep learning palm vein identification system and method based on cloud side end cooperated computing |
| CN110516837A (en) * | 2019-07-10 | 2019-11-29 | 马欣 | A kind of Intelligence Diagnosis method, system and device based on AI |
| CN110278416A (en) * | 2019-07-12 | 2019-09-24 | 山东智洋电气股份有限公司 | Power transmission line intelligent prison based on artificial intelligence claps device |
| CN110363735A (en) * | 2019-07-22 | 2019-10-22 | 广东工业大学 | A kind of car networking image data fusing method and relevant apparatus |
| CN110719210A (en) * | 2019-12-05 | 2020-01-21 | 赣江新区智慧物联研究院有限公司 | Industrial equipment predictive maintenance method based on cloud edge cooperation |
Non-Patent Citations (3)
| Title |
|---|
| BILAL HUSSAIN, ET.AL: "Artificial intelligence-powered mobile edge computing-based anomaly detection in cellular networks", pages 4986 - 4996 * |
| 上海海事大学等: "《中国物流科技发展报告 2018-2019》", 上海浦江教育出版社, pages: 143 - 144 * |
| 赵玲: "基于边缘计算的电暖设备监控管理技术的研究与实现", no. 7, pages 381 - 382 * |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112188502A (en) * | 2020-09-16 | 2021-01-05 | 中国南方电网有限责任公司超高压输电公司 | Resource allocation method for front-end and back-end cooperative communication in transformer substation monitoring |
| CN112187932A (en) * | 2020-09-29 | 2021-01-05 | 长江勘测规划设计研究有限责任公司 | Intelligent monitoring and early warning method for small and medium reservoir dam based on edge calculation |
| CN112183498A (en) * | 2020-11-11 | 2021-01-05 | 成都摘果子科技有限公司 | Edge calculation system based on animal identification |
| CN112286691A (en) * | 2020-11-12 | 2021-01-29 | 济南浪潮高新科技投资发展有限公司 | Cloud edge-side cooperation method based on heterogeneous decision model generation technology |
| CN112565438A (en) * | 2020-12-07 | 2021-03-26 | 厦门博海中天信息科技有限公司 | Edge-side cooperative intelligent identification method and system |
| CN112666911A (en) * | 2020-12-29 | 2021-04-16 | 煤炭科学研究总院 | Cooperative control system |
| CN112769796A (en) * | 2020-12-30 | 2021-05-07 | 华北电力大学 | Cloud network side collaborative defense method and system based on end side edge computing |
| CN112506673A (en) * | 2021-02-04 | 2021-03-16 | 国网江苏省电力有限公司信息通信分公司 | Intelligent edge calculation-oriented collaborative model training task configuration method |
| CN113139945A (en) * | 2021-02-26 | 2021-07-20 | 山东大学 | Intelligent image detection method, equipment and medium for air conditioner outdoor unit based on Attention + YOLOv3 |
| CN112988327A (en) * | 2021-03-04 | 2021-06-18 | 杭州谐云科技有限公司 | Container safety management method and system based on cloud edge cooperation |
| CN113033355A (en) * | 2021-03-11 | 2021-06-25 | 中北大学 | Abnormal target identification method and device based on intensive power transmission channel |
| CN112950400A (en) * | 2021-03-30 | 2021-06-11 | 煤炭科学研究总院 | Data processing platform |
| CN113079530A (en) * | 2021-03-31 | 2021-07-06 | 广东电网有限责任公司电力调度控制中心 | Cloud edge collaborative operation and maintenance support system based on 5G slice |
| CN113079530B (en) * | 2021-03-31 | 2022-05-27 | 广东电网有限责任公司电力调度控制中心 | Cloud edge collaborative operation and maintenance support system based on 5G slice |
| CN112947585A (en) * | 2021-04-09 | 2021-06-11 | 广东电网有限责任公司电力调度控制中心 | Power grid unmanned aerial vehicle inspection method, device and system based on 5G cloud edge-end cooperation |
| CN113221981A (en) * | 2021-04-28 | 2021-08-06 | 之江实验室 | Edge deep learning-oriented data cooperative processing optimization method |
| CN113155197A (en) * | 2021-05-07 | 2021-07-23 | 南京邮电大学 | Intelligent water Internet of things system |
| CN113596390B (en) * | 2021-06-16 | 2024-02-13 | 国网浙江省电力有限公司电力科学研究院 | Transformer substation video monitoring abnormity early warning system based on three-layer architecture and implementation method |
| CN113596390A (en) * | 2021-06-16 | 2021-11-02 | 国网浙江省电力有限公司电力科学研究院 | Transformer substation video monitoring abnormity early warning system based on three-layer architecture and implementation method |
| CN113452961A (en) * | 2021-06-21 | 2021-09-28 | 上海鹰觉科技有限公司 | Water surface monitoring alarm system, method and medium based on edge calculation |
| WO2022096959A1 (en) * | 2021-06-25 | 2022-05-12 | Sensetime International Pte. Ltd. | Scene detection method and apparatus, electronic device and computer storage medium |
| CN114127814B (en) * | 2021-06-25 | 2023-06-20 | 商汤国际私人有限公司 | Scene detection method and device, electronic equipment and computer storage medium |
| CN114127814A (en) * | 2021-06-25 | 2022-03-01 | 商汤国际私人有限公司 | Scene detection method and device, electronic equipment and computer storage medium |
| CN113867263A (en) * | 2021-08-27 | 2021-12-31 | 大唐互联科技(武汉)有限公司 | Intelligent cutter management system based on cloud edge cooperation and machine learning |
| CN113783862A (en) * | 2021-09-02 | 2021-12-10 | 付腾瑶 | Method and device for data verification in edge cloud cooperation process |
| CN113778686A (en) * | 2021-09-16 | 2021-12-10 | 上海电信科技发展有限公司 | Distributed image recognition cloud service platform system |
| CN113778686B (en) * | 2021-09-16 | 2024-03-15 | 上海电信科技发展有限公司 | Distributed image recognition cloud service platform system |
| CN114359781A (en) * | 2021-12-02 | 2022-04-15 | 国家石油天然气管网集团有限公司 | Intelligent recognition system for cloud-side collaborative autonomous learning |
| CN114202738A (en) * | 2021-12-02 | 2022-03-18 | 广西电网有限责任公司钦州供电局 | Power grid monitoring method, device and equipment based on edge calculation and artificial intelligence |
| CN114140447A (en) * | 2021-12-06 | 2022-03-04 | 国网新疆电力有限公司信息通信公司 | Cloud edge cooperation technology-based power equipment image identification method and system |
| CN115052130A (en) * | 2022-05-27 | 2022-09-13 | 合肥富煌君达高科信息技术有限公司 | High low temperature experiment unmanned on duty bug information wireless transmission system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111582016A (en) | Intelligent maintenance-free power grid monitoring method and system based on cloud edge collaborative deep learning | |
| CN111928888B (en) | Intelligent monitoring and analyzing method and system for water pollution | |
| CN111432179A (en) | Intelligent coal conveying belt inspection system and method based on computer vision | |
| CN112804302B (en) | Cloud edge cooperation-based power video image analysis system and method | |
| CN210691345U (en) | Cloud intelligence safety inspection auxiliary system based on degree of depth learning | |
| CN112149522A (en) | Intelligent visual external-damage-prevention monitoring system and method for cable channel | |
| CN109460744B (en) | Video monitoring system based on deep learning | |
| CN112112629A (en) | Safety business management system and method in drilling operation process | |
| CN117319609A (en) | Internet of things big data intelligent video monitoring system and method | |
| CN110807460B (en) | Transformer substation intelligent patrol system based on image recognition and application method thereof | |
| CN112950400A (en) | Data processing platform | |
| CN103067514A (en) | Cloud computing resource optimization method and cloud computing resource optimization system used for video mointoring and analysis system | |
| CN113203049A (en) | Intelligent monitoring and early warning system and method for pipeline safety | |
| CN110381298A (en) | A kind of method, apparatus and system of tunnel video monitoring | |
| CN112686130B (en) | Wisdom fishing boat supervision decision-making system | |
| CN117235443A (en) | Electric power operation safety monitoring method and system based on edge AI | |
| CN116986246A (en) | Intelligent inspection system and method for coal conveying belt | |
| CN116055690A (en) | Method and equipment for processing machine room monitoring video | |
| CN113642403A (en) | Crowd abnormal intelligent safety detection system based on edge calculation | |
| CN103093579B (en) | Debris flow or landslide alarm system based on videos | |
| CN102355575A (en) | Distributed video monitoring device with pre-warning function | |
| CN110148290A (en) | Information-based big data system is supervised in the early warning of Intellisense Mine Safety in Production and prevention and control | |
| CN117440018A (en) | Network camera equipment fortune pipe platform based on thing networking | |
| CN107820051A (en) | Monitoring system and its monitoring method and device | |
| CN117409527A (en) | Fire safety detection system based on edge cloud cooperation |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200825 |