CN116385925A - Intelligent safety management method and system for production site - Google Patents
Intelligent safety management method and system for production site Download PDFInfo
- Publication number
- CN116385925A CN116385925A CN202310224236.2A CN202310224236A CN116385925A CN 116385925 A CN116385925 A CN 116385925A CN 202310224236 A CN202310224236 A CN 202310224236A CN 116385925 A CN116385925 A CN 116385925A
- Authority
- CN
- China
- Prior art keywords
- early warning
- warning information
- historical
- dangerous
- user
- 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
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 92
- 238000007726 management method Methods 0.000 title claims abstract description 25
- 231100001267 hazard identification Toxicity 0.000 claims abstract description 32
- 238000000034 method Methods 0.000 claims abstract description 19
- 238000011156 evaluation Methods 0.000 claims description 34
- 239000011159 matrix material Substances 0.000 claims description 14
- 238000000513 principal component analysis Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 abstract description 6
- 238000010248 power generation Methods 0.000 abstract description 4
- 230000009471 action Effects 0.000 description 13
- 230000009467 reduction Effects 0.000 description 7
- 238000012544 monitoring process Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011112 process operation Methods 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000008054 signal transmission 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
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computational Linguistics (AREA)
- General Factory Administration (AREA)
Abstract
The application relates to the technical field of intelligent safety management, and provides a production field intelligent safety management method and system, wherein the method comprises the following steps: based on the image acquisition device, carrying out video acquisition on the production site to obtain real-time video information of the production site; performing hazard identification on the real-time video information of the production site through a hazard identification model to obtain a hazard identification result; evaluating the dangerous recognition result to generate early warning information; and sending the early warning information to a first user and a second user, wherein the early warning information is used for supervising the second user. By adopting the method, the technical problem that dangerous accidents occur due to the fact that field staff are difficult to monitor effectively in the power generation process of the power plant can be solved.
Description
Technical Field
The application relates to the technical field of intelligent safety management, in particular to a production field intelligent safety management method and system.
Background
At present, most of domestic power plant management modes still adopt a traditional mode, the management method is relatively simple and extensive, operation and maintenance modes are behind, operation and maintenance management workload is large, and for field operation, the ideal purposes of compliance of the working range of operators, standard operation behaviors, controllable and controllable whole-process operation and manageable operation cannot be achieved, and the requirement of field operation safety is difficult to meet.
The safety production relates to the life and property safety of people, and because the power plant has wide production field area, a large number of field devices and complex conditions, the behaviors of field operators cannot be fixed and predicted, the effective monitoring is difficult, the production safety accidents are often caused, and the life and property safety of people is seriously threatened.
In summary, in the prior art, there is a technical problem that dangerous accidents occur due to the fact that field staff are difficult to effectively monitor in the power generation process of a power plant.
Disclosure of Invention
Based on the foregoing, it is necessary to provide a method and a system for intelligent safety management in a production site.
A production site intelligent security management method, wherein the method is applied to a production site intelligent security management system, and the system is in communication connection with an image acquisition device, and comprises the following steps: based on the image acquisition device, carrying out video acquisition on the production site to obtain real-time video information of the production site; performing hazard identification on the real-time video information of the production site through a hazard identification model to obtain a hazard identification result; evaluating the dangerous recognition result to generate early warning information; and sending the early warning information to a first user and a second user, wherein the early warning information is used for supervising the second user.
In one embodiment, the performing risk identification on the real-time video information of the production site through a risk identification model to obtain a risk identification result further includes: obtaining historical production field video information; extracting features of the video information of the historical production site to obtain a historical dangerous data set; constructing a dangerous identification model; training the hazard identification model based on the historical hazard data set to obtain the hazard identification model; and carrying out hazard identification on the real-time video information of the production site through the hazard identification model to obtain the hazard identification result.
In one embodiment, the feature extracting the historical production site video information to obtain a historical dangerous data set further includes: presetting a characteristic identification standard rule; performing feature recognition on the historical production field video information based on the feature recognition standard rule to obtain a plurality of feature recognition results; and carrying out principal component analysis on the plurality of feature recognition results to obtain the historical dangerous data set.
In one embodiment, the performing principal component analysis on the feature recognition results to obtain the historical risk dataset further includes: obtaining a first feature recognition data set according to the feature recognition results; performing decentralization processing on the first characteristic identification data set to obtain a second characteristic identification data set; obtaining a covariance matrix of the first feature recognition according to the second feature recognition data set; obtaining a first eigenvalue and a first eigenvector according to the covariance matrix of the first feature recognition; and obtaining the historical dangerous data set according to the first characteristic value and the first characteristic vector.
In one embodiment, the evaluating the risk identification result to generate early warning information further includes: obtaining a plurality of historical dangerous accident samples; obtaining a plurality of historical dangerous accident data sets based on the plurality of historical dangerous accident samples, wherein the plurality of historical dangerous accident samples and the plurality of historical dangerous accident data sets have corresponding relations; carrying out relevance evaluation on the plurality of historical dangerous accident samples and the plurality of historical dangerous accident data to obtain a plurality of relevance evaluation coefficients; screening the plurality of relevance evaluation coefficients based on a relevance evaluation coefficient threshold, and adding the plurality of historical dangerous accident data corresponding to the plurality of relevance evaluation coefficients meeting the relevance evaluation coefficient threshold to a dangerous accident database; performing principal component analysis on the dangerous accident database to obtain the dangerous accident data set; and evaluating the dangerous identification result based on the dangerous accident data set to generate early warning information, wherein the early warning information comprises first early warning information and second early warning information.
In one embodiment, the sending the early warning information to the first user and the second user further includes: if the early warning information is first early warning information, the first early warning information is sent to a second user, and the first early warning information is used for carrying out danger reminding on the second user; and if the early warning information is second early warning information, the second early warning information is sent to the first user, and the second early warning information is used for the first user to conduct danger supervision on the second user.
A production site intelligent security management system, the system in communication with an image acquisition device, comprising:
the video acquisition module is used for acquiring video of the production site based on the image acquisition device to obtain real-time video information of the production site;
the risk identification module is used for carrying out risk identification on the real-time video information of the production site through a risk identification model to obtain a risk identification result;
the early warning information generation module is used for evaluating the dangerous identification result and generating early warning information;
the second user supervision module is used for sending the early warning information to the first user and the second user, and the early warning information is used for supervising the second user.
The intelligent safety management method and system for the production site solve the technical problem that dangerous accidents occur due to the fact that site workers are difficult to effectively monitor in the power generation process of a power plant. The method comprises the steps of obtaining real-time video information of a production site through a movable image acquisition device of the production site, constructing a hazard identification model based on a historical hazard data set, carrying out hazard identification on the real-time video information of the production site through the hazard identification model, timely obtaining a hazard signal of the production site, carrying out hazard assessment on the hazard signal of the production site, generating early warning information through an assessment result, and sending the early warning information to a first user and a second user to realize supervision on site staff, so that the hazard signal can be found timely, production safety accidents can be effectively avoided, and life and property safety of people is guaranteed.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
FIG. 1 is a schematic flow chart of a smart security management method in a production site;
fig. 2 is a schematic structural diagram of a smart security management system for a production site.
Reference numerals illustrate: the system comprises a video acquisition module 1, a danger identification module 2, an early warning information generation module 3 and a second user supervision module 4.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
As shown in fig. 1, the present application provides a production site intelligent security management method: the method is applied to a production field intelligent safety management system, and the system is in communication connection with an image acquisition device and comprises the following steps:
step S100: based on the image acquisition device, carrying out video acquisition on the production site to obtain real-time video information of the production site;
specifically, the image acquisition device refers to various intelligent cameras installed on the production site of a power plant, including fixed type and movable type, for example: the intelligent spherical camera, the intelligent gun-type camera, the intelligent distributed control spherical camera and other devices are used for monitoring production site operators in real time in the whole process, recording collected audio and video data in real time in the whole process and automatically archiving and uniformly storing the collected audio and video data. The intelligent safety management system of the production site is in communication connection with the image acquisition device, namely the image acquisition device sends the acquired video information to the intelligent safety management system of the production site through the signal transmission module. The production site is subjected to real-time video acquisition through an image acquisition device arranged at the production site, real-time video information of the production site is obtained, and raw materials are provided for hazard identification of the real-time video information.
Step S200: performing hazard identification on the real-time video information of the production site through a hazard identification model to obtain a hazard identification result;
in one embodiment, step S200 of the present application further includes:
step S210: obtaining historical production field video information;
step S220: extracting features of the video information of the historical production site to obtain a historical dangerous data set;
in one embodiment, step S220 of the present application further includes:
step S221: presetting a characteristic identification standard rule;
step S222: performing feature recognition on the historical production field video information based on the feature recognition standard rule to obtain a plurality of feature recognition results;
step S223: and carrying out principal component analysis on the plurality of feature recognition results to obtain the historical dangerous data set.
Specifically, the historical production site video information refers to production site videos acquired and stored through an image acquisition device, and characteristic identification standard rules are set, wherein the characteristic identification standard rules refer to various rules violating safety production regulations in various regulations of a power plant production site. And screening and storing all actions meeting the characteristic recognition standard rule in the historical production site video to obtain a plurality of dangerous actions violating the rule, namely a plurality of characteristic recognition results, then performing dimension reduction processing on the plurality of characteristic recognition results to obtain a characteristic recognition dataset obtained through the dimension reduction processing, namely the historical dangerous dataset, and providing training data for constructing a dangerous recognition model in the next step by obtaining the historical dangerous dataset.
In one embodiment, step S223 of the present application further includes:
step S2231: obtaining a first feature recognition data set according to the feature recognition results;
step S2232: performing decentralization processing on the first characteristic identification data set to obtain a second characteristic identification data set;
step S2233: obtaining a covariance matrix of the first feature recognition according to the second feature recognition data set;
step S2234: obtaining a first eigenvalue and a first eigenvector according to the covariance matrix of the first feature recognition;
step S2235: and obtaining the historical dangerous data set according to the first characteristic value and the first characteristic vector.
Specifically, first, data normalization processing is performed on each feature data in the feature recognition results, and a feature data set matrix is constructed to obtain the first feature recognition data set. And then carrying out decentralization processing on each feature data in the feature recognition results, wherein the decentralization processing refers to solving the average value of each feature in the feature recognition results, then subtracting the average value of each feature from all the feature recognition results, and then obtaining a new feature value, and the second feature recognition data set is a data matrix and is composed of the new feature values. And calculating the second feature recognition data set through a covariance formula to obtain a covariance matrix of the first feature recognition of the second feature recognition data set, and then calculating the feature value and the feature vector of the covariance matrix of the first feature recognition through matrix calculation, wherein each feature value corresponds to one feature vector. And selecting the first K largest eigenvalues and the eigenvectors corresponding to the first eigenvalues from the first eigenvector, and projecting the original features in the first feature recognition dataset onto the selected eigenvectors to obtain the first feature recognition dataset after dimension reduction, namely the historical dangerous dataset. And carrying out principal component analysis on the plurality of feature recognition results, so that feature data in the plurality of feature recognition results can be subjected to dimension reduction, redundant data are removed on the premise of guaranteeing information quantity, and the sample quantity of the feature data in the plurality of feature recognition results is reduced, thereby accelerating the operation speed of a training model on the data.
Step S230: constructing a dangerous identification model;
step S240: training the hazard identification model based on the historical hazard data set to obtain the hazard identification model;
step S250: and carrying out hazard identification on the real-time video information of the production site through the hazard identification model to obtain the hazard identification result.
Specifically, the risk identification model is a neural network model which can be continuously subjected to self-iterative optimization in ware learning, and is obtained through a training data set. Inputting each characteristic data in the historical dangerous data set into the human recognition model for training, outputting a recognition result, when the model is trained to a convergence state, namely, when the output result tends to a stable value, the model training is successful, and then carrying out dangerous judgment on the real-time video information of the production site through the dangerous recognition model to obtain dangerous actions of operators on the production site, namely, the dangerous recognition result, for example: dangerous actions such as not carrying a safety helmet, not wearing work clothes, playing a mobile phone, dozing off and the like. The real-time video information of the production site is identified by constructing a dangerous identification model, so that dangerous actions of site operators can be rapidly distinguished by artificial intelligence means, problems can be timely found, and serious production safety accidents are avoided.
Step S300: evaluating the dangerous recognition result to generate early warning information;
in one embodiment, step S300 of the present application further includes:
step S310: obtaining a plurality of historical dangerous accident samples;
step S320: obtaining a plurality of historical dangerous accident data sets based on the plurality of historical dangerous accident samples, wherein the plurality of historical dangerous accident samples and the plurality of historical dangerous accident data sets have corresponding relations;
step S330: carrying out relevance evaluation on the plurality of historical dangerous accident samples and the plurality of historical dangerous accident data to obtain a plurality of relevance evaluation coefficients;
step S340: screening the plurality of relevance evaluation coefficients based on a relevance evaluation coefficient threshold, and adding the plurality of historical dangerous accident data corresponding to the plurality of relevance evaluation coefficients meeting the relevance evaluation coefficient threshold to a dangerous accident database;
step S350: performing principal component analysis on the dangerous accident database to obtain the dangerous accident data set;
step S360: and evaluating the dangerous identification result based on the dangerous accident data set to generate early warning information, wherein the early warning information comprises first early warning information and second early warning information.
Specifically, the plurality of historical dangerous accident samples refer to a plurality of generated power plant production safety accidents, including general safety accidents, larger safety accidents and major safety accidents. Particularly serious safety accidents. And obtaining a plurality of influence factors such as the cause, the passing of each safety accident and the like, namely a plurality of historical dangerous accident data sets, wherein the plurality of historical dangerous accident data sets and each safety accident are in one-to-one correspondence. The relevance evaluation is to mine the relation between the historical dangerous accident samples and the historical dangerous accident data to obtain a plurality of relevance evaluation coefficients, and the relevance evaluation coefficients are used for measuring coefficient indexes of the relation between the historical dangerous accident samples and the historical dangerous accident data. Setting a relevance evaluation coefficient threshold, screening the relevance evaluation coefficients according to the relevance evaluation coefficient threshold, constructing a dangerous accident database, adding the historical dangerous accident data corresponding to the relevance evaluation coefficients meeting the relevance evaluation coefficient threshold to the dangerous accident database, performing dimension reduction on feature data in the dangerous accident database to obtain a dangerous accident data set obtained through dimension reduction, evaluating the dangerous identification result according to the dangerous accident data set, grading the dangerous identification result, and generating first early warning information and second early warning information based on the grading result. The first early warning information refers to dangerous actions with low dangerous coefficients, for example: not wearing helmets correctly, not wearing protective gloves, etc. The second early warning information refers to dangerous actions with high risk coefficient and easy production safety accidents, for example: not wearing a safety helmet, playing a mobile phone during working hours, sleeping and the like. And by acquiring the early warning information, support is provided for monitoring production field operators in the next step.
Step S400: and sending the early warning information to a first user and a second user, wherein the early warning information is used for supervising the second user.
In one embodiment, step S400 of the present application further includes:
step S410: if the early warning information is first early warning information, the first early warning information is sent to a second user, and the first early warning information is used for carrying out danger reminding on the second user;
step S420: and if the early warning information is second early warning information, the second early warning information is sent to the first user, and the second early warning information is used for the first user to conduct danger supervision on the second user.
Specifically, the first user is a production site supervisor, and the second user is a production site operator. The first early warning information is dangerous actions with low dangerous coefficients, and the second early warning information is dangerous actions with high dangerous coefficients and easy production safety accidents. When the system finds that the dangerous action coefficient of the second user is lower, the system sends the first early warning information to the second user to remind the user to correct, for example: the notification is carried out by means of sending mobile phone short messages, sending voice, vibrating a WUB electronic chip and the like. And when the system finds that the dangerous action coefficient of the second user is high, sending the second early warning information to the first user, and when the first user criticizes the dangerous action of the second user and teaches the second user to correct. The technical problem that dangerous accidents occur due to the fact that field staff are difficult to effectively monitor in the power generation process of a power plant is solved.
In one embodiment, as shown in FIG. 2, there is provided a production site intelligent security management system communicatively coupled to an image capture device, comprising: the system comprises a video acquisition module 1, a danger identification module 2, an early warning information generation module 3 and a second user supervision module 4, wherein:
the video acquisition module 1 is used for carrying out video acquisition on a production site based on the image acquisition device to obtain real-time video information of the production site;
the risk identification module 2 is used for carrying out risk identification on the real-time video information of the production site through a risk identification model to obtain a risk identification result;
the early warning information generation module 3 is used for evaluating the dangerous identification result and generating early warning information;
and the second user supervision module 4 is used for sending the early warning information to the first user and the second user, and the early warning information is used for supervising the second user.
In one embodiment, the system further comprises:
the historical video information acquisition module is used for acquiring historical production site video information;
the historical feature extraction module is used for carrying out feature extraction on the historical production field video information to obtain a historical dangerous data set;
the model building module is used for building a dangerous identification model;
the model training module is used for training the dangerous identification model based on the historical dangerous data set to obtain the dangerous identification model;
and the risk identification module is used for carrying out risk identification on the real-time video information of the production site through the risk identification model to obtain the risk identification result.
In one embodiment, the system further comprises:
the rule presetting module is used for presetting characteristic recognition standard rules;
the characteristic recognition module is used for carrying out characteristic recognition on the historical production field video information based on the characteristic recognition standard rule to obtain a plurality of characteristic recognition results;
and the principal component analysis module is used for carrying out principal component analysis on the plurality of characteristic recognition results to obtain the historical dangerous data set.
In one embodiment, the system further comprises:
the first data set obtaining module is used for obtaining a first feature identification data set according to the feature identification results;
the decentralization module is used for decentralizing the first characteristic identification data set to obtain a second characteristic identification data set;
the covariance matrix obtaining module is used for obtaining a covariance matrix of the first feature recognition according to the second feature recognition data set;
the first information acquisition module is used for acquiring a first eigenvalue and a first eigenvector according to the covariance matrix identified by the first characteristics;
the historical dangerous data set obtaining module is used for obtaining the historical dangerous data set according to the first characteristic value and the first characteristic vector.
In one embodiment, the system further comprises:
a history sample obtaining module for obtaining a plurality of history dangerous accident samples;
a historical data set obtaining module, configured to obtain a plurality of historical dangerous accident data sets based on the plurality of historical dangerous accident samples, where the plurality of historical dangerous accident samples and the plurality of historical dangerous accident data sets have a correspondence;
the relevance evaluation module is used for carrying out relevance evaluation on the plurality of historical dangerous accident samples and the plurality of historical dangerous accident data to obtain a plurality of relevance evaluation coefficients;
the evaluation coefficient screening module is used for screening the plurality of relevance evaluation coefficients based on a relevance evaluation coefficient threshold value and adding the plurality of historical dangerous accident data corresponding to the plurality of relevance evaluation coefficients meeting the relevance evaluation coefficient threshold value to a dangerous accident database;
the principal component analysis module is used for carrying out principal component analysis on the dangerous accident database to obtain the dangerous accident data set;
the early warning information generation module is used for evaluating the dangerous identification result based on the dangerous accident data set to generate early warning information, and the early warning information comprises first early warning information and second early warning information.
In one embodiment, the system further comprises:
the first early warning information sending module is used for sending the first early warning information to a second user if the early warning information is first early warning information, and the first early warning information is used for carrying out danger reminding on the second user;
the second early warning information sending module is used for sending the second early warning information to the first user if the early warning information is the second early warning information, and the second early warning information is used for the first user to conduct danger supervision on the second user.
In summary, the present application provides a production field intelligent security management method and system, which have the following technical effects:
1. the production site real-time video information is identified by constructing the hazard identification model, the hazard actions of site operation personnel can be rapidly distinguished through an artificial intelligence means, early warning information is generated and sent to a first user and a second user to realize supervision of the site operation personnel, hazard signals are timely found and remedied, production safety accidents can be effectively avoided, and the life and property safety of people can be guaranteed.
2. The feature data in the dangerous accident database can be subjected to dimension reduction by carrying out principal component analysis on the dangerous accident database, redundant data are removed on the premise of guaranteeing the information quantity, and the sample quantity of the feature data in the dangerous accident database is reduced, so that the calculation speed of a training model on the data is increased.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (7)
1. A production site intelligent security management method, wherein the method is applied to a production site intelligent security management system, and the system is in communication connection with an image acquisition device, and comprises the following steps:
based on the image acquisition device, carrying out video acquisition on the production site to obtain real-time video information of the production site;
performing hazard identification on the real-time video information of the production site through a hazard identification model to obtain a hazard identification result;
evaluating the dangerous recognition result to generate early warning information;
and sending the early warning information to a first user and a second user, wherein the early warning information is used for supervising the second user.
2. The method of claim 1, wherein performing hazard recognition on the real-time video information of the production site through a hazard recognition model to obtain a hazard recognition result comprises:
obtaining historical production field video information;
extracting features of the video information of the historical production site to obtain a historical dangerous data set;
constructing a dangerous identification model;
training the hazard identification model based on the historical hazard data set to obtain the hazard identification model;
and carrying out hazard identification on the real-time video information of the production site through the hazard identification model to obtain the hazard identification result.
3. The method of claim 2, wherein the feature extracting the historical production site video information to obtain a historical risk dataset comprises:
presetting a characteristic identification standard rule;
performing feature recognition on the historical production field video information based on the feature recognition standard rule to obtain a plurality of feature recognition results;
and carrying out principal component analysis on the plurality of feature recognition results to obtain the historical dangerous data set.
4. A method as claimed in claim 3, wherein said principal component analysis of said plurality of feature recognition results to obtain said historical risk dataset comprises:
obtaining a first feature recognition data set according to the feature recognition results;
performing decentralization processing on the first characteristic identification data set to obtain a second characteristic identification data set;
obtaining a covariance matrix of the first feature recognition according to the second feature recognition data set;
obtaining a first eigenvalue and a first eigenvector according to the covariance matrix of the first feature recognition;
and obtaining the historical dangerous data set according to the first characteristic value and the first characteristic vector.
5. The method of claim 1: the method is characterized in that the step of evaluating the dangerous identification result to generate early warning information comprises the following steps:
obtaining a plurality of historical dangerous accident samples;
obtaining a plurality of historical dangerous accident data sets based on the plurality of historical dangerous accident samples, wherein the plurality of historical dangerous accident samples and the plurality of historical dangerous accident data sets have corresponding relations;
carrying out relevance evaluation on the plurality of historical dangerous accident samples and the plurality of historical dangerous accident data to obtain a plurality of relevance evaluation coefficients;
screening the plurality of relevance evaluation coefficients based on a relevance evaluation coefficient threshold, and adding the plurality of historical dangerous accident data corresponding to the plurality of relevance evaluation coefficients meeting the relevance evaluation coefficient threshold to a dangerous accident database;
performing principal component analysis on the dangerous accident database to obtain the dangerous accident data set;
and evaluating the dangerous identification result based on the dangerous accident data set to generate early warning information, wherein the early warning information comprises first early warning information and second early warning information.
6. The method of claim 1, wherein the sending the pre-warning information to the first user and the second user comprises:
if the early warning information is first early warning information, the first early warning information is sent to a second user, and the first early warning information is used for carrying out danger reminding on the second user;
and if the early warning information is second early warning information, the second early warning information is sent to the first user, and the second early warning information is used for the first user to conduct danger supervision on the second user.
7. A production site intelligent security management system, the system in communication with an image acquisition device, comprising:
the video acquisition module is used for acquiring video of the production site based on the image acquisition device to obtain real-time video information of the production site;
the risk identification module is used for carrying out risk identification on the real-time video information of the production site through a risk identification model to obtain a risk identification result;
the early warning information generation module is used for evaluating the dangerous identification result and generating early warning information;
the second user supervision module is used for sending the early warning information to the first user and the second user, and the early warning information is used for supervising the second user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310224236.2A CN116385925A (en) | 2023-03-09 | 2023-03-09 | Intelligent safety management method and system for production site |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310224236.2A CN116385925A (en) | 2023-03-09 | 2023-03-09 | Intelligent safety management method and system for production site |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116385925A true CN116385925A (en) | 2023-07-04 |
Family
ID=86979795
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310224236.2A Pending CN116385925A (en) | 2023-03-09 | 2023-03-09 | Intelligent safety management method and system for production site |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116385925A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117095465A (en) * | 2023-10-19 | 2023-11-21 | 华夏天信智能物联(大连)有限公司 | Coal mine safety supervision method and system |
-
2023
- 2023-03-09 CN CN202310224236.2A patent/CN116385925A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117095465A (en) * | 2023-10-19 | 2023-11-21 | 华夏天信智能物联(大连)有限公司 | Coal mine safety supervision method and system |
| CN117095465B (en) * | 2023-10-19 | 2024-02-06 | 华夏天信智能物联(大连)有限公司 | Coal mine safety supervision method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111445106B (en) | Safety control method and system for fault processing operation site of electricity acquisition equipment | |
| CN108833831A (en) | A kind of power construction intelligent safety monitor system | |
| CN112183265A (en) | Electric power construction video monitoring and alarming method and system based on image recognition | |
| CN108830745B (en) | Power grid cascading failure diagnosis, early warning and evaluation system based on monitoring information | |
| CN116385925A (en) | Intelligent safety management method and system for production site | |
| CN113542690B (en) | Building construction safety monitoring system and method | |
| CN115358155A (en) | Power big data abnormity early warning method, device, equipment and readable storage medium | |
| CN115131706B (en) | Power operation violation datamation intelligent image recognition system and method | |
| CN115567690A (en) | Intelligent monitoring system capable of automatically identifying dangerous points of field operation | |
| CN112686130B (en) | Wisdom fishing boat supervision decision-making system | |
| CN116844315A (en) | Artificial intelligent early warning method, system and storage medium | |
| CN116911596A (en) | Worker risk early warning method and system based on operation stability model | |
| CN115909212A (en) | Real-time early warning method for typical violation behaviors of power operation | |
| CN113762225B (en) | Automatic monitoring alarm system for chemical workshop | |
| CN116136897A (en) | Information processing method and device | |
| CN113988687A (en) | Nuclear power device state monitoring method and system | |
| CN113392576A (en) | Staying balloon main cable tension state assessment early warning method | |
| CN117014231B (en) | Industrial control network intrusion protection method and system based on ensemble learning | |
| LU501401B1 (en) | Action risk identification method for power system field operation based on graph convolution | |
| CN117111540B (en) | Environment monitoring and early warning method and system for IO remote control bus module | |
| CN117172559B (en) | Risk identification early warning method, system and storage medium for Internet of things data | |
| CN117499272B (en) | Intelligent operation and maintenance cloud platform control method and control system thereof | |
| CN113743326B (en) | Safety belt wearing state monitoring system, method, device and computer equipment | |
| CN113591393B (en) | Fault diagnosis method, device, equipment and storage medium of intelligent substation | |
| CN115001138A (en) | Main network maintenance single-start completion automatic permission system and method for power system |
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 |