CN111813841A - Complex environment intelligent safety management and control system based on multi-source data fusion - Google Patents
Complex environment intelligent safety management and control system based on multi-source data fusion Download PDFInfo
- Publication number
- CN111813841A CN111813841A CN202010609047.3A CN202010609047A CN111813841A CN 111813841 A CN111813841 A CN 111813841A CN 202010609047 A CN202010609047 A CN 202010609047A CN 111813841 A CN111813841 A CN 111813841A
- Authority
- CN
- China
- Prior art keywords
- information
- personnel
- field
- positioning
- control system
- 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
- 230000004927 fusion Effects 0.000 title claims abstract description 16
- 238000012544 monitoring process Methods 0.000 claims abstract description 21
- 238000010276 construction Methods 0.000 claims abstract description 8
- 230000006399 behavior Effects 0.000 claims description 22
- 238000005516 engineering process Methods 0.000 claims description 19
- 238000004519 manufacturing process Methods 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 9
- 238000000034 method Methods 0.000 claims description 9
- 238000002372 labelling Methods 0.000 claims description 6
- 238000011176 pooling Methods 0.000 claims description 6
- 238000010977 unit operation Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000005096 rolling process Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000009471 action Effects 0.000 claims description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/248—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/256—Integrating or interfacing systems involving database management systems in federated or virtual databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Public Health (AREA)
- Probability & Statistics with Applications (AREA)
- Water Supply & Treatment (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a complex environment intelligent safety management and control system based on multi-source data fusion, which is applied to the field of electric power. The system establishes a three-dimensional light weight model on site, positions information of positioning personnel, working states of the bringing-in units and operation contents of monitoring personnel, and realizes multi-source fusion of online and offline data, qualitative and quantitative data and the like, so that an active security database is established. The invention not only supports the online monitoring of the network cloud platform, but also supports the task access of the intelligent mobile terminal. For the management layer, comprehensive information of the unit can be monitored in real time, and daily operation contents can be checked; for field personnel, the state information of the work and the construction field can be known in time, and the personal safety is guaranteed; for the system, according to preset setting, bad states and wrong operation can be timely reminded and alarmed, potential safety hazards are reduced, and efficiency is improved.
Description
Technical Field
The invention belongs to the technical field of field control of an electric power system, and relates to a complex environment intelligent safety management and control system based on multi-source data fusion for monitoring and guaranteeing production safety.
Background
Safety is a first requirement of power production, especially personal safety issues, relating to the vital interests of power plant personnel. The overall goal of the power production safety is to prevent accidents that have great influence on society, great loss on the development of productivity and the value guarantee and increment of domestic assets, and particularly to avoid personal casualty accidents of power production. The principle of safety management in the power production process is 'safety is first, and prevention is the main', so that the safety of production is guaranteed to have very important significance. However, in the past decade, many casualties caused by power safety production occur in the whole country, and huge losses are caused to the safety of lives and property. Although casualty accidents are reduced by means of restriction of various strict regulations and rules, the problem of safety management and control is not fundamentally solved.
Analyzing the past accident cases, summarizing the unfortunate reasons mainly comprises the following aspects: the operation ticket or the work ticket is not strictly executed; the field worker is careless and the safety consciousness is relaxed; each working group on site is lack of cooperation; missing or unclear site identification, etc. Therefore, the mechanism of personal safety management mainly depends on system constraint, the management link is mainly responsible for each level of responsible person step by step, the mode is highly dependent on the perfection of the system on one hand and the experience and responsibility of a manager on the other hand, the manager can only strengthen the safety management through repeated emphasis and occasional field spot check, the position state of field workers cannot be mastered in real time basically, and the illegal and illegal behaviors of the field cannot be prevented in real time, so that the mode has a lot of uncontrollable factors. This is a relatively passive mode of security management. The construction and implementation of the active safety system can avoid safety risks existing in the work in real time, greatly reduce personal casualty accidents and reduce life and property losses.
Aiming at the practical problems, many researches and inventions are based on the scene, and some systems are developed for monitoring and guiding, but the systems are often deficient in accurate positioning and intelligent control. In consideration of the current situation, high and new technologies such as a mobile personnel accurate positioning technology, an internet of things technology, an artificial intelligence technology, a data processing technology, an internet technology and the like are mature and gradually improved. The invention aims to develop a set of active safety management and control system, change passive after-tracking into active prevention in advance, strengthen risk management and control and hidden danger investigation and management, monitor and correct unsafe behaviors of personnel, and realize intelligent personnel and equipment management, thereby achieving the important goal of power production safety.
The technical route of the invention is as follows: and integrating three-dimensional information of the power plant, accurate personnel flow positioning and identification information, unit running state information and field operation task information to construct an active safety database through multi-source data fusion. Based on the database, personnel, equipment and operation management and control of the whole unit can be realized, field operation behaviors are monitored and intelligently guided, unsafe behaviors are alarmed and corrected in time, and personal safety accidents are actively reduced and avoided.
Disclosure of Invention
The invention provides a complex environment intelligent safety management and control system based on multi-source data fusion, aiming at realizing the safety management and control of power production, reducing safety risks, improving working efficiency, realizing active safety accidents and preventing personal and equipment accidents from happening. The system integrates multi-source data, utilizes multiple advanced intelligent technologies to construct an active safety database, can realize field monitoring and error correction, effectively solves the problem of the deficiency of the electric power production safety field in high-precision and fine safety control, provides powerful safety guarantee for operators, and improves the economic benefit of enterprises.
According to some embodiments, the invention adopts the following technical scheme:
the utility model provides a complex environment intelligent security management and control system based on multisource data fusion who is applied to electric power field which the characterized in that includes following content:
A. establishing a lightweight three-dimensional model of the on-site unit, dividing different safe regions according to prior knowledge, and prefabricating information such as prompt, monitoring, alarm and the like;
B. high-precision personnel positioning is realized, and personnel information and personnel behaviors are identified;
C. the unit SIS system is docked, production equipment information is fused, and the unit operation condition is obtained in real time;
D. the SAP system is connected, the field construction work content of an operator is obtained, and the field operation is monitored;
E. and multi-source data are fused to establish an active security database, so that real-time field monitoring of the Internet and safety control of online operation are realized.
Preferably, step a is characterized by:
a1, determining the proportion of modeling equipment through images and CAD drawing data, utilizing 3ds Max software to simulate modeling, collecting all areas and equipment of the power plant, drawing a three-dimensional graph, and establishing a coordinate system the same as an actual scene, thereby showing all appearances of the units of the power plant, and in addition, realizing practical functions of path roaming, scene layering, scene switching, route navigation and the like.
A2, dividing areas with different security levels, labeling the three-dimensional model area from no risk to low risk, medium risk and high risk, and labeling risk notice and operation security specifications. In addition, the basic attribute information of each equipment facility in the three-dimensional model is labeled, so that the personnel can conveniently check and manage the equipment.
And A3, three-dimensional modeling property and light weight. The model is simplified in order to reduce the occupation of computer resources and improve the loading and displaying speed of the three-dimensional model. The mesh is a basic unit forming a model, and the simplified model is a simplification of the mesh. The invention simplifies the model by adopting an edge folding algorithm based on quadratic error measurement. The method sequences the edges contained in the grid by deleting the cost, replaces the edge with the minimum price each time, and continuously repeats the operation until the requirement is met.
False error Δ (u)0→ui) Representing selected mesh vertices u0To uiSum of squares of distances:
wherein, P (u)i) Represents uiSet of associated grids, p ═ a, b, c, d)TDenotes that ax + by + cz + d is 0, a2+b2+c21, so:
Then the minimum edge folding cost Δ M ═ u0 T(Q(u1)+Q(u2))u0。
Preferably, the high-precision positioning of indoor articles and people is realized by using ultra-wideband (UWB) -based technology, the identification and classification of the action characteristics of the human machine are realized by using a convolutional neural network, and the step B is characterized in that:
b1, arranging a WIFI wireless network on the site to fully cover, and providing the optimal 30cm positioning accuracy reaching 10cm level and generally shielding in a three-dimensional space based on a novel high-precision wireless positioning system. And fixing a plurality of micro base stations, and accurately positioning and tracking field personnel by using a TDOA (time difference of arrival) positioning algorithm through the relative positions of the micro base stations and the carried micro labels.
Let the coordinates of the mobile tag be (x, y) and the coordinates of the ith (i ═ 1, 2, 3) base station be (x)i,yi) Therefore, the position of the moving label under the two-dimensional model can be expressed as:
the position coordinates of the mobile tag can be obtained according to the formula, and the moving track of the mobile tag can be obtained in the same way.
B2, identifying personal information of the field personnel through a face identification technology; through deep learning technology, the behavior dynamics of personnel is identified, and unsafe, lost work, misoperation and other behaviors are warned and recorded, including but not limited to crowding, off duty, approaching a danger source, leaving a group, entering a risk level area and the like.
The invention is mainly based on a convolutional neural network algorithm, and consists of 7 layers of models, wherein the 7 layers of models comprise 2 convolutional layers, 2 pooling layers, 2 full-link layers and 1 Softmax regression layer.
And (3) rolling layers: firstly, dividing an input image into a plurality of small blocks, then extracting a feature map for each small block by using a filter, wherein each filter corresponds to one small block, and then performing convolution operation on the plurality of feature maps again to obtain the feature map again.
A pooling layer: the feature map is feature compressed to reduce the image space, and the max method is adopted in the invention, namely, the maximum value in a feature group is taken.
Full connection layer: all features are concatenated and the output value is sent to the Softmax classifier.
Softmax regression layer: assuming m training samples, k identification tags, i.e. xi∈Rn+1,yiE {0, 1, 2, …, k }, assuming that the function of the probability p (y ═ y | x) of estimating for each sample the class to which it belongs is:
wherein θ represents a vector, and θi∈Rn+1Then the class probability estimated for each sample is:
preferably, step C, real-time data information of the unit operation in the SIS database is obtained, and on one hand, the real-time data information is used for overall monitoring of the unit, and on the other hand, the real-time data information is labeled in a corresponding scene of the three-dimensional model, so that the state of field personnel can be conveniently controlled.
Preferably, step D is characterized by:
d1, butting the SAP system to obtain the field operation contents required to be carried out, including the distribution, the verification, the approval, the picking and the submission of tasks.
D2, when the task is picked up and enters the site to operate, the positioning and identifying technology in B is used to monitor the construction situation, remind the attention matters related to the task and the dangerous attention matters in the operation area, monitor the behavior dynamics of the personnel and warn the related improper behaviors.
Preferably, step E is characterized by:
e1, the active safety database fuses three-dimensional model information, personnel positioning and identifying information, equipment running state information and field operation content information of the power plant to form a set of comprehensive database system integrating collection, display, monitoring, alarming, recording and the like.
E2, the online cloud platform accesses the active security database to obtain various statistical data faces of the whole plant, including but not limited to equipment state statistics, personnel work completion conditions and the like.
E3, the individual accesses the database through the mobile client to obtain task information, site information, individual evaluation information, etc.
And after the steps are completed, the complex environment intelligent safety management and control system based on multi-source data fusion is established. For field operators, the active security database is accessed through the mobile client, the operators go to a designated area to take operation after getting related tasks, in the process, the clients can look up related state information and notice reminding in the database so as to operate according to rules in time, and meanwhile, the database receives a field positioner, a camera device and the like, judges and identifies the behavior of the operators, and evaluates, guides, warns and the like. The management personnel can access and acquire the conditions, task completion conditions and the like of the whole unit through the cloud internet so as to intelligently manage field equipment, personnel operation and the like.
Compared with the prior art, the invention has the beneficial effects that:
the invention realizes the visualization of the field environment through three-dimensional lightweight modeling, and leads the monitoring and supervision to be more visual and intuitive. Under the three-dimensional scene, all-round tracking monitoring can be carried out to various three-dimensional operations and cross operations under the whole plant environment.
The invention is based on a novel high-precision wireless positioning system, and can provide the optimal positioning precision of 10cm grade and 30cm under general shielding in a three-dimensional space. Therefore, high-precision personnel identification and high-efficiency dynamic behavior tracking are realized.
According to the invention, the state information and the engineering operation task information of the power plant are fused, and the three-dimensional model and the indoor positioning identification technology are combined, so that the operation amount of staff can be guided and evaluated finely, the problem of subjective errors is solved fundamentally, the life safety of personnel is guaranteed, and the economic benefit of the power plant is improved.
Drawings
FIG. 1 is a system framework diagram;
FIG. 2 is a three-dimensional model implementation flow;
FIG. 3 is a field personnel location, identification framework;
FIG. 4 is a field personnel task implementation step;
FIG. 5 is a global monitoring system of an internet cloud platform intelligent management and control system.
Detailed Description
The invention is further described with reference to the following figures and examples.
The implementation of the present invention is exemplified by Guangyu coal-electric company Limited, Xin-Hua-N.
Fig. 1 shows the framework of the overall system. An active safety database is established by a three-dimensional lightweight simulation model, accurate personnel positioning, tracking and identifying information, unit state monitoring information, personnel operation task information and the like, and online and offline intelligent safety control is realized. According to the framework of fig. 1, an intelligent management and control system based on multi-source data fusion for complex environment in the field of electric power is characterized by comprising the following components:
A. establishing a lightweight three-dimensional model of the on-site unit, dividing different safe regions according to prior knowledge, and prefabricating information such as prompt, monitoring, alarm and the like;
B. high-precision personnel positioning is realized, and personnel information and personnel behaviors are identified;
C. the unit SIS system is docked, production equipment information is fused, and the unit operation condition is obtained in real time;
D. the SAP system is connected, the field construction work content of an operator is obtained, and the field operation is monitored;
E. and multi-source data are fused to establish an active security database, so that real-time field monitoring of the Internet and safety control of online operation are realized.
Step a is characterized in that:
a1, determining the proportion of modeling equipment through images and CAD drawing data, utilizing 3ds Max software to simulate modeling, collecting all areas and equipment of the power plant, drawing a three-dimensional graph, and establishing a coordinate system the same as an actual scene, thereby showing all appearances of the units of the power plant, and in addition, realizing practical functions of path roaming, scene layering, scene switching, route navigation and the like. An example of a portion of a three-dimensional model is shown in figure 2.
A2, dividing areas with different security levels, labeling the three-dimensional model area from no risk to low risk, medium risk and high risk, and labeling risk notice and operation security specifications. In addition, the basic attribute information of each equipment facility in the three-dimensional model is labeled, so that the personnel can conveniently check and manage the equipment.
And A3, three-dimensional modeling property and light weight. The model is simplified in order to reduce the occupation of computer resources and improve the loading and displaying speed of the three-dimensional model. The mesh is a basic unit forming a model, and the simplified model is a simplification of the mesh. The invention simplifies the model by adopting an edge folding algorithm based on quadratic error measurement. The method sequences the edges contained in the grid by deleting the cost, replaces the edge with the minimum price each time, and continuously repeats the operation until the requirement is met.
False error Δ (u)0→ui) Representing selected mesh vertices u0To uiSum of squares of distances:
wherein, P (u)i) Represents uiSet of associated grids, p ═ a, b, c, d)TDenotes that ax + by + cz + d is 0, a2+b2+c21, so:
Then the minimum edge folding cost Δ M ═ u0 T(Q(u1)+Q(u2))u0。
Step B is characterized in that:
b1, arranging a WIFI wireless network on the site to fully cover, and providing the optimal 30cm positioning accuracy reaching 10cm level and generally shielding in a three-dimensional space based on a novel high-precision wireless positioning system. And fixing a plurality of micro base stations, and accurately positioning and tracking field personnel by using a TDOA (time difference of arrival) positioning algorithm through the relative positions of the micro base stations and the carried micro labels.
Let the coordinates of the mobile tag be (x, y) and the coordinates of the ith (i ═ 1, 2, 3) base station be (x)i,yi) Therefore, the position of the moving label under the two-dimensional model can be expressed as:
the position coordinates of the mobile tag can be obtained according to the formula, and the moving track of the mobile tag can be obtained in the same way.
B2, identifying personal information of the field personnel through a face identification technology; through deep learning technology, the behavior dynamics of personnel is identified, and unsafe, lost work, misoperation and other behaviors are warned and recorded, including but not limited to crowding, off duty, approaching a danger source, leaving a group, entering a risk level area and the like. The activity track of the person can be displayed in a three-dimensional graph, including person information, task data, and the like, as shown in fig. 3.
The invention is mainly based on a convolutional neural network algorithm, and consists of 7 layers of models, wherein the 7 layers of models comprise 2 convolutional layers, 2 pooling layers, 2 full-link layers and 1 Softmax regression layer.
And (3) rolling layers: firstly, dividing an input image into a plurality of small blocks, then extracting a feature map for each small block by using a filter, wherein each filter corresponds to one small block, and then performing convolution operation on the plurality of feature maps again to obtain the feature map again.
A pooling layer: the feature map is feature compressed to reduce the image space, and the max method is adopted in the invention, namely, the maximum value in a feature group is taken.
Full connection layer: all features are concatenated and the output value is sent to the Softmax classifier.
Softmax regression layer: assuming m training samples, k identification tags, i.e. xi∈Rn+1,yiE {0, 1, 2, …, k }, assuming that the function of the probability p (y ═ y | x) of estimating for each sample the class to which it belongs is:
wherein θ represents a vector, and θi∈Rn+1Then the class probability estimated for each sample is:
and step C, acquiring real-time data information of unit operation in the SIS database, on one hand, the real-time data information is used for comprehensively monitoring the unit, and on the other hand, the real-time data information is marked in a corresponding scene of the three-dimensional model, so that the state of field personnel can be conveniently controlled.
Step D is characterized in that:
d1, butting the SAP system to obtain the field operation contents required to be carried out, including the distribution, the verification, the approval, the picking and the submission of tasks.
D2, when the task is picked up and enters the site to operate, the positioning and recognition technology in B is used to monitor the construction situation, and remind the attention matters related to the task and the dangerous attention matters in the operation area, and monitor the behavior dynamics of the personnel and warn the related improper behaviors, and the operation flow of the mobile terminal task is shown in figure 4.
Preferably, step E is characterized by:
e1, the active safety database fuses three-dimensional model information, personnel positioning and identifying information, equipment running state information and field operation content information of the power plant to form a set of comprehensive database system integrating collection, display, monitoring, alarming, recording and the like.
E2, the online cloud platform accesses the active security database to obtain various statistical data faces of the whole plant, including but not limited to equipment state statistics, personnel work completion conditions and the like. An overview of the cloud platform is shown in fig. 5.
E3, the individual accesses the database through the mobile client to obtain task information, site information, individual evaluation information, etc.
The above description is only a preferred embodiment of the present invention, and is not limited to the present invention, and has wide application value for some industrial field applications in the field and even across fields, and only needs to make adjustment changes to part of the contents according to local conditions.
Claims (6)
1. The utility model provides a complex environment intelligent security management and control system based on multisource data fusion who is applied to electric power field which the characterized in that includes following content:
A. establishing a lightweight three-dimensional model of the on-site unit, dividing different safe regions according to prior knowledge, and presetting information such as prompting, monitoring and alarming;
B. high-precision personnel positioning is realized, and personnel information and personnel behaviors are identified;
C. the unit SIS system is docked, production equipment information is fused, and the unit operation condition is obtained in real time;
D. the SAP system is connected, the field construction work content of an operator is obtained, and the field operation is monitored;
E. and multi-source data are fused to establish an active security database, so that real-time field monitoring of the Internet and safety control of online operation are realized.
2. The complex environment intelligent safety management and control system based on multi-source data fusion of claim 1, characterized in that:
a1, determining the proportion of modeling equipment through images and CAD drawing data, utilizing 3ds Max software to simulate modeling, collecting all areas and equipment of the power plant, drawing a three-dimensional graph, and establishing a coordinate system which is the same as an actual scene, so that the appearance of a unit of the power plant is completely displayed, and in addition, the practical functions of path roaming, scene layering, scene switching, route navigation and the like can be realized;
a2, dividing areas with different security levels, labeling the three-dimensional model area from no risk to low risk, medium risk and high risk, and labeling risk notice and operation security specifications; in addition, the basic attribute information of each equipment facility in the three-dimensional model is labeled, so that the personnel can conveniently check and manage the equipment;
a3, three-dimensional modeling and light weight: the model is simplified in order to reduce the occupation of computer resources and improve the loading and displaying speed of the three-dimensional model; the grid is a basic unit forming a model, and the simplified model is a simplified grid; the method adopts an edge folding algorithm based on secondary error measurement to simplify the model; the method sequences edges contained in the grid by deleting the cost, replaces the edge with the minimum price each time, and continuously repeats the operation until the requirement is met;
false error Δ (u)0→ui) Representing selected mesh vertices u0To uiSum of squares of distances:
wherein, P (u)i) Represents uiSet of associated grids, p ═ a, b, c, d)TDenotes that ax + by + cz + d is 0, a2+b2+c21, so:
Then the minimum edge folding cost Δ M ═ u0 T(Q(u1)+Q(u2))u0。
3. The complex environment intelligent safety management and control system based on multi-source data fusion of claim 1, which utilizes ultra-wideband (UWB) technology to realize high-precision positioning of indoor articles and persons, and utilizes convolutional neural network to realize identification and classification of persons and action characteristics thereof, and is characterized in that:
b1, arranging a WIFI wireless network on site to fully cover, and providing the optimal positioning precision of 10cm grade and 30cm under general shielding in a three-dimensional space based on a novel high-precision wireless positioning system; fixing a plurality of micro base stations, and accurately positioning and tracking field personnel by using a TDOA (time difference of arrival) positioning algorithm through the relative positions of the micro base stations and the carried micro labels;
let the coordinates of the mobile tag be (x, y) and the coordinates of the ith (i ═ 1, 2, 3) base station be (x)i,yi) Therefore, the position of the moving label under the two-dimensional model can be expressed as:
according to the formula, the position coordinates of the mobile tag can be obtained, and the moving track of the mobile tag can be obtained in the same way;
b2, identifying personal information of the field personnel through a face identification technology; through a deep learning technology, the behavior dynamics of personnel is identified, and the behaviors of insecurity, disability, misoperation and the like are warned and recorded, wherein the behaviors comprise but are not limited to crowding, off duty, approaching a danger source, leaving a group, entering a risk level area and the like;
the method is mainly based on a convolutional neural network algorithm, and consists of 7 layers of models, wherein each model comprises 2 convolutional layers, 2 pooling layers, 2 full-link layers and 1 Softmax regression layer;
and (3) rolling layers: firstly, dividing an input image into a plurality of small blocks, then extracting a feature map from each small block by using a filter, wherein each filter corresponds to one small block, and then performing convolution operation on a plurality of feature maps again to obtain the feature map again;
a pooling layer: the feature map is compressed, so as to reduce the image space, the invention adopts max method, namely, the maximum value in a feature group is taken;
full connection layer: connecting all the characteristics, and sending an output value to a Softmax classifier;
softmax regression layer: assuming m training samples, k identification tags, i.e. xi∈Rn+1,yiE {0, 1, 2, …, k }, assuming that the function of the probability p (y ═ y | x) of estimating for each sample the class to which it belongs is:
wherein θ represents a vector, and θi∈Rn+1Then the class probability estimated for each sample is:
4. the complex environment intelligent safety management and control system based on multi-source data fusion of claim 1, characterized in that:
and content C, acquiring real-time data information of unit operation in the SIS database, on one hand, the real-time data information is used for comprehensively monitoring the unit, and on the other hand, the real-time data information is marked in a corresponding scene of the three-dimensional model, so that the state of field personnel can be conveniently controlled.
5. The complex environment intelligent safety management and control system based on multi-source data fusion of claim 1, characterized in that:
d1, butting the SAP system to obtain the on-site operation contents required to be carried out, including the issuing, the auditing, the approving, the picking and the submitting of tasks;
d2, when the task is picked up and enters the site to operate, the positioning and identifying technology in B is used to monitor the construction situation, remind the attention matters related to the task and the dangerous attention matters in the operation area, monitor the behavior dynamics of the personnel and warn the related improper behaviors.
6. The complex environment intelligent safety management and control system based on multi-source data fusion of claim 1, characterized in that:
e1, fusing three-dimensional model information, personnel positioning and identifying information, equipment running state information and field operation content information of the power plant by an active safety database to form a comprehensive database system integrating acquisition, display, monitoring, alarming, recording and the like;
e2, the online cloud platform accesses the active security database to obtain various statistical data faces of the whole plant, including but not limited to equipment state statistics, personnel work completion conditions and the like;
e3, the individual accesses the database through the mobile client to obtain task information, site information, individual evaluation information, etc.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010609047.3A CN111813841A (en) | 2020-06-23 | 2020-06-23 | Complex environment intelligent safety management and control system based on multi-source data fusion |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010609047.3A CN111813841A (en) | 2020-06-23 | 2020-06-23 | Complex environment intelligent safety management and control system based on multi-source data fusion |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111813841A true CN111813841A (en) | 2020-10-23 |
Family
ID=72856603
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010609047.3A Pending CN111813841A (en) | 2020-06-23 | 2020-06-23 | Complex environment intelligent safety management and control system based on multi-source data fusion |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111813841A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113408968A (en) * | 2021-08-19 | 2021-09-17 | 南通市立新机械制造有限公司 | Safety production area personnel management method and system based on big data analysis |
WO2023065771A1 (en) * | 2021-10-19 | 2023-04-27 | 山西全安新技术开发有限公司 | Regulation violation behavior identification method and intelligent anti-regulation violation sensor system |
CN117217968A (en) * | 2023-11-07 | 2023-12-12 | 安元科技股份有限公司 | Dangerous chemical enterprise safety risk management and control platform based on UE4 twin technology |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110009195A (en) * | 2019-03-08 | 2019-07-12 | 晋能电力集团有限公司嘉节燃气热电分公司 | Thermal power plant's risk pre-control management system based on physical vlan information fusion technology |
CN110135319A (en) * | 2019-05-09 | 2019-08-16 | 广州大学 | A kind of anomaly detection method and its system |
CN111091609A (en) * | 2019-12-11 | 2020-05-01 | 云南电网有限责任公司保山供电局 | Transformer substation field operation management and control system and method based on three-dimensional dynamic modeling |
-
2020
- 2020-06-23 CN CN202010609047.3A patent/CN111813841A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110009195A (en) * | 2019-03-08 | 2019-07-12 | 晋能电力集团有限公司嘉节燃气热电分公司 | Thermal power plant's risk pre-control management system based on physical vlan information fusion technology |
CN110135319A (en) * | 2019-05-09 | 2019-08-16 | 广州大学 | A kind of anomaly detection method and its system |
CN111091609A (en) * | 2019-12-11 | 2020-05-01 | 云南电网有限责任公司保山供电局 | Transformer substation field operation management and control system and method based on three-dimensional dynamic modeling |
Non-Patent Citations (3)
Title |
---|
胡自飞: "基于TDOA技术的工厂人员安防定位系统设计", 电子技术应用, vol. 44, no. 5, pages 144 - 150 * |
郭思怡: "建筑运维阶段信息模型的轻量化方法", 图学学报, vol. 39, no. 1, pages 123 - 128 * |
魏丽冉: "基于深度神经网络的人体动作识别方法", 济南大学学报, vol. 33, no. 3, pages 215 - 223 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113408968A (en) * | 2021-08-19 | 2021-09-17 | 南通市立新机械制造有限公司 | Safety production area personnel management method and system based on big data analysis |
WO2023065771A1 (en) * | 2021-10-19 | 2023-04-27 | 山西全安新技术开发有限公司 | Regulation violation behavior identification method and intelligent anti-regulation violation sensor system |
CN117217968A (en) * | 2023-11-07 | 2023-12-12 | 安元科技股份有限公司 | Dangerous chemical enterprise safety risk management and control platform based on UE4 twin technology |
CN117217968B (en) * | 2023-11-07 | 2024-01-23 | 安元科技股份有限公司 | Dangerous chemical enterprise safety risk management and control platform based on UE4 twin technology |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111813841A (en) | Complex environment intelligent safety management and control system based on multi-source data fusion | |
CN109978409B (en) | Multi-engineering enterprise-level intelligent construction site block chain management method | |
CN111242574A (en) | Intelligent site inspection management system and method based on GPS technology | |
Wang et al. | Model construction of planning and scheduling system based on digital twin | |
CN107146065A (en) | Railway engineering management platform system | |
CN112418764A (en) | 5G visual warehouse pipe system | |
CN112070454B (en) | Design method of expressway maintenance construction area control safety management system | |
CN113902237A (en) | On-site operation risk management and control system | |
CN113034311A (en) | Building construction supervision system and method based on BIM | |
CN114841660B (en) | Enterprise intelligent security management and control cloud platform based on field information | |
CN115860499A (en) | Multi-professional work-type coordination construction management system based on BIM technology | |
CN111311133B (en) | Monitoring system applied to power grid production equipment | |
CN103903088A (en) | High-speed railway construction project quality risk control system and method | |
Sun et al. | Unmanned technology-based civil-military intelligent logistics system: from construction to integration | |
Deberdieva et al. | Experience in the management of business processes with the use of digital technologies by Russian companies of a petrochemical complex | |
Xue et al. | Developing a unified framework for data sharing in the smart construction using text analysis | |
CN111709597B (en) | Power grid production domain operation monitoring system | |
CN113379370A (en) | Segment production informatization management system | |
CN107633308A (en) | Thermal power plant's cruising inspection system based on Internet of Things | |
CN115132368A (en) | Infectious disease prevention and control monitoring method and system based on big data platform | |
Diange et al. | Research on the construction of civil airport safety management system based on digital twin technology | |
CN115457211A (en) | Transformer substation management method and system based on digital twins | |
CN112163797B (en) | Water service engineering real-time monitoring method and system based on BIM technology | |
CN114943472A (en) | Operation safety supervision system applied to transformer substation | |
CN111401154B (en) | AR-based logistics accurate auxiliary operation device for transparent distribution |
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 |