CN113162240B - Power line carrier intelligent monitoring method and system of city information model - Google Patents

Power line carrier intelligent monitoring method and system of city information model Download PDF

Info

Publication number
CN113162240B
CN113162240B CN202110515830.8A CN202110515830A CN113162240B CN 113162240 B CN113162240 B CN 113162240B CN 202110515830 A CN202110515830 A CN 202110515830A CN 113162240 B CN113162240 B CN 113162240B
Authority
CN
China
Prior art keywords
model
power
urban
city
building
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.)
Active
Application number
CN202110515830.8A
Other languages
Chinese (zh)
Other versions
CN113162240A (en
Inventor
刘俊伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Terry Digital Technology Beijing Co ltd
Original Assignee
Terra It Technology Beijing Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Terra It Technology Beijing Co ltd filed Critical Terra It Technology Beijing Co ltd
Priority to CN202110515830.8A priority Critical patent/CN113162240B/en
Publication of CN113162240A publication Critical patent/CN113162240A/en
Application granted granted Critical
Publication of CN113162240B publication Critical patent/CN113162240B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00006—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment
    • H02J13/00007—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment using the power network as support for the transmission
    • 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
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B70/00—Technologies for an efficient end-user side electric power management and consumption
    • Y02B70/30—Systems integrating technologies related to power network operation and communication or information technologies for improving the carbon footprint of the management of residential or tertiary loads, i.e. smart grids as climate change mitigation technology in the buildings sector, including also the last stages of power distribution and the control, monitoring or operating management systems at local level
    • 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
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y02B90/20—Smart grids as enabling technology in buildings sector
    • 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
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/40—Display of information, e.g. of data or controls
    • 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
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S20/00—Management or operation of end-user stationary applications or the last stages of power distribution; Controlling, monitoring or operating thereof
    • Y04S20/20—End-user application control systems
    • Y04S20/242—Home appliances
    • 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
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S40/00—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them
    • Y04S40/12—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them characterised by data transport means between the monitoring, controlling or managing units and monitored, controlled or operated electrical equipment
    • Y04S40/121—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them characterised by data transport means between the monitoring, controlling or managing units and monitored, controlled or operated electrical equipment using the power network as support for the transmission

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Geometry (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Power Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Civil Engineering (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Structural Engineering (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Architecture (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention provides an intelligent power carrier monitoring method for an urban model, which is characterized by comprising the following steps of: s1 building a two-dimensional model of the urban road and the building based on the artificial intelligent network; s2, making city model real object according to the two-dimensional model of the step S1, and arranging a light-emitting device at the position where the electric power equipment or the electric appliance exists in the road and the building of the model real object; s3, constructing an urban power carrier signal transmission system and establishing an urban power carrier intelligent monitoring model; s4 real-time monitoring the power operation state of the city according to the model established in the step S3. The invention can acquire real-time visual space-time distribution monitoring of the urban electric power operation state through video shooting of the luminous 3D printed urban model and artificial intelligent model identification, thereby realizing intelligent monitoring of the urban electric power operation state.

Description

Power line carrier intelligent monitoring method and system of city information model
Technical Field
The invention relates to an intelligent detection method of urban power carrier waves, in particular to an intelligent power carrier wave monitoring method and system of an urban model, and belongs to the field of intelligent power detection.
Background
The method comprises the following steps of designing a digital twin city, designing a model for online verification, carrying out digital diagnosis, carrying out intelligent prediction, carrying out autonomous learning and carrying out automatic optimization. And the urban power naturally has the technical inherent property of automatic detection. Therefore, how to construct the inherent property of the power into the digital twin city, and realizing the intelligent management of the urban power is a large shell for realizing the intelligent power management of the digital twin city. The power line monitoring method has the advantages that a special line does not need to be erected, construction is convenient and fast, cost performance is high, and the method is basically consistent with distribution of dispatching management.
However, the PLC technology has the following defects: the distribution transformer has a barrier effect on power carrier signals, and the space range of the transmission signals is limited; in addition, electromagnetic wave signals are attenuated within a range of several tens of meters. The wireless communication technology is a method for solving the defects in the two aspects, namely, a distribution transformer is not needed, and only wireless signal conversion equipment for power carrier signals is needed to be arranged in a range of dozens of meters, so that the problem of signal attenuation on a power line can be solved. However, for the indoor and outdoor areas of a city, the propagation distances required for signals are different, and the propagation is generally within tens of meters on one floor indoors, and the propagation from outdoor to indoor is in the hundreds of meters or even thousands of meters.
If in order to realize the visualization of electric power condition distribution, coordinate the signal transmission requirement of different distances, consider to have the unmanned aerial vehicle flight of geographical positioning device and send outdoor data in real time, perhaps rely on indoor robot to gather data, though feasible to miniature garden, then increase the cost on the city level, unmanned aerial vehicle and indoor robot can not accomplish to carry out the task of patrolling and examining at all times yet. The power equipment at each place in the city is subjected to wireless data acquisition, and a huge city system makes the urban power inspection based on unmanned aerial vehicles or robots especially unrealistic.
Again, wireless technology is becoming a reliable solution to the above-mentioned problems. The concentrator is accessed by using a power line carrier, so that a carrier signal is converted into a wireless signal, and a local lossless signal transmission process is realized. However, the technology only stays on the remote meter reading technology (CN 103743448A).
The augmented reality technology (AR) is one of the feasible solutions to the spatial distribution of the on-site power operation, and although the on-site visual monitoring of the operation state of the on-site field equipment (CN 109947052A) can be realized by the AR technology, the implementation range is limited to the factory (CN111966068A) or the home (CN 111505953A), so it is difficult to provide an intelligent monitoring solution for the power operation of the whole city.
In the acquisition of monitoring basic data of power operation, in the aspect of power carrier abnormal signal detection, the prior art provides an intelligent identification scheme for electric signals by using a convolutional neural network, but is also limited to the aspect of non-visual low-voltage power (CN 112364753A). For the data stream of the huge electrical signals of the city changing with time, the huge electrical parameters are difficult to form real-time and rapid processing, so that the method is only limited in a small range of enterprise units.
Disclosure of Invention
In order to solve the problems, the invention considers a visualization technology of an urban model for establishing intelligent power monitoring of machine learning, and the model can be a 3D model or a model entity of a semantic model. Three technical difficulties need to be considered for this purpose: firstly, how to realize physical visual distribution of the electric power operation state in the urban model, and secondly, how to represent the space-time distribution of the urban electric power operation state; and third to provide an improved algorithm by which intelligent monitoring of the power carrier is relied upon.
Therefore, the invention provides an intelligent power carrier monitoring method for an urban model, which is characterized by comprising the following steps of:
s1 building a two-dimensional model of the urban road and the building based on the artificial intelligent network;
s2, making city model real object according to the two-dimensional model of the step S1, and arranging a light-emitting device at the position where the electric power equipment or the electric appliance exists in the road and the building of the model real object;
s3, constructing an urban power carrier signal transmission system and establishing an urban power carrier intelligent monitoring model;
s4 real-time monitoring the power operation state of the city according to the model established in the step S3.
About S1
S1 specifically includes:
s1-1, establishing an urban road network model of an artificial intelligent network;
s1-2, building a city building network model of the artificial intelligent network;
s1-3, the models established in the steps S1-1 and S1-2 are fused to form a two-dimensional model of the urban road and the building.
Wherein, step S1-1 specifically includes: s1-1-1, establishing an urban geographic coordinate system E, wherein an XOY plane represents the ground, generating road continuous nodes by a node generator comprising an encoder and a decoder by utilizing an RNN recurrent neural network algorithm based on urban remote sensing images, connecting the two nodes before and after generation in the generation process, inputting the new generated nodes into the node generator to continuously generate new nodes, continuously connecting the generated new nodes, and circularly connecting the nodes to form a road network;
s1-1-2, widening all lines in a road network according to a preset width w to form road width lines with a certain width, and accordingly obtaining an urban road network model, wherein w is widened according to the corresponding road width in the remote sensing image, preferably, w is 0.5-1.5 times of the average value of all road widths in the remote sensing image, more preferably, 0.5-1 times of motor vehicle roads and non-motor vehicle roads and 1-1.5 times of pedestrian roads. It is understood that a pedestrian road shall include a road within a street in a city, a pedestrian way beside a non-motorized lane, a district or a factory building, etc., which may be traveled by a person or a road vehicle or a work task vehicle (e.g., a wheeled machine, a fire truck, an ambulance, a police vehicle, etc.).
In one embodiment, the widening is done on both sides with the lines forming the road network as the central axis.
Step S1-2 specifically includes:
s1-2-1, based on the urban remote sensing image in the step S1-1, extracting a series of feature maps obtained by different convolutional layers by using a VGG-16 algorithm without an added layer as a CNN main network, wherein the feature maps are 1/2-1/10, preferably 1/8 of the size of an input image;
meanwhile, a characteristic pyramid is constructed by using different layers of a CNN main network through an image pyramid algorithm FPN, and the frames of a plurality of buildings are predicted,
s1-2-2, for each building in the plurality of buildings, obtaining a local feature map F of the building by using a RoIAlign algorithm on the feature maps obtained by the series of different convolutional layers and the corresponding frame of the building;
s1-2-2, forming a polygonal boundary cover M by adopting convolution layer processing on the local characteristic diagram F of each building, and then forming a plurality of predicted vertexes P of the boundary cover M by utilizing convolution layer processing; wherein polygonal bounding box M refers specifically to the vertical projection of the XOY plane describing the building in E;
s1-2-3, selecting the point with the highest probability in P as the starting point
Figure 582878DEST_PATH_IMAGE001
Performing multi-step prediction by using a multi-layer RNN algorithm of convolution long-short term memory ConvLSTM to obtain multiple prediction points
Figure 581927DEST_PATH_IMAGE002
(t is step number) closed building boundary polygons to form an urban building network model;
and S1-3, specifically, fusing the models established in the steps S1-1 and S1-2 according to the relative coordinate positions of the buildings and the roads in the remote sensing image in the urban geographic coordinate system E to form a two-dimensional model of the urban roads and the buildings.
About S2
S2 specifically includes:
s2-1 the intersection point of the longest and the next longest diagonal lines in each polygon boundary in the two-dimensional model of urban road and building represents the index point of the building
Figure 755420DEST_PATH_IMAGE003
And forming a building indexing circle by taking the indexing point as a circle center r as a radius, and forming a road indexing circle at a position where electric equipment (such as a power transformer and the like) or electric appliances (such as a street lamp, a traffic signal lamp and the like) exist in a road in the two-dimensional model, thereby obtaining an urban road with the building and the road indexing circle and the two-dimensional model of the building
Figure 766101DEST_PATH_IMAGE004
(ii) a The two-dimensional model of the urban road and the building with the building and the road index circle can also be subjected to
Figure 999636DEST_PATH_IMAGE004
Semantization recognition of urban roads and buildings with buildings and road index circles is carried out to form corresponding two-dimensional semantic models
Figure 361347DEST_PATH_IMAGE005
。
It should be understood that the two-dimensional model of roads includes the previously described pedestrian roads, not just motor or non-motor roads.
S2-2 presetting two-dimensional model
Figure 72952DEST_PATH_IMAGE004
Z coordinate H of the middle polygon boundary under E forms a three-dimensional model of the city road and the building with the building and the road index circle
Figure 344664DEST_PATH_IMAGE006
Will be
Figure 749101DEST_PATH_IMAGE006
Model data is imported into 3D printing equipment, and the printing city model with building and road indexing circular holes is printed out
Figure 332529DEST_PATH_IMAGE007
Wherein, in the step (A),
Figure 847824DEST_PATH_IMAGE008
or will alternatively
Figure 98676DEST_PATH_IMAGE005
Data import 2D printing equipment prints out
Figure 798648DEST_PATH_IMAGE009
And (4) modeling.
It should be understood that when selecting, the
Figure 603793DEST_PATH_IMAGE009
When the model is used, the semantic model can be printed to form an urban drawing, and the urban drawing is manufactured into a drawing board with a certain height H.
S2-3 is in
Figure 922779DEST_PATH_IMAGE007
Or
Figure 28138DEST_PATH_IMAGE009
A light-emitting device is arranged in each indexing circular hole in the model; the light emitting device is an LED, preferably an OLED, more preferably an AMOLED, wherein r is determined according to the number of circuit lines of electrical equipment or appliances in the building and the size of the light emitting device. For example, when there are two sets of lines for weak electric and strong electric devices in a building, the index circle radius r of the building corresponding to the building should be considered to be able to accommodate at least two of the light emitting devices.
In one embodiment, the light-emitting device will be mounted
Figure 774377DEST_PATH_IMAGE007
And packaging the model to form the display screen.
Wherein said
Figure 473343DEST_PATH_IMAGE007
Models or
Figure 64861DEST_PATH_IMAGE009
The scale of the model and the actual city is 1:10000-1: 100000. In order to identify the electrical equipment or appliances in the urban printing model, the size of the display screen is roughly in the range of tens of centimeters to ten meters, considering that the resolution of the prior art printer (especially the resolution of the 3D printer) and the pixel resolution formed by the light-emitting device are matched, calculated with the urban radius of 15-60 km. The monitoring display of the electric power operation condition can be carried out indoors or outdoors according to the requirement.
It should be understood that the city remote sensing image can be gridded as required, and the steps S2-1-S2-3 are performed for each grid point g
Figure 290306DEST_PATH_IMAGE007
And (5) making a model. When the ratio of the total weight of the iron core is H =0,
Figure 207447DEST_PATH_IMAGE007
the model is converted into a two-dimensional printing model. For ease of understanding, here denominated two-dimensional printing model, while in reality the 3D printing result is three-dimensional in the strict sense with a slight height in the Z-axis of the E-coordinate systemAnd (4) modeling. To for
Figure 987184DEST_PATH_IMAGE009
The model is made into a drawing paper board with a certain height H, and a semantic 3D model object is also formed.
About S3
S3 specifically includes:
the constructed urban power carrier signal transmission system comprises:
s3-1, attaching a PLC circuit to the power line of the road and the building of the city, forming a PLC signal, setting a concentrator in each partition according to the preset partition specification of city power use, receiving the PLC signal and converting the PLC signal into a wireless signal A through a wireless transmission module in the concentrator; wherein, the wireless signal A comprises a corresponding index circle center in a road and/or a building
Figure 647972DEST_PATH_IMAGE003
Coordinate information under E and modulation signal type information in PLC, wherein the modulation signal type comprises at least one of FSK, SSB, PSK, BPSK, QPSK, PAM and 16 QAM.
For example, if the wireless signal A is from an index center
Figure 849628DEST_PATH_IMAGE003
(whereiniCircle center number) is generated when the electric equipment and/or electric appliance in the building B with the coordinates (X, Y, H) under E is used or not used, the wireless signal A comprises coordinate information such as the coordinates (X, Y, H) so as to indicate that the wireless signal A comes from the index circle center
Figure 937670DEST_PATH_IMAGE003
Building with coordinates (X, Y, H). In this way, spatial distribution recognition is achieved by collectively wirelessly transmitting the power operating state by the coordinate signal.
It can be understood that the division of the grid point g of the urban grid may be according to the division rule, and the grid point g represents only one division; of course, the division may be performed without being defined by the above-described division, and in this case, the grid point g includes at least one division. It is thus understood that grid points g are not necessarily rectangular grid points.
S3-2, a setting server is used for receiving a wireless signal A which is sent by the concentrator and contains the coordinate information and the type information of the modulation signal in the PLC;
the establishing of the urban power carrier intelligent monitoring model comprises the following steps:
s3-3 server establishes the corresponding relation between the power parameter contained in the wireless signal A containing the coordinate information and the modulation signal type information in PLC and the light-emitting parameter of the light-emitting device, and makes the light-emitting parameter including at least one of voltage and current pseudo-colorized or grayed, the light-emitting parameter including light-emitting wavelength or gray level WL and light-emitting intensity
Figure 204703DEST_PATH_IMAGE010
；
In one embodiment, S3-3 specifically includes:
s3-3-1 defines seven different visible light wave bands of FSK, SSB, PSK, BPSK, QPSK, PAM and 16QAM, namely the middle wavelength of each wave band of seven spectral wave bands of red, orange, yellow, green, indigo and purple generated by the standard white light under the color separation of a prism
Figure 669182DEST_PATH_IMAGE011
（jSerial number for modulation signal type) as modulation signal type information, each band range being
Figure 603640DEST_PATH_IMAGE012
Are all different; when the gray scale range is defined, the gray scale range is divided into 7 parts by 255 gray scales, the gray scale range is divided into 0 to 34 parts from the minimum gray scale 0, 221-255 parts, and the remaining five equal gray scale ranges are divided, wherein each part is the most middle gray scale range
Figure 597004DEST_PATH_IMAGE011
Corresponding to the type information of the corresponding modulation signal, the gray scale range is
Figure 492279DEST_PATH_IMAGE013
. Wherein the most intermediate gray level is understood to be exactly the intermediate gray level when the gray level is odd; when even, it is optionally one of the two intermediate gray levels. For example, three grayscale ranges of 0,1,2 take 1, and four grayscale ranges of 0,1,2,3 take 1 or 2.
S3-3-2 for each
Figure 760449DEST_PATH_IMAGE003
The standard peak value of the power parameter represented by the voltage or current parameter in one day is
Figure 549414DEST_PATH_IMAGE014
Then the relationship between the power parameter and the luminous intensity is established as
Figure 713679DEST_PATH_IMAGE015
Wherein
Figure 220883DEST_PATH_IMAGE016
Is a constant, the absolute value of which characterizes the luminance parameter,
Figure 151799DEST_PATH_IMAGE017
in order to measure the value of the electrical parameter,
Figure 529691DEST_PATH_IMAGE018
the time of day is predicted value,
Figure 396016DEST_PATH_IMAGE019
the measured value of the time of day is,
Figure 124937DEST_PATH_IMAGE020
is composed of
Figure 469331DEST_PATH_IMAGE014
Over time
Figure 967308DEST_PATH_IMAGE021
A varying piecewise function and for each day, demarcated by the local time at 12 amBinormal distribution function, i.e.
Figure 879901DEST_PATH_IMAGE022
Wherein
Figure 96119DEST_PATH_IMAGE023
Standard deviations and mathematical expectations of the voltage and current parameters, respectively, in the corresponding time segment;
s3-3-3 establishment
Figure 978624DEST_PATH_IMAGE024
In relation to pseudo-colouration or greyscale
Figure 596687DEST_PATH_IMAGE025
And
Figure 804814DEST_PATH_IMAGE026
wherein
Figure 632962DEST_PATH_IMAGE027
The predicted value and the measured value correspond to the light emission wavelength or the gray scale value, respectively.
In one embodiment, the coordinate information represents a division or grid
Figure 319158DEST_PATH_IMAGE028
Wherein the coordinate information of an optional indexing circle is used as the dividing area or the grid point
Figure 791728DEST_PATH_IMAGE028
And at this time, the parameters in step S3-3-2
Figure 170757DEST_PATH_IMAGE014
，
Figure 95987DEST_PATH_IMAGE017
Wherein
Figure 585875DEST_PATH_IMAGE023
As the divisions or grid points
Figure 53896DEST_PATH_IMAGE028
Is measured at all the index circles
Figure 338247DEST_PATH_IMAGE029
The average is an arithmetic average or a weighted average.
It should be understood that, when two or more modulation signals exist in the power line, the wavelength band of the mixed light of the visible light in the corresponding wavelength band is the light-emitting wavelength band.
Figure 16353DEST_PATH_IMAGE030
Rather than being a dust-invariant, it should be statistically derived from data over a fixed period or season over a fixed period of time, short term being related to the season, long term being related to local economic development. It is recommended to renew every 1-3 years according to the latest 3-5 years of data.
S3-4, acquiring power parameters in the urban power line to obtain a pseudo-colorization or graying result, and controlling the corresponding according to coordinate information
Figure 44352DEST_PATH_IMAGE007
Models or
Figure 491514DEST_PATH_IMAGE009
Light-emitting means in the model, or obtaining the same
Figure 336979DEST_PATH_IMAGE031
And according to the coordinate information, will correspond
Figure 236802DEST_PATH_IMAGE031
Conversion to RGB values, and
Figure 68491DEST_PATH_IMAGE016
control the correspondence together
Figure 635739DEST_PATH_IMAGE007
Models or
Figure 402838DEST_PATH_IMAGE009
A light-emitting device in the model, thereby realizing pseudo color or gray scale display of corresponding wave bands and obtaining an urban power distribution detection diagram; the acquisition is carried out within a preset fixed time interval T, the T is between 1s and 1h, a detection image Pic is acquired based on the power distribution detection diagram, the detection image Pic is divided into a training set and a verification set, and the ratio of the training set to the verification set is 5:1-1: 1; are simultaneously obtained based on
Figure 524378DEST_PATH_IMAGE032
Standard chart
Figure 159758DEST_PATH_IMAGE033
. Standard chart
Figure 581512DEST_PATH_IMAGE033
The method refers to a detection image obtained according to power parameters under the normal power operation condition of a city.
In one embodiment, it is also contemplated to provide light-emitting means
Figure 644146DEST_PATH_IMAGE007
Models or
Figure 646125DEST_PATH_IMAGE009
The image of the model (when none of the light-emitting devices was operated) was subtracted from the detected image Pic as a background.
It will be appreciated that the pseudo-colour or grey scale display obtained corresponds one-to-one to the coordinate information, similar to the real time scene pictures captured by the camera, and displayed in the display screen, thus approximating the video signal transmission process, but is different from the progressive or interlaced display of the prior art, since it is clear that this is similar to that of the display screen of the prior art
Figure 819617DEST_PATH_IMAGE007
Models or
Figure 95878DEST_PATH_IMAGE009
The coordinates of the indexing circle corresponding to the wireless signal a in the model are often not regularly arranged according to a matrix form. Due to the need for an accurate representation of the coordinates, an accurate position description of the pseudo-color values or gray values derived from the radio signal a cannot be achieved on the basis of equally sized display pixels.
The power distribution detection map is pseudocolorized or grayed out or based on
Figure 63834DEST_PATH_IMAGE032
And
Figure 425545DEST_PATH_IMAGE034
conversion to RGB value and
Figure 278095DEST_PATH_IMAGE016
controlled to emit light
Figure 408862DEST_PATH_IMAGE007
Models or
Figure 813298DEST_PATH_IMAGE009
Model, and the detected image is of the luminescence
Figure 662305DEST_PATH_IMAGE007
The power distribution detection diagram obtained by image acquisition of the model is
Figure 177600DEST_PATH_IMAGE021
Live video images of a time of day. Particularly, the power distribution detection diagram is shot in real time by adopting an image acquisition device and is acquired.
S3-5, training by using an artificial intelligence model AI and using the collected detection image Pic and/or the power parameter as input ends to obtain a power monitoring result intermediate model, and substituting the intermediate model and the standard graph into a verification set continuously
Figure 287508DEST_PATH_IMAGE033
And stopping training when the difference value is within a preset threshold range to obtain an intelligent monitoring model of the urban power line carrier
Figure 862846DEST_PATH_IMAGE035
Wherein, in the step (A),
Figure 199149DEST_PATH_IMAGE036
representing the input.
The artificial intelligence model AI comprises any one or combination of CNN, GAN, DNN and SVM, the detection image Pic is collected by using an imaging spectrometer or a camera, and the imaging spectrometer or the camera is aimed at the light-emitting device
Figure 518135DEST_PATH_IMAGE007
Models or
Figure 498860DEST_PATH_IMAGE009
Acquiring an image of the model; the power monitoring result comprises a power score
Figure 979520DEST_PATH_IMAGE037
The method is set according to the false color value or gray value error obtained by the false color value or gray value in the detection image corresponding to the coordinate information at the current moment and the standard image, wherein when the error is 0-10% as a normal value, when 10-50% as a suspicious value, more than 50% as an abnormal value, the error is respectively expressed by 0, -1 and 1.
In one embodiment, the CNN is used as an artificial intelligent model, the detection image Pic is used as an input end, the power score is used as an output end, and an urban power carrier intelligent monitoring model is established
Figure 803120DEST_PATH_IMAGE038
；
In one embodiment, power monitoring result acquisition is achieved with a GAN-CNN model, by randomly generating a set of parameters from historical power parameters, and by generating a random image with generator G
Figure 660217DEST_PATH_IMAGE039
Inputting into a discriminator D to discriminate authenticity, substituting the result into the discriminator by a verification set, and obtaining a standard chart
Figure 354504DEST_PATH_IMAGE033
Comparing the obtained results, and continuously fine-tuning the training generator G and the discriminator D to form a GAN model, and inputting the actually measured power parameters
Figure 537223DEST_PATH_IMAGE017
Obtaining a detection image Pic; then, the obtained detection image Pic is used as a CNN input end, and the power score is used as an output end to be trained to obtain an urban power carrier intelligent monitoring model, namely a GAN-CNN model (GC), namely
Figure 707174DEST_PATH_IMAGE040
。
It will be appreciated that in light of the foregoing, the reason is that
Figure 633541DEST_PATH_IMAGE030
The AI model also requires training to more accurately obtain a more accurate model, rather than being a dust-free one. And the selected input data form and the characteristics of the model algorithm determine the applicable artificial intelligence model AI.
About S4
Step S4 specifically includes:
the S4-1 server receives the wireless signal A' of the city power in real time to obtain the power parameter, and obtains the pseudo-colorization or graying result according to the step S3-3, or obtains the corresponding result according to the step S3-3-1-S3-3-3
Figure 713493DEST_PATH_IMAGE031
Obtaining a real-time detection image Pic' according to step S3-4;
s4-2 substituting the electric power parameter and/or the real-time detection image Pic' into the intelligent monitoring model of the urban electric power carrier
Figure 676901DEST_PATH_IMAGE035
Obtaining the space-time distribution result of the power operation state, and making the corresponding light-emitting device normally on, slowly flash, or quickly flash and ^ er when the result is normal, suspicious or abnormalOr for each on the power distribution detection map
Figure 209513DEST_PATH_IMAGE003
All have corresponding power scores
Figure 408413DEST_PATH_IMAGE037
And a blinking state.
The invention also provides a system for realizing the intelligent power carrier monitoring method of the city model, which is characterized by comprising the following steps: a city power carrier signal transmission system, a detection image acquisition device, a monitoring center, a 3D printing device or a 2D printing device, wherein,
the urban power line carrier signal transmission system comprises a PLC circuit, a concentrator and a server;
the server is used for receiving a wireless signal A sent by the urban power carrier signal transmission system, establishing an urban power carrier intelligent monitoring model and communicating with the monitoring center;
the detection image acquisition device is used for acquiring a detection image Pic' of the city model real object provided with the light-emitting device; preferably, the detection image acquisition device is an imaging spectrometer or a camera;
the monitoring center is used for establishing a two-dimensional model of the urban road and the building based on the artificial intelligent network; and controls the 3D printing equipment or the 2D printing equipment to print the city model, and is also used for calling the city power carrier intelligent monitoring model established by the server, and,
the system comprises a city power carrier intelligent monitoring model, a power distribution detection graph, a detection image acquisition device, a power distribution detection graph and a power distribution detection graph, wherein the city power wireless signal A is used for receiving a city real-time power wireless signal sent by a server to form the power distribution detection graph, the detection image acquisition device is controlled to acquire a detection image and acquire the acquired detection image, and a power operation state space-time distribution result of a real-time monitoring city is obtained according to the city power carrier intelligent monitoring model.
The present invention also provides a computer-readable non-transitory storage medium in which a program that can be run by the server and the monitoring center to implement the power carrier wave intelligent monitoring method of the above city model is stored.
Has the advantages that: (1) the city model provided with the light-emitting device is utilized to realize real-time visual monitoring of the power operation state, (2) the data based on the intelligent model is simple to obtain and process, and the spatial-temporal change of the electrical parameters in the power line can be represented in the city model only by converting a remotely received wireless signal describing a power carrier signal into a light-emitting signal, and (3) the intelligent monitoring of the city power operation state can be realized by the system for realizing the intelligent monitoring method of the power carrier of the city model.
Drawings
FIG. 13D is a flow chart of a power carrier intelligent monitoring method for printing a city model,
FIG. 2(a) is a schematic diagram of an RNN recurrent neural network algorithm process extracted from an urban road network and an urban road network generation process,
FIG. 2(b) is a schematic diagram of local road network broadening within the circle of the generated urban road network in FIG. 2(a),
FIG. 3 is a flow chart of the extraction of the multi-layer RNN building boundaries and building index circles based on the convolutional long short term memory ConvLSTM of the CNN backbone network,
FIG. 4 shows a city local gridding and power compartmentalization internal building group two-dimensional model Mod established in a city remote sensing image according to the algorithm of FIG. 32D，
FIG. 5 is a schematic flow chart of power carrier intelligent monitoring of a 3D printed city model implemented by a power carrier intelligent monitoring system based on the 3D printed city model,
the reference numeral, 1, the server, 2, the monitoring center, 3, the imaging spectrometer, 4.3D printing equipment.
Detailed Description
Example 1
Fig. 1 shows a power carrier wave intelligent monitoring method for a 3D printed city model, which includes S1 building a two-dimensional model of an urban road and a building based on an artificial intelligence network; s2, manufacturing a 3D printing city model according to the two-dimensional model of the step S1, and arranging a light-emitting device AMOLED at the position where the power equipment or the electric appliance exists on the road and the building of the model; s3, constructing an urban power carrier signal transmission system and establishing an urban power carrier intelligent monitoring model; s4 real-time monitoring the power operation state of the city according to the model established in the step S3.
S1 specifically includes:
s1-1 the establishment of the urban road network model of the artificial intelligent network specifically comprises the following steps: establishing an urban geographic coordinate system E (shown in figure 4), wherein an XOY plane represents the ground (the X direction is north), defining step length l (selected from 1-5m according to the total length of a road) and a vector direction r as an attribute vector V by utilizing an RNN recurrent neural network algorithm based on an urban remote sensing image, and taking each initial node and K incident road passing directions
Figure 342871DEST_PATH_IMAGE041
The points of (A) are used as input points (K initial attribute vectors correspond to K points and the corresponding initial points), K +1 input points and the attribute vector V are input into an encoder, and a decoder generates a new node; in particular for each direction of each starting point
Figure 601814DEST_PATH_IMAGE042
Corresponds to the coordinates under E
Figure 356144DEST_PATH_IMAGE043
The attribute vector V corresponding to coordinate increments
Figure 483369DEST_PATH_IMAGE044
WhereintThe sequence number representing the current input point (0 for the start point and 1 for the first new input point), the coordinate and attribute vector V are input to the encoder, and the decoder will emit a new node generated under E
Figure 272333DEST_PATH_IMAGE045
Wherein
Figure 967757DEST_PATH_IMAGE046
，
Figure 209382DEST_PATH_IMAGE047
. Exemplary in FIG. 2(a)Giving a road network generation process of 100 node generation cycles in total every 20 node generation cycles;
fig. 2(b) is a schematic diagram of the local road network widening within the circle in fig. 2 (a). And (c) widening the local road network of the fig. 2(b) towards two sides by taking the generated road network line as a central axis according to a preset width w to form a road width line with a certain width, thereby obtaining an urban road network model, wherein the w is 1-1.1 times of the average value of the widths of all roads in the remote sensing image.
Referring to fig. 3, the step S1-2 of establishing the city architectural network model of the artificial intelligence network specifically includes:
s1-2-1, based on the urban remote sensing image in the step S1-1, extracting a series of feature maps obtained by different convolutional layers by using a VGG-16 algorithm without an added layer as a CNN main network, wherein the feature maps are 1/2-1/10, preferably 1/8 of the size of an input image;
meanwhile, a characteristic pyramid is constructed by using different layers of a CNN main network through an image pyramid algorithm FPN, and the frames of a plurality of buildings are predicted,
s1-2-2, for each building in the plurality of buildings, obtaining a local feature map F of the building by using a RoIAlign algorithm on the feature maps obtained by the series of different convolutional layers and the corresponding frame of the building;
s1-2-2, forming a hexagonal boundary cover M by adopting convolutional layer processing on the local feature map F of each building, and forming 6 prediction vertexes P of the boundary cover M by utilizing convolutional layer processing; wherein hexagonal bounding box M refers specifically to the vertical projection of the XOY plane describing the building in E;
s1-2-3, selecting the point with the highest probability in P as the starting point
Figure 750085DEST_PATH_IMAGE001
6-step prediction is carried out by utilizing a multilayer RNN algorithm of convolution long-short term memory ConvLSTM to obtain 6 prediction points
Figure 534501DEST_PATH_IMAGE002
Figure 135247DEST_PATH_IMAGE048
Closed building boundary polygons, forming a city building net model (as shown in figure 4);
according to the power division rule, the vehicle road curve represented by white in fig. 4 is divided into two power divisions, east and west, and is different from the urban grid division (quartering in fig. 4). With the upper right containing two power divisions for the grid point of interest g.
Step S1-3 shown in fig. 5 specifically includes, under the urban geographic coordinate system E, fusing the models established in steps S1-1 and S1-2 according to the relative coordinate positions of the buildings and roads in the remote sensing image, and forming a two-dimensional model of the urban roads (not shown) and the buildings.
Example 2
This example is a continuation of example 1. As shown in fig. 3 and 5, taking city buildings as an example, S2 specifically includes:
s2-1, the intersection point of the longest diagonal line and the next longest diagonal line in each polygon boundary in the two-dimensional model of the city building represents the index point of the building
Figure 864168DEST_PATH_IMAGE003
And a building indexing circle (figure 3) is formed by taking the indexing point as the center r (the size can accommodate more than 10 AMOLED pixel elements) as the radius, so that the urban road with the building indexing circle and a two-dimensional model of the building are obtained
Figure 208562DEST_PATH_IMAGE004
。
S2-2 presetting two-dimensional model
Figure 972119DEST_PATH_IMAGE004
The Z coordinate of the middle polygon boundary under E is H = w, and a three-dimensional model of the city building with a building index circle is formed
Figure 743766DEST_PATH_IMAGE006
Will be
Figure 905906DEST_PATH_IMAGE006
Model data is imported into 3D printing equipment, prints 3D who has building and road index round hole and prints city model
Figure 53991DEST_PATH_IMAGE007
(FIG. 5);
s2-3 is in
Figure 672054DEST_PATH_IMAGE007
And AMOLED is arranged in each indexing circular hole in the model and packaged to form a display screen. The model
Figure 614602DEST_PATH_IMAGE007
The scale of the scale to the real city is 1: 100000.
Example 3
S3 specifically includes:
the constructed urban power carrier signal transmission system comprises:
s3-1, attaching a PLC circuit to the power line of the road and the building of the city, forming a PLC signal, and setting a concentrator (existing in the building of lattice point g in FIG. 5) in each partition according to the preset partition specification of the city power use, and receiving the PLC signal and converting the PLC signal into a wireless signal A through a wireless transmission module in the concentrator; wherein, the wireless signal A comprises a corresponding index circle center in a road building
Figure 318116DEST_PATH_IMAGE003
And coordinate information under E and modulation signal type information in the PLC, wherein the modulation signal types comprise FSK, SSB, PSK, BPSK, QPSK, PAM and 16 QAM.
S3-2, setting a server 1 for receiving a wireless signal A which is sent by the concentrator and contains the coordinate information and the type information of the modulation signal in the PLC;
the establishing of the urban power carrier intelligent monitoring model comprises the following steps:
s3-3, the server 1 establishes the corresponding relation between the power parameter contained in the wireless signal A containing the coordinate information and the modulation signal type information in the PLC and the light-emitting parameter of the light-emitting device; the method specifically comprises the following steps:
s3-3-1 defines seven different visible light wave bands of FSK, SSB, PSK, BPSK, QPSK, PAM and 16QAM as 683nm, 600nm, 578nm, 535nm, 453nm, 430nm and 400nm respectively
Figure 879678DEST_PATH_IMAGE012
All are different (based on standard red-orange-yellow-green-blue spindle violet).
S3-3-2 for each
Figure 617827DEST_PATH_IMAGE003
The standard peak value of the power parameter represented by the current parameter in one day is
Figure 731277DEST_PATH_IMAGE014
Then the relationship between the power parameter and the luminous intensity is established as
Figure 922087DEST_PATH_IMAGE049
，
Figure 411974DEST_PATH_IMAGE017
For the value of the measured current parameter,
Figure 863684DEST_PATH_IMAGE050
to
Figure 148035DEST_PATH_IMAGE021
The time of day is predicted value,
Figure 826141DEST_PATH_IMAGE051
over time
Figure 119719DEST_PATH_IMAGE021
A piecewise function that varies and is a bi-normal distribution function for each day bounded by the local time at 12 am, i.e. a distribution function that is normalized
Figure 301301DEST_PATH_IMAGE052
(ii) a I.e., 0, and 11.5 and 13, respectively, the minimum and maximum amounts of electricity used in one day. S3-3-3 establishment
Figure 756554DEST_PATH_IMAGE024
In relation to pseudo-colorization
Figure 797322DEST_PATH_IMAGE053
And
Figure 629012DEST_PATH_IMAGE054
the predicted value and the measured value correspond to the emission wavelength, respectively.
S3-4 collecting power parameters in urban power line to obtain corresponding parameters
Figure 930680DEST_PATH_IMAGE032
And
Figure 556833DEST_PATH_IMAGE034
and according to the coordinate information, will correspond
Figure 209532DEST_PATH_IMAGE032
And
Figure 969546DEST_PATH_IMAGE034
converted into RGB values, and controlled to correspond to 120
Figure 860142DEST_PATH_IMAGE007
The light-emitting device in the model realizes pseudo color or gray scale display in corresponding wave bands to obtain an urban power distribution detection diagram; the acquisition is carried out within a preset fixed time interval T, the T is 1s, a detection image Pic is acquired based on the power distribution detection diagram, the detection image Pic is divided into a training set and a verification set, and the ratio of the training set to the verification set is 2: 1; are simultaneously obtained based on
Figure 922776DEST_PATH_IMAGE032
Standard chart Picst。
For collecting operation in which none of the light-emitting devices is emitting light
Figure 797191DEST_PATH_IMAGE007
The image of the model being taken as background during said acquisitionIs subtracted from the detected image Pic.
S3-5, using GAN-CNN model to realize power monitoring result acquisition, generating parameter group from historical power parameters by random, and generating random image Pic by generator GrdAnd history detection image PichisInputting the data into a discriminator D to discriminate authenticity, and substituting the result obtained by substituting the verification set into the discriminator with a standard chart PicstComparing the obtained results, and continuously fine-tuning the training generator G and the discriminator D to form a GAN model, and inputting the actually measured power parameters
Figure 970683DEST_PATH_IMAGE017
Obtaining a detection image Pic; then, the obtained detection image Pic is used as a CNN input end, and the power score is used as an output end to be trained to obtain an urban power carrier intelligent monitoring model, namely a GAN-CNN model (GC), namely
Figure 246944DEST_PATH_IMAGE040
。
The detection image Pic is acquired by using an imaging spectrometer, and the imaging spectrometer is aligned with a light-emitting device
Figure 355845DEST_PATH_IMAGE007
Acquiring an image of the model; the power monitoring result comprises a power score
Figure 717556DEST_PATH_IMAGE037
The false color value in the detection graph corresponding to the coordinate information at the current moment and the false color value or gray value error obtained by the standard graph are set, when the error is 0-10% as a normal value, when 10-50% as a suspicious value, more than 50% as an abnormal value, respectively expressed by 0, -1, 1.
Example 4
Step S4 specifically includes:
as shown in FIG. 5, the S4-1 server 1 receives the wireless signal A' of the urban electric power in real time to obtain the current parameter, and obtains the corresponding parameter according to the step S3-3-1-S3-3-3
Figure 429160DEST_PATH_IMAGE032
And
Figure 559927DEST_PATH_IMAGE034
the real-time detection image Pic' is obtained according to step S3-4.
S4-2 substituting the electric power parameter and/or the real-time detection image Pic' into the intelligent monitoring model of the urban electric power carrier
Figure 964364DEST_PATH_IMAGE040
And obtaining a space-time distribution result of the power operation state, and enabling the corresponding light-emitting device to be normally bright, slowly twinkle or rapidly twinkle when the result is normal, suspicious or abnormal. For each on the power distribution detection map
Figure 938005DEST_PATH_IMAGE003
All have corresponding power scores
Figure 187721DEST_PATH_IMAGE037
And a blinking state.
Example 5
As shown in fig. 5, a system for implementing the power carrier intelligent monitoring method of 3D printed city model in the methods of embodiments 1 to 4 includes a city power carrier signal transmission system (existing in the building of fig. 5), a monitoring center 2, an imaging spectrometer 3, a 3D printing device 4, wherein,
the urban power carrier signal transmission system comprises a PLC circuit, a concentrator and a server 1;
the server 1 is used for receiving a wireless signal A sent by an urban power carrier signal transmission system, establishing an urban power carrier intelligent monitoring model and communicating with the monitoring center 2;
the imaging spectrometer 3 is used for acquiring a detection graph Pic' of a 3D printing city model provided with a light-emitting device;
the monitoring center 2 is used for establishing a two-dimensional model of an urban road and a building based on an artificial intelligent network; and controls the 3D printing device 4 to print the 3D city model, and is also used for calling the intelligent monitoring model of the city power carrier established by the server 1, and,
the system is used for receiving real-time electric power wireless signals A in the city sent by the server 1 to form an electric power distribution detection diagram, controlling the imaging spectrometer 3 to collect detection images and obtain the collected detection images, and obtaining a space-time distribution result of the electric power operation state of the real-time monitoring city according to the urban electric power carrier intelligent monitoring model.
Example 6
The difference between this embodiment and embodiments 2-5 is only that the city model is a drawing board with a certain height H, and a semantic 3D model object is formed, that is to say
Figure 438574DEST_PATH_IMAGE009
And (4) modeling.

Claims (12)

1. The intelligent power carrier monitoring method for the urban model is characterized by comprising the following steps of:
s1 building a two-dimensional model of the urban road and the building based on the artificial intelligent network;
s2, making city model real object according to the two-dimensional model of the step S1, and arranging a light-emitting device at the position where the electric power equipment or the electric appliance exists in the road and the building of the model real object;
s3, constructing an urban power carrier signal transmission system and establishing an urban power carrier intelligent monitoring model;
s4, monitoring the power operation state of the city in real time according to the model established in the step S3;
s1 specifically includes:
s1-1, establishing an urban road network model of an artificial intelligent network; s1-1 specifically includes: s1-1-1, establishing an urban geographic coordinate system E, wherein an XOY plane represents the ground; generating a road network based on the city remote sensing image; s1-1-2, widening all lines in the road network according to a preset width w to form road width lines with a certain width, so as to obtain an urban road network model;
s1-2, building a city building network model of the artificial intelligent network;
s1-3, fusing the models established in the steps S1-1 and S1-2 to form a two-dimensional model of the urban road and the building;
s2 specifically includes:
s2-1 the intersection point of the longest and the next longest diagonal lines in each polygon boundary in the two-dimensional model of urban road and building represents the index point of the building
Figure DEST_PATH_IMAGE001
And forming a building indexing circle by taking the indexing point as the circle center r as the radius, and forming a road indexing circle at the position where the power equipment or the electrical appliance exists in the road in the two-dimensional model, thereby obtaining the urban road with the building and the road indexing circle and the two-dimensional model of the building
Figure DEST_PATH_IMAGE002
(ii) a Or the two-dimensional model Mod of the urban road and the building with the building and the road indexing circle2DSemantization recognition of urban roads and buildings with buildings and road indexing circles is carried out to form corresponding two-dimensional semantic model Mod2D’(ii) a S2-2 presetting two-dimensional model Mod2DZ coordinate H of the middle polygon boundary under the urban geographic coordinate system E to form a three-dimensional model Mod of the urban road and the building with the building and the road index circle3DMod will3DModel data is imported into 3D printing apparatus, prints out 3D who has building and road index round hole and prints city model Mod3DCITYWherein H =0-1.5 w; or will Mod2D’Mod is printed out to data import 2D printing apparatus2D’CITY(ii) a S2-3 at Mod3DCITYOr Mod2D'CITYA light-emitting device is arranged in each indexing circular hole in the model; or, at Mod3DCITYOr Mod2D'CITYMod provided with light-emitting devices after the light-emitting devices are arranged in the indexing circular holes in the model3DCITYModels or Mods2D'CITYPackaging the model to form a display screen;
s3 the method for constructing the urban power carrier signal transmission system comprises the following steps:
s3-1 attaching PLC circuit to power line of city road and building to form PLC signal, and using predetermined division rule according to city powerThe wireless transmission module is used for converting the PLC signals into wireless signals A; wherein, the wireless signal A comprises a corresponding index circle center in a road and/or a building
Figure 541851DEST_PATH_IMAGE001
Coordinate information under E and modulation signal type information in PLC, wherein the modulation signal type comprises at least one of FSK, SSB, PSK, BPSK, QPSK, PAM and 16 QAM; s3-2, a setting server is used for receiving a wireless signal A which is sent by the concentrator and contains the coordinate information and the type information of the modulation signal in the PLC;
the establishing of the urban power carrier intelligent monitoring model comprises the following steps:
s3-3 server establishes correspondence between power parameters and lighting parameters of lighting device in wireless signal A containing coordinate information and modulation signal type information in PLC, and makes lighting parameters including at least one of voltage and current pseudo-color or gray scale, lighting parameters including lighting wavelength or gray scale WL, lighting intensity
Figure DEST_PATH_IMAGE003
；
S3-4, collecting power parameters in the city power line to obtain pseudo-colorization or graying results, and controlling corresponding Mod according to coordinate information3DCITYModels or Mods2D'CITYThe light-emitting device in the model realizes pseudo color or gray scale display of corresponding wave bands to obtain an urban power distribution detection diagram; the acquisition is carried out within a preset fixed time interval T, the T is between 1s and 1h, a detection image Pic is acquired based on the power distribution detection diagram, the detection image Pic is divided into a training set and a verification set, the ratio of the training set to the verification set is 5:1-1:1, and a standard diagram Pic is obtained at the same timest(ii) a S3-5, training by using an artificial intelligence model AI and using the collected detection image Pic and/or power parameters as input ends to obtain a power monitoring result intermediate model, and substituting the intermediate model and the standard graph Pic with a verification set continuouslystThe obtained results are poorStopping training when the difference value is within the range of the preset threshold value, and obtaining the urban power line carrier intelligent monitoring model
Figure DEST_PATH_IMAGE004
Wherein, in the step (A),
Figure DEST_PATH_IMAGE005
representing the input.
2. The method of claim 1, wherein,
s1-1-1 specifically includes: based on the urban remote sensing image, utilizing an RNN recurrent neural network algorithm, generating road continuous nodes through a node generator comprising an encoder and a decoder, connecting the two nodes before and after generation in the generation process, inputting the new generated nodes into the node generator to continuously generate new nodes, continuously connecting the generated new nodes, and circularly connecting the nodes to form a road network;
in S1-1-2, w is widened according to the corresponding road width in the remote sensing image, wherein w is 0.5-1.5 times of the average value of all road widths in the remote sensing image, or 0.5-1 times of motor vehicle roads and non-motor vehicle roads and 1-1.5 times of pedestrian roads.
3. The method according to claim 2, wherein step S1-2 specifically comprises:
s1-2-1, based on the urban remote sensing image in the step S1-1, extracting a series of feature maps obtained by different convolutional layers by using a VGG-16 algorithm without an added layer as a CNN main network, wherein the feature maps are 1/2-1/10 of the size of an input image;
meanwhile, a feature pyramid is constructed by using different layers of a CNN backbone network through an image pyramid algorithm FPN, and the borders of a plurality of buildings are predicted, and S1-2-2 obtains a local feature map F of the building by using a RoIAlign algorithm for the feature map obtained by the series of different convolutional layers and the corresponding border of the building for each building in the plurality of buildings;
s1-2-2, forming a polygonal boundary cover M by adopting convolution layer processing on the local characteristic diagram F of each building, and then forming a plurality of predicted vertexes P of the boundary cover M by utilizing convolution layer processing; wherein polygonal bounding box M refers specifically to the vertical projection of the XOY plane describing the building in E;
s1-2-3, selecting the point with the highest probability in P as the starting point
Figure DEST_PATH_IMAGE006
Performing multi-step prediction by using a multi-layer RNN algorithm of convolution long-short term memory ConvLSTM to obtain multiple prediction points
Figure DEST_PATH_IMAGE007
Forming a closed building boundary polygon to form an urban building network model, wherein t is a step number,
Figure DEST_PATH_IMAGE008
。
4. the method of claim 1, wherein step S1-3 comprises, in particular, fusing the models established in steps S1-1 and S1-2 to form a two-dimensional model of the urban road and the buildings, according to the relative coordinate positions of the buildings and the roads in the remote sensing image, in the urban geographic coordinate system E.
5. The method of claim 1, wherein the light emitting device is an LED, an OLED, or an AMOLED, and wherein the Mod is3DCITYModels or Mods2D'CITYThe scale of the model and the actual city is 1:10000-1: 100000.
6. The method of claim 1,
s3-3 specifically comprises:
s3-3-1 defines seven different visible light wave bands of FSK, SSB, PSK, BPSK, QPSK, PAM and 16QAM, namely the middle wavelength of each wave band of seven spectral wave bands of red, orange, yellow, green, indigo and purple generated by the standard white light under the color separation of a prism
Figure DEST_PATH_IMAGE009
As modulation signal type information, whereinjFor modulating the signal type number, each band range is
Figure DEST_PATH_IMAGE010
；
When the gray scale range is defined, the gray scale range is divided into 7 parts by 255 gray scales, the gray scale range is divided into 0 to 34 parts from the minimum gray scale 0, 221-255 parts, and the remaining five equal gray scale ranges are divided, wherein each part is the most middle gray scale range
Figure 803199DEST_PATH_IMAGE009
Corresponding to the type information of the corresponding modulation signal, the gray scale range is
Figure DEST_PATH_IMAGE011
；
S3-3-2 for each
Figure 395986DEST_PATH_IMAGE001
The standard peak value of the power parameter represented by the voltage or current parameter in one day is
Figure DEST_PATH_IMAGE012
Then the relationship between the power parameter and the luminous intensity is established as
Figure DEST_PATH_IMAGE013
Wherein the number of the first group is a constant number,
Figure DEST_PATH_IMAGE014
in order to measure the value of the electrical parameter,
Figure DEST_PATH_IMAGE015
the time of day is predicted value,
Figure DEST_PATH_IMAGE016
the measured value of the time of day is,
Figure DEST_PATH_IMAGE017
is composed of
Figure 197720DEST_PATH_IMAGE012
Over time
Figure DEST_PATH_IMAGE018
A piecewise function that varies and is a bi-normal distribution function for each day bounded by the local time at 12 am, i.e. a distribution function that is normalized
Figure DEST_PATH_IMAGE019
Wherein
Figure DEST_PATH_IMAGE020
Standard deviations and mathematical expectations of the voltage and current parameters, respectively, in the corresponding time segment; s3-3-3 establishment
Figure DEST_PATH_IMAGE021
In relation to pseudo-colouration or greyscale
Figure DEST_PATH_IMAGE022
And
Figure DEST_PATH_IMAGE023
wherein R is
Figure 559562DEST_PATH_IMAGE010
Or
Figure 850866DEST_PATH_IMAGE011
，
Figure DEST_PATH_IMAGE024
And
Figure DEST_PATH_IMAGE025
corresponding to the light-emitting wavelength or gray value for the predicted value and the measured value, respectively, based on
Figure 524424DEST_PATH_IMAGE024
Obtaining a standard chart Picst(ii) a The S3-4 comprises: acquiring power parameters in urban power lines to obtain corresponding
Figure DEST_PATH_IMAGE026
And according to the coordinate information, will correspond
Figure 536374DEST_PATH_IMAGE026
Conversion to RGB values, and
Figure DEST_PATH_IMAGE027
control corresponding Mod3DCITYModels or Mods2D'CITYThe light-emitting device in the model realizes pseudo color or gray scale display in corresponding wave bands to obtain an urban power distribution detection diagram; the acquisition is carried out within a preset fixed time interval T, the T is between 1s and 1h, and the acquired detection image Pic is divided into a training set and a verification set, wherein the ratio of the training set to the verification set is 5:1-1: 1; are simultaneously obtained based on
Figure 267569DEST_PATH_IMAGE024
Standard chart PicstCollecting Mod when each light-emitting device does not emit light3DCITYModels or Mods2D'CITYThe image of the model is taken as background and subtracted in said acquired detection image Pic.
7. The method of claim 6, wherein the coordinate information represents a division or a grid point
Figure DEST_PATH_IMAGE028
Wherein the coordinate information of an optional indexing circle is used as the dividing area or the grid point
Figure 464195DEST_PATH_IMAGE028
And at this time, the parameters in step S3-3-2
Figure 562733DEST_PATH_IMAGE012
，
Figure 768586DEST_PATH_IMAGE014
Wherein
Figure 885446DEST_PATH_IMAGE020
Is the division or grid point giIs measured at all the index circles
Figure DEST_PATH_IMAGE029
The average is an arithmetic average or a weighted average.
8. The method as claimed in claim 1, wherein the artificial intelligence model AI in S3-5 includes any one or a combination of CNN, GAN, DNN, SVM, and the detection image Pic acquisition uses an imaging spectrometer or camera directed at Mod where a light emitting device is disposed3DCITYModels or Mods2D'CITYAcquiring an image of the model; the power monitoring result comprises a power score
Figure DEST_PATH_IMAGE030
The method is set according to the false color value or gray value error obtained by the false color value or gray value in the detection image corresponding to the coordinate information at the current moment and the standard image, wherein when the error is 0-10% as a normal value, when 10-50% as a suspicious value, more than 50% as an abnormal value, the error is respectively expressed by 0, -1 and 1.
9. The method according to claim 1 or 8, wherein step S4 specifically comprises:
the method comprises the steps that S4-1, a server receives electric power wireless signals A 'in a city in real time to obtain electric power parameters, pseudo-colorization or graying results are obtained according to the step S3-3, and a real-time detection image Pic' is obtained according to the step S3-4; s4-2 substituting the electric power parameter and/or the real-time detection image Pic' into the intelligent monitoring model of the urban electric power carrier
Figure 597182DEST_PATH_IMAGE004
Obtaining the space-time distribution result of the power operation state, and enabling the corresponding light-emitting device to be normally bright, slowly twinkle or rapidly twinkle when the result is normal, suspicious or abnormal, and/or enabling each light-emitting device to be on the power distribution detection graph
Figure DEST_PATH_IMAGE031
There is a corresponding power score, and a flashing state.
10. The method according to claim 6 or 7, wherein step S4 specifically comprises:
the S4-1 server receives the wireless signal A' of the power in the city in real time to obtain the power parameter, or obtains the corresponding power parameter according to the step S3-3-1-S3-3-3
Figure 901124DEST_PATH_IMAGE026
Obtaining a real-time detection image Pic' according to step S3-4; s4-2 substituting the electric power parameter and/or the real-time detection image Pic' into the intelligent monitoring model of the urban electric power carrier
Figure 520455DEST_PATH_IMAGE004
Obtaining the space-time distribution result of the power operation state, and enabling the corresponding light-emitting device to be normally bright, slowly twinkle or rapidly twinkle when the result is normal, suspicious or abnormal, and/or enabling each light-emitting device to be on the power distribution detection graph
Figure 898347DEST_PATH_IMAGE031
There is a corresponding power score, S, and a flashing state.
11. A system for implementing the intelligent power carrier monitoring method of the city model according to any one of claims 1 to 10, comprising: a city power carrier signal transmission system, a detection image acquisition device, a monitoring center, a 3D printing device or a 2D printing device, wherein,
the urban power line carrier signal transmission system comprises a PLC circuit, a concentrator and a server;
the server is used for receiving a wireless signal A sent by the urban power carrier signal transmission system, establishing an urban power carrier intelligent monitoring model and communicating with the monitoring center;
the detection image acquisition device is used for acquiring a detection image Pic' of the city model real object provided with the light-emitting device; preferably, the detection image acquisition device is an imaging spectrometer or a camera;
the monitoring center is used for establishing a two-dimensional model of the urban road and the building based on the artificial intelligent network; and controls the 3D printing equipment or the 2D printing equipment to print the city model, and is also used for calling the city power carrier intelligent monitoring model established by the server, and,
the system comprises a city power carrier intelligent monitoring model, a power distribution detection graph, a detection image acquisition device, a power distribution detection graph and a power distribution detection graph, wherein the city power wireless signal A is used for receiving a city real-time power wireless signal sent by a server to form the power distribution detection graph, the detection image acquisition device is controlled to acquire a detection image and acquire the acquired detection image, and a power operation state space-time distribution result of a real-time monitoring city is obtained according to the city power carrier intelligent monitoring model.
12. A computer-readable non-transitory storage medium having stored therein a program executable by a server and a monitoring center to implement the power carrier intelligent monitoring method of the city model according to any one of claims 1 to 10.
CN202110515830.8A 2021-05-12 2021-05-12 Power line carrier intelligent monitoring method and system of city information model Active CN113162240B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110515830.8A CN113162240B (en) 2021-05-12 2021-05-12 Power line carrier intelligent monitoring method and system of city information model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110515830.8A CN113162240B (en) 2021-05-12 2021-05-12 Power line carrier intelligent monitoring method and system of city information model

Publications (2)

Publication Number Publication Date
CN113162240A CN113162240A (en) 2021-07-23
CN113162240B true CN113162240B (en) 2022-04-12

Family

ID=76874663

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110515830.8A Active CN113162240B (en) 2021-05-12 2021-05-12 Power line carrier intelligent monitoring method and system of city information model

Country Status (1)

Country Link
CN (1) CN113162240B (en)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113522196B (en) * 2021-08-04 2022-04-26 南京元初科技有限公司 Intelligent monitoring system and intelligent monitoring method for preparation of block copolymer of aromatic hydrocarbon, conjugated diene and epoxide
CN113794948A (en) * 2021-08-10 2021-12-14 邹平市供电有限公司 Method and system for collecting power consumption in remote area
CN113963095B (en) * 2021-09-01 2022-07-05 泰瑞数创科技(北京)有限公司 Urban three-dimensional map video stream encryption method and system based on artificial intelligence
CN113920266B (en) * 2021-11-03 2022-10-21 泰瑞数创科技(北京)股份有限公司 Artificial intelligence generation method and system for semantic information of city information model
CN114326492B (en) * 2021-12-20 2023-09-01 中国科学院上海高等研究院 Digital twin virtual-real linkage system of process industrial equipment
CN114780666B (en) * 2022-06-23 2022-09-27 四川见山科技有限责任公司 Road label optimization method and system in digital twin city
CN116337158B (en) * 2023-05-24 2023-08-01 中国建筑科学研究院有限公司 Building health monitoring device and method
CN116865787B (en) * 2023-07-06 2024-02-09 北京煜邦电力技术股份有限公司 Method for intelligently selecting transmission opportunity of power carrier signal

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104899922A (en) * 2015-06-08 2015-09-09 安徽中兴继远信息技术股份有限公司 Three-dimensional holographic generation method for intelligent power grid visualization application
WO2016147045A1 (en) * 2015-03-16 2016-09-22 Greenstar Research And Development India Private Limited. Virtual presence device
CN108073996A (en) * 2018-01-29 2018-05-25 四川万益能源科技有限公司 Urban energy panorama interactive mode big data platform management system and method
CN110083119A (en) * 2019-05-08 2019-08-02 国网江苏省电力有限公司信息通信分公司 A kind of the visual power system machine room monitoring system and method twin based on number
CN110866161A (en) * 2019-12-26 2020-03-06 中冶沈勘工程技术有限公司 Urban underground space three-dimensional information visualization system and method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016147045A1 (en) * 2015-03-16 2016-09-22 Greenstar Research And Development India Private Limited. Virtual presence device
CN104899922A (en) * 2015-06-08 2015-09-09 安徽中兴继远信息技术股份有限公司 Three-dimensional holographic generation method for intelligent power grid visualization application
CN108073996A (en) * 2018-01-29 2018-05-25 四川万益能源科技有限公司 Urban energy panorama interactive mode big data platform management system and method
CN110083119A (en) * 2019-05-08 2019-08-02 国网江苏省电力有限公司信息通信分公司 A kind of the visual power system machine room monitoring system and method twin based on number
CN110866161A (en) * 2019-12-26 2020-03-06 中冶沈勘工程技术有限公司 Urban underground space three-dimensional information visualization system and method

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
城市轨道交通三维城市景观快速建模方法研究;吕希奎 等;《城市轨道交通研究》;20121231;全文 *
基于公共信息模型对象聚合的高压配电网功能单元信息模型;金勇 等;《电力***自动化》;20160510;第40卷(第9期);全文 *

Also Published As

Publication number Publication date
CN113162240A (en) 2021-07-23

Similar Documents

Publication Publication Date Title
CN113162240B (en) Power line carrier intelligent monitoring method and system of city information model
US11869192B2 (en) System and method for vegetation modeling using satellite imagery and/or aerial imagery
CN108900576A (en) A kind of intelligence community application service system based on 5G
CN107450540A (en) Indoor mobile robot navigation system and method based on infrared road sign
CN105516654A (en) Scene-structure-analysis-based urban monitoring video fusion method
Gao et al. AQ360: UAV-aided air quality monitoring by 360-degree aerial panoramic images in urban areas
Chen et al. Valid: A comprehensive virtual aerial image dataset
CN106682592A (en) Automatic image recognition system and method based on neural network method
CN107004302A (en) Model building device, threedimensional model generating means, modeling method and program
CN114240868A (en) Unmanned aerial vehicle-based inspection analysis system and method
CN113240249A (en) Urban engineering quality intelligent evaluation method and system based on unmanned aerial vehicle augmented reality
Gao et al. Large-scale synthetic urban dataset for aerial scene understanding
CN104517126A (en) Air quality assessment method based on image analysis
CN113313006B (en) Urban illegal building supervision method, system and storage medium based on unmanned aerial vehicle
US20210117583A1 (en) Systems for the classification of interior structure areas based on exterior images
KR20110134479A (en) Geospatial modeling system for colorizing images and related methods
CN115880466A (en) Urban engineering surveying and mapping method and system based on unmanned aerial vehicle remote sensing
CN111612779A (en) Water area algae small target detection method and system based on aerial image and CIM
CN110521286A (en) Image analysis technology
US11544832B2 (en) Deep-learned generation of accurate typical simulator content via multiple geo-specific data channels
CN116762090A (en) Method, system, and non-transitory computer-readable recording medium for supporting experience sharing between users
CN108195358B (en) Power transmission line data acquisition method based on unmanned aerial vehicle inspection simulation training system
CN115373416A (en) Intelligent inspection method for railway power through line
CN114782903A (en) ESN-based highway river-crossing grand bridge group fog recognition and early warning method
CN110658844B (en) Ultra-high voltage direct current line channel unmanned aerial vehicle monitoring method and 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
GR01 Patent grant
GR01 Patent grant
CP03 Change of name, title or address

Address after: 22 / F, building 683, zone 2, No. 5, Zhongguancun South Street, Haidian District, Beijing 100086

Patentee after: Terry digital technology (Beijing) Co.,Ltd.

Address before: 100190 22 / F, building 683, zone 2, 5 Zhongguancun South Street, Haidian District, Beijing

Patentee before: Terra-IT Technology (Beijing) Co.,Ltd.

CP03 Change of name, title or address