CN113221302B - Dynamic gridding processing method and system for smart city detection data - Google Patents
Dynamic gridding processing method and system for smart city detection data Download PDFInfo
- Publication number
- CN113221302B CN113221302B CN202110579735.4A CN202110579735A CN113221302B CN 113221302 B CN113221302 B CN 113221302B CN 202110579735 A CN202110579735 A CN 202110579735A CN 113221302 B CN113221302 B CN 113221302B
- Authority
- CN
- China
- Prior art keywords
- grid
- detection
- detection data
- smart city
- data
- 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
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
-
- 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
-
- 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
- G06N3/08—Learning methods
-
- 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
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
- Y02A30/60—Planning or developing urban green infrastructure
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Arrangements For Transmission Of Measured Signals (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a dynamic gridding processing method and a dynamic gridding processing system for smart city detection data, wherein the method comprises the following steps: initializing processing parameters; gridding a pipe network structure based on the grid scale; acquiring grid detection data, and calculating a detection value based on a feature detection line; judging whether the detection value is normal, if so, returning to the previous step to continue acquisition and calculation. The invention can combine the utilization of big data with urban pipe network data to realize informatization, industrialization and urban deep fusion, thereby realizing the refinement and dynamic utilization and management of fine big data, improving urban management effect and improving the living quality of citizens.
Description
[ field of technology ]
The invention belongs to the technical field of energy automation, and particularly relates to a dynamic gridding processing method and system for smart city detection data.
[ background Art ]
The energy engineering automation is a more traditional subject, but with the development of big data artificial intelligence technology, how to combine the traditional subject with urban explosion and improvement of information technology capability and combine the urban treatment is a current research hot spot; for urban pipe networks, how to combine energy engineering automation with smart cities is a current global research hotspot.
Smart cities are technologies that use information and communication technology to sense, analyze, integrate, and integrate, various key information of the urban operation core system, thereby intelligently responding to various demands including civilian, environmental protection, public safety, urban services, industrial and commercial activities. The essence is that advanced information technology is utilized to realize intelligent management and operation of cities, thereby creating better life for people in cities and promoting harmony and sustainable growth of cities. The smart city is a city informatization advanced form which fully uses the new generation information technology in each industry of the city based on the next generation innovation of the knowledge society, realizes the deep integration of informatization, industrialization and towns, is beneficial to relieving the large city diseases, improving the township quality, realizing the refinement and dynamic management, improving the city management effect and improving the living quality of citizens.
On the other hand, with the development of a smart city system constructed by each city for improving management efficiency, each region and each management department establish respective data management and service platforms, and can manage and use public data information in the management authority; under the large background, how to apply the management of urban pipe network information to the management of intelligent cities and how to apply the function of data is a problem to be solved. The invention combines the grid scale and sensitivity improvement through the characteristic detection line, thereby being capable of utilizing big data to perform non-customized processing on the detection data of the smart city; the network detection data of the smart city are observed through different grid scales, so that possible situations can be detected and diagnosed, and the required data can be obtained. The invention combines the grid scale and sensitivity improvement through the characteristic detection line, thereby being capable of utilizing big data to perform non-customized processing on the detection data of the smart city; the sensitivity of the detection data is improved or reduced by dynamically adjusting the grid scale, and the calculated amount is reduced or increased simultaneously, so that a relative balance is achieved between the two, and the utilization efficiency of the detection data is improved; the feature detection lines growing in the two-dimensional direction can find feature detection lines aiming at different types of detection data and corresponding pipe network areas, and the sensitivity is ensured while the calculation is performed based on the feature detection lines; through binarization input and a model building mode based on an input structure, the calculation amount of the neural network model is greatly reduced while grid structure information is not lost, and a relatively accurate judgment result is obtained.
[ invention ]
In order to solve the above problems in the prior art, the present invention provides a smart city detection data dynamic gridding processing method, which includes the following steps:
step S1: initializing processing parameters;
step S2: gridding a pipe network structure based on the grid scale;
step S3: acquiring grid detection data, and calculating a detection value based on a feature detection line;
step S4: judging whether the detection value is normal or not, if so, returning to the step S3 to continue to acquire and calculate; otherwise, enter step S5;
step S5: increasing the grid scale, when the grid scale reaches the scale threshold, entering a step S6, otherwise, entering a step S2;
step S6: and calculating the grid center of each grid, calculating the deviation parameter of the grid center, and inputting the deviation parameter into the neural network model to obtain a detection result.
Further, the step S1 specifically includes: initializing a grid scale.
Further, the pipe network is a gas pipe network.
Further, the grid scale is the number of pipe network nodes or the size of the pipe network coverage area.
Further, the feature detection line includes one or more grids and their precedence relationships.
Further, the feature detection lines include detection data types, grid positions of the detection data, and/or calculation manners of the detection lines.
Further, after the pipe network structure is meshed, feature detection lines corresponding to different mesh scales are calculated.
A smart city detection data dynamic gridding processing device, comprising:
a storage unit configured to store an application program; and
the processing unit is electrically coupled to the input unit and the storage unit and is configured to execute the smart city detection data dynamic meshing processing method.
A smart city detection data dynamic gridding processing system, comprising: a server and a plurality of clients;
the server is used for executing a dynamic gridding processing method of the smart city detection data;
the clients are used for obtaining processing results.
A storage medium for dynamic meshing of smart city detection data, the storage medium storing instructions for performing a method of dynamic meshing of smart city detection data.
The beneficial effects of the invention include: the grid scale and sensitivity improvement are combined through the feature detection line, so that the detection data of the smart city can be subjected to non-customized processing by utilizing the big data; the sensitivity of the detection data is improved or reduced by dynamically adjusting the grid scale, and the calculated amount is reduced or increased simultaneously, so that a relative balance is achieved between the two, and the utilization efficiency of the detection data is improved; the feature detection lines growing in the two-dimensional direction can find feature detection lines aiming at different types of detection data and corresponding pipe network areas, and the sensitivity is ensured while the calculation is performed based on the feature detection lines; through binarization input and a model building mode based on an input structure, the calculation amount of the neural network model is greatly reduced while grid structure information is not lost, and a relatively accurate judgment result is obtained.
[ description of the drawings ]
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate and together with the description serve to explain the invention, if necessary:
fig. 1 is a schematic diagram of a smart city detection data dynamic meshing processing method according to the present invention.
[ detailed description ] of the invention
The present invention will now be described in detail with reference to the drawings and the specific embodiments thereof, wherein the exemplary embodiments and the description are for the purpose of illustrating the invention only and are not to be construed as limiting the invention.
The smart city construction involves uniformly integrating and fusing information means such as current Internet architecture, equipment sensing technology, batch information processing and the like by utilizing advanced technologies such as cloud computing, big data decision analysis, internet of things and the like at present, applying perceptibility, internetworking and intellectualization to each layer of a park in a manner of intelligent response such as monitoring, analysis and integration, and fusing scattered, independent and differential and interactive pipe network data in different pipe network area ranges to form a pipe network data set; however, how to find useful information from pipe network data and improve data sensitivity so that the data can be spoken is a matter of consuming software and hardware resources. In the case where important data or data characteristics have been located, identification algorithms may be written in advance to find specific problems with specific data, using features of the previously defined sensitive data. And when the problem changes, the original program needs to be rewritten again, and the upgrade is only feasible to be deployed again. In the utilization of urban pipe network data, special data are needed to be positioned first so as to further play a role for the special data.
The smart city detection data dynamic meshing processing method comprises the following steps:
step S1: initializing processing parameters; specific: initializing a grid scale; grid scale initialized based on parameters such as complexity of a pipe network, size of a pipe network structure and the like;
preferably: initially setting the grid scale to a larger value;
the processing parameters further include: a scale threshold (upper limit value of mesh scale adjustment), a period threshold (period judgment index that the detected data is stable under the current mesh scale), and the like;
step S2: gridding a pipe network structure based on the grid scale; specific: dividing a pipe network structure based on grid scale, dividing the pipe network structure into one or more grids, wherein each grid meets the current grid scale; the larger the grid scale is, the larger each grid is, and the more pipe network nodes or the larger areas are covered in the grids; the greater the amount of detected data that is involved to be processed; for example: dividing the pipe network structure according to the grid scale and the coverage area so that the size of each grid is 100m 2 The method comprises the steps of carrying out a first treatment on the surface of the Dividing according to detection nodes so that 500 detection nodes are contained in each grid;
preferably: dividing grids according to continuity of the detection nodes; the detection nodes contained in the divided grid areas are directly communicated;
preferably: the pipe network is a gas pipe network;
preferably; the grid scale is the number of pipe network nodes or the size of a pipe network coverage area;
alternatively, the following is used: the pipe network structure is an abstract pipe network logic structure; at this time, selecting a corresponding pipe network structure according to the grid scale; the pipe network is abstracted through the pipe network structure, so that the data quantity to be processed can be further reduced;
the feature detection line comprises one or more grids and precedence relations thereof; further: the characteristic detection line comprises a detection data type, a grid position of the detection data and/or a calculation mode of the detection line; obviously, the feature detection lines are the same or different for different grid dimensions;
preferably: after the grid pipe network structure is meshed, calculating feature detection lines corresponding to different grid scales; the feature detection line is acquired based on historical detection data;
preferably: acquiring grid detection data based on the feature detection lines; the feature detection lines correspond to the current grid scale, that is, the feature detection lines which can best embody the data features under the current scale can be found through the change of the feature detection lines under different grid scales; that is, the improvement of the grid scale and the sensitivity is combined through the feature detection line, so that the detection data of the smart city can be subjected to non-customized processing by utilizing the big data;
before gridding processing, acquiring a characteristic detection line based on historical detection data; of course, the feature detection line may be acquired before entering step S2; the method for acquiring the characteristic detection line based on the historical detection data specifically comprises the following steps:
step SA1: acquiring current grid N i,j And the historical detection data in the 4 neighborhood grids form a detection data set; wherein: n (N) i,j Is a grid at a two-dimensional location (i, j); where (i, j) is a two-dimensional representation of the grid location, not necessarily a direct correspondence to the physical location, but a two-dimensional representation based on the adjacent relationship of the gridDimension number position; when the grids are obtained in a one-dimensional segmentation mode, the grids with two-dimensional identifications can be obtained through two-dimensional of one-dimensional numbers; on the first entry into this step SA1, the first grid N 1,1 As the current grid, and the first grid N 1,1 As a detection line starting point;
alternatively, the following is used: randomly selecting a grid as a detection line starting point;
alternatively, the following is used: acquiring current grid N i,j And the historical detection data in the 8 neighborhood grids form a detection data set;
step SA2: acquiring a characteristic value Ci based on the detection data set; specific: the characteristic value Ci comprises a change value Vi, an extreme value Mi and an average value Ai; obtaining a difference value between the maximum value and the minimum value as a variation value Vi, obtaining the maximum value or the minimum value as an extremum Mi, and obtaining an average value as an average value Ai; the characteristic values are of various types, a plurality of characteristic detection lines can be correspondingly generated, and the calculation modes of the various characteristic detection lines are correspondingly adopted; the calculation mode is closely related to the type of the detection data aimed at by the calculation mode;
step SA3: calculating grid gradient change value DA of characteristic value in different directions i The method comprises the steps of carrying out a first treatment on the surface of the Selecting a grid in the gradient change direction of a specific grid as a Next grid Next_N i,j The method comprises the steps of carrying out a first treatment on the surface of the The change direction is four directions instead of downward growth, so that the detection feature detection lines grow in four directions of the two-dimensional plane along with the change of the grid gradient value;
forward grid gradient change value
Backward grid gradient change value
Left grid gradient change value
Gradient change value of right grid
Preferably: the specific grid gradient change direction refers to the direction in which the grid gradient changes most rapidly; when the grid in the direction of the fastest gradient change of the grid is on the characteristic detection line, taking the direction of the next fastest gradient change as the gradient change direction of the specific grid, and so on until a grid is found; of course, if there is no next grid that can be selected, this may mean termination of feature detection line growth;
alternatively, the following is used: the specific grid gradient change direction refers to the direction in which the grid gradient changes slowest; when the grid in the direction of the slowest gradient change of the grid is on the characteristic detection line, taking the direction of the slowest gradient change as the gradient change direction of the specific grid, and analogizing;
step SA4: next mesh next_n i,j As the current grid N i,j The next node on the feature detection line; step SA5: judging whether the length of the detection line meets the condition, if so, entering a step SA6, otherwise, finishing the detection line determination; the condition is that the minimum length of the detection line is determined to beWherein m, n are each the maximum value of i, j;
preferably: the condition can also be a termination condition that the feature detection line cannot continue growing;
step SA6: next mesh next_n i,j As the current grid N i,j And go to step SA1;
preferably: performing the above processing once for each detection data type to obtain feature detection lines for different detection data types;
step S3: acquiring grid detection data, and calculating a detection value based on a feature detection line; specific: acquiring corresponding types of detection data from the involved grid positions based on the feature detection lines; calculating detection data of corresponding types based on a calculation mode of the feature detection line to obtain a detection value;
the sensitivity of different types of detection data to different feature detection lines is different, which is related to the properties of the data types themselves, for example: fluctuation range of data, etc.; the detection line with the strongest sensitivity can be directly selected, the corresponding relation can be stored, and the detection line to be adopted can be searched through the corresponding relation; the detection line has an inherent calculation mode according to different formation modes, and detection can be carried out by adopting detection lines of similar calculation types so as to reduce the calculation of the detection lines; for example: the calculation mode of the change detection line is to acquire a difference value between a maximum value and a minimum value as a characteristic value;
preferably: repeating the steps S3-S4 for different detection data types to obtain different corresponding detection values, and comparing the detection values with different characteristic detection lines to judge whether the detection values are normal or not; when all types of detection data are displayed normally, cycling is performed between the steps S3-S4, and when one type of detection data is displayed abnormally, the step S5 is performed to adjust the scale, and the cycling is broken;
step S4: judging whether the detection value is normal or not, if so, returning to the step S3 to continue to acquire and calculate; otherwise, enter step S5;
whether the detection value is normal or not is judged specifically as follows: the detection value is compared with a standard value on a characteristic detection line calculated from historical data of a grid on the detection line to obtain a deviation value, for example: historical average data; the detection value is calculated according to the detection data obtained in the previous detection and calculation period; the historical data is deleted and filtered, and the detection data corresponding to the abnormal grid is deleted and only the historical data of the normal grid is reserved; when the step is carried out, the sensitivity is adjusted by matching with the scale condition, so that the judgment means such as complex artificial intelligence and the like are not required to be introduced, and only a simple calculation means is required; a fitting means can be adopted to obtain a standard value; in the two means, the calculated amount is exponentially reduced for the region, the characteristic detection line is equivalent to directly grasping a key part in the grid, and the wide spread network calculation is carried out without continuously acquiring all detection data in the region;
the fitting means comprises the following specific steps: fitting the historical data to obtain a standard curve, inputting the detection value into the standard curve to calculate a variance value, and taking the variance value as a deviation value;
preferably: the deviation value is Euclidean distance between the detection value and the standard value of each grid on the detection line;
preferably: when the number of periods for which the detection value remains normal reaches the period threshold, the grid scale is reduced and the step S2 and the step S5 are returned: increasing the grid scale, when the grid scale reaches the scale threshold, entering a step S6, otherwise, entering a step S2; the sensitivity of the detection data is increased or reduced by continuously adjusting the grid scale, and the calculated amount is reduced or increased simultaneously, so that a relative balance is achieved between the two;
preferably: an inverse relationship exists between the scale threshold and the calculated amount;
step S6: calculating a grid center of each grid, calculating a deviation parameter of the grid center, and inputting the deviation parameter into a neural network model to obtain a detection result;
when the grid acquisition scale has increased to a relatively high value, the sensitivity of detection through the feature detection lines is reduced, so that information brought by the data deviation amount is limited, and therefore, the grid scale threshold is set according to the detection sensitivity of the feature detection lines, and the scale acquired when the sensitivity does not increase continuously with the increase of the grid scale is the scale threshold;
preferably: the grid center is a detection data value or a detection node;
calculating the grid center of each grid, and calculating the deviation parameters of the grid center, wherein the deviation parameters are specifically as follows: acquiring a detection data set of each grid, taking the current average value of the detection data set as a grid center, and calculating a difference value between the current average value and a historical average value (for example, a standard value on a fitting curve) as a deviation parameter; of course, the neural network model needs to be trained by adopting historical data in advance;
preferably: binarizing the deviation parameter, updating the deviation parameter to be 1 when the deviation parameter is larger than a cut-off threshold value, otherwise, 0; the input of the binarized neural network model is an m-n-dimensional matrix, and the element value of the matrix is 0 or 1; when the neural network model is input, when n is less than 10, setting the neural network model as an m-input n-1 layer (n is less than 10) neural network model, adopting a convolution calculation mode, wherein at the moment, each neuron input of the input layer is an n-dimensional vector, the number of the input neurons is m, and obtaining a detection result through n-1 layer convolution; according to the invention, through the binarization input and the model building mode based on the input structure, the calculation amount of the neural network model is greatly reduced while the grid structure information is not lost, and a relatively accurate judgment result is obtained;
the replacement: when m is less than 10, setting the input as n input, and setting the m-1 layer convolutional neural network model; the convolutional neural network model further comprises a full connection layer;
preferably: when the values of m and n are larger, the further dimension reduction is only carried out on m and n, and the dimension reduction mode can be various modes such as adjacent grid deviation parameter combination and the like;
in order to substitute the structural information of the grid, increase the detection precision while not increasing excessive calculation amount and play the role of the grid, the invention further improves the input deviation parameter input convolutional neural network;
alternatively, the following is used: calculating the grid center of each grid, and calculating the deviation parameters of the grid center, wherein the deviation parameters are specifically as follows: acquiring a detection data set of each grid, and acquiring detection nodes in the grid, wherein the average value of difference values between the detection data of the detection nodes and the detection data of other detection nodes in the grid is minimum; taking the acquired detection node as a grid center; calculating deviation data between the current grid center and the historical grid center as deviation parameters;
preferably: the deviation parameter includes a deviation distance; the offset distance is a physical distance, a topological distance and the like between the current grid center and the historical grid center; for example: the number of the separated detection nodes and the like;
preferably: the deviation parameter further comprises a deviation angle; the deviation angle is a physical deviation angle between a current grid center and a historical grid center;
alternatively, the following is used: the deviation distance is the physical attribute gap between the current grid center and the historical grid center; when the current grid center and the historical grid center are both in the same physical attribute pipe network range, the difference between the current grid center and the historical grid center is 0; when the difference of the physical properties of the pipe network ranges is larger, the deviation distance is larger;
through the method, the change sensitivity in the continuous refinement process of the grids often means that the detected data is abnormal when the grid sensitivity is reduced, the abnormal detected data can be found more accurately through the neural network model, and in fact, the grids or the range of the grids, in which the abnormal detected data occurs, can be further positioned under the condition of increasing the structural complexity of the neural network model; in the smart city construction process involving artificial intelligence, the coverage of the digital grid can enable more data to speak in combination with big data;
the various illustrative logical blocks, modules, and circuits described herein may be implemented or performed with a general purpose processor, a Digital Signal Processor (DSP), an ASIC, a field programmable gate array signal (FPGA) or other Programmable Logic Device (PLD), discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any commercially available processor, controller, microcontroller or state machine. A processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration. The steps of a method or algorithm described in connection with the disclosure herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may reside in any form of tangible storage medium. Some examples of storage media that may be used include Random Access Memory (RAM), read Only Memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, and so forth. A storage medium may be coupled to the processor such that the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. A software module may be a single instruction, or many instructions, and may be distributed over several different code segments, among different programs, and across several storage media.
The functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored as one or more instructions on a tangible computer-readable medium. The computer-readable medium includes a computer-readable storage medium. Computer readable storage media can be any available storage media that can be accessed by a computer. By way of example, and not limitation, such computer-readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. In addition, the propagated signal is not included within the scope of computer-readable storage media. Computer-readable media also includes communication media including any medium that facilitates transfer of a computer program from one place to another. The connection may be a communication medium, for example. For example, if the software is transmitted from a web site, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital Subscriber Line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of communication medium. Combinations of the above should also be included within the scope of computer-readable media. Alternatively, or in addition, the functions described herein may be performed, at least in part, by one or more hardware logic components. For example, illustrative types of hardware logic components that may be used include Field Programmable Gate Arrays (FPGAs), program-specific integrated circuits (ASICs), program-specific standard products (ASSPs), system-on-a-chip (SOCs), complex Programmable Logic Devices (CPLDs), and the like.
Thus, the computer program product may perform the operations presented herein. For example, such a computer program product may be a computer-readable tangible medium having instructions tangibly stored (and/or encoded) thereon, the instructions being executable by one or more processors to perform the operations described herein. The computer program product may comprise packaged material.
The software or instructions may also be transmitted over a transmission medium. For example, software may be transmitted from a website, server, or other remote source using a transmission medium such as a coaxial cable, fiber optic cable, twisted pair, digital Subscriber Line (DSL), or wireless technologies such as infrared, radio, or microwave.
Furthermore, modules and/or other suitable means for performing the methods and techniques described herein may be downloaded and/or otherwise obtained by the user terminal and/or base station as appropriate. For example, such a device may be coupled to a server to facilitate the transfer of means for performing the methods described herein. Alternatively, the various methods described herein may be provided via storage means (e.g., RAM, ROM, a physical storage medium such as a CD or floppy disk, etc.), such that a user terminal and/or base station may obtain the various methods when coupled to or provided with the device. Furthermore, any other suitable technique for providing the methods and techniques described herein to a device may be utilized.
The foregoing description is only of the preferred embodiments of the invention, and all changes and modifications that come within the meaning and range of equivalency of the structures, features and principles of the invention are therefore intended to be embraced therein.
Claims (8)
1. A dynamic gridding processing method for smart city detection data, which is characterized by comprising the following steps:
step S1: initializing processing parameters;
step S2: gridding a pipe network structure based on a grid scale;
step S3: acquiring grid detection data, and calculating a detection value based on a feature detection line; the feature detection line comprises one or more grids and precedence relations thereof; the characteristic detection line comprises a detection data type, a grid position of the detection data and/or a calculation mode of the detection line; the feature detection lines are the same or different for different grid dimensions; the feature detection line is acquired based on historical detection data; acquiring grid detection data based on the feature detection lines; the characteristic detection lines correspond to the current grid scale, and under different grid scales, the characteristic detection lines which can best embody the data characteristics under the current scale can be found through the change of the characteristic detection lines;
step S4: judging whether the detection value is normal or not, if so, returning to the step S3 to continue to acquire and calculate; otherwise, enter step S5;
step S5: increasing the grid scale, when the grid scale reaches the scale threshold, entering a step S6, otherwise, entering a step S2;
step S6: and calculating the grid center of each grid, calculating the deviation parameter of the grid center, and inputting the deviation parameter into the neural network model to obtain a detection result.
2. The smart city detection data dynamic gridding processing method according to claim 1, wherein the step S1 specifically comprises: initializing a grid scale.
3. The smart city detection data dynamic meshing processing method of claim 2, wherein the pipe network is a gas pipe network.
4. The method for dynamically meshing smart city detection data according to claim 3, wherein the mesh scale is the number of nodes of the network or the size of the coverage area of the network.
5. The method for dynamically meshing smart city detection data according to claim 4, wherein feature detection lines corresponding to different mesh scales are calculated after meshing the pipe network structure.
6. A smart city detection data dynamic gridding processing device, comprising:
a storage unit configured to store an application program; and
a processing unit, electrically coupled to an input unit and the storage unit, the processing unit being configured to perform the smart city detection data dynamic meshing processing method of any one of claims 1-5.
7. A smart city detection data dynamic gridding processing system, comprising: a server and a plurality of clients;
the server is used for executing the dynamic gridding processing method of the smart city detection data according to any one of claims 1 to 5;
the clients are used for obtaining processing results.
8. A storage medium for dynamic meshing of smart city detection data, wherein the storage medium is configured to store instructions for performing the method for dynamic meshing of smart city detection data of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110579735.4A CN113221302B (en) | 2021-05-26 | 2021-05-26 | Dynamic gridding processing method and system for smart city detection data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110579735.4A CN113221302B (en) | 2021-05-26 | 2021-05-26 | Dynamic gridding processing method and system for smart city detection data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113221302A CN113221302A (en) | 2021-08-06 |
| CN113221302B true CN113221302B (en) | 2023-07-28 |
Family
ID=77099650
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110579735.4A Active CN113221302B (en) | 2021-05-26 | 2021-05-26 | Dynamic gridding processing method and system for smart city detection data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113221302B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2927644A1 (en) * | 2014-03-31 | 2015-10-07 | Alcatel Lucent | System and method for performing problem-solving in smart grid networks |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107256237A (en) * | 2017-05-23 | 2017-10-17 | 中国电子科技集团公司第二十八研究所 | The LOF cluster datas abnormal point detecting method and detecting system optimized based on dynamic grid |
| CN108320060B (en) * | 2018-03-14 | 2022-01-07 | 成都市自来水有限责任公司 | Artificial water quality monitoring point site selection method based on urban water supply pipe network |
| CN110852458A (en) * | 2019-11-08 | 2020-02-28 | 重庆工商职业学院 | City pipe network supervision method based on big data |
-
2021
- 2021-05-26 CN CN202110579735.4A patent/CN113221302B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2927644A1 (en) * | 2014-03-31 | 2015-10-07 | Alcatel Lucent | System and method for performing problem-solving in smart grid networks |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113221302A (en) | 2021-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113128793A (en) | Photovoltaic power combination prediction method and system based on multi-source data fusion | |
| CN106777093B (en) | Skyline inquiry system based on space time sequence data flow application | |
| Jalalkamali | Using of hybrid fuzzy models to predict spatiotemporal groundwater quality parameters | |
| CN111432368B (en) | Ranging and positioning method suitable for sparse anchor node WSN | |
| CN111461410A (en) | Air quality prediction method and device based on transfer learning | |
| CN112287294A (en) | Time-space bidirectional soil water content interpolation method based on deep learning | |
| CN110134907B (en) | Rainfall missing data filling method and system and electronic equipment | |
| CN117291444B (en) | Digital rural business management method and system | |
| CN117117833A (en) | Photovoltaic output power prediction method and device, electronic equipment and storage medium | |
| CN117241215A (en) | Wireless sensor network distributed node cooperative positioning method based on graph neural network | |
| CN113221302B (en) | Dynamic gridding processing method and system for smart city detection data | |
| Liang et al. | Surrogate-assisted Phasmatodea population evolution algorithm applied to wireless sensor networks | |
| Qi et al. | Combining weather factors to predict traffic flow: A spatial‐temporal fusion graph convolutional network‐based deep learning approach | |
| CN113240219A (en) | Land utilization simulation and prediction method | |
| CN117593877A (en) | Short-time traffic flow prediction method based on integrated graph convolution neural network | |
| Wang et al. | Design of wireless sensor network using statistical fractal measurements | |
| CN113360716B (en) | Logical processing method and system for gas pipe network structure | |
| CN114418243B (en) | Distributed new energy cloud grid prediction method and system | |
| CN113326596B (en) | Method and system for setting detection points of complex gas pipe network structure | |
| CN116451801A (en) | Complex underlying meteorological data grid analysis method and system based on big data and machine learning | |
| CN113780644B (en) | Photovoltaic output prediction method based on online learning | |
| CN117175535A (en) | Wind power group power prediction method, system, equipment and medium | |
| CN115903085A (en) | Agricultural meteorological disaster early warning method and device and storage medium | |
| CN104463924A (en) | Digital elevation terrain model generation method based on scattered point elevation sample data | |
| CN116150699B (en) | Traffic flow prediction method, device, equipment and medium based on deep learning |
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 |