CN117892060A - Early warning method and system based on fusion of transformer model and multiple perception parameters - Google Patents
Early warning method and system based on fusion of transformer model and multiple perception parameters Download PDFInfo
- Publication number
- CN117892060A CN117892060A CN202311789908.0A CN202311789908A CN117892060A CN 117892060 A CN117892060 A CN 117892060A CN 202311789908 A CN202311789908 A CN 202311789908A CN 117892060 A CN117892060 A CN 117892060A
- Authority
- CN
- China
- Prior art keywords
- transformer
- model
- data
- state
- gim
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000008447 perception Effects 0.000 title claims abstract description 25
- 230000004927 fusion Effects 0.000 title claims abstract description 20
- 238000013210 evaluation model Methods 0.000 claims abstract description 71
- 230000007547 defect Effects 0.000 claims description 31
- 238000003860 storage Methods 0.000 claims description 27
- 238000012545 processing Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 12
- 238000000547 structure data Methods 0.000 claims description 12
- 238000012216 screening Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 abstract description 12
- 238000012800 visualization Methods 0.000 abstract description 7
- 230000009466 transformation Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 238000010276 construction Methods 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000013507 mapping Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000009960 carding Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000007794 visualization technique Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000010079 rubber tapping Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/185—Electrical failure alarms
-
- 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
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Biology (AREA)
- Emergency Management (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- Software Systems (AREA)
- Testing Electric Properties And Detecting Electric Faults (AREA)
Abstract
The invention discloses an early warning method and system based on transformer model and multi-perception parameter fusion, and belongs to the technical field of state evaluation and early warning of power transformation main equipment. The early warning method of the invention comprises the following steps: acquiring state data of a target transformer; identifying the state data of the target transformer based on a pre-constructed early warning model; the early warning model is obtained by associating a transformer state evaluation model which is of multiple layers and is fused with multiple perception parameters with a transformer GIM model, the transformer state evaluation model is built according to transformer data, and the transformer GIM model is built according to transformer substation data; the transformer data and the transformer substation data have a one-to-one correspondence with the state data of the transformer; and outputting an identification result, and carrying out early warning on the target transformer based on the identification result. The method and the device can effectively improve the visualization efficiency of the transformer state evaluation model.
Description
Technical Field
The invention relates to the technical field of transformer main equipment state evaluation and early warning, in particular to an early warning method and system based on transformer model and multi-perception parameter fusion.
Background
Along with the construction of a novel power system and the increase of power loads, the requirements on continuous reliable power supply and safe and stable operation of a power grid are also higher and higher. Therefore, extensive equipment state evaluation is necessary to be carried out, the running state of the equipment is known, and equipment with poor running state is maintained or replaced in time. The transformer is a key device for power transformation, and state evaluation is an important link for operation maintenance and health management. In order to ensure the intuitiveness and accuracy of the state evaluation result, three-dimensional visualization of the evaluation model is required. The transformer state evaluation model established based on the online monitoring data in the current use faces two major problems, namely the lack of fine division of state indexes in multiple levels and multiple dimensions, the lack of associated application of the state indexes to three-dimensional models and the complexity of a visualization method.
In the aspect of hierarchical division, the model performs state evaluation by fusion analysis on numerical state data acquired by multiple types of sensors. The transformer has complex internal structure, numerous functional parts and various state indexes related to the operation conditions of the transformer. The influence relation among the indexes, the corresponding relation between the indexes and the defects, the corresponding relation between the defects and the occurrence parts and the like are complicated. The hierarchical architecture of the evaluation model directly influences the comprehensiveness and intuitiveness of the evaluation result, and more defects are identified, so that the defects are difficult to accurately position. Thus, such a visualization method of the evaluation model is only to roughly display the evaluation result on the three-dimensional model.
In three-dimensional model-dependent applications, device fault diagnosis typically employs a laser point cloud model. The laser point cloud model does not have a hierarchical structure, needs complex processes such as segmentation, optimization and component recognition, and is slow to render. In the power grid construction process, the three-dimensional model used is mainly a GIM model. The GIM model has slightly lower precision, fineness and accuracy than the point cloud model, but has great advantages in loading speed, establishing speed and model data processing. The GIM shows less transformer substation details in the conventional data in a refined manner on the visual effect, the information comprises the indoor environment, the transformer, the insulator and the like of the transformer substation, and the defects that the internal running state of the transformer cannot be embodied and the real-time monitoring data cannot be reflected in the GIM data are overcome on the informatization degree of the online monitoring data.
Disclosure of Invention
Aiming at the problems, the invention provides an early warning method based on the fusion of a transformer model and multiple perception parameters, which comprises the following steps:
acquiring state data of a target transformer;
identifying the state data of the target transformer based on a pre-constructed early warning model;
the early warning model is obtained by associating a multi-level transformer state evaluation model which fuses multiple perception parameters with a transformer power grid information GIM model, wherein the transformer state evaluation model is built according to transformer data, and the transformer GIM model is built according to transformer substation data;
the transformer data and the transformer substation data have a one-to-one correspondence with the state data of the transformer;
and outputting an identification result, and carrying out early warning on the target transformer based on the identification result.
Optionally, according to the transformer data, a multi-level transformer state evaluation model integrating multiple perception parameters is established, including:
based on the transformer data, dividing an initial transformer state evaluation model into a plurality of layers, dividing a multi-perception parameter input into the initial transformer state evaluation model into a plurality of state levels, and associating the plurality of layers with the plurality of state levels to establish the transformer state evaluation model with the multi-layer and multi-perception parameter fusion.
Optionally, based on the transformer data, dividing the initial transformer state estimation model into a plurality of levels includes:
and screening out transformer structure data, various sensor layout position data and typical defect data of the transformer in the transformer data, and dividing an initial transformer state evaluation model into a plurality of layers based on the transformer structure data, the various sensor layout position data and the typical defect data of the transformer.
Optionally, dividing the multi-perception parameters input into the initial transformer state evaluation model into a plurality of state levels includes:
and performing softening treatment on the judgment boundary of the multi-perception parameter state, and dividing the multi-perception parameter into a plurality of state grades.
Optionally, after dividing the multi-perception parameter into a plurality of state levels, the early warning method further includes:
and setting confidence level for the state of the multi-perception parameter.
Optionally, building a transformer GIM model according to the substation data includes:
a substation GIM file in substation data is obtained, the substation GIM file is analyzed, all levels of models stored in the analyzed substation GIM file are restored to an original hierarchical structure, and the original hierarchical structure is stored;
constructing a three-dimensional grid model of the transformer based on the stored original hierarchical structure;
processing the three-dimensional grid model to reduce the number of patches and reduce the weight of patches to obtain an optimized three-dimensional grid model;
the sensor perception data is mapped to an optimized three-dimensional mesh model to build a transformer GIM model.
Optionally, after the three-dimensional grid model of the transformer is constructed, the early warning method further includes: and storing the three-dimensional grid model in a general storage format.
In still another aspect, the present invention further provides an early warning system based on the fusion of the transformer GIM model and multiple perception parameters, including:
the data acquisition unit is used for acquiring state data of the target transformer;
the identification unit is used for identifying the state data of the target transformer based on a pre-constructed early warning model;
the early warning model is obtained by associating a transformer state evaluation model which is of multiple layers and is fused with multiple perception parameters with a transformer GIM model, the transformer state evaluation model is built according to transformer data, and the transformer GIM model is built according to transformer substation data;
the transformer data and the transformer substation data have a one-to-one correspondence with the state data of the transformer;
and the output unit is used for outputting the identification result and carrying out early warning on the target transformer based on the identification result.
Optionally, according to the transformer data, a multi-level transformer state evaluation model integrating multiple perception parameters is established, including:
based on the transformer data, dividing an initial transformer state evaluation model into a plurality of layers, dividing a multi-perception parameter input into the initial transformer state evaluation model into a plurality of state levels, and associating the plurality of layers with the plurality of state levels to establish the transformer state evaluation model with the multi-layer and multi-perception parameter fusion.
Optionally, based on the transformer data, dividing the initial transformer state estimation model into a plurality of levels includes:
and screening out transformer structure data, various sensor layout position data and typical defect data of the transformer in the transformer data, and dividing an initial transformer state evaluation model into a plurality of layers based on the transformer structure data, the various sensor layout position data and the typical defect data of the transformer.
Optionally, dividing the multi-perception parameters input into the initial transformer state evaluation model into a plurality of state levels includes:
and performing softening treatment on the judgment boundary of the multi-perception parameter state, and dividing the multi-perception parameter into a plurality of state grades.
Optionally, after dividing the multi-perception parameter into a plurality of state levels, confidence is set for the state where the multi-perception parameter is located.
Optionally, building a transformer GIM model according to the substation data includes:
a substation GIM file in substation data is obtained, the substation GIM file is analyzed, all levels of models stored in the analyzed substation GIM file are restored to an original hierarchical structure, and the original hierarchical structure is stored;
constructing a three-dimensional grid model of the transformer based on the stored original hierarchical structure;
processing the three-dimensional grid model to reduce the number of patches and reduce the weight of patches to obtain an optimized three-dimensional grid model;
the sensor perception data is mapped to an optimized three-dimensional mesh model to build a transformer GIM model.
Optionally, after the three-dimensional grid model of the transformer is constructed, the three-dimensional grid model is stored in a general storage format.
In yet another aspect, the present invention also provides a computing device comprising: one or more processors;
a processor for executing one or more programs;
the method as described above is implemented when the one or more programs are executed by the one or more processors.
In yet another aspect, the present invention also provides a computer readable storage medium having stored thereon a computer program which, when executed, implements a method as described above.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides an early warning method based on a transformer GIM model and multi-perception parameter fusion, which comprises the following steps: acquiring state data of a target transformer; identifying the state data of the target transformer based on a pre-constructed early warning model; the early warning model is obtained by associating a transformer state evaluation model which is of multiple layers and is fused with multiple perception parameters with a transformer GIM model, the transformer state evaluation model is built according to transformer data, and the transformer GIM model is built according to transformer substation data; the transformer data and the transformer substation data have a one-to-one correspondence with the state data of the transformer; and outputting an identification result, and carrying out early warning on the target transformer based on the identification result. The method and the device can effectively improve the visualization efficiency of the transformer state evaluation model.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a flow chart of an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating a hierarchical division of a transformer state evaluation model according to an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating an example of hierarchical division of a transformer state evaluation model according to an embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating a judgment boundary softening in accordance with an embodiment of the present invention;
fig. 6 is a block diagram of the system of the present invention.
Detailed Description
The exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, however, the present invention may be embodied in many different forms and is not limited to the examples described herein, which are provided to fully and completely disclose the present invention and fully convey the scope of the invention to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the accompanying drawings is not intended to be limiting of the invention. In the drawings, like elements/components are referred to by like reference numerals.
Unless otherwise indicated, terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art. In addition, it will be understood that terms defined in commonly used dictionaries should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense.
Example 1:
the invention provides an early warning method based on a transformer GIM model and multi-perception parameter fusion, which is shown in figure 1 and comprises the following steps:
step 1, acquiring state data of a target transformer;
step 2, identifying the state data of the target transformer based on a pre-constructed early warning model;
the early warning model is obtained by associating a transformer state evaluation model and a transformer GIM model, wherein the transformer state evaluation model is established according to transformer data, and the transformer GIM model is established according to transformer substation data;
the transformer data and the transformer substation data have a one-to-one correspondence with the state data of the transformer;
and step 3, outputting an identification result, and carrying out early warning on the target transformer based on the identification result.
Based on the transformer data, a multi-level transformer state evaluation model integrating multiple perception parameters is established, and the method comprises the following steps:
based on the transformer data, dividing an initial transformer state evaluation model into a plurality of layers, dividing a multi-perception parameter input into the initial transformer state evaluation model into a plurality of state grades, and associating the plurality of layers with the plurality of state grades so as to establish the transformer state evaluation model with the plurality of layers and the multi-perception parameter fusion.
Wherein dividing the initial transformer state assessment model into a plurality of levels based on the transformer data comprises:
and screening out transformer structure data, various sensor layout position data and typical defect data of the transformer in the transformer data, and dividing an initial transformer state evaluation model into a plurality of layers based on the transformer structure data, the various sensor layout position data and the typical defect data of the transformer.
Wherein dividing the multi-perception parameters input into the initial transformer state evaluation model into a plurality of state levels comprises:
and performing softening treatment on the judgment boundary of the multi-perception parameter state, and dividing the multi-perception parameter into a plurality of state grades.
After dividing the multi-perception parameter into a plurality of state levels, the early warning method further comprises the following steps:
and setting confidence level for the state of the multi-perception parameter.
The method comprises the steps of obtaining substation data, and establishing a transformer GIM model based on the substation data, wherein the method comprises the following steps:
a substation GIM file in substation data is obtained, the substation GIM file is analyzed, all levels of models stored in the analyzed substation GIM file are restored to an original hierarchical structure, and the original hierarchical structure is stored;
constructing a three-dimensional grid model of the transformer based on the stored original hierarchical structure;
processing the three-dimensional grid model to reduce the number of patches and reduce the weight of patches to obtain an optimized three-dimensional grid model;
the sensor perception data is mapped to an optimized three-dimensional mesh model to build a transformer GIM model.
After the three-dimensional grid model of the transformer is constructed, the early warning method further comprises the following steps: and storing the three-dimensional grid model in a general storage format.
The invention is further illustrated by the following examples:
as shown in fig. 2, the steps of the embodiment include:
and step 101, carding the transformer structure, various sensor layout positions and typical defects to realize hierarchical division of a transformer state evaluation model.
Step 102, softening the judgment boundary of the state of the input parameter, dividing the parameter into a plurality of state grades, and giving the confidence of the state of the criterion.
And step 103, establishing a multi-parameter fusion multi-level transformer state evaluation model based on the evidence theory.
And 104, analyzing the substation GIM file, restoring each level of models stored in the file into an original hierarchical structure, and storing in a lossless manner.
And 105, constructing a three-dimensional grid model of the whole transformer according to the analysis data, and converting the three-dimensional grid model into a general storage format.
And 106, optimizing the reconstructed three-dimensional grid model, reducing the number of patches in terms of primitives, and lightening the model in terms of storage.
Step 107, mapping the sensor perception data to a three-dimensional model, and associating the hierarchy of the transformer state evaluation model with the hierarchy of the GIM model.
The method and the device can effectively improve the visualization efficiency of the transformer state evaluation model. With the construction of a novel power system and the increase of power loads, the requirements on continuous and reliable power supply, safe and stable operation of a power grid become higher. Therefore, the state evaluation of the equipment needs to be widely carried out, the running state of the equipment is known, and the equipment with poor running state is overhauled or replaced in time. The transformer is used as a key main equipment of the power transformation, and the state evaluation of the transformer is an important link for carrying out operation, maintenance and health management work. In order to ensure the visual and accurate state evaluation result, the three-dimensional visualization of the evaluation model is required. The current evaluation model stays in one-dimensional or two-dimensional numerical analysis, cannot be effectively connected with the existing massive three-dimensional models in the power grid system, is repeatedly modeled in visualization, is complex in steps, is slow in rendering, and causes resource waste.
The invention combines the hierarchical structure of the transformer state evaluation model with the hierarchical structure of the GIM model. The method not only simplifies the expansion of the state evaluation range, but also can quickly multiplex the existing three-dimensional model, thereby effectively reducing the workload related to the visual task.
The invention is deployed and used in the online monitoring system of the transformer substation, and can obtain the GIM model through a digital handover platform of a through foundation department, thereby reducing the mapping cost of the operation and maintenance stage of the transformer substation.
Meanwhile, based on the visual effect of the invention, the cost of manpower, material resources and time for manually reaching the site to analyze the fault position is reduced, the workload of first-line personnel is greatly reduced, and the cost reduction and synergy of the transformer substation can be realized.
In conclusion, the method can greatly improve the on-line monitoring efficiency and effect of the transformer substation and accelerate the realization of unmanned and intelligent transformation of the transformer substation.
Step 101, carding the transformer structure, various sensor layout positions and typical defects to realize hierarchical division of a transformer state evaluation model.
Specifically, a transformer to be monitored is selected, and the transformer is divided into a body, a sleeve, a tapping switch, a cooler system, a non-electric quantity protection device and the like according to a transformer real object, a design drawing and related reference files. Different transformer models can be added and deleted with components according to actual conditions.
Specifically, based on relevant specifications of transformer state detection and operation and maintenance experience, the type of the sensor to be arranged is selected, and the installation position and the detectable range of the sensor are recorded. The data collected by the sensor is used as an input parameter of a transformer state evaluation model.
Specifically, based on data statistics, typical defects of the transformer are analyzed, and the defects are combed and divided according to defect types and defect occurrence positions. Meanwhile, the defects are related to the input parameters according to the correlation between the defects and the data acquired by the sensors. The division is shown in fig. 3. An example of a model hierarchy after division is shown in fig. 4.
Step 102, softening the judgment boundary of the state of the input parameter, dividing the parameter into a plurality of state grades, and giving the confidence of the state of the criterion.
Specifically, the states of the input parameters are classified into four classes of normal, attention, serious, and critical. According to the operation data after transformer delivery test, installation test, type test and operation, the data collected by the situations of history faults and the like, the range of each input parameter under different state levels is judged, and the actually collected values are normalized based on the input parameter values under the normal state. When the input parameter value is at the boundary of two states, a state grade judgment error easily occurs, so that the input parameter is softened based on a Gaussian cloud theory, and the confidence coefficient of the input parameter at different state grades is obtained, as shown in fig. 5.
And step 103, establishing a multi-parameter fusion multi-level transformer state evaluation model based on the evidence theory.
Specifically, based on the association relation between the defect type and the corresponding input parameter, a correlation rule method is adopted to give weight to the input parameter. Aiming at abnormal conditions such as input parameter deficiency, serious deviation of the input parameter from a criterion range and the like, a correction coefficient is set, and the input parameter weight is corrected. And carrying out weighted calculation on the normalized input parameters based on the weights to obtain the confidence coefficient of the defect in each state level.
Specifically, based on the evidence theory, the specific state of the defect is judged according to the confidence level of each state level of the defect.
Specifically, repeating the steps on the defect layer, and carrying out weighted calculation on the state confidence coefficient of different defects to obtain the confidence coefficient of the performance under each state level. Judging the state of the performance based on evidence theory. And finally obtaining the states of all elements of the five layers through layer-by-layer analysis.
And 104, analyzing the substation GIM file, restoring each level of models stored in the file into an original hierarchical structure, and storing in a lossless manner.
Specifically, the GIM file digitally handed over by the grid infrastructure engineering itself has a hierarchical structure, which is classified into 5 stages according to the substation system functions, system partitions, and range sizes, including 1 stage total station stage, 2 stage system stage, 3 stage system stage, 4 stage equipment stage, 5 stage component stage. Each model is formed by combining a previous model, the component model is built based on a geometric model, and the geometric model is composed of a plurality of primitives with parameters. The device level and the component level can be directly related to the transformer state evaluation model after correction. The generic GIM format exported using the design tool may lose hierarchy. The geometric information of the GIM model needs to be analyzed, a hierarchical structure is reserved, and parameterized modeling is performed again.
Specifically, according to the stored reference relation, each level of model in the file is parsed and restored into the original hierarchical structure of the GIM, and the hierarchical structure is stored in a JSON form.
And 105, constructing a three-dimensional grid model of the whole transformer according to the analysis data, and converting the three-dimensional grid model into a general storage format.
Specifically, constructing a basic primitive from a parameter model into a three-dimensional model according to parameters stored in the geometric model and a space coordinate system specified in a GIM standard; then, combining the basic primitives according to the hierarchical structure and the space transformation matrix of the GIM, and constructing an integral three-dimensional grid model of the GIM; the built three-dimensional model is stored in FBX format.
And 106, optimizing the reconstructed three-dimensional grid model, reducing the number of patches in terms of primitives, and lightening the model in terms of storage.
Specifically, the number of primitive patches is cut down at the time of modeling and after modeling. The number of patches constructing the model is appropriately graded according to the radius of the model during modeling. As the radius increases, the number of patches relatively decreases. Taking a model with radian as an example, the larger the radius, the more gentle the radian, and the fewer the number of patches required. After modeling, the model is further patch-simplified by the QEM edge collapse algorithm. Firstly, calculating the cost of each effective point pair (edges which can be eliminated) in the model, then deleting the point pair with the minimum cost, eliminating each edge, and obtaining the optimal simplified model through iteration.
Specifically, the model is light-weighted during storage, and the geometric model and texture information of the same type are stored only once and are directly called when needed.
Step 107, mapping the sensor perception data to a three-dimensional model, and associating the hierarchy of the transformer state evaluation model with the hierarchy of the GIM model.
Specifically, the attribute information corresponding to each layer of the model is written into a database sql file, and the construction of the attribute table is completed.
Specifically, according to the hierarchical structure of the state evaluation model, a key value pair is formed for each level of elements and the corresponding states thereof. A null JSON is created for each component and the key-value pair and device ID are written to JSON. And gradually writing the embedded JSON objects according to the calling relation among the files recorded in the GIM model. Finally, all individual JSON objects are nested into a complete JSON file that can correlate the output information of the state evaluation model and reflect the complete GIM data hierarchy.
Example 2:
the invention also provides an early warning system 200 based on the fusion of the transformer GIM model and the multi-perception parameters, as shown in FIG. 6, comprising:
a data acquisition unit 201, configured to acquire status data of a target transformer;
an identifying unit 202, configured to identify the state data of the target transformer based on a pre-constructed early warning model;
the early warning model is obtained by associating a transformer state evaluation model which is of multiple layers and is fused with multiple perception parameters with a transformer GIM model, the transformer state evaluation model is built according to transformer data, and the transformer GIM model is built according to transformer substation data;
the transformer data and the transformer substation data have a one-to-one correspondence with the state data of the transformer;
and the output unit 203 is configured to output a recognition result, and perform early warning on the target transformer based on the recognition result.
Based on the transformer data, a multi-level transformer state evaluation model integrating multiple perception parameters is established, and the method comprises the following steps:
based on the transformer data, dividing an initial transformer state evaluation model into a plurality of layers, dividing a multi-perception parameter input into the initial transformer state evaluation model into a plurality of state grades, and associating the plurality of layers with the plurality of state grades so as to establish the transformer state evaluation model with the plurality of layers and the multi-perception parameter fusion.
Wherein dividing the initial transformer state assessment model into a plurality of levels based on the transformer data comprises:
and screening out transformer structure data, various sensor layout position data and typical defect data of the transformer in the transformer data, and dividing an initial transformer state evaluation model into a plurality of layers based on the transformer structure data, the various sensor layout position data and the typical defect data of the transformer.
Wherein dividing the multi-perception parameters input into the initial transformer state evaluation model into a plurality of state levels comprises:
and performing softening treatment on the judgment boundary of the multi-perception parameter state, and dividing the multi-perception parameter into a plurality of state grades.
After the multi-perception parameters are divided into a plurality of state levels, confidence is set for the state where the multi-perception parameters are located.
The method comprises the steps of obtaining substation data, and establishing a transformer GIM model based on the substation data, wherein the method comprises the following steps:
a substation GIM file in substation data is obtained, the substation GIM file is analyzed, all levels of models stored in the analyzed substation GIM file are restored to an original hierarchical structure, and the original hierarchical structure is stored;
constructing a three-dimensional grid model of the transformer based on the stored original hierarchical structure;
processing the three-dimensional grid model to reduce the number of patches and reduce the weight of patches to obtain an optimized three-dimensional grid model;
the sensor perception data is mapped to an optimized three-dimensional mesh model to build a transformer GIM model.
After a three-dimensional grid model of the transformer is constructed, the three-dimensional grid model is stored in a general storage format.
The method and the device can effectively improve the visualization efficiency of the transformer state evaluation model.
Example 3:
based on the same inventive concept, the invention also provides a computer device comprising a processor and a memory for storing a computer program comprising program instructions, the processor for executing the program instructions stored by the computer storage medium. The processor may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application SpecificIntegrated Circuit, ASIC), off-the-shelf Programmable gate arrays (FPGAs) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., which are the computational core and control core of the terminal adapted to implement one or more instructions, in particular adapted to load and execute one or more instructions within a computer storage medium to implement the corresponding method flow or corresponding functions to implement the steps of the method in the embodiments described above.
Example 4:
based on the same inventive concept, the present invention also provides a storage medium, in particular, a computer readable storage medium (Memory), which is a Memory device in a computer device, for storing programs and data. It is understood that the computer readable storage medium herein may include both built-in storage media in a computer device and extended storage media supported by the computer device. The computer-readable storage medium provides a storage space storing an operating system of the terminal. Also stored in the memory space are one or more instructions, which may be one or more computer programs (including program code), adapted to be loaded and executed by the processor. The computer readable storage medium herein may be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory. One or more instructions stored in a computer-readable storage medium may be loaded and executed by a processor to implement the steps of the methods in the above-described embodiments.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The scheme in the embodiment of the invention can be realized by adopting various computer languages, such as object-oriented programming language Java, an transliteration script language JavaScript and the like.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (16)
1. An early warning method based on fusion of a transformer model and multiple perception parameters is characterized by comprising the following steps:
acquiring state data of a target transformer;
identifying the state data of the target transformer based on a pre-constructed early warning model;
the early warning model is obtained by associating a multi-level transformer state evaluation model which fuses multiple perception parameters with a transformer power grid information GIM model, wherein the transformer state evaluation model is built according to transformer data, and the transformer GIM model is built according to transformer substation data;
the transformer data and the transformer substation data have a one-to-one correspondence with the state data of the transformer;
and outputting an identification result, and carrying out early warning on the target transformer based on the identification result.
2. The method of claim 1, wherein establishing a multi-level and multi-perception parameter-fused transformer state assessment model based on transformer data comprises:
based on the transformer data, dividing an initial transformer state evaluation model into a plurality of layers, dividing a multi-perception parameter input into the initial transformer state evaluation model into a plurality of state levels, and associating the plurality of layers with the plurality of state levels to establish the transformer state evaluation model with the multi-layer and multi-perception parameter fusion.
3. The method of claim 2, wherein the dividing the initial transformer state assessment model into a plurality of levels based on the transformer data comprises:
and screening out transformer structure data, various sensor layout position data and typical defect data of the transformer in the transformer data, and dividing an initial transformer state evaluation model into a plurality of layers based on the transformer structure data, the various sensor layout position data and the typical defect data of the transformer.
4. The method of claim 2, wherein dividing the multi-perception parameters input to the initial transformer state estimation model into a plurality of state levels comprises:
and performing softening treatment on the judgment boundary of the multi-perception parameter state, and dividing the multi-perception parameter into a plurality of state grades.
5. The method according to claim 4, wherein after dividing the multi-perception parameter into a plurality of state levels, the method further comprises:
and setting confidence level for the state of the multi-perception parameter.
6. The method of claim 1, wherein building a transformer GIM model from substation data comprises:
a substation GIM file in substation data is obtained, the substation GIM file is analyzed, all levels of models stored in the analyzed substation GIM file are restored to an original hierarchical structure, and the original hierarchical structure is stored;
constructing a three-dimensional grid model of the transformer based on the stored original hierarchical structure;
processing the three-dimensional grid model to reduce the number of patches and reduce the weight of patches to obtain an optimized three-dimensional grid model;
the sensor perception data is mapped to an optimized three-dimensional mesh model to build a transformer GIM model.
7. The method according to claim 6, wherein after the three-dimensional grid model of the transformer is constructed, the method further comprises: and storing the three-dimensional grid model in a general storage format.
8. An early warning system based on a transformer GIM model and multi-perception parameter fusion, which is characterized by comprising:
the data acquisition unit is used for acquiring state data of the target transformer;
the identification unit is used for identifying the state data of the target transformer based on a pre-constructed early warning model;
the early warning model is obtained by associating a transformer state evaluation model which is of multiple layers and is fused with multiple perception parameters with a transformer GIM model, the transformer state evaluation model is built according to transformer data, and the transformer GIM model is built according to transformer substation data;
the transformer data and the transformer substation data have a one-to-one correspondence with the state data of the transformer;
and the output unit is used for outputting the identification result and carrying out early warning on the target transformer based on the identification result.
9. The warning system of claim 8 wherein establishing a multi-level and multi-perceptive parameter-fused transformer state assessment model based on transformer data comprises:
based on the transformer data, dividing an initial transformer state evaluation model into a plurality of layers, dividing a multi-perception parameter input into the initial transformer state evaluation model into a plurality of state levels, and associating the plurality of layers with the plurality of state levels to establish the transformer state evaluation model with the multi-layer and multi-perception parameter fusion.
10. The early warning system of claim 9, wherein the dividing the initial transformer state assessment model into a plurality of levels based on the transformer data comprises:
and screening out transformer structure data, various sensor layout position data and typical defect data of the transformer in the transformer data, and dividing an initial transformer state evaluation model into a plurality of layers based on the transformer structure data, the various sensor layout position data and the typical defect data of the transformer.
11. The early warning system of claim 9, wherein the dividing the multiple perception parameters input to the initial transformer state estimation model into multiple state levels comprises:
and performing softening treatment on the judgment boundary of the multi-perception parameter state, and dividing the multi-perception parameter into a plurality of state grades.
12. The warning system of claim 12 wherein the confidence level is set for the state in which the multi-perception parameter is located after the multi-perception parameter is divided into a plurality of state levels.
13. The method of claim 8, wherein building a transformer GIM model from substation data comprises:
a substation GIM file in substation data is obtained, the substation GIM file is analyzed, all levels of models stored in the analyzed substation GIM file are restored to an original hierarchical structure, and the original hierarchical structure is stored;
constructing a three-dimensional grid model of the transformer based on the stored original hierarchical structure;
processing the three-dimensional grid model to reduce the number of patches and reduce the weight of patches to obtain an optimized three-dimensional grid model;
the sensor perception data is mapped to an optimized three-dimensional mesh model to build a transformer GIM model.
14. The warning system of claim 13 wherein the three-dimensional mesh model of the transformer is stored in a generic storage format after the three-dimensional mesh model is constructed.
15. A computer device, comprising:
one or more processors;
a processor for executing one or more programs;
the method of any of claims 1-7 is implemented when the one or more programs are executed by the one or more processors.
16. A computer readable storage medium, characterized in that a computer program is stored thereon, which computer program, when executed, implements the method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311789908.0A CN117892060A (en) | 2023-12-22 | 2023-12-22 | Early warning method and system based on fusion of transformer model and multiple perception parameters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311789908.0A CN117892060A (en) | 2023-12-22 | 2023-12-22 | Early warning method and system based on fusion of transformer model and multiple perception parameters |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117892060A true CN117892060A (en) | 2024-04-16 |
Family
ID=90641962
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311789908.0A Pending CN117892060A (en) | 2023-12-22 | 2023-12-22 | Early warning method and system based on fusion of transformer model and multiple perception parameters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117892060A (en) |
-
2023
- 2023-12-22 CN CN202311789908.0A patent/CN117892060A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106874483A (en) | A kind of device and method of the patterned quality of data evaluation and test based on big data technology | |
| CN108985471B (en) | Aircraft management system based on 3D lightweight model | |
| CN112712305B (en) | Aircraft system and health assessment method and device thereof | |
| Salamak et al. | Analytical modelling in Dynamo | |
| CN116467674B (en) | Intelligent fault processing fusion updating system and method for power distribution network | |
| CN117411192B (en) | Monitoring method and system for uninterruptible power supply parallel operation system | |
| CN105320805A (en) | Pico-satellite multi-source reliability information fusion method | |
| CN112685820A (en) | Digital power station delivery method, medium and equipment based on BIM and GIS | |
| CN115630771B (en) | Big data analysis method and system applied to intelligent construction site | |
| CN113407723A (en) | Multi-source heterogeneous power load data fusion method, device, equipment and storage medium | |
| CN113312748A (en) | Online modeling method and system for load model | |
| CN117217020A (en) | Industrial model construction method and system based on digital twin | |
| CN110716520A (en) | Flight control servo actuator reliability evaluation modeling method based on multi-source information fusion | |
| CN112862211A (en) | Method and device for assigning orders of dynamic ring defects of communication management system | |
| CN117909864A (en) | Power failure prediction system and method | |
| CN117043776A (en) | Method and system for digital design and authentication | |
| CN116541748A (en) | Power grid fault diagnosis method and system based on artificial intelligence technology | |
| CN117892060A (en) | Early warning method and system based on fusion of transformer model and multiple perception parameters | |
| Kovalyov | Design and development of a power system digital twin: A model-based approach | |
| CN116433018A (en) | Digital twinning-based power distribution network risk situation sensing method and device | |
| CN115797104A (en) | Multi-path informatization identification method for business expansion installation | |
| CN115510721A (en) | Real-time detection method and system for key parameters based on digital twins | |
| CN104123469A (en) | Detection scheduling system and method for context consistency in pervasive computing environment | |
| CN111105140A (en) | Comprehensive risk assessment method for running state of power distribution network | |
| CN110555218A (en) | Production model update system, apparatus, method, and computer-readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |