CN118038272A - Artificial intelligence evaluation algorithm based on electric power inspection scene - Google Patents
Artificial intelligence evaluation algorithm based on electric power inspection scene Download PDFInfo
- Publication number
- CN118038272A CN118038272A CN202410232701.1A CN202410232701A CN118038272A CN 118038272 A CN118038272 A CN 118038272A CN 202410232701 A CN202410232701 A CN 202410232701A CN 118038272 A CN118038272 A CN 118038272A
- Authority
- CN
- China
- Prior art keywords
- data set
- inspection
- evaluation
- electric
- power
- 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
- 238000007689 inspection Methods 0.000 title claims abstract description 80
- 238000011156 evaluation Methods 0.000 title claims abstract description 48
- 238000013473 artificial intelligence Methods 0.000 title claims description 16
- 238000013210 evaluation model Methods 0.000 claims abstract description 39
- 238000004458 analytical method Methods 0.000 claims abstract description 37
- 238000012423 maintenance Methods 0.000 claims abstract description 35
- 238000000605 extraction Methods 0.000 claims abstract description 23
- 238000004364 calculation method Methods 0.000 claims abstract description 11
- 238000000034 method Methods 0.000 claims abstract description 4
- 238000001514 detection method Methods 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 7
- 238000013135 deep learning Methods 0.000 claims description 5
- 238000001931 thermography Methods 0.000 claims description 5
- 238000010438 heat treatment Methods 0.000 claims description 4
- 238000012854 evaluation process Methods 0.000 claims description 3
- 238000010248 power generation Methods 0.000 claims description 3
- 238000011157 data evaluation Methods 0.000 abstract description 2
- 208000025274 Lightning injury Diseases 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000012535 impurity Substances 0.000 description 2
- 239000012212 insulator Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- 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)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Primary Health Care (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Water Supply & Treatment (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Public Health (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of power inspection data evaluation, and discloses an artificial intelligent evaluation algorithm based on a power inspection scene, wherein the artificial intelligent evaluation algorithm based on the power inspection scene performs calculation evaluation through an intelligent inspection evaluation system, and the method comprises the following steps: the method comprises the steps that firstly, a data acquisition module acquires an image data set and an electric data set, and simultaneously, the data acquisition module acquires a reference data set according to a database, and screens and generates an effective characteristic data set; step two, the intelligent analysis module collects variable data sets through a large data platform, combines the variable data sets with a reference data set, calculates and generates an evaluation model, and substitutes the effective characteristic data sets into the evaluation model to generate an operation and maintenance index; and thirdly, guiding a manager to carry out equipment maintenance by the inspection management module according to the operation and maintenance index, and transmitting the guiding record back to the feature extraction unit to form a closed loop.
Description
Technical Field
The invention relates to the technical field of power inspection data evaluation, in particular to an artificial intelligent evaluation algorithm based on a power inspection scene.
Background
The power inspection refers to periodic inspection and maintenance work of key infrastructures such as transmission lines, substations, power distribution equipment and the like. Inspection activities are typically performed by specialized inspection personnel, but with the development of technology, the use of automated tools such as robotics, robots, and sensors is becoming more common. Detailed inspection plans including inspection routes, schedules, required tools and equipment, and security measures need to be formulated before inspection. At the same time, historical data and reports of previous inspection are analyzed to determine areas of significant interest. The inspection content comprises visual inspection, thermal imager detection, electrical test and data collection, and a large amount of data is analyzed by using a computer learning algorithm to evaluate and predict equipment faults and power grid operation trends from multiple dimensions. Regular power inspection is an important component of power grid management, ensures the reliability and safety of a power system, can find and solve problems in time, and realizes the transition from passive rush repair to active operation and maintenance, thereby improving the overall performance and efficiency of the power grid.
At present, the traditional power inspection evaluation algorithm relies on manual design standards to extract data features, lacks sufficient capacity to extract deep features of data, limits the effectiveness of identifying defects of complex inspection scenes, and further depends on manual intervention to ensure the accuracy of evaluation results when facing new power failure conditions, and has poor robustness of an identification model and low evaluation efficiency.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an artificial intelligent evaluation algorithm based on a power inspection scene, which has the advantages of high data feature extraction quality, high intelligent evaluation accuracy, strong applicability and the like, and solves the problems of the lack of deep feature extraction capability, low evaluation result accuracy and the like of the traditional power inspection evaluation algorithm.
In order to achieve the above purpose, the present invention provides the following technical solutions: the artificial intelligent evaluation algorithm based on the power inspection scene carries out calculation evaluation through an intelligent inspection evaluation system, the intelligent inspection evaluation system comprises a data acquisition module, an intelligent analysis module and an inspection management module, and the artificial intelligent evaluation algorithm based on the power inspection scene comprises the following steps:
The method comprises the steps that firstly, a data acquisition module acquires an image data set and an electric data set through a camera device, a thermal imager and an electric detection device, and meanwhile, the data acquisition module acquires a reference data set according to a database, combines the image data set and the electric data set, screens and generates an effective characteristic data set Yxtz, and transmits the effective characteristic data set to an intelligent analysis module through a network;
Step two, the intelligent analysis module collects variable data sets through a large data platform, calculates and generates an evaluation model Pgmx by combining a reference data set, substitutes an effective characteristic data set Yxtz into the evaluation model Pgmx, evaluates and generates an operation and maintenance index Ywzs, and transmits the operation and maintenance index Ywzs to the inspection management module;
and thirdly, guiding a manager to carry out equipment maintenance by the inspection management module according to the operation and maintenance index Ywzs, and transmitting the guiding record back to the feature extraction unit to form a closed loop.
Preferably, the data acquisition module comprises an image acquisition unit, an electric acquisition unit and a feature extraction unit, wherein the image acquisition unit is connected with the photographing device and the thermal imager through a network to acquire an image dataset in real time and number the image dataset, and the image dataset is TX n and corresponds to an image shot by electric inspection.
Preferably, the electrical collection unit is connected with the electrical detection device through a network to collect and number an electrical data set, wherein the electrical data set is DQ n and corresponds to the resistance test result data.
Preferably, the feature extraction unit collects and numbers a reference data set through a network connection database, the reference data set is composed of a reference image standard data set, a reference electric power operation data set, a reference evaluation model, a reference maintenance standard data set and a reference record standard data set, the reference data sets are numbered as CK tx、CKdq、CKyx、CKmx、CKjx and CK jl,CKtx corresponding to the reference image standard data set of the appearance of the electric equipment, CK dq corresponding to the reference electric standard data set of the electric equipment electric detection, CK yx corresponding to the reference electric power operation data set of the electric equipment in the working state, CK mx corresponding to the reference evaluation model of the electric equipment in the historical inspection evaluation, CK jx represents the reference maintenance standard data set of the power equipment failure replacement part, CK jl corresponding to the reference record standard data set of the intelligent inspection evaluation system data backtracking.
Preferably, the feature extraction unit generates the valid feature data set Yxtz by screening according to the image dataset, the electrical dataset and the reference dataset, and the screening generation formula is as follows:
Yxtz＝(TXn∩CKtx)∪(DQn∩CKdq)∪[(TXn∪DQn)∩CKyx]
In the formula, yxtz represents an effective characteristic data set, (TX n∩CKtx) represents high-quality characteristic data which accords with a reference image standard and can effectively represent the actual physical state and the thermal imaging state of the power equipment in the image data set, (DQ n∩CKdq) represents high-quality characteristic data which accords with the reference electric standard and can effectively detect the actual electric performance of the power equipment in the electric data set, and [ (TX n∪DQn)∩CKyx ] represents that when the power equipment executes the reference operation data state, the image data set and the electric data set acquire the effective characteristic data representing the load current, the voltage level and the heating state.
Preferably, the intelligent analysis module comprises a variable analysis unit and a constant analysis unit, wherein the variable analysis unit is connected with a large data platform through a network to collect variable data sets in real time and number the variable data sets, the variable data sets are BL 1、BL2、BL3、…BLn, and a plurality of key factors which influence the large fluctuation of the power generation variable of the power equipment are corresponding.
Preferably, the variable analysis unit generates the evaluation model Pgmx according to the variable dataset and the reference dataset, and transmits the evaluation model to the constant analysis unit, and the calculation formula is as follows:
in the formula, pgmx represents an evaluation model, 0.1BL n+0.2BLn+1+0.3BLn+2+0.4BLn+3 represents an average number of key variables which influence the overall performance of the power equipment under the natural environment under the condition of different weight addition, Representing an evaluation model generated by deep learning of a reference evaluation model according to the weight average of the key variables.
Preferably, the constant analysis unit substitutes the valid characteristic data set Yxtz into the evaluation model Pgmx, and evaluates and generates the operation and maintenance index Ywzs, and the calculation formula is as follows:
Wherein Ywzs denotes an operation and maintenance index, θ denotes an error constant reserved in the evaluation process, Representing the operational index evaluated in turn for all data in the active feature data set.
Preferably, the inspection management module comprises an inspection guiding unit and a tracking management unit, wherein the inspection guiding unit guides a manager to carry out equipment inspection by comparing with a reference inspection standard data set CK jx according to an operation and maintenance index Ywzs.
Preferably, the tracking management unit stores the guide record according to the reference record standard data set CK jl, and returns the guide record to the feature extraction unit through the network to form a closed loop, and the feature extraction unit stores the data into the reference power operation data set according to the guide record.
Compared with the prior art, the invention provides an artificial intelligent evaluation algorithm based on a power inspection scene, which has the following beneficial effects:
1. According to the invention, the image acquisition unit, the electric acquisition unit and the characteristic extraction unit are arranged through the data acquisition module, the image data set, the electric data set and the reference data set are acquired through the camera device, the thermal imager, the electric detection device and the database, the effective characteristic data set Yxtz is generated through screening, the data are subjected to normalized cleaning, impurity removal and distortion data separation, the data characteristic extraction quality is high, and more reliable and accurate data support is provided for subsequent analysis and evaluation.
2. According to the invention, a variable analysis unit and a constant analysis unit are arranged through an intelligent analysis module, the variable analysis unit acquires variable data sets in real time through a large data platform, the conditions of lightning stroke, high temperature or accident and the like which affect the overall performance of the power equipment occur in numbered natural environments, the reference evaluation model with theoretical basis is combined with a reference data set, an evaluation model Pgmx is calculated and generated, key variables clamped by different weights improve the expansibility of a deep learning evaluation model, the flexibility and applicability to complex conditions are high, the constant analysis unit substitutes an effective characteristic data set Yxtz into the evaluation model Pgmx, an operation and maintenance index Ywzs is evaluated and generated, a plurality of dimensions such as the abrasion degree of parts, the residual life, the safety risk and the quality stability are found, a patrol management module guides management personnel to carry out equipment overhaul according to the operation and maintenance index Ywzs, guides records are returned to a feature extraction unit to form a closed loop, the patrol new data features of each round can be combined with historical record screening to identify effective features, and the intelligent evaluation accuracy is high in applicability is ensured.
Drawings
FIG. 1 is a step diagram of the algorithm of the present invention.
FIG. 2 is a schematic diagram of the system of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, an artificial intelligence evaluation algorithm based on a power inspection scene performs calculation evaluation through an intelligent inspection evaluation system, wherein the intelligent inspection evaluation system comprises a data acquisition module, an intelligent analysis module and an inspection management module, and the artificial intelligence evaluation algorithm based on the power inspection scene comprises the following steps:
Step one, the data acquisition module acquires an image dataset and an electric dataset through a camera device, a thermal imager and an electric detection device, the data acquisition module acquires a reference dataset according to a database, the data acquisition module respectively numbers the image dataset, the electric dataset and the reference dataset through an image acquisition unit, an electric acquisition unit and a feature extraction unit, the image dataset numbers are TX n and correspond to images shot by electric inspection, the image dataset covers the line appearance, the tower appearance, the insulator appearance, the transformer appearance and the thermal imaging image of parts of the electric equipment, the electric dataset numbers are DQ n and correspond to resistance test result data, the electric dataset covers the insulation resistance test value and the grounding resistance test value of the electric equipment, the reference data set consists of a reference image standard data set, a reference electric power operation data set, a reference evaluation model, a reference maintenance standard data set and a reference record standard data set, wherein the reference data sets are numbered CK tx、CKdq、CKyx、CKmx、CKjx and CK jl, the numbers of the reference data sets correspond to the reference image standard data set, the reference electric power operation data set, the reference evaluation model, the reference maintenance standard data set and the reference record standard data set in sequence, the reference image standard data set CK tx covers a line reference appearance image of the electric power equipment, a reference tower appearance image, a reference insulator appearance image, a reference transformer appearance image and a part thermal imaging reference image, the reference electric power operation data set CK dq covers a load current value in a normal operation state of the electric power equipment, a ground resistance test reference value, and a reference electric power operation data set CK yx covers a load current value in a normal operation state of the electric power equipment, the voltage level value and the heating temperature value, the reference evaluation model CK mx covers a calculation formula group of a historical power inspection evaluation model, the reference inspection standard data set CK jx covers professional maintenance operation details and inspection optimization periods corresponding to fault hidden trouble problems, the reference record standard data set CK jl covers a data record template of power equipment historical maintenance replacement, the characteristic extraction unit screens and generates an effective characteristic data set Yxtz according to an image data set, an electric data set and a reference data set, and the effective characteristic data set Yxtz is transmitted to an intelligent analysis module through a network, and the screening and generating formula is as follows:
Yxtz＝(TXn∩CKtx)∪(DQn∩CKdq)∪[(TXn∪DQn)∩CKyx]
In the formula, yxtz represents an effective characteristic data set, (TX n∩CKtx) represents high-quality characteristic data which accords with a reference image standard and can effectively represent an actual physical state and a thermal imaging state of the power equipment in an image data set, an intersection symbol can be quickly matched with a common part of the two groups of data sets, (DQ n∩CKdq) represents high-quality characteristic data which accords with the reference electric standard and can effectively detect the actual electric performance of the power equipment in an electric data set, the intersection symbol can be quickly matched with the common part of the two groups of data sets, [ (TX n∪DQn)∩CKyx ] represents that when the power equipment executes the reference operation data state, the image data set and the electric data set acquire effective characteristic data representing load current, voltage level and heating state, the integrity of the two groups of data sets can be ensured by the intersection symbol, and according to the effective characteristic data set Yxtz, the normalization cleaning and impurity removal and distortion data separation are carried out, the effective characteristic extraction quality is higher, and more reliable and accurate data support is provided for subsequent analysis and evaluation;
Step two, the intelligent analysis module comprises a variable analysis unit and a constant analysis unit, the intelligent analysis module collects variable data sets through a large data platform, the variable analysis unit numbers the variable data sets, the variable data sets are BL 1、BL2、BL3、…BLn, a plurality of key factors which influence the power generation variable of the power equipment to greatly fluctuate are corresponding, for example, the conditions of lightning stroke, high temperature or accident and the like which influence the overall performance of the power equipment occur in a natural environment, the reference data sets are combined, an evaluation model Pgmx is calculated and generated, and then the evaluation model Pgmx is transmitted to the constant analysis unit, and the calculation formula is as follows:
in the formula, pgmx represents an evaluation model, 0.1BL n+0.2BLn+1+0.3BLn+2+0.4BLn+3 represents an average number of key variables which influence the overall performance of the power equipment under the natural environment under the condition of different weight addition, The evaluation model generated by deep learning of the reference evaluation model according to the weight average number of the key variables is represented, the reference evaluation model with a theoretical basis is utilized according to the evaluation model Pgmx, the expansibility of the deep learning evaluation model is improved by combining the key variables clamped by different weights, and the flexibility and the applicability to complex situations are high;
the constant analysis unit substitutes the effective characteristic data set Yxtz into the evaluation model Pgmx, evaluates and generates the operation and maintenance index Ywzs, and transmits the operation and maintenance index Ywzs to the inspection management module, wherein the calculation formula is as follows:
Wherein Ywzs denotes an operation and maintenance index, θ denotes an error constant reserved in the evaluation process, Representing operation and maintenance indexes which are evaluated sequentially for all data in the effective characteristic data set, intelligently evaluating high-quality data characteristics according to the operation and maintenance indexes Ywzs, finding deep potential problems from multiple dimensions such as the abrasion degree of parts, the residual life, the safety risk, the quality stability and the like, and ensuring high accuracy and strong applicability of an evaluation result;
And the inspection management module comprises an inspection guiding unit and a tracking management unit, wherein the inspection guiding unit guides a manager to carry out equipment inspection by comparing with a reference inspection standard data set CK jx according to an operation and maintenance index Ywzs, guides the manager to carry out professional maintenance and provides a detailed optimization period and maintenance flow, ensures the safety management of a power grid system, the tracking management unit stores guiding records according to a reference record standard data set CK jl, and transmits the guiding records to the characteristic extraction unit through a network to form a closed loop, and the characteristic extraction unit stores data into a reference power operation data set according to the guiding records, so that the inspection new data characteristics of each round can be combined with the history record to screen and identify effective characteristics.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. An artificial intelligence evaluation algorithm based on a power inspection scene is characterized in that: the artificial intelligence evaluation algorithm based on the power inspection scene carries out calculation evaluation through an intelligent inspection evaluation system, the intelligent inspection evaluation system comprises a data acquisition module, an intelligent analysis module and an inspection management module, and the artificial intelligence evaluation algorithm based on the power inspection scene comprises the following steps:
The method comprises the steps that firstly, a data acquisition module acquires an image data set and an electric data set through a camera device, a thermal imager and an electric detection device, and meanwhile, the data acquisition module acquires a reference data set according to a database, combines the image data set and the electric data set, screens and generates an effective characteristic data set Yxtz, and transmits the effective characteristic data set to an intelligent analysis module through a network;
Step two, the intelligent analysis module collects variable data sets through a large data platform, calculates and generates an evaluation model Pgmx by combining a reference data set, substitutes an effective characteristic data set Yxtz into the evaluation model Pgmx, evaluates and generates an operation and maintenance index Ywzs, and transmits the operation and maintenance index Ywzs to the inspection management module;
and thirdly, guiding a manager to carry out equipment maintenance by the inspection management module according to the operation and maintenance index Ywzs, and transmitting the guiding record back to the feature extraction unit to form a closed loop.
2. The artificial intelligence evaluation algorithm based on the power inspection scene according to claim 1, wherein: the data acquisition module comprises an image acquisition unit, an electric acquisition unit and a feature extraction unit, wherein the image acquisition unit is connected with the photographing device and the thermal imager through a network to acquire an image data set in real time and number the image data set, and the image data set is TX n and corresponds to an image shot by electric power inspection.
3. The artificial intelligence evaluation algorithm based on the power inspection scene according to claim 2, wherein: the electrical collection unit is connected with the electrical detection device through a network to collect an electrical data set and number, and the electrical data set is DQ n and corresponds to the resistance test result data.
4. The artificial intelligence evaluation algorithm based on the power inspection scene according to claim 3, wherein: the feature extraction unit is connected with the database through a network to acquire and number a reference data set, the reference data set consists of a reference image standard data set, a reference electric power operation data set, a reference evaluation model, a reference overhaul standard data set and a reference record standard data set, the reference data sets are numbered as CK tx、CKdq、CKyx、CKmx、CXjx and CK jl,CKtx corresponding to the reference image standard data set of the appearance of the electric equipment, CK dq corresponding to the reference electric standard data set of the electric equipment electric detection, CK yx corresponding to the reference electric power operation data set in the working state of the electric equipment, CK mx corresponding to the reference evaluation model of the historical inspection evaluation electric equipment, CK jx represents the reference overhaul standard data set of the electric equipment fault replacement part, CK jl corresponding to the reference record standard data set of the intelligent inspection evaluation system data backtracking.
5. The artificial intelligence evaluation algorithm based on the power inspection scene according to claim 4, wherein: the feature extraction unit generates an effective feature data set Yxtz through screening according to the image data set, the electric data set and the reference data set, and a screening generation formula is as follows:
Yxtz＝(TXn∩CKtx)∪(DQn∩CKdq)∪[(TXn∪DQn)∩CKyx]
In the formula, yxtz represents an effective characteristic data set, (TX n∩CKtx) represents high-quality characteristic data which accords with a reference image standard and can effectively represent the actual physical state and the thermal imaging state of the power equipment in the image data set, (DQ n∩CKdq) represents high-quality characteristic data which accords with the reference electric standard and can effectively detect the actual electric performance of the power equipment in the electric data set, and [ (TX n∪DQn)∩CKyx ] represents that when the power equipment executes the reference operation data state, the image data set and the electric data set acquire the effective characteristic data representing the load current, the voltage level and the heating state.
6. The artificial intelligence evaluation algorithm based on the power inspection scene according to claim 5, wherein: the intelligent analysis module comprises a variable analysis unit and a constant analysis unit, wherein the variable analysis unit is connected with a big data platform through a network to collect variable data sets in real time and number the variable data sets, the variable data sets are numbered as BL 1、BL2、BL3、…BLn, and a plurality of key factors which influence the large fluctuation of the power generation variable of the power equipment are correspondingly used.
7. The artificial intelligence evaluation algorithm based on the power inspection scene according to claim 6, wherein: the variable analysis unit calculates and generates an evaluation model Pgmx according to the variable data set and the reference data set, and transmits the evaluation model to the constant analysis unit, and the calculation formula is as follows:
in the formula, pgmx represents an evaluation model, 0.1BL n+0.2BLn+1+0.3BLn+2+0.4BLn+3 represents an average number of key variables which influence the overall performance of the power equipment under the natural environment under the condition of different weight addition, Representing an evaluation model generated by deep learning of a reference evaluation model according to the weight average of the key variables.
8. The artificial intelligence evaluation algorithm based on the power inspection scene according to claim 7, wherein: the constant analysis unit substitutes the effective characteristic data set Yxtz into the evaluation model Pgmx, and evaluates and generates an operation and maintenance index Ywzs, and the calculation formula is as follows:
Wherein Ywzs denotes an operation and maintenance index, θ denotes an error constant reserved in the evaluation process, Representing the operational index evaluated in turn for all data in the active feature data set.
9. The artificial intelligence evaluation algorithm based on the power inspection scene according to claim 8, wherein: the inspection management module comprises an inspection guiding unit and a tracking management unit, wherein the inspection guiding unit guides a manager to carry out equipment inspection by comparing with a reference inspection standard data set CK jx according to an operation and maintenance index Ywzs.
10. The artificial intelligence evaluation algorithm based on the power inspection scene according to claim 9, wherein: the tracking management unit stores the guide record according to the reference record standard data set CK jl, and transmits the guide record back to the characteristic extraction unit through the network to form a closed loop, and the characteristic extraction unit stores the data into the reference power operation data set according to the guide record.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410232701.1A CN118038272A (en) | 2024-03-01 | 2024-03-01 | Artificial intelligence evaluation algorithm based on electric power inspection scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410232701.1A CN118038272A (en) | 2024-03-01 | 2024-03-01 | Artificial intelligence evaluation algorithm based on electric power inspection scene |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118038272A true CN118038272A (en) | 2024-05-14 |
Family
ID=91001954
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410232701.1A Pending CN118038272A (en) | 2024-03-01 | 2024-03-01 | Artificial intelligence evaluation algorithm based on electric power inspection scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118038272A (en) |
-
2024
- 2024-03-01 CN CN202410232701.1A patent/CN118038272A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106019084B (en) | Medium-voltage power distribution network disconnection fault diagnosis method based on power distribution and utilization data correlation | |
| CN109800697B (en) | Transformer target detection and appearance defect identification method based on VGG-net style migration | |
| CN111160791A (en) | Abnormal user identification method based on GBDT algorithm and factor fusion | |
| CN113222036B (en) | Automatic defect identification method and device for high-voltage cable grounding system | |
| CN113095189B (en) | Machine vision and data analysis-based intelligent monitoring and management system for operating environment safety of power system transformer substation | |
| CN110766313A (en) | Cable tunnel comprehensive state evaluation method based on operation and maintenance system | |
| CN116986246A (en) | Intelligent inspection system and method for coal conveying belt | |
| CN116308883A (en) | Regional power grid data overall management system based on big data | |
| CN117391357B (en) | Scheduling self-checking system for power grid scheduling operation management based on big data | |
| CN118038295A (en) | Real-time online identification system for defects of power transmission line | |
| CN117350964A (en) | Cross-modal multi-level feature fusion-based power equipment detection method | |
| CN117277566A (en) | Power grid data analysis power dispatching system and method based on big data | |
| CN117350447A (en) | Multisource heterogeneous power data fusion algorithm applicable to power grid | |
| CN116881661A (en) | Performance automatic analysis method and system based on low-voltage power capacitor | |
| CN117057666A (en) | Distribution quality evaluation method and system for digital distribution network | |
| CN111678558A (en) | Infrared thermal imaging oil level and temperature monitoring system and method applied to oil filling equipment | |
| CN118038272A (en) | Artificial intelligence evaluation algorithm based on electric power inspection scene | |
| CN116545111A (en) | Information interaction system based on internal and external networks of transformer substation | |
| CN114167837B (en) | Intelligent fault diagnosis method and system for railway signal system | |
| CN113780224B (en) | Unmanned inspection method and system for transformer substation | |
| CN115796832A (en) | Comprehensive evaluation method for health state of power transformation equipment based on multidimensional parameters | |
| CN115587016A (en) | Power equipment operation analysis method | |
| Tang et al. | Fault diagnosis of the external insulation infrared images based on Mask Region convolutional neural network and perceptual hash joint algorithm | |
| CN115693692A (en) | Voltage qualification rate improving method based on power distribution network voltage data analysis | |
| CN116703246B (en) | Intelligent management method and system for power distribution system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |