Database fusion method and monitoring method for electric power environment risk based on remote sensing technology

Abstract

The invention belongs to the technical field of data processing, and particularly relates to a remote sensing technology-based database fusion method for power environment risks, which comprises the following steps of: analyzing each record in a dynamic risk database one by one by taking a historical database as a benchmark; if the two databases both record the specific risk target, the existing risk attribute of the historical database is reserved, and the missing attribute is copied to the historical database from the dynamic risk database; if only the dynamic risk database records the specific risk target, adding the complete record of the dynamic risk database to a historical database; and if only the historical database records the specific risk target, the attributes are verified, supplemented and perfected based on the monitoring area where the power equipment and the risk target are located. Through the method, the risk attribute coverage rate can be effectively improved, the problems of incomplete data and matching delay caused by data splitting in a traditional method are solved, the cost is reduced, and the accuracy is ensured. The invention further provides a remote sensing technology-based power environment risk monitoring method.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and particularly relates to a database fusion method and a monitoring method for power environment risks based on remote sensing technology. Background Art

[0002] Currently, in the process of monitoring the safe and stable operation of power equipment, it is usually necessary to integrate multi-source data to achieve a comprehensive risk assessment. The above multi-source data generally includes a historical database as a reference and a dynamic risk database obtained through real-time monitoring. In the process of fusing the above two types of data, the following problems often exist: The historical database and the dynamic risk database are often stored independently, and there is a lack of an effective fusion mechanism between systems. The historical records and real-time monitoring data of the same risk source may be scattered in multiple databases, resulting in duplicate data entry or missing key information. In addition, when the risk attribute descriptions of the same target in different databases are inconsistent, the existing methods are difficult to effectively retain the continuity of historical data, and may also miss the supplement of new risk attributes. For new risk targets existing in the dynamic database but not covered by the reference database, the existing technology lacks an automated extension mechanism, relying on manual verification, which leads to low efficiency and is error-prone.

[0003] The above problems often cause the monitoring of the environmental risks around power equipment to be inaccurate due to data incompleteness, risk warning delays due to the inability to quickly match multi-source data, and waste of labor costs due to manual verification of data. Summary of the Invention

[0004] The present invention provides a database fusion method and a monitoring method for power environment risks based on remote sensing technology, which can effectively solve the problems in the background art.

[0005] To achieve the above object, the technical solution of the present invention is as follows: A database fusion method for power environment risks based on remote sensing technology is used to fuse a historical database and a dynamic risk database; The historical database stores the first spatial information and the first attribute information of several power equipment, and the first attribute information includes historical risk attribute information registered for the power equipment; The dynamic risk database stores the second spatial information and target risk attribute information of several risk targets, and both the historical risk attribute information and the target risk attribute information are composed of several risk attributes; The fusion method includes: Taking the historical database as a reference, analyzing each record in the dynamic risk database one by one; If both the historical database and the dynamic risk database have records of specific risk targets, the existing risk attributes in the historical database shall be retained, and if the risk attributes missing in the historical database are reflected in the dynamic risk database, they shall be copied from the dynamic risk database into the historical database; If only the dynamic risk database has records of specific risk targets, the complete records in the dynamic risk database shall be newly added to the historical database; If only the historical database has records of specific risk targets, the attributes shall be verified, supplemented and perfected based on the power equipment and the monitoring area where the risk targets are located.

[0006] The power environment risk monitoring method based on remote sensing technology adopts the database fusion method for power environment risk based on remote sensing technology as described above; The first spatial information is obtained through the distribution map of power equipment, and the first attribute information is obtained through the inventory information of power equipment and the historically registered risk data; The second spatial information and the target risk attribute information are obtained by analyzing the remote sensing images in the monitoring area; The power environment risk is monitored through the database completed by fusion.

[0007] Further, the risk attributes at least include risk name, relative position of the risk, risk level and risk area.

[0008] Further, the first spatial information and the first attribute information are converted into spatial vector graphics through forward projection calculation and stored in the historical database.

[0009] Further, the analysis of the remote sensing images includes: Extracting the specific risk targets in the remote sensing images, and forming a risk spatial distribution map of the environment around the power equipment based on the extraction results as the second spatial information; For the risk spatial distribution map, the conversion of the position coordinates of the specific risk targets to the coordinates of the power equipment is completed, and based on the conversion results, combined with the spatial vector graphics for analysis, the target risk attribute information is extracted.

[0010] Further, the base map image data is stored in the existing monitoring and management platform, and the remote sensing images are aligned based on the base map image data through the geometric correction method.

[0011] Further, the extraction of the specific risk targets in the remote sensing images includes: Using the remote sensing image processing algorithm to automatically train samples for preliminary target extraction; Manually verifying the preliminary extracted targets in an artificial interaction manner.

[0012] Furthermore, the database after fusion is used to monitor the power environment risk, including: Processing the real-time and historical remote sensing images; After the processing is completed, with respect to the historical remote sensing images, extracting the changed areas in the real-time remote sensing images; Performing shape regularization processing on the changed areas to form a changed vector map for risk target detection; Fusing and updating the changed vector map with the database after fusion is completed.

[0013] Furthermore, processing the real-time and historical remote sensing images includes georeferencing registration.

[0014] Furthermore, processing the real-time and historical remote sensing images includes image color equalization and unified processing.

[0015] Furthermore, storing the base map image data in the existing monitoring and management platform; Before fusing and updating the changed vector map with the database after fusion is completed, it further includes: manually verifying the changed vector map in combination with the base map image data.

[0016] Through the technical solution of the present invention, the following technical effects can be achieved: In the present invention, for the records where the historical database and the dynamic risk database coexist, the authority of the historical data is retained, and at the same time, the missing attributes are incrementally supplemented from the dynamic risk database; for the records that only exist in the dynamic risk database, they are automatically added to the historical database, which can avoid manual omission; through the above measures, the coverage rate of risk attributes can be effectively improved, solving the problems of data incompleteness and matching delay caused by data fragmentation in the traditional method, and ensuring the accuracy of monitoring while reducing the labor cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0018] Figure 1 It is a flowchart of a database fusion method for power environment risk based on remote sensing technology.

[0019] Figure 2 It is a flowchart of a power environment risk monitoring method based on remote sensing technology. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0022] Embodiment 1

[0023] A database fusion method for power environment risks based on remote sensing technology, as Figure 1 shown, is used to fuse a historical database and a dynamic risk database; the historical database stores the first spatial information and the first attribute information of several power equipment, and the first attribute information includes the historical risk attribute information registered for the power equipment; the dynamic risk database stores the second spatial information and the target risk attribute information of several risk targets, and both the historical risk attribute information and the target risk attribute information are composed of several risk attributes; The fusion method includes: Taking the historical database as a benchmark, analyze each record in the dynamic risk database one by one; If both the historical database and the dynamic risk database have records for a specific risk target, retain the existing risk attributes in the historical database, and if the risk attributes missing in the historical database are reflected in the dynamic risk database, copy them from the dynamic risk database into it; If only the dynamic risk database has a record for a specific risk target, add the complete record of the dynamic risk database to the historical database; If only the historical database has a record for a specific risk target, verify, supplement and improve the attributes based on the monitoring areas where the power equipment and the risk target are located.

[0024] In the above technical solution, for the records coexisting in the historical database and the dynamic risk database, the authority of the historical data is retained, and at the same time, the missing attributes are incrementally supplemented from the dynamic risk database; for the records existing only in the dynamic risk database, they are automatically added to the historical database, which can avoid manual omission; through the above measures, the coverage rate of risk attributes can be effectively improved, solving the problems of data incompleteness and matching delay caused by data fragmentation in traditional methods, and ensuring the accuracy of monitoring while reducing labor costs.

[0025] After the first spatial information of power equipment and the second spatial information of risk targets are obtained, it can make the judgment of whether the risk targets are the same target more accurate. Based on accurate spatial coordinate matching, it can help analyze the clustering of risk targets, locate the causes of risks, and predict the evolution trend, etc.

[0026] Embodiment 2

[0027] A method for monitoring power environment risks based on remote sensing technology, such as Figure 2 shown, adopts the database fusion method for power environment risks based on remote sensing technology described in Embodiment 1; among them, the first spatial information is obtained through the distribution map of power equipment, and the first attribute information is obtained through the ledger information of power equipment and the historically registered risk data; the second spatial information and the target risk attribute information are obtained by analyzing the remote sensing images in the monitoring area. The specific process generally includes steps such as image data acquisition and preprocessing, risk target identification and interpretation, and risk attribute extraction, etc.; the power environment risks are monitored through the completed database. In this embodiment, the historical database is specifically used as the historical environment risk database DB1, and the basic data is sorted and stored in the database. The dynamic risk database is used as the power equipment surrounding environment risk database DB2 based on spatial information technology. After the two databases are fused, a comprehensive power equipment surrounding environment risk database DB3 is formed.

[0028] In this embodiment, the distribution map of power equipment, ledger information, and historically registered risk data are often stored in the existing monitoring and management platform; the distribution map can be accurate to the coordinates of the equipment and the spatial connection mode of the transmission lines between the equipment; the remote sensing images can be obtained at set intervals to capture the changes in the environment in real time, making up for the limitations of fixed-point monitoring.

[0029] As an optimization of the above embodiment, the risk attributes at least include the risk name, relative position of the risk, risk level, and risk area. Specifically, in the actual operating environment, most of the hidden dangers that invade power equipment are in the form of surfaces, such as plastic films, plastic greenhouses, or construction machinery. This classification name can be used as the risk name; while the relative position of the risk often needs to be determined based on a certain reference object, and specifically can be reflected by the distance value and offset of the risk target. The above two values are obtained based on the coordinates of a certain power equipment or other reference coordinates. For example, the distance value can refer to the distance from the centroid coordinate of the risk target to the coordinate of a certain power equipment; the plastic films, plastic greenhouses, or construction machinery described above are reflected in the form of surfaces during the identification process and have obvious boundary senses. The identification of the risk area can be obtained through image processing. This part is the prior art and will not be elaborated here. Of course, the above risk attributes are only specific examples of some attributes. When other risk attributes can be involved in the environmental risk monitoring of the present invention, they are also within the protection scope of the present invention.

[0030] Preferably, as in the above embodiments, the first spatial information and the first attribute information are converted into spatial vector graphics through forward projection and stored in the historical database. In this preferred solution, vector graphics are used to replace raster or text coordinates, and only geometric features and associated attribute fields are stored, which can effectively reduce the storage volume. Through spatial indexing, the later data query efficiency can be improved; during the implementation process, vector graphics support coordinate system conversion and unify the multi-source spatial data benchmark, which can solve the matching deviation caused by the coordinate system difference between historical data and dynamic data.

[0031] Preferably, as in the above embodiments, the analysis of the remote sensing image includes: A1: Extract specific risk targets in the remote sensing image and form a risk spatial distribution map of the environment around the power equipment based on the extraction results as the second spatial information; using image processing technology, the optimization solution can identify planar or other forms of risk targets from the remote sensing image and convert them into a clear risk spatial distribution map. This process provides more comprehensive and detailed information for the risk assessment of the environment around the power equipment, makes the distribution of risk sources more intuitive, and improves the spatial accuracy of monitoring; A2: For the risk spatial distribution map, complete the conversion of the position coordinates of specific risk targets to the coordinates of the power equipment, and perform analysis by combining the conversion results with the spatial vector graphics to extract the target risk attribute information. This step can further improve the spatial correlation between the risk targets and the power equipment. Through conversion, the system can accurately judge the position of the risk targets relative to the power equipment and eliminate the matching deviation caused by inconsistent coordinate systems or spatial errors.

[0032] Combining the spatial vector graphics of the power equipment and the risk spatial distribution map can more effectively analyze the relative positions of risk targets, which is particularly crucial for judging whether risk targets are repeated between different databases; during the database merging process, if both the historical database and the dynamic risk database have records of specific risk targets, the conversion of spatial coordinates unifies the position relationship of the risk targets in the two databases. This not only helps to ensure that there is no error in the docking of the two records, but also can avoid the problem of inaccurate data matching caused by inconsistent coordinate systems or spatial errors through precise comparison of spatial positions.

[0033] As an optimization of the above embodiments, store the base map image data in the existing monitoring and management platform, and align the remote sensing image based on the base map image data through a geometric correction method. The geometric correction method corrects the remote sensing image so that its spatial position is consistent with the coordinate system of the base map image data. Since the remote sensing image itself may have geometric distortions due to factors such as imaging angle and terrain influence, geometric correction can correct these distortions to ensure that the spatial information of the remote sensing image is accurately aligned with the base map image data stored in the monitoring platform. The aligned remote sensing image and base map can be processed under the same coordinate reference, which can ensure that the spatial relationship between the risk targets in the image and the existing spatial vector graphics is correct. This process can eliminate the spatial errors caused by image distortion, improve the accuracy of the data, and ensure that there is no error transmission in subsequent analyses.

[0034] During specific implementation, extracting specific risk targets from the remote sensing image may specifically include: B1: Automatically train samples using remote sensing image processing algorithms to preliminarily extract targets; B2: Manually check the preliminarily extracted targets based on the way of human-computer interaction.

[0035] In the above process, the remote sensing image processing algorithm can specifically adopt convolutional neural network, support vector machine, random forest, etc., to learn and train the existing sample data. The system automatically identifies specific risk targets in the remote sensing image, such as planar targets like plastic films, plastic greenhouses, construction machinery, etc. The extraction results form preliminary target candidate areas for subsequent construction of spatial distribution maps. During the human-computer interaction process, the probability of misidentification or mislabeling can be significantly reduced, ensuring that the new records are more authoritative and accurate when merged into the historical database.

[0036] As an optimization of the above embodiments, monitoring the power environment risk through the completed database fusion includes: C1: Process the real-time and historical remote sensing images; C2: After the processing is completed, extract the changed areas in the real-time remote sensing image relative to the historical remote sensing image; C3: Regularize the shapes of the changed areas to form a changed vector map for risk target detection; C4: Fuse and update the changed vector map with the completed database fusion.

[0037] In the above implementation process, after the acquisition and preprocessing of the image data are completed, after the target change detection and the formation of the changed vector map for target detection, further manual checking can be carried out, and a work order for on-site verification and processing of risks can be pushed, and on-site verification and filling can be carried out. Of course, on-site tracking and inspection of risks are also preferably carried out.

[0038] By extracting the changed areas from real-time and historical remote sensing images, any new changes or potential risks in the environment around power equipment can be detected in real time; the shape regularization process makes the contours of the changed areas clearer and more standardized, enabling the system to more precisely identify the specific forms and attributes of the changed areas.

[0039] In the present invention, based on the spatial vector graph as the benchmark, the database completed by fusing based on this benchmark can provide accurate geospatial information, enabling seamless docking of the risk targets after the changed area extraction and shape regularization process with the existing power equipment and environmental data. Through this spatial data integration, the system can achieve efficient and accurate spatial matching and updating, ensuring the precise fusion of all newly added risk targets with historical data. This refined spatial analysis not only improves the positioning and morphological analysis capabilities of risk targets but also enhances the automation degree of database updating, significantly improving the timeliness and accuracy of the monitoring system.

[0040] As an optimization of the above embodiment, processing the real-time and historical remote sensing images includes georeference registration; georeference registration ensures the alignment of the spatial coordinates of the real-time and historical images, eliminating the spatial errors caused by differences in shooting angles, times, or geographical locations between different images, enabling the two to be compared and analyzed in a unified coordinate system. This registration accuracy helps to accurately identify geographical changes, especially when monitoring the environment around power equipment, ensuring the consistency of targets and risk areas.

[0041] On the basis of the above embodiment, the real-time and historical remote sensing images can be further processed to include image color equalization and unification processing. Image color equalization and unification processing eliminate the color differences caused by lighting, weather conditions, or equipment differences, making the colors of the real-time image and the historical image visually consistent, avoiding the influence of color differences on the accuracy of image analysis and target recognition. Color consistency improves the comparability between images, helps to clearly distinguish different risk areas or changed targets, and enhances the accuracy and reliability of data analysis.

[0042] To ensure the effect of fusing the change vector map with the completed database, the base map image data is stored in the existing monitoring and management platform. After storage, before fusing and updating the change vector map with the completed database, it also includes: manually verifying the change vector map in combination with the base map image data. Manually verifying the change vector map in combination with the base map image data can significantly improve the accuracy of change area recognition, correct the errors in automated extraction through manual intervention, and ensure that the change vector map reflects the real environmental changes. In addition, manual verification strengthens data quality control, ensures data accuracy, avoids the influence of factors such as light changes or image distortion, and at the same time uses geographical context information to enhance the recognition of risk targets, providing a more comprehensive and accurate risk assessment. This combined visual interactive verification method reduces human errors and improves the data fusion accuracy, ultimately ensuring that the fusion update with the historical database is more accurate and reliable.

[0043] During the implementation process, fusing and updating the change vector map with the completed database includes adding records for newly added targets: handling the attribute status change of the implementation records of existing change targets: setting the problem records that cannot be improved in attributes through manual verification as items to be rechecked, formulating a hidden danger verification and handling plan, and pushing it to the mobile terminal for on-site recheck and problem handling. The on-site inspection personnel can conduct on-site recheck and supplement attribute information according to the above results; for the problems to be handled, the on-site inspection personnel can supplement relevant texts and photos of the handling process, complete the handling and record, and each handling forms a record, which is updated to the completed database DB3: for the newly discovered risk problems on-site, the on-site inspection personnel can add records and record attributes, fill in the handling records. The above processes can all be realized through the corresponding developed mobile terminal. Finally, the problem hidden danger status can be set according to the handling records, the detection target can be achieved, and the risk closed-loop management can be completed.

[0044] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification only illustrates the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A database fusion method for power environment risk based on remote sensing technology, characterized in that: Used to merge historical database and dynamic risk database; The historical database stores first spatial information and first attribute information of a number of electric power equipment, wherein the first attribute information includes historical risk attribute information registered for the electric power equipment; The dynamic risk database stores the second spatial information and target risk attribute information of a plurality of risk targets, wherein the historical risk attribute information and the target risk attribute information are both composed of a plurality of risk attributes; Fusion methods include: Based on the historical database, each record in the dynamic risk database is analyzed one by one; If both the historical database and the dynamic risk database have records for a specific risk target, the existing risk attributes in the historical database are retained, and if the risk attributes missing from the historical database are reflected in the dynamic risk database, they are copied from the dynamic risk database to the dynamic risk database; If only the dynamic risk database has records for a specific risk target, then the complete records of the dynamic risk database are added to the historical database; If only the historical database has records for a specific risk target, the attributes are verified, supplemented and improved based on the monitoring area where the power equipment and the risk target are located.

2. The power environment risk monitoring method based on remote sensing technology is characterized by: Adopting the database fusion method of power environment risk based on remote sensing technology as claimed in claim 1; The first spatial information is obtained through a distribution map of the power equipment, and the first attribute information is obtained through the ledger information and historically registered risk data of the power equipment; The second spatial information and target risk attribute information are obtained by analyzing remote sensing images within the monitoring area; The power environment risks are monitored through the integrated database.

3. The electric power environment risk monitoring method based on remote sensing technology according to claim 2 is characterized in that: The risk attributes include at least the risk name, the relative position of the risk, the risk level and the risk area.

4. The electric power environment risk monitoring method based on remote sensing technology according to claim 2 is characterized in that: The first spatial information and the first attribute information are converted into spatial vector graphics through projection calculation and stored in the historical database.

5. The method for monitoring electric power environment risk based on remote sensing technology according to claim 4 is characterized in that: Analyzing the remote sensing image includes: Extracting the specific risk target in the remote sensing image, and forming a risk space distribution map of the surrounding environment of the power equipment based on the extraction result as the second spatial information; With respect to the risk space distribution map, the conversion of the specific risk target location coordinates to the power equipment coordinates is completed, and the analysis is performed based on the conversion result in combination with the space vector graphics to extract the target risk attribute information.

6. The electric power environment risk monitoring method based on remote sensing technology according to claim 5 is characterized in that: The base map image data is stored in the existing monitoring management platform, and the remote sensing image is aligned through a geometric correction method based on the base map image data.

7. The method for monitoring electric power environment risk based on remote sensing technology according to claim 5 is characterized in that: Extracting the specific risk target from the remote sensing image includes: Use remote sensing image processing algorithms to automatically train samples for preliminary target extraction; The preliminary extracted targets are manually checked based on manual interaction.

8. The electric power environment risk monitoring method based on remote sensing technology according to claim 2 is characterized in that: The integrated database is used to monitor power environmental risks, including: Processing real-time and historical remote sensing images; After processing, the changed areas in the real-time remote sensing images are extracted relative to the historical remote sensing images; Performing shape regularization processing on the change area to form a change vector diagram for risk target detection; The change vector diagram is merged and updated with the merged database.

9. The electric power environment risk monitoring method based on remote sensing technology according to claim 8 is characterized in that: Real-time and historical remote sensing images are processed including geo-referencing.

10. The electric power environment risk monitoring method based on remote sensing technology according to claim 8 or 9, characterized in that: The real-time and historical remote sensing images are processed including image color balancing and unified processing.

11. The electric power environment risk monitoring method based on remote sensing technology according to claim 8 is characterized in that: Store base map image data in the existing monitoring and management platform; Before fusing and updating the change vector map with the fused database, the method further includes: manually checking the change vector map in combination with the base map image data.

Images