Water and electricity switching station deformation monitoring method and system based on unmanned aerial vehicle laser scanning

Abstract

The invention relates to the technical field of power station deformation monitoring, and provides a hydropower switching station deformation monitoring method and system based on unmanned aerial vehicle laser scanning, and the method comprises the steps: scanning a hydropower switching station through an airborne laser scanner, and obtaining original point cloud data; preprocessing the original point cloud data to obtain switching station point cloud data; performing three-dimensional model reconstruction on the hydropower switching station based on the switching station cloud data to obtain a hydropower switching station area three-dimensional model; establishing a deformation evaluation index model, and performing deformation analysis on the three-dimensional model of the hydropower switching station region through the deformation evaluation index model to obtain a deformation evaluation index of the hydropower switching station; the hydroelectric switching station is evaluated through the deformation risk level evaluation model and the deformation evaluation index, and the deformation risk level of the hydroelectric switching station is obtained; and according to the different deformation risk levels, corresponding dangerous case processing schemes are adopted for the hydroelectric switching station. According to the invention, the accuracy of deformation monitoring is improved, and the high-precision monitoring of the deformation of the water and electricity switching station is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of power station deformation monitoring, and in particular to a hydropower switch station deformation monitoring method and system based on unmanned aerial vehicle laser scanning. Background Art

[0002] As a key infrastructure in the power system, the structural safety and operational stability of the hydropower switch station are directly related to the reliable operation and power supply safety of the power system. Hydropower switch stations are prone to structural deformation, settlement and other problems during long-term operation. If these problems are not discovered and handled in time, they may lead to equipment failures and even safety accidents.

[0003] The existing technology usually uses fixed laser scanners or ground 3D scanners to monitor the deformation of hydropower switch stations. Although these devices can obtain deformation data, they have obvious deficiencies in data processing and error correction. Especially in complex actual monitoring environments, affected by environmental factors such as temperature and humidity and the material characteristics of equipment, the monitoring data often has large errors. At the same time, the existing technology lacks a systematic data processing mechanism and accurate error correction methods, making it difficult to ensure the accuracy of deformation monitoring results.

[0004] In view of the above problems, there is an urgent need for a deformation monitoring method and system for hydropower switch stations based on UAV laser scanning. Through adaptive statistical algorithms, multi-scale filtering and error correction data processing methods, the accuracy of deformation monitoring data can be improved to achieve high-precision monitoring of hydropower switch station deformation. Summary of the invention

[0005] In view of this, the present invention proposes a deformation monitoring method and system for a hydropower switch station based on UAV laser scanning, which solves the problem that in the existing technology, the monitoring data often has large errors in a complex actual monitoring environment due to the influence of environmental factors such as temperature and humidity and the material characteristics of the equipment.

[0006] The technical solution of the present invention is implemented as follows: In the first aspect, the present invention provides a method for monitoring deformation of a hydropower switch station based on drone laser scanning, comprising the following steps:

[0007] Scan the hydropower switch station with an airborne laser scanner to obtain raw point cloud data;

[0008] Preprocess the original point cloud data to obtain switch site cloud data;

[0009] Reconstruct the 3D model of the hydropower switch station based on the switch station cloud data to obtain the 3D model of the hydropower switch station area;

[0010] Establishing a deformation assessment index model, and performing deformation analysis on the three-dimensional model of the hydropower switch station area through the deformation assessment index model to obtain a deformation assessment index of the hydropower switch station;

[0011] The hydropower switch station is evaluated by using the deformation risk level evaluation model and the deformation evaluation index to obtain the deformation risk level of the hydropower switch station;

[0012] According to different deformation risk levels, corresponding risk handling plans are adopted for hydropower switch stations.

[0013] On the basis of the above technical solution, preferably, scanning the hydropower switch station by an airborne laser scanner to obtain the original point cloud data specifically includes:

[0014] According to the spatial layout and equipment distribution of the hydropower switch station, multiple scanning position points are set, and each scanning position point is connected according to the optimal scanning path to form a flight path, and the flight path covers the entire monitoring area of ​​the hydropower switch station;

[0015] The Beidou positioning system is used to locate the UAV's flight position in real time, and the UAV is controlled to fly along the described flight path. The UAV uses a laser scanner to continuously emit laser pulses and receive reflected signals during flight, converting the received signals into raw point cloud data and transmitting them to the ground workstation in real time.

[0016] On the basis of the above technical solution, preferably, the preprocessing of the original point cloud data to obtain the switch site cloud data specifically includes:

[0017] Adopting adaptive statistical outlier removal algorithm to filter the original point cloud data to obtain filtered point cloud data;

[0018] The calculation formula of the dynamic threshold of the adaptive statistical outlier removal algorithm is:

[0019] T y =μ0+k0·σ0;

[0020] Among them, T y is the dynamic threshold, μ0 is the mean of the point cloud data in the local neighborhood, σ0 is the standard deviation of the point cloud data in the local neighborhood, and k0 is the point cloud density adjustment coefficient;

[0021] Using a multi-scale filtering method to perform noise reduction processing on the filtered point cloud data to obtain noise-reduced point cloud data, and performing data consistency verification on the noise-reduced point cloud data by a verification method based on neighborhood consistency to obtain switch site cloud data;

[0022] The calculation formula of the multi-scale filtering method is:

[0023]

[0024] Among them, p'(xx) is the denoised point cloud data at the spatial position xx, p(xx') is the filtered point cloud data at the spatial position xx, σ1 is the standard deviation of the Gaussian kernel, and xx' is the other points in the neighborhood of the spatial position xx.

[0025] On the basis of the above technical solution, preferably, the three-dimensional model of the hydropower switch station is reconstructed based on the switch station cloud data to obtain the three-dimensional model of the hydropower switch station area, which specifically includes:

[0026] Adaptive meshing algorithm is used to triangulate the switch station cloud data to obtain a three-dimensional mesh model, and the three-dimensional mesh model is optimized by combining the feature preservation algorithm to obtain a three-dimensional model of the hydropower switch station area.

[0027] By comparing and analyzing the field measurement data with the model data, the deviations of the three-dimensional model of the hydropower switch station area in terms of geometric accuracy, surface feature restoration and spatial position are obtained and integrated, the comprehensive accuracy evaluation index of the three-dimensional model of the hydropower switch station area is calculated, and an accuracy evaluation report is generated.

[0028] On the basis of the above technical solution, preferably, the deformation assessment index model is established, and deformation analysis is performed on the three-dimensional model of the hydropower switch station area through the deformation assessment index model to obtain the deformation assessment index of the hydropower switch station, which specifically includes:

[0029] By analyzing historical monitoring data and current environmental conditions, the evaluation dimensions of displacement, deformation rate and deformation direction are set, and a weight coefficient is assigned to each evaluation dimension to obtain a deformation evaluation index model;

[0030] The calculation formula of the deformation evaluation index model is:

[0031]

[0032] Among them, F is the deformation evaluation index, D, V, θ are displacement, deformation rate, deformation direction angle, α1, β1, γ1 are the initial weight coefficients of displacement, deformation rate, deformation direction angle, k1, k2, k3 are the adjustment coefficients of displacement, deformation rate, deformation direction angle, ΔD, ΔV, Δθ are the changes of displacement, deformation rate, deformation direction angle, D1, V1, θ1 are the initial values ​​of displacement, deformation rate, deformation direction angle, respectively;

[0033] Based on the deformation assessment index model, a deformation analysis is performed on the three-dimensional model of the hydropower switch station area, and the influence of environmental factors, equipment factors and measurement factors are considered, and an adaptive error correction algorithm is used to perform multi-factor error correction on the deformation analysis results;

[0034] The calculation formula of the adaptive error correction algorithm is:

[0035]

[0036] Wherein, C is the error correction coefficient, T and H are temperature and humidity respectively, M is the material characteristic parameter, T0, H0, M0 are the standard reference values ​​of temperature, humidity and material characteristics respectively, q1, q2, q3 are the weight coefficients of temperature, humidity and material characteristics respectively, ΔT, ΔH, ΔM are the changes of temperature, humidity and material characteristics respectively.

[0037] On the basis of the above technical solution, preferably, the deformation risk level of the hydropower switch station is evaluated by the deformation risk level evaluation model and the deformation evaluation index to obtain the deformation risk level of the hydropower switch station, specifically including:

[0038] Establish a deformation risk level assessment model, which is based on historical monitoring data and current environmental conditions. The historical monitoring data is analyzed to determine key risk assessment factors, which include geological conditions, equipment aging degree and environmental changes. The fuzzy comprehensive evaluation method is used to assign weights to each factor to form a multi-level deformation risk level assessment model, standardize the deformation assessment indicators, and dynamically adjust them in combination with real-time monitoring data to calculate the deformation risk level of the hydropower switch station;

[0039] The calculation formula of the deformation risk level is:

[0040]

[0041]

[0042] Among them, R is the deformation risk level score, W i is the weight coefficient of the i-th key risk assessment factor, B i is the standardized value of the i-th key risk assessment factor, A i is the dynamic adjustment coefficient of the i-th key risk assessment factor, n is the number of key risk assessment factors, τ is the environmental impact correction coefficient, ΔE is the environmental change, E0 is the environmental reference value, δ is the time change correction coefficient, Δt is the time change, t0 is the reference time, α2 and β2 are the equipment status influence coefficient and seasonal change influence coefficient respectively, P i is the current equipment performance parameter, P0 is the equipment standard performance parameter, S i is the seasonal factor parameter, and S0 is the benchmark value of the seasonal factor parameter.

[0043] On the basis of the above technical solutions, preferably, the corresponding dangerous situation handling solutions are adopted for the hydropower switch station according to different deformation risk levels, specifically including:

[0044] Establish a risk handling solution library according to the deformation risk level, and formulate corresponding risk handling solutions for different deformation risk levels, wherein the different deformation risk levels include low risk level, medium risk level, high risk level, and extremely high risk level;

[0045] Execute the corresponding treatment plan, and evaluate and provide feedback on the treatment effect of the hazard treatment plan through real-time monitoring data, establish a treatment effect evaluation index system, and the treatment effect evaluation indicators include deformation trend improvement, structural stability improvement and safety margin recovery rate. Use a dynamic evaluation method to monitor the deformation changes after treatment in real time. When the treatment effect does not meet the standard, generate improvement suggestions through the optimization algorithm, and dynamically adjust the hazard treatment plan based on the improvement suggestions.

[0046] In a second aspect, the present invention further provides a hydropower switch station deformation monitoring system based on drone laser scanning, the system comprising:

[0047] A data scanning module is used to scan the hydropower switch station through an airborne laser scanner to obtain original point cloud data;

[0048] A data processing module is used to pre-process the original point cloud data to obtain switch site cloud data;

[0049] A model reconstruction module is used to reconstruct a three-dimensional model of a hydropower switch station based on the switch station cloud data to obtain a three-dimensional model of the hydropower switch station area;

[0050] A deformation analysis module, used to establish a deformation parameter identification model, and to perform deformation analysis on the three-dimensional model of the hydropower switch station area through the deformation parameter identification model to obtain deformation parameters of the hydropower switch station;

[0051] A risk level module, used to evaluate the hydropower switch station through the deformation risk level evaluation model and the deformation parameters to obtain the deformation risk level of the hydropower switch station;

[0052] The danger handling module is used to adopt corresponding danger handling solutions for the hydropower switch station according to different deformation risk levels.

[0053] In a third aspect, the present invention further provides an electronic device, comprising: at least one processor, at least one memory, a communication interface and a bus;

[0054] Among them, the processor, memory, and communication interface communicate with each other through the bus, the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to implement steps such as a hydropower switch station deformation monitoring method based on drone laser scanning.

[0055] In a fourth aspect, the present invention also provides a computer-readable storage medium, which stores computer instructions, and the computer instructions enable a computer to implement steps such as a method for monitoring deformation of a hydropower switch station based on drone laser scanning.

[0056] The method and system for monitoring deformation of a hydropower switch station based on unmanned aerial vehicle laser scanning of the present invention have the following beneficial effects compared with the prior art:

[0057] (1) The original point cloud data was obtained by airborne laser scanner, and data preprocessing and 3D model reconstruction were performed. The deformation evaluation index model and error correction algorithm were combined to improve the accuracy of deformation monitoring. The data processing method based on adaptive statistical algorithm, multi-scale filtering and error correction realized high-precision deformation monitoring and risk assessment of hydropower switch station.

[0058] (2) By establishing a deformation assessment index model and combining it with an adaptive error correction algorithm, the deformation state of the hydropower switch station is accurately analyzed. By comprehensively considering the three evaluation dimensions of displacement, deformation rate, and deformation direction, and dynamically compensating for environmental, equipment, and measurement factors, the accuracy and reliability of deformation monitoring are improved, ensuring that the monitoring results under different conditions can maintain a high degree of accuracy, providing a guarantee for the safe operation of the hydropower switch station.

[0059] (3) By establishing a deformation risk level assessment model based on multiple risk assessment factors and combining it with the fuzzy comprehensive evaluation method and dynamic adjustment mechanism, a quantitative assessment of the deformation risk of the hydropower switch station is achieved, thereby accurately reflecting the impact of multiple dimensions such as geological conditions, equipment aging and environmental changes, and providing a more reliable and comprehensive risk assessment result. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0061] Figure 1 This is a flow chart of a method for monitoring deformation of a hydropower switch station based on UAV laser scanning according to the present invention;

[0062] Figure 2 This is a structural diagram of a hydropower switch station deformation monitoring system based on drone laser scanning according to the present invention. DETAILED DESCRIPTION

[0063] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] See also Figure 1 The present invention provides a method for monitoring deformation of a hydropower switch station based on unmanned aerial vehicle laser scanning, comprising the following steps:

[0065] Scan the hydropower switch station with an airborne laser scanner to obtain raw point cloud data;

[0066] Preprocessing the original point cloud data to obtain switch site cloud data, wherein the preprocessing includes data filtering, noise reduction processing and data consistency verification;

[0067] Reconstructing a three-dimensional model of a hydropower switch station based on the switch station cloud data, obtaining a three-dimensional model of the hydropower switch station area, and evaluating the accuracy of the three-dimensional model of the hydropower switch station area;

[0068] Establishing a deformation assessment index model, wherein the deformation assessment index system includes displacement, deformation rate and deformation direction, performing deformation analysis on the three-dimensional model of the hydropower switch station area through the deformation assessment index model, obtaining the deformation assessment index of the hydropower switch station, and performing error correction during deformation analysis;

[0069] The hydropower switch station is evaluated by using the deformation risk level evaluation model and the deformation evaluation index to obtain the deformation risk level of the hydropower switch station;

[0070] According to different deformation risk levels, corresponding risk handling plans are adopted for hydropower switch stations.

[0071] Specifically, this embodiment acquires raw point cloud data through an airborne laser scanner, performs data preprocessing and three-dimensional model reconstruction, and combines the deformation assessment index model and the error correction algorithm to improve the accuracy of deformation monitoring. The data processing method based on the adaptive statistical algorithm, multi-scale filtering and error correction realizes high-precision monitoring and risk assessment of the deformation of the hydropower switch station.

[0072] Scanning the hydropower switch station by an airborne laser scanner to obtain original point cloud data specifically includes:

[0073] According to the spatial layout and equipment distribution of the hydropower switch station, multiple scanning position points are set, and each scanning position point is connected according to the optimal scanning path to form a flight path, and the flight path covers the entire monitoring area of ​​the hydropower switch station;

[0074] The Beidou positioning system is used to locate the UAV's flight position in real time, and the UAV is controlled to fly along the described flight path. The UAV uses a laser scanner to continuously emit laser pulses and receive reflected signals during flight, converting the received signals into raw point cloud data and transmitting them to the ground workstation in real time.

[0075] Specifically, this embodiment ensures that there are no blind spots in the monitoring area by reasonably setting multiple scanning position points and combining the spatial layout and equipment distribution characteristics of the hydropower switch station. The design of the optimal scanning path ensures comprehensive coverage of the entire monitoring area. By planning the optimal scanning path, the invalid flight distance is reduced, the work efficiency of the scanning operation is improved, and energy consumption is reduced. By using the Beidou positioning system for real-time positioning, the accuracy of the drone's flight position is ensured, the spatial position accuracy of the laser scanning data is improved, and reliable basic data is provided for deformation analysis.

[0076] The preprocessing of the original point cloud data to obtain the switch site cloud data specifically includes:

[0077] Adopting adaptive statistical outlier removal algorithm to filter the original point cloud data to obtain filtered point cloud data;

[0078] The calculation formula of the dynamic threshold of the adaptive statistical outlier removal algorithm is:

[0079] T y =μ0+k0·σ0;

[0080] Among them, T y is the dynamic threshold, μ0 is the mean of the point cloud data in the local neighborhood, σ0 is the standard deviation of the point cloud data in the local neighborhood, and k0 is the point cloud density adjustment coefficient;

[0081] Using a multi-scale filtering method to perform noise reduction processing on the filtered point cloud data to obtain noise-reduced point cloud data, and performing data consistency verification on the noise-reduced point cloud data by a verification method based on neighborhood consistency to obtain switch site cloud data;

[0082] The calculation formula of the multi-scale filtering method is:

[0083]

[0084] Among them, p'(xx) is the denoised point cloud data at the spatial position xx, p(xx') is the filtered point cloud data at the spatial position xx, σ1 is the standard deviation of the Gaussian kernel, and xx' is the other points in the neighborhood of the spatial position xx.

[0085] Specifically, this embodiment uses an adaptive statistical outlier removal algorithm to automatically adjust filtering parameters according to the local characteristics of point cloud data. The introduction of dynamic thresholds makes the filtering process more flexible and adapts to data characteristics of different regions, thereby improving the accuracy of outlier identification and reducing the misjudgment rate.

[0086] The multi-scale filtering method can effectively remove noise while maintaining the original data characteristics. Through the application of Gaussian kernel function, it can achieve accurate filtering of noise of different scales, improving the quality and availability of point cloud data. The verification method based on neighborhood consistency ensures the continuity of point cloud data in spatial distribution, avoids spatial breaks or discontinuities that may occur during data processing, and improves the reliability of deformation monitoring results.

[0087] The three-dimensional model reconstruction of the hydropower switch station based on the switch station cloud data to obtain the three-dimensional model of the hydropower switch station area specifically includes:

[0088] Adaptive meshing algorithm is used to triangulate the switch station cloud data to obtain a 3D mesh model. The 3D mesh model is optimized with feature preservation algorithm to ensure accurate expression of key structural features and restoration of details, thus obtaining a 3D model of the hydropower switch station area.

[0089] The calculation formula of the adaptive grid division density function is:

[0090] D(x,y,z)=D0·(1+λ0·C(x,y,z));

[0091] Where D(x,y,z) is the grid division density at the spatial point (x,y,z), D0 is the reference grid density, C(x,y,z) is the local curvature function, and λ0 is the adaptive adjustment coefficient;

[0092] By comparing and analyzing the field measurement data with the model data, the deviations of the three-dimensional model of the hydropower switch station area in terms of geometric accuracy, surface feature restoration and spatial position are obtained and integrated, the comprehensive accuracy evaluation index of the three-dimensional model of the hydropower switch station area is calculated, and an accuracy evaluation report is generated;

[0093] The calculation formula of the comprehensive accuracy evaluation index is:

[0094] E=w1·E g +w2·E s +w3·E p ;

[0095] Among them, E is the comprehensive accuracy evaluation index, E g is the geometric accuracy deviation, E s is the surface feature restoration deviation, E p is the spatial position deviation, w1, w2, and w3 are the weight coefficients of geometric accuracy deviation, surface feature restoration deviation, and spatial position deviation, respectively.

[0096] Specifically, this embodiment uses an adaptive meshing algorithm to achieve precise adjustment of mesh density, automatically encrypt the mesh in complex structural areas to improve detail performance, appropriately reduce mesh density in flat areas, optimize computing resources, and ensure that the model is both accurate and efficient. The feature preservation algorithm ensures that important structural features are not simplified or lost, improves the accuracy of the model's expression of key parts, provides a reliable reference benchmark for deformation monitoring, and enhances the practicality and reliability of the model. A multi-dimensional accuracy assessment mechanism is established, and the importance of different evaluation indicators is balanced through weight coefficients. A comprehensive accuracy assessment report is provided to make the assessment results more objective and credible.

[0097] The deformation assessment index model is established, and the deformation assessment index system includes displacement, deformation rate and deformation direction. The deformation assessment index model is used to perform deformation analysis on the three-dimensional model of the hydropower switch station area to obtain the deformation assessment index of the hydropower switch station. Error correction is performed during deformation analysis, specifically including:

[0098] By analyzing historical monitoring data and current environmental conditions, the evaluation dimensions of displacement, deformation rate and deformation direction are set, and a weight coefficient is assigned to each evaluation dimension to obtain a deformation evaluation index model;

[0099] The calculation formula of the deformation evaluation index model is:

[0100]

[0101] Among them, F is the deformation evaluation index, D, V, θ are displacement, deformation rate, deformation direction angle, α1, β1, γ1 are the initial weight coefficients of displacement, deformation rate, deformation direction angle, k1, k2, k3 are the adjustment coefficients of displacement, deformation rate, deformation direction angle, ΔD, ΔV, Δθ are the changes of displacement, deformation rate, deformation direction angle, D1, V1, θ1 are the initial values ​​of displacement, deformation rate, deformation direction angle, respectively;

[0102] Based on the deformation assessment index model, deformation analysis is performed on the three-dimensional model of the hydropower switch station area, and the influence of environmental factors (such as temperature and humidity), equipment factors (such as material characteristics) and measurement factors (such as scanning angle) are considered, and an adaptive error correction algorithm is used to perform multi-factor error correction on the deformation analysis results;

[0103] The calculation formula of the adaptive error correction algorithm is:

[0104]

[0105] Wherein, C is the error correction coefficient, T and H are temperature and humidity respectively, M is the material characteristic parameter, T0, H0, M0 are the standard reference values ​​of temperature, humidity and material characteristics respectively, q1, q2, q3 are the weight coefficients of temperature, humidity and material characteristics respectively, ΔT, ΔH, ΔM are the changes of temperature, humidity and material characteristics respectively.

[0106] Specifically, this embodiment uses a multi-dimensional evaluation system to comprehensively consider the displacement, deformation rate and deformation direction, introduces weight coefficients to make the evaluation more objective and reasonable, improves the accuracy and reliability of deformation evaluation, and provides a more comprehensive basis for decision-making. By considering the influence of environmental factors such as temperature and humidity, and dynamically compensating for environmental influences based on an adaptive error correction algorithm, the reliability of monitoring results under different environmental conditions is improved, and the scope of application of the present invention is expanded. The measurement accuracy is improved through multi-factor error correction, the influence of material properties on the measurement results is considered, and the errors caused by measurement factors such as scanning angle are compensated, thereby improving the accuracy of deformation monitoring.

[0107] The step of evaluating the hydropower switch station by using the deformation risk level evaluation model and the deformation evaluation index to obtain the deformation risk level of the hydropower switch station specifically includes:

[0108] Establish a deformation risk level assessment model, which is based on historical monitoring data and current environmental conditions. The historical monitoring data is analyzed to determine key risk assessment factors, which include geological conditions, equipment aging degree and environmental changes. The fuzzy comprehensive evaluation method is used to assign weights to each factor to form a multi-level deformation risk level assessment model, standardize the deformation assessment indicators, and dynamically adjust them in combination with real-time monitoring data to calculate the deformation risk level of the hydropower switch station;

[0109] The calculation formula of the deformation risk level is:

[0110]

[0111]

[0112] Among them, R is the deformation risk level score, W i is the weight coefficient of the i-th key risk assessment factor, B i is the standardized value of the i-th key risk assessment factor, A iis the dynamic adjustment coefficient of the i-th key risk assessment factor, n is the number of key risk assessment factors, τ is the environmental impact correction coefficient, ΔE is the environmental change, E0 is the environmental reference value, δ is the time change correction coefficient, Δt is the time change, t0 is the reference time, α2 and β2 are the equipment status influence coefficient and seasonal change influence coefficient respectively, P i is the current equipment performance parameter, P0 is the equipment standard performance parameter, S i is the seasonal factor parameter, and S0 is the benchmark value of the seasonal factor parameter.

[0113] Specifically, this embodiment realizes comprehensive quantification of risks through a multi-level deformation risk level assessment model, determines key risk factors based on historical data to improve the pertinence of the assessment, adopts a fuzzy comprehensive evaluation method to make the assessment results more objective, establishes a standardized assessment system, and improves the comparability of the assessment. The timeliness of the assessment is ensured by a dynamic adjustment mechanism of real-time monitoring data, the environmental impact correction coefficient compensates for the impact of environmental changes, the time change correction reflects the evolution of risk over time, and the seasonal change impact coefficient is used to consider the impact of seasonal factors. The assessment accuracy is improved based on the comprehensive consideration of multiple key risk assessment factors, the rationality of the impact of each factor is ensured by the scientific allocation of weight coefficients, the equipment status impact coefficient is used to reflect the impact of equipment performance on risk, and standardized processing is used to improve the comparability between different factors. The real-time update of risk levels is achieved through a dynamic adjustment mechanism, and the multi-level assessment model supports hierarchical management of risks.

[0114] The corresponding risk handling solutions for the hydropower switch station according to different deformation risk levels specifically include:

[0115] Establish a risk handling solution library according to the deformation risk level, and formulate corresponding risk handling solutions for different deformation risk levels, wherein the different deformation risk levels include low risk level, medium risk level, high risk level, and extremely high risk level;

[0116] For low-risk levels: increase the frequency of daily inspections and record the trend of deformation data changes;

[0117] For medium risk levels: set up temporary monitoring points, activate early warning mechanisms, and develop preventive maintenance plans;

[0118] For high-risk levels: implement emergency reinforcement measures, increase monitoring frequency, and start 24-hour real-time monitoring;

[0119] For extremely high risk levels: immediately stop equipment operation, implement emergency reinforcement and transformation, and carry out partial or complete transformation if necessary;

[0120] Execute the corresponding treatment plan, and evaluate and provide feedback on the treatment effect of the dangerous situation treatment plan through real-time monitoring data. If necessary, dynamically adjust the plan and establish a treatment effect evaluation index system. The treatment effect evaluation indicators include the improvement of deformation trend, the improvement of structural stability and the safety margin recovery rate. Use a dynamic evaluation method to monitor the deformation changes after treatment in real time. When the treatment effect does not meet the standard, generate improvement suggestions through the optimization algorithm, and dynamically adjust the dangerous situation treatment plan based on the improvement suggestions.

[0121] Specifically, this embodiment realizes risk classification management by establishing a complete hierarchical processing system, and formulates differentiated processing plans for different risk levels, which ensures the pertinence of processing measures and improves the standardization and operability of risk management. By presetting different levels of risk handling plans, the response speed is improved, the processing procedures for risks at all levels are clarified, the decision-making time is reduced, a rapid response mechanism is established, the disposal efficiency is improved, and the possibility of risk expansion is reduced. This application takes processing measures of corresponding intensity according to the risk level, ensures the processing effect through real-time monitoring, supports precise adjustment through dynamic evaluation, and optimizes the execution effect of the risk handling plan. By establishing a processing effect evaluation indicator system, the processing effect is monitored and evaluated in real time, and improvement suggestions are provided based on the optimization algorithm to support dynamic optimization and adjustment of the plan.

[0122] See also Figure 2 The present invention also provides a hydropower switch station deformation monitoring system based on drone laser scanning, the system comprising:

[0123] A data scanning module is used to scan the hydropower switch station through an airborne laser scanner to obtain original point cloud data;

[0124] A data processing module is used to pre-process the original point cloud data to obtain switch site cloud data;

[0125] A model reconstruction module is used to reconstruct a three-dimensional model of a hydropower switch station based on the switch station cloud data to obtain a three-dimensional model of the hydropower switch station area;

[0126] A deformation analysis module, used to establish a deformation parameter identification model, and to perform deformation analysis on the three-dimensional model of the hydropower switch station area through the deformation parameter identification model to obtain deformation parameters of the hydropower switch station;

[0127] A risk level module, used to evaluate the hydropower switch station through the deformation risk level evaluation model and the deformation parameters to obtain the deformation risk level of the hydropower switch station;

[0128] The danger handling module is used to adopt corresponding danger handling solutions for the hydropower switch station according to different deformation risk levels.

[0129] Specifically, a hydropower switch station deformation monitoring system based on drone laser scanning in this embodiment realizes the automation of the entire process from data collection to dangerous situation handling. The functional modules are seamlessly connected to improve the system operation efficiency, and the unified data processing standards ensure the accuracy of information transmission. The data scanning module ensures the accurate collection of original data, the data processing module provides high-quality point cloud data, and the model reconstruction module realizes precise three-dimensional visualization to form a complete data processing chain. The deformation analysis module of this embodiment provides accurate deformation parameters, the risk level module realizes scientific risk assessment, the multi-dimensional analysis improves the comprehensiveness of the assessment, and the analysis reduces human errors. This embodiment realizes automated risk assessment and early warning, accurate selection of dangerous situation handling solutions, and systematic monitoring and management, which improves management efficiency and decision-making accuracy.

[0130] The present invention also discloses an electronic device, comprising: at least one processor, at least one memory communication interface and a bus: wherein the processor, memory and communication interface communicate with each other through the bus; the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to implement a hydropower switch station deformation monitoring method based on drone laser scanning.

[0131] The present invention also discloses a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, wherein the computer instructions enable the computer to implement all or part of the steps of a method for monitoring deformation of a hydropower switch station based on laser scanning by an unmanned aerial vehicle according to an embodiment of the present invention. The storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0132] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for monitoring deformation of a hydropower switch station based on UAV laser scanning, characterized in that: The following steps are involved: Scan the hydropower switch station with an airborne laser scanner to obtain raw point cloud data; Preprocess the original point cloud data to obtain switch site cloud data; Reconstruct the 3D model of the hydropower switch station based on the switch station cloud data to obtain the 3D model of the hydropower switch station area; Establishing a deformation assessment index model, and performing deformation analysis on the three-dimensional model of the hydropower switch station area through the deformation assessment index model to obtain a deformation assessment index of the hydropower switch station; The hydropower switch station is evaluated by using the deformation risk level evaluation model and the deformation evaluation index to obtain the deformation risk level of the hydropower switch station; According to different deformation risk levels, corresponding risk handling plans are adopted for hydropower switch stations.

2. The method for monitoring deformation of a hydropower switch station based on drone laser scanning as claimed in claim 1, characterized in that: Scanning the hydropower switch station by an airborne laser scanner to obtain original point cloud data specifically includes: According to the spatial layout and equipment distribution of the hydropower switch station, multiple scanning position points are set, and each scanning position point is connected according to the optimal scanning path to form a flight path, and the flight path covers the entire monitoring area of ​​the hydropower switch station; The Beidou positioning system is used to locate the UAV's flight position in real time, and the UAV is controlled to fly along the described flight path. The UAV uses a laser scanner to continuously emit laser pulses and receive reflected signals during flight, converting the received signals into raw point cloud data and transmitting them to the ground workstation in real time.

3. The method for monitoring deformation of a hydropower switch station based on drone laser scanning as claimed in claim 1, characterized in that: The preprocessing of the original point cloud data to obtain the switch site cloud data specifically includes: Adopting adaptive statistical outlier removal algorithm to filter the original point cloud data to obtain filtered point cloud data; The calculation formula of the dynamic threshold of the adaptive statistical outlier removal algorithm is: T y =μ0+k0·σ0; Among them, T y is the dynamic threshold, μ0 is the mean of the point cloud data in the local neighborhood, σ0 is the standard deviation of the point cloud data in the local neighborhood, and k0 is the point cloud density adjustment coefficient; Using a multi-scale filtering method to perform noise reduction processing on the filtered point cloud data to obtain noise-reduced point cloud data, and performing data consistency verification on the noise-reduced point cloud data by a verification method based on neighborhood consistency to obtain switch site cloud data; The calculation formula of the multi-scale filtering method is: Among them, p'(xx) is the denoised point cloud data at the spatial position xx, p(xx') is the filtered point cloud data at the spatial position xx, σ1 is the standard deviation of the Gaussian kernel, and xx' is the other points in the neighborhood of the spatial position xx.

4. A method for monitoring deformation of a hydropower switch station based on drone laser scanning as claimed in claim 3, characterized in that: The three-dimensional model reconstruction of the hydropower switch station based on the switch station cloud data to obtain the three-dimensional model of the hydropower switch station area specifically includes: Adaptive meshing algorithm is used to triangulate the switch station cloud data to obtain a three-dimensional mesh model, and the three-dimensional mesh model is optimized by combining the feature preservation algorithm to obtain a three-dimensional model of the hydropower switch station area. By comparing and analyzing the field measurement data with the model data, the deviations of the three-dimensional model of the hydropower switch station area in terms of geometric accuracy, surface feature restoration and spatial position are obtained and integrated, the comprehensive accuracy evaluation index of the three-dimensional model of the hydropower switch station area is calculated, and an accuracy evaluation report is generated.

5. The method for monitoring deformation of a hydropower switch station based on drone laser scanning as claimed in claim 1, characterized in that: The step of establishing a deformation assessment index model, and performing deformation analysis on the three-dimensional model of the hydropower switch station area by using the deformation assessment index model to obtain a deformation assessment index of the hydropower switch station, specifically includes: By analyzing historical monitoring data and current environmental conditions, the evaluation dimensions of displacement, deformation rate and deformation direction are set, and a weight coefficient is assigned to each evaluation dimension to obtain a deformation evaluation index model; The calculation formula of the deformation evaluation index model is: Among them, F is the deformation evaluation index, D, V, θ are displacement, deformation rate, deformation direction angle, α1, β1, γ1 are the initial weight coefficients of displacement, deformation rate, deformation direction angle, k1, k2, k3 are the adjustment coefficients of displacement, deformation rate, deformation direction angle, ΔD, ΔV, Δθ are the changes of displacement, deformation rate, deformation direction angle, D1, V1, θ1 are the initial values ​​of displacement, deformation rate, deformation direction angle, respectively; Based on the deformation assessment index model, a deformation analysis is performed on the three-dimensional model of the hydropower switch station area, and the influence of environmental factors, equipment factors and measurement factors are considered, and an adaptive error correction algorithm is used to perform multi-factor error correction on the deformation analysis results; The calculation formula of the adaptive error correction algorithm is: Wherein, C is the error correction coefficient, T and H are temperature and humidity respectively, M is the material characteristic parameter, T0, H0, M0 are the standard reference values ​​of temperature, humidity and material characteristics respectively, q1, q2, q3 are the weight coefficients of temperature, humidity and material characteristics respectively, ΔT, ΔH, ΔM are the changes of temperature, humidity and material characteristics respectively.

6. A method for monitoring deformation of a hydropower switch station based on drone laser scanning as claimed in claim 5, characterized in that: The step of evaluating the hydropower switch station by using the deformation risk level evaluation model and the deformation evaluation index to obtain the deformation risk level of the hydropower switch station specifically includes: Establish a deformation risk level assessment model, which is based on historical monitoring data and current environmental conditions. The historical monitoring data is analyzed to determine key risk assessment factors, which include geological conditions, equipment aging degree and environmental changes. The fuzzy comprehensive evaluation method is used to assign weights to each factor to form a multi-level deformation risk level assessment model, standardize the deformation assessment indicators, and dynamically adjust them in combination with real-time monitoring data to calculate the deformation risk level of the hydropower switch station; The calculation formula of the deformation risk level is: Among them, R is the deformation risk level score, W i is the weight coefficient of the i-th key risk assessment factor, B i is the standardized value of the i-th key risk assessment factor, A i is the dynamic adjustment coefficient of the i-th key risk assessment factor, n is the number of key risk assessment factors, τ is the environmental impact correction coefficient, ΔE is the environmental change, E0 is the environmental reference value, δ is the time change correction coefficient, Δt is the time change, t0 is the reference time, α2 and β2 are the equipment status influence coefficient and seasonal change influence coefficient respectively, P i is the current equipment performance parameter, P0 is the equipment standard performance parameter, S i is the seasonal factor parameter, and S0 is the benchmark value of the seasonal factor parameter.

7. The method for monitoring deformation of a hydropower switch station based on drone laser scanning as claimed in claim 1, characterized in that: The corresponding risk handling solutions for the hydropower switch station according to different deformation risk levels specifically include: Establish a risk handling solution library according to the deformation risk level, and formulate corresponding risk handling solutions for different deformation risk levels, wherein the different deformation risk levels include low risk level, medium risk level, high risk level, and extremely high risk level; Execute the corresponding treatment plan, and evaluate and provide feedback on the treatment effect of the hazard treatment plan through real-time monitoring data, establish a treatment effect evaluation index system, and the treatment effect evaluation indicators include deformation trend improvement, structural stability improvement and safety margin recovery rate. Use a dynamic evaluation method to monitor the deformation changes after treatment in real time. When the treatment effect does not meet the standard, generate improvement suggestions through the optimization algorithm, and dynamically adjust the hazard treatment plan based on the improvement suggestions.

8. A hydropower switch station deformation monitoring system based on drone laser scanning, characterized in that: The system comprises: A data scanning module is used to scan the hydropower switch station through an airborne laser scanner to obtain original point cloud data; A data processing module is used to pre-process the original point cloud data to obtain switch site cloud data; A model reconstruction module is used to reconstruct a three-dimensional model of a hydropower switch station based on the switch station cloud data to obtain a three-dimensional model of the hydropower switch station area; A deformation analysis module, used to establish a deformation parameter identification model, and to perform deformation analysis on the three-dimensional model of the hydropower switch station area through the deformation parameter identification model to obtain deformation parameters of the hydropower switch station; A risk level module, used to evaluate the hydropower switch station through the deformation risk level evaluation model and the deformation parameters to obtain the deformation risk level of the hydropower switch station; The danger handling module is used to adopt corresponding danger handling solutions for the hydropower switch station according to different deformation risk levels.

9. An electronic device, characterized in that: include: at least one processor, at least one memory, a communication interface, and a bus; The processor, memory, and communication interface communicate with each other via the bus, the memory stores program instructions executable by the processor, and the processor calls the program instructions to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions enable a computer to implement the method according to any one of claims 1 to 7.

Images