Power transmission and transformation project water conservation measure effect optimization method and system

Abstract

The invention provides a power transmission and transformation project water conservation measure effect optimization method and system, and relates to the technical field of water and soil conservation, and the method comprises the steps: building an intervention feature time sequence chain through analyzing a periodic water and soil intervention process of a power transmission and transformation project; performing measure behavior, measure excitation and measure change time sequence feature extraction on the water conservation measures, and constructing a water conservation feature time sequence chain; performing time sequence alignment on the intervention feature time sequence chain and the water conservation feature time sequence chain to obtain an effect evaluation feature pair; and performing optimization compensation on the water conservation deviation based on the effect evaluation features to obtain optimization compensation features for performing optimization adjustment on water conservation measures. The technical problem that in the prior art, accurate prediction and dynamic optimization of the power transmission and transformation project water conservation effect are difficult to achieve, and consequently the water conservation measure effect is poor is solved. The technical effects of accurately predicting and dynamically optimizing the water conservation effect of the power transmission and transformation project and improving the accuracy and reliability of the water conservation measures of the power transmission and transformation project are achieved.

Description

Technical Field

[0001] This invention relates to the field of soil and water conservation technology, specifically to a method and system for optimizing the effectiveness of soil and water conservation measures in power transmission and transformation projects. Background Technology

[0002] As a crucial infrastructure for energy transmission, power transmission and transformation projects typically traverse complex and varied terrains, with long construction periods and wide-ranging disturbances, significantly impacting regional soil and water conservation. During construction, extensive excavation, filling, road excavation, and site leveling activities lead to vegetation damage, altered landforms, and soil disturbance, resulting in soil erosion, siltation, and ecological degradation. To mitigate the adverse ecological impacts of power transmission and transformation projects, relevant departments usually require a series of soil and water conservation measures during construction and operation, including temporary drainage, retaining walls, greening restoration, and ecological slope protection. However, traditional soil and water conservation design and effectiveness evaluation rely primarily on static planning and empirical judgment, lacking analysis of the temporal relationship between dynamic construction disturbances and the response of soil and water conservation measures. This makes accurate prediction and dynamic optimization of soil and water conservation effects difficult, leading to ineffective measures and impacting ecological stability.

[0003] Existing technologies have limitations in accurately predicting and dynamically optimizing the water conservation effects of power transmission and transformation projects, leading to poor effectiveness of water conservation measures. Summary of the Invention

[0004] The purpose of this application is to provide a method and system for optimizing the effectiveness of water conservation measures in power transmission and transformation projects, in order to solve the technical problem that existing technologies are unable to accurately predict and dynamically optimize the effectiveness of water conservation measures in power transmission and transformation projects, resulting in poor effectiveness of water conservation measures.

[0005] In view of the above problems, this application provides a method and system for optimizing the effectiveness of water conservation measures in power transmission and transformation projects.

[0006] The first aspect of this application provides a method for optimizing the effectiveness of soil and water conservation measures in power transmission and transformation projects. The method includes: analyzing the periodic soil and water intervention procedures of the power transmission and transformation project and establishing an intervention feature time-series chain; extracting the time-series features of the soil and water conservation measures' behavior, incentives, and changes to construct a soil and water conservation feature time-series chain; coupling the intervention feature time-series chain with the soil and water conservation feature time-series chain for time-series analysis and aligning the time-series according to the coupling time-series relationship to obtain effect evaluation feature pairs; performing soil and water conservation deviation analysis based on the effect evaluation feature pairs, optimizing and compensating for the soil and water conservation deviations to obtain optimization compensation features for optimizing and adjusting soil and water conservation measures.

[0007] Optionally, water conservation targets are located in the coverage area of ​​the power transmission and transformation project to obtain the distribution of water conservation targets; based on the distribution of water conservation targets, spatial grid segmentation is performed to construct a water conservation spatial response grid.

[0008] Optionally, for each grid cell in the water conservation spatial response grid, the construction cycle of the power transmission and transformation project is analyzed to identify the surface disturbance behavior of each cycle and extract intervention feature parameters; based on the disturbance time sequence relationship of the intervention feature parameters, the intervention feature time sequence chain of each grid cell is constructed.

[0009] Optionally, behavioral features, incentive features, and change features are extracted from the implementation process of water conservation measures within the grid cell to establish a time-series node water conservation assessment model; according to the time-series behavioral features in the water conservation measures, water conservation feature analysis is performed using the time-series node water conservation assessment model to establish the water conservation feature time-series chain.

[0010] Optionally, each grid cell in the water conservation spatial response grid corresponds to a set of terrain, landform, soil, and vegetation attribute parameters.

[0011] Optionally, cross-correlation analysis is performed on the intervention feature time series chain of each grid cell and the water conservation feature time series chain to determine the time overlap range between intervention changes and water conservation responses. The time overlap range includes a lag time range and a lead time range. A maximum time delay threshold is set according to the time overlap range, and causal constraint rules are set according to the type of power transmission and transformation project. Specifically, for structural measures, the water conservation response time is limited to not being earlier than the intervention action time; for pretreatment measures, the response can be earlier than the intervention action time; and for biological measures, the response lag time is limited to not exceeding the maximum time delay threshold. A spatial propagation weight matrix is ​​constructed based on the topographic slope, runoff path, and grid adjacency relationship of the construction area to describe the attenuation of the impact of upstream intervention on downstream response. Under the time constraint of the maximum time delay threshold and the weight conditions of the spatial propagation weight matrix, time series alignment relationship matching is performed. The intervention feature time series chain and the water conservation feature time series chain are time-aligned according to the matched alignment relationship to obtain the intervention-water conservation effect evaluation feature pair.

[0012] Optionally, a temporal matching matrix is ​​constructed between the intervention feature time series chain and the water conservation feature time series chain. The matrix elements of the temporal matching matrix are used to represent the matching cost between each time node. The matching cost is calculated based on the numerical difference, rate of change difference, or trend difference at the corresponding time node, and is weighted and corrected by spatial propagation weights to obtain a comprehensive cost function. A dynamic programming search algorithm is used to minimize the comprehensive cost function to obtain the optimal alignment path between the intervention and the water conservation response. Based on the optimal alignment path, the corresponding time point set of the intervention behavior and the water conservation response is extracted to determine the temporal alignment relationship.

[0013] Optionally, the time difference between nodes in the set of time points is calculated, and the average lag time is statistically analyzed; the average lag time is used as a representative parameter of the time alignment relationship to determine the time alignment relationship, which is used to reflect the time coupling relationship between intervention and water conservation response within the grid cell.

[0014] Optionally, the water conservation target is used to perform a target evaluation traversal on the effect evaluation features to identify water conservation deviation features that fail to achieve the water conservation target; water conservation measure parameters or intervention parameters are adjusted for compensation based on the water conservation deviation features and the corresponding target deviation amount, with the water conservation target as the standard, to obtain the optimized compensation features of each grid unit; based on the spatial propagation weight matrix, the optimized compensation features of each grid unit are optimized by weight accumulation, with the goal of maximizing the target and minimizing the measure cost of all grid units, and spatial smoothing adjustment is performed to obtain the final optimized compensation features.

[0015] A second aspect of this application provides a system for optimizing the effectiveness of soil and water conservation measures in power transmission and transformation projects. The system includes: an intervention feature time-series chain establishment module for analyzing the periodic soil and water intervention procedures of power transmission and transformation projects and establishing an intervention feature time-series chain; a soil and water conservation feature time-series chain construction module for extracting time-series features of measure behavior, measure incentives, and measure changes from soil and water conservation measures and constructing a soil and water conservation feature time-series chain; an effectiveness evaluation feature pair acquisition module for coupling the intervention feature time-series chain with the soil and water conservation feature time-series chain for time-series analysis and time-series alignment according to the coupling time-series relationship to obtain effectiveness evaluation feature pairs; and a deviation optimization and compensation module for performing soil and water conservation deviation analysis based on the effectiveness evaluation feature pairs, optimizing and compensating for the soil and water conservation deviations, and obtaining optimization compensation features for optimizing and adjusting soil and water conservation measures.

[0016] One or more technical solutions provided in this application have at least the following technical effects or advantages: The method provided in this application establishes an intervention feature time-series chain by analyzing the periodic soil and water conservation intervention procedures of power transmission and transformation projects; extracts the time-series features of measure behavior, measure incentives, and measure changes of soil and water conservation measures to construct a soil and water conservation feature time-series chain; couples the intervention feature time-series chain with the soil and water conservation feature time-series chain for time-series analysis and aligns the time sequences according to the coupling time-series relationship to obtain effect evaluation feature pairs; performs soil and water conservation deviation analysis based on the effect evaluation feature pairs, optimizes and compensates for the soil and water conservation deviations, and obtains optimization compensation features for optimizing and adjusting soil and water conservation measures. This achieves the technical effect of accurate prediction and dynamic optimization of soil and water conservation effects in power transmission and transformation projects, improving the accuracy and reliability of soil and water conservation measures in power transmission and transformation projects.

[0017] The above description is merely an overview of the technical solution of this application. To enable a clearer understanding of the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0019] Figure 1 A flowchart illustrating the method for optimizing the effectiveness of water conservation measures in power transmission and transformation projects provided in this application.

[0020] Figure 2 A schematic diagram of the structure of the water conservation measures optimization system for power transmission and transformation projects provided in this application.

[0021] Figure labeling: Module 11 for establishing time series chain of intervention features, Module 12 for constructing time series chain of water conservation features, Module 13 for obtaining feature pairs for effect evaluation, and Module 14 for deviation optimization and compensation. Detailed Implementation

[0022] This application provides a method and system for optimizing the effectiveness of water conservation measures in power transmission and transformation projects. It addresses the technical problem that existing technologies struggle to accurately predict and dynamically optimize the effectiveness of water conservation measures in power transmission and transformation projects, leading to ineffective measures. The method achieves the technical effect of accurately predicting and dynamically optimizing the effectiveness of water conservation measures in power transmission and transformation projects, thereby improving the accuracy and reliability of these measures.

[0023] The technical solutions of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. It should be understood that the present invention is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention. It should also be noted that, for ease of description, only the parts related to the present invention are shown in the accompanying drawings, not all of them.

[0024] Example 1, as Figure 1As shown, this application provides a method for optimizing the effectiveness of water conservation measures in power transmission and transformation projects. The method includes: We analyze the periodic water and soil intervention procedures in power transmission and transformation projects and establish a time-series chain of intervention characteristics.

[0025] Specifically, the cyclical soil and water intervention process in power transmission and transformation projects refers to the collection of surface disturbances and soil and water environment interventions triggered by different construction stages throughout the entire construction process of power transmission and transformation projects. These interventions exhibit clear stages, cyclical patterns, and spatial differences. Based on the overall construction plan of the power transmission and transformation project, the project is divided into multiple stages, including the construction preparation stage, foundation construction stage, main structure installation stage, line erection stage, and ecological restoration stage. Each stage involves different types of soil and water disturbance activities. For example, foundation construction activities such as excavation and pouring during the infrastructure stage significantly disturb the surface soil. Excavation generates a large amount of excavated soil and waste; if not properly handled, this waste can be washed away during rainfall, causing severe soil erosion. Simultaneously, excavation also damages existing vegetation and soil structure, reducing the soil's erosion resistance.

[0026] By utilizing construction logs, combined with high-resolution remote sensing imagery, UAV aerial survey data, and topographic elevation models (DEMs), surface changes at each stage of the power transmission and transformation project were detected and analyzed. Multiple intervention characteristic parameters were obtained, including the type of disturbance, the extent, intensity, and duration of the disturbance. Disturbance types included excavation, filling, and road excavation; disturbance extent included the disturbed area and vegetation damage; and disturbance intensity included slope changes and the degree of geomorphic disturbance. Using time as the main axis, these intervention characteristic parameters from each stage and construction unit were integrated chronologically to form an intervention characteristic time-series chain. This chain encompasses the intensity and persistence of the impact of each construction stage on surface water and soil disturbance, providing data support for optimizing water conservation measures.

[0027] Furthermore, before analyzing the periodic water and soil intervention procedures of power transmission and transformation projects and establishing the intervention characteristic time sequence chain, the process includes: locating water conservation targets in the coverage construction area of ​​the power transmission and transformation project to obtain the distribution of water conservation targets; and constructing a water conservation spatial response grid based on the distribution of water conservation targets.

[0028] Furthermore, each grid cell in the water conservation spatial response grid corresponds to a set of terrain, landform, soil, and vegetation attribute parameters.

[0029] Specifically, before analyzing the cyclical soil and water intervention procedures of power transmission and transformation projects, based on the route of the power transmission and transformation project, the layout of substations, and the construction land area, the project boundary is used as the basic spatial unit. Topographic features are calculated in a Geographic Information System (GIS) using elevation data and remote sensing imagery, and watershed and runoff path divisions are performed. Simultaneously, soil maps, geological materials, and vegetation cover data are imported to locate soil and water conservation targets within the construction area covered by the power transmission and transformation project. This yields the distribution of soil and water conservation targets covering the entire construction area, determining the control targets and key areas for soil and water conservation in the construction area. For example, for areas with high slopes, strong disturbance, and easy erosion, the focus is on reducing runoff erosion intensity and controlling sediment output. Earthen or stone retaining walls are constructed around the construction site to prevent waste soil and slag generated during construction from being washed into surrounding water bodies by rainwater, causing siltation. For areas with damaged vegetation, elevated cableways are used to transport materials, reducing the impact of construction vehicles on vegetation. In forest areas, artificial planting of trees and shrubs is employed, while in grassland areas, grass seeding is used to improve vegetation restoration rates. For runoff pathways or low-lying areas, drainage and retaining measures are implemented to optimize surface runoff paths and reduce the risk of concentrated erosion.

[0030] Based on the spatial information characteristics of the distribution of soil and water conservation targets, GIS technology is used to divide the construction area into several adaptive grids according to topographic slope changes, runoff confluence paths, geomorphological zoning characteristics, and vegetation distribution characteristics. A spatial response grid for soil and water conservation analysis is constructed, with each grid cell serving as an independent soil and water response calculation unit to record local soil and water changes and the response of soil and water conservation measures. The size of each grid cell is determined based on the project scale and the distribution of soil and water conservation targets, generally ranging from tens to hundreds of meters in side length. Each grid cell in the spatial response grid corresponds to a set of topographic, geomorphological, soil, and vegetation attribute parameters. Topographic parameters include elevation, slope, and aspect, reflecting surface morphology; geomorphological parameters include surface type, erosion sensitivity, and surface roughness; soil parameters include soil type and permeability, reflecting soil erosion resistance and soil and water conservation capacity; and vegetation parameters include vegetation type, vegetation coverage, and vegetation recovery capacity, used to assess the soil and water conservation potential of the biolayer. By constructing a spatial response grid for water conservation, large and complex construction environments can be discretized, enabling intervention behaviors and water conservation responses to be matched and aligned within a unified spatial framework. This improves the accuracy of extracting construction disturbances at each stage of power transmission and transformation projects, thereby enhancing the effectiveness of water conservation.

[0031] Furthermore, the periodic water and soil intervention procedures of the power transmission and transformation project are analyzed, and an intervention feature time series chain is established, including: analyzing the construction cycle of the power transmission and transformation project for each grid unit in the water conservation spatial response grid, identifying the surface disturbance behavior of each cycle, and extracting intervention feature parameters; and constructing the intervention feature time series chain of each grid unit based on the disturbance time series relationship of the intervention feature parameters.

[0032] Specifically, the time schedule, construction procedures, and work nodes for each construction stage are obtained based on the construction plan of the power transmission and transformation project. According to the construction cycle, the entire construction period is divided into multiple stages, and the water conservation spatial response grid, which is predefined in the construction area, is mapped to the construction plan. The construction cycle of each grid cell in the water conservation spatial response grid is analyzed, and each grid cell is labeled with the construction type involved in each stage. Each type of construction activity will cause different types and intensities of disturbance to the surface. Construction operation type, operation area, operation time, and construction machinery information are extracted from the construction log. Remote sensing imagery and UAV aerial survey data are acquired to generate a digital elevation model. The impact before and after construction is compared, and the difference method is used to calculate topographic changes, exposed bare land area, and vegetation cover changes to obtain the surface disturbance behavior. Based on the surface disturbance behavior of each cycle, intervention characteristic parameters are extracted. These intervention characteristic parameters reflect the impact characteristics of construction activities on the soil and water environment, including disturbance type, range of the disturbance area, intensity, and duration. Based on the temporal relationship of different grid intervention characteristic parameters within the construction cycle, an intervention characteristic temporal chain is constructed for each grid unit to reflect the continuity and changing trend of construction disturbance behavior in different grid units over time. By performing construction cycle analysis and intervention characteristic parameter extraction for each grid unit, refined management of soil and water conservation work in the power transmission and transformation station project is achieved, ensuring that soil and water conservation measures can be optimized and implemented more effectively, thereby improving the effectiveness of these measures.

[0033] Extract the temporal characteristics of water conservation measures, including measures behavior, measures incentives, and measures changes, and construct a water conservation feature temporal chain.

[0034] Furthermore, the construction of the water conservation feature time series chain includes: extracting behavioral features, incentive features, and change features of the water conservation measures implementation process within the grid cell, and establishing a time series node water conservation assessment model; and performing water conservation feature analysis using the time series node water conservation assessment model according to the time series behavioral features in the water conservation measures, and establishing the water conservation feature time series chain.

[0035] Specifically, the behavioral, incentive, and change characteristics of water conservation measures implemented within each grid cell of the spatial response grid for water conservation are extracted. Behavioral characteristics refer to the specific implementation forms and operational types of water conservation measures within the grid cell, such as slope protection construction, vegetation replanting, and temporary drainage facility deployment, reflecting the specific execution behavior of water conservation measures and obtained through field surveys and construction records. Incentive characteristics refer to the external conditions or constraints driving the implementation of water conservation measures, such as water conservation implementation requirements documents, obtained by reviewing engineering management documents and construction plans. Change characteristics extraction refers to the attribute changes of water conservation measures at different time points, including changes in construction intensity, coverage area, and degree of biological restoration, reflecting the dynamic state of water conservation measures over time, obtained through long-term monitoring data collection and analysis. Monitoring methods include, but are not limited to, remote sensing technology, UAV mapping, and soil erosion monitoring equipment. Based on the extracted behavioral, incentive, and change characteristics, a time-series node water conservation assessment model is constructed. This model is used to transform the behavioral, incentive, and change characteristics of water conservation measures within the grid cell into quantifiable water conservation effect indicators. For example, the implementation data of water conservation measures in each grid cell of the water conservation spatial response grid are organized, and the behavioral features, incentive features, and change features are organized into input vectors according to time series. The corresponding output targets are water conservation effectiveness indicators at each time node, such as soil loss, runoff reduction rate, and vegetation cover restoration rate. To obtain the dynamic impact of water conservation measures over time, input sequences from multiple time nodes within a historical time range are used as model inputs. The data is divided into training and validation sets. An appropriate LSTM or GRU network for time series modeling is selected. The predicted effectiveness indicators for each time node are calculated through forward propagation, and the loss function is calculated based on the mean squared error. Backpropagation and weight updates are performed using the Adam optimizer, and iterative training is continued until the loss converges. After training, the validation set data is input into the model for prediction to evaluate the model performance. Finally, the trained model is used as a time series node water conservation evaluation model to analyze and evaluate the water conservation effectiveness of each grid cell at each time node.

[0036] This study analyzes the temporal behavioral characteristics of water conservation measures, identifying the behavioral, incentive, and change characteristics at each time point. For example, in vegetation restoration measures, it analyzes the changes in planting behavior, ecological restoration incentives, and vegetation coverage at different time points. Using a temporal node water conservation assessment model, the measures at each time point are evaluated and analyzed to obtain the temporal node water conservation assessment results. Based on the temporal behavioral characteristics of the water conservation measures, the assessment results for each time point are arranged chronologically, forming a temporal chain of water conservation characteristics. By obtaining this temporal chain, problems and shortcomings in the implementation of water conservation measures can be identified, providing decision support for optimizing these measures. For instance, if the temporal node water conservation assessment results indicate that the water conservation measures at a certain time point are ineffective, the measures can be adjusted and optimized by analyzing the behavioral and incentive characteristics to improve their effectiveness.

[0037] The intervention feature time series chain and the water conservation feature time series chain are coupled and analyzed, and time series alignment is performed according to the coupling time series relationship to obtain effect evaluation feature pairs.

[0038] Furthermore, the intervention feature time series chain and the water conservation feature time series chain are coupled and analyzed, and time series alignment is performed according to the coupling time series relationship to obtain effect evaluation feature pairs. This includes: performing cross-correlation analysis on the intervention feature time series chain and the water conservation feature time series chain of each grid unit to determine the time crossover range between intervention changes and water conservation responses. The time crossover range includes a lag time range and a lead time range. A maximum time delay threshold is set according to the time crossover range, and causal constraint rules are set according to the type of power transmission and transformation project. For structural measures, the water conservation response time is limited to not being earlier than the time of intervention action. For pretreatment measures, the response time is limited to be earlier than the intervention time, and for biological measures, the response lag time is limited to not exceeding the maximum time delay threshold. Based on the terrain slope, runoff path, and grid adjacency of the construction area, a spatial propagation weight matrix is ​​constructed to describe the attenuation of the impact of upstream intervention on downstream response. Under the time constraint of the maximum time delay threshold and the weight of the spatial propagation weight matrix, temporal alignment relationship matching is performed. The intervention feature time series chain and the water conservation feature time series chain are time-aligned according to the matched alignment relationship to obtain the intervention-water conservation effect evaluation feature pair.

[0039] Specifically, depending on the construction type and water conservation measures of the power transmission and transformation project, the response times of water conservation measures vary. For example, structural water conservation measures, such as drainage ditches and retaining walls, typically have synchronous or very short lag response times; biological water conservation measures, such as vegetation restoration, have significant lag response times; and pre-treatment water conservation measures, such as pre-construction drainage or diversion, are pre-emptive responses. Based on cross-correlation algorithms, cross-correlation analysis is performed on the intervention feature time series and water conservation feature time series of each grid cell. For example, using statistical analysis software such as Python's NumPy or SciPy libraries, discrete cross-correlation functions are used to calculate the correlation and time lag relationship between the two time series of intervention feature time series and water conservation feature time series in each grid cell. By analyzing the results of the cross-correlation function, the peak value of the cross-correlation function and the corresponding time lag are obtained, and the time overlap range between the intervention change and the water conservation response is determined. The time overlap range includes the lag time range and the lead time range. The lag time range refers to the time period after the water conservation intervention occurs, and the lead time range refers to the pretreatment measures carried out before construction. The water conservation response is earlier than the intervention.

[0040] Based on the time overlap range, a maximum time delay threshold is set. This maximum time delay threshold is a time limit that defines the maximum acceptable time difference between the intervention and the water conservation response. This ensures that the water conservation response does not lag indefinitely behind the intervention, thus guaranteeing the effectiveness of the water conservation measures. Furthermore, causal constraint rules are formulated based on the type of power transmission and transformation project and the type of water conservation measure. These causal constraint rules are set according to the type of power transmission and transformation project to ensure that the causal relationship between the intervention and the water conservation response conforms to the actual situation. Specifically, for structural measures, such as drainage ditches and retaining walls, the water conservation response should occur immediately or within a short period after the intervention. Therefore, the water conservation response time is limited to not being earlier than the intervention time. For pretreatment measures, such as pre-construction drainage and diversion measures, the response is limited to occur between the intervention and the intervention, reflecting the pre-treatment effect. Moreover, for biological water conservation measures, such as vegetation restoration and ecological slope protection, the response has a natural lag. Therefore, the response lag time is limited to not exceeding the maximum time delay threshold.

[0041] Then, the digital elevation model (DEM) is analyzed using GIS software to calculate the elevation difference between adjacent pixels in each grid cell to obtain the topographic slope of the construction area. The D8 algorithm in the DEM is then used to clarify the upstream and downstream adjacency relationships and water flow convergence direction of each grid cell, obtaining the runoff path. Based on the division results of the water conservation spatial response grid, the grid adjacency relationships are obtained, identifying the direct upstream and downstream units of each grid cell. After obtaining the topographic slope, runoff path, and grid adjacency relationships of the construction area, for each adjacent or water-connected grid cell, the influence attenuation coefficient is calculated using an exponential decay function based on spatial distance, slope difference, and flow direction consistency. For each grid cell, after calculating its upstream influence attenuation coefficient, a row vector is formed. This process is repeated for all grid cells. Based on the calculated influence attenuation coefficients, a spatial propagation weight matrix is ​​constructed. The influence attenuation coefficients in this matrix are the weight values, used to characterize the propagation intensity of upstream intervention on the downstream water conservation response. This represents the physical mapping of construction disturbance along the terrain, and attenuates exponentially with increasing distance and decreasing slope deviation. For example, if an intervention in a grid cell has a strong impact on the water conservation response of a downstream grid cell, its weight value will be higher; conversely, its weight value will be lower. The spatial propagation weight matrix is ​​used to correct the spatial correlation between intervention and response during temporal alignment, thereby achieving a comprehensive consideration of the spatial propagation impact.

[0042] Under the time constraint of the maximum time delay threshold, and combined with the weight conditions of the spatial propagation weight matrix, the intervention feature time series chain and the water conservation feature time series chain are coupled and analyzed. Through a dynamic programming search algorithm, the optimal time alignment path is obtained, and time relationship matching is performed. Then, the intervention feature time series chain and the water conservation feature time series chain are time-aligned according to the matched alignment relationship to obtain the intervention-water conservation effect evaluation feature pair. The intervention-water conservation effect evaluation feature pair refers to the set of corresponding time points of intervention behavior and water conservation response extracted through time alignment relationship. It not only includes the temporal correspondence, but also reflects the comprehensive impact of spatial propagation and construction disturbance, thereby improving the comprehensiveness and accuracy of the actual impact assessment of intervention behavior on water conservation effect, and thus improving the optimization effect of water conservation measures.

[0043] Furthermore, under the time constraint of the maximum delay threshold and the weight condition of the spatial propagation weight matrix, temporal alignment relationship matching is performed, including: constructing a temporal matching matrix between the intervention feature temporal chain and the water conservation feature temporal chain, wherein the matrix elements of the temporal matching matrix are used to represent the matching cost between each time node, the matching cost is calculated based on the numerical difference, rate of change difference, or trend difference at the corresponding time node, and weighted and corrected in combination with the spatial propagation weight to obtain a comprehensive cost function; using a dynamic programming search algorithm to minimize the comprehensive cost function to obtain the optimal alignment path between the intervention and the water conservation response; extracting the corresponding time point set of the intervention behavior and the water conservation response based on the optimal alignment path to determine the temporal alignment relationship.

[0044] Specifically, under the time constraint of the maximum delay threshold and the weighting condition of the spatial propagation weight matrix, temporal alignment relationship matching is performed to determine the optimal temporal coupling path between construction disturbance behavior and water conservation response process. First, based on the intervention feature time series chain and the water conservation feature time series chain, a temporal matching matrix is ​​constructed under the constraint of the maximum delay threshold. Each element of the temporal matching matrix represents the matching cost between an intervention time node and a water conservation response node. The matching cost is calculated based on the numerical difference, rate of change difference, or trend difference at the corresponding time node. The numerical difference refers to the absolute difference between the intervention intensity and the response, reflecting the degree of influence. The rate of change difference is determined by comparing the first derivatives of the two time series, reflecting the similarity between the rate of change of the disturbance and the rate of change of the response. The trend difference reflects the consistency of the two sequences in the direction of change. Specifically, after obtaining the numerical difference, rate of change difference, or trend difference, a preliminary matching cost is obtained through weighted fusion. The weight coefficients of the numerical difference, rate of change difference, or trend difference are determined by empirical weights or optimal coefficients determined through training, controlling the contribution ratio of different difference terms. After calculating the matching cost between each time node, spatial propagation weights are introduced to weight and correct the matching cost. Specifically, the spatial propagation weight matrix is ​​applied to each time series matching cost to obtain the corrected comprehensive cost function. The comprehensive cost function obtained after weight correction not only reflects the temporal differences, but also comprehensively reflects the spatial coupling effect of the two time series, ensuring the physical consistency and spatial rationality of the water conservation effect evaluation.

[0045] The Dynamic Time Warping (DTW) algorithm is employed as the dynamic programming search algorithm to minimize the comprehensive cost function. The DTW algorithm aligns nonlinear time series by searching for the path with the minimum cumulative cost in the time-series matching matrix. The DTW algorithm allows for local scaling of the time axis, effectively obtaining the correlation between intervention and water conservation response at multiple time points. By recursively solving for the minimum cumulative cost at each time point, the optimal alignment path between intervention and water conservation response is obtained. The optimal alignment path consists of a series of matching points, representing the strongest temporal coupling between the disturbance behavior of intervention at time and the response effect of water conservation at time. Based on the optimal alignment path, the corresponding time point set of intervention and water conservation response is extracted, and time-series statistical indicators such as average lag time and response lead are calculated to determine the temporal alignment relationship.

[0046] By determining the time alignment relationship, the water conservation effect of power transmission and transformation projects can be accurately predicted, thereby accurately assessing the actual impact of intervention measures on the water conservation effect, providing reliable data for the optimization of water conservation measures, and improving the effectiveness and reliability of water conservation measure optimization.

[0047] Furthermore, based on the optimal alignment path, the corresponding time point set of intervention behavior and water conservation response is extracted, and the time alignment relationship is determined, including: calculating the time difference between nodes in the time point set and calculating the average lag time; using the average lag time as a representative parameter of the time alignment relationship, the time alignment relationship is determined to reflect the time coupling relationship between intervention and water conservation response within the grid cell.

[0048] Specifically, after obtaining the set of corresponding time points for intervention and water conservation response based on the optimal alignment path, the time difference between each pair of matched nodes is calculated to reflect the reaction lag or lead time of the water conservation response relative to the intervention. Positive values ​​indicate that the response lags behind the intervention, while negative values ​​indicate that the response precedes the intervention. After obtaining the time differences for all nodes, the average lag time is calculated. The average lag time reflects the average reaction time of the water conservation response to the construction intervention within a specific grid cell, integrating the time matching characteristics between multiple intervention times and corresponding water conservation effects. A shorter average lag time indicates a tighter temporal coupling between the intervention and the water conservation response, with the intervention producing water conservation effects quickly. Conversely, a looser temporal coupling indicates a relatively delayed manifestation of water conservation effects, with the water conservation response experiencing a delay, potentially influenced by factors such as topography, poor soil permeability, or delayed implementation of measures. Using the average lag time as a representative parameter of the time-series alignment relationship, the determination of the time-series alignment relationship can effectively reflect the time coupling relationship between intervention and response under water conservation measures in different grids, realize the quantitative dynamic correlation between construction disturbances of power transmission and transformation projects and responses to water conservation measures, and thus formulate and adjust water conservation strategies more effectively and accurately.

[0049] Based on the aforementioned effect evaluation characteristics, water conservation deviation analysis is performed, and the water conservation deviation is optimized and compensated to obtain optimization compensation characteristics, which are used to optimize and adjust water conservation measures.

[0050] Furthermore, based on the aforementioned effect evaluation features, water conservation deviation analysis is performed, and the water conservation deviation is optimized and compensated to obtain optimized compensation features for optimizing and adjusting water conservation measures. This includes: using water conservation targets to perform target evaluation traversal on the aforementioned effect evaluation features to identify water conservation deviation features that have failed to achieve the water conservation targets; adjusting water conservation measure parameters or intervention parameters according to the water conservation deviation features and the corresponding target deviation amounts, with the goal of achieving the water conservation targets, to obtain optimized compensation features for each grid unit; and based on the spatial propagation weight matrix, performing weight accumulation optimization on the optimized compensation features of each grid unit, with the goal of maximizing the targets and minimizing the cost of measures for all grid units, to perform spatial smoothing adjustment and obtain the final optimized compensation features.

[0051] Specifically, water conservation targets are established, which refer to the expected effects of soil and water conservation measures in each grid within the power transmission and transformation project construction area, such as vegetation coverage and soil erosion modulus. The effectiveness evaluation features of the water conservation targets are used to perform a target evaluation traversal, comparing each effectiveness evaluation feature pair with the established water conservation target for that unit, and calculating the deviation between the effectiveness evaluation feature pair and the water conservation target. For example, if the water conservation target is a vegetation coverage rate of 80%, but the actual vegetation coverage rate of the water conservation response is 60%, the deviation is -20%. Through this traversal comparison, all water conservation deviation features that fail to meet the targets are identified. These deviation features represent the difference between the actual water conservation response and the water conservation target, reflecting the degree of deviation between the implementation effect of water conservation measures and the expected target.

[0052] Based on the identified water conservation deviation characteristics and corresponding target deviations, the parameters of water conservation measures or intervention parameters are adjusted for compensation. For example, if the vegetation coverage is lower than the target value, the planting density can be increased or the planting area expanded; if the soil erosion modulus is higher than the target value, engineering protection measures can be strengthened, such as adding retaining walls or drainage facilities. The water conservation measure parameters refer to the specific parameters for implementing water conservation measures, while the intervention parameters refer to parameters that can be adjusted during construction. Through adjustment and compensation, the optimized compensation characteristics of each grid unit are obtained. These optimized compensation characteristics reflect the adjusted water conservation measure parameters or intervention parameters and are used for subsequent optimization and adjustment of measures.

[0053] By utilizing a spatial propagation weight matrix, considering the impact of upstream intervention on downstream water conservation response, for each grid cell, the cumulative impact contribution is calculated based on the optimized compensation characteristics of its upstream cells and the corresponding spatial propagation weights. Weight accumulation optimization is then performed. Through the spatial propagation weight matrix, the mutual influence between upstream and downstream grid cells is comprehensively considered, and the compensation parameters of the grid cells are corrected to reflect both their own biases and the positive or negative impacts of upstream intervention, thereby achieving overall optimization and coordination between upstream and downstream. For example, if an upstream grid cell increases its vegetation planting area, it will have a positive impact on the water conservation response of the downstream grid cell, which is quantified and accumulated through the spatial propagation weight matrix. A comprehensive optimization model is constructed for all grid cells, aiming to maximize the objective of all grid cells and minimize the cost of measures. Spatial smoothing adjustments are made to limit drastic changes in compensation parameters between adjacent cells. Optimization algorithms, such as linear programming and genetic algorithms, are used to reduce the total cost of water conservation measures while meeting the water conservation objectives. During the optimization process, the optimization algorithm iteratively adjusts the compensation parameters of each grid cell, while cumulatively considering the propagation impact from upstream to downstream, until the overall objective function converges, obtaining the final optimized compensation characteristics. For example, using a genetic algorithm for optimization, the compensation parameters of each grid cell, such as vegetation increase area and slope extension length, are encoded into vector form. The set of compensation parameters for the entire grid area forms a single entity. A population is then randomly initialized, with each entity representing a combination of compensation schemes. For each entity, the cumulative impact of each grid cell is calculated using a spatial propagation weight matrix, and the maximum extent to which the water conservation target is met is calculated based on the cumulative compensation amount. Simultaneously, a comprehensive objective function is constructed by combining the actual costs of each measure. The genetic algorithm iteratively updates the population through selection, crossover, and mutation operations, retaining schemes with high target achievement, low cost, and good spatial smoothness. In each iteration, the compensation parameters of each grid cell are continuously adjusted, accumulating the upstream impact on the downstream, thereby gradually approaching the globally optimal solution. Iteration continues until the population fitness converges or reaches the preset number of iterations, at which point the final optimized compensation feature is output. This optimized compensation feature reflects the water conservation measure parameters or intervention parameters after correction by the spatial propagation weight matrix and spatial evaluation, and is used to guide the optimization and adjustment of actual water conservation measures.

[0054] By analyzing and optimizing water conservation deviations based on effect evaluation characteristics, water conservation measures can be precisely optimized to ensure that the measures in each grid unit achieve the expected goals. Furthermore, by utilizing a spatial propagation weight matrix, the impact of upstream intervention on downstream water conservation responses is comprehensively considered, achieving optimal coordination between upstream and downstream areas. Through weight accumulation optimization and spatial smoothing adjustment, the spatial continuity and consistency of water conservation measures throughout the construction area are ensured. By comprehensively considering water conservation effectiveness and cost constraints, dynamic optimization of water conservation effects in power transmission and transformation projects is achieved, improving the accuracy, effectiveness, and economy of water conservation measure optimization for power transmission and transformation projects.

[0055] Example 2, based on the same inventive concept as the method for optimizing the effectiveness of water conservation measures in power transmission and transformation projects in the foregoing examples, such as... Figure 2 As shown, this application provides a system for optimizing the effectiveness of water conservation measures in power transmission and transformation projects, wherein the system includes: The intervention feature time series chain establishment module 11 is used to analyze the periodic water and soil intervention procedures of power transmission and transformation projects and establish the intervention feature time series chain; the water conservation feature time series chain construction module 12 is used to extract the time series features of water conservation measures, such as measures behavior, measures incentives, and measures changes, and construct the water conservation feature time series chain; the effect evaluation feature pair acquisition module 13 is used to couple the intervention feature time series chain with the water conservation feature time series chain for time series analysis, and perform time series alignment according to the coupling time series relationship to obtain the effect evaluation feature pair; the deviation optimization and compensation module 14 is used to perform water conservation deviation analysis based on the effect evaluation feature pair, optimize and compensate for the water conservation deviation, obtain optimization compensation features, and use them to optimize and adjust water conservation measures.

[0056] Furthermore, the intervention feature time sequence chain establishment module 11 is also used to: locate water conservation targets in the coverage construction area of ​​the power transmission and transformation project and obtain the distribution of water conservation targets; and perform spatial grid segmentation based on the distribution of water conservation targets to construct a water conservation spatial response grid.

[0057] Furthermore, the intervention feature time series chain establishment module 11 is also used to: analyze the construction cycle of the power transmission and transformation project for each grid cell in the water conservation spatial response grid, identify the surface disturbance behavior of each cycle, and extract intervention feature parameters; and construct the intervention feature time series chain of each grid cell based on the interference time series relationship of the intervention feature parameters.

[0058] Furthermore, the water conservation feature time series chain construction module 12 is also used to: extract behavioral features, incentive features and change features of the water conservation measures implementation process within the grid unit, and establish a time series node water conservation assessment model; and perform water conservation feature analysis using the time series node water conservation assessment model according to the time series behavioral features in the water conservation measures, and establish the water conservation feature time series chain.

[0059] Furthermore, the intervention feature time series chain establishment module 11 is also used for: each grid cell in the water conservation spatial response grid corresponds to a set of terrain, landform, soil, and vegetation attribute parameters.

[0060] Furthermore, the effect evaluation feature acquisition module 13 is also used to: perform cross-correlation analysis on the intervention feature time series chain of each grid unit and the water conservation feature time series chain to determine the time crossover range between intervention changes and water conservation responses, wherein the time crossover range includes a lag time range and a lead time range; set a maximum time delay threshold according to the time crossover range, and set causal constraint rules according to the type of power transmission and transformation project, wherein for structural measures, the water conservation response time is limited to not being earlier than the intervention action time, for pretreatment measures, the response can be earlier than the intervention action time, and for biological measures, the response lag time is limited to not exceeding the maximum time delay threshold; construct a spatial propagation weight matrix according to the topographic slope, runoff path, and grid adjacency relationship of the construction area to describe the attenuation of the impact of upstream intervention on downstream response; under the time constraint of the maximum time delay threshold and the weight conditions of the spatial propagation weight matrix, perform time series alignment relationship matching, and perform time series alignment of the intervention feature time series chain and the water conservation feature time series chain according to the matched alignment relationship to obtain the intervention-water conservation effect evaluation feature pair.

[0061] Furthermore, the effect evaluation feature acquisition module 13 is also used to: construct a time-series matching matrix between the intervention feature time-series chain and the water conservation feature time-series chain, wherein the matrix elements of the time-series matching matrix are used to represent the matching cost between each time node, and the matching cost is calculated based on the numerical difference, rate of change difference or trend difference at the corresponding time node, and weighted and corrected by combining spatial propagation weights to obtain a comprehensive cost function; use a dynamic programming search algorithm to minimize the comprehensive cost function to obtain the optimal alignment path between the intervention and the water conservation response; extract the corresponding time point set of the intervention behavior and the water conservation response based on the optimal alignment path to determine the time-series alignment relationship.

[0062] Furthermore, the effect evaluation feature acquisition module 13 is also used to: calculate the time difference between nodes in the time point set and calculate the average lag time; use the average lag time as a representative parameter of the time alignment relationship to determine the time alignment relationship, which is used to reflect the time coupling relationship between intervention and water conservation response within the grid cell.

[0063] Furthermore, the deviation optimization compensation module 14 is also used to: perform target evaluation traversal on the effect evaluation features using water conservation targets, identify water conservation deviation features that fail to achieve water conservation targets; adjust water conservation measure parameters or intervention parameters according to the water conservation deviation features and the corresponding target deviation amounts, with the goal of achieving water conservation targets, to obtain the optimized compensation features of each grid unit; and perform weight accumulation optimization on the optimized compensation features of each grid unit based on the spatial propagation weight matrix, with the goal of maximizing the target and minimizing the measure cost of all grid units, to perform spatial smoothing adjustment, and obtain the final optimized compensation features.

[0064] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0065] Obviously, those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of this application.

Claims

1. A method for optimizing the effectiveness of water conservation measures in power transmission and transformation projects, characterized in that, include: Analyze the periodic water and soil intervention procedures in power transmission and transformation projects, and establish a time-series chain of intervention characteristics; Extract temporal features of water conservation measures, including measures behavior, measures incentives, and measures changes, and construct a water conservation feature temporal chain. The intervention feature time series chain and the water conservation feature time series chain are coupled and analyzed, and time series alignment is performed according to the coupling time series relationship to obtain effect evaluation feature pairs; Based on the aforementioned effect evaluation characteristics, water conservation deviation analysis is performed, and the water conservation deviation is optimized and compensated to obtain optimization compensation characteristics, which are used to optimize and adjust water conservation measures.

2. The method for optimizing the effectiveness of water conservation measures in power transmission and transformation projects according to claim 1, characterized in that, Before analyzing the cyclic soil and water intervention procedures in power transmission and transformation projects and establishing the intervention characteristic time sequence chain, the following steps are included: Locate water conservation targets in the construction area covered by power transmission and transformation projects to obtain the distribution of water conservation targets; Based on the distribution of water conservation targets, spatial grid segmentation is performed to construct a water conservation spatial response grid.

3. The method for optimizing the effectiveness of water conservation measures in power transmission and transformation projects according to claim 2, characterized in that, Analyze the cyclic water and soil intervention procedures in power transmission and transformation projects, and establish a time-series chain of intervention characteristics, including: For each grid cell in the water conservation spatial response grid, the construction cycle of the power transmission and transformation project is analyzed to identify the surface disturbance behavior in each cycle and extract intervention feature parameters. Based on the temporal relationship of the intervention feature parameters, the temporal chain of the intervention feature of each grid cell is constructed.

4. The method for optimizing the effectiveness of water conservation measures in power transmission and transformation projects according to claim 3, characterized in that, The construction of the water conservation feature time-series chain includes: Behavioral, incentive, and change characteristics of the water conservation measures implementation process within the grid cell are extracted to establish a time-series node water conservation assessment model. Based on the temporal behavioral characteristics of water conservation measures, the water conservation characteristics are analyzed using the temporal node water conservation assessment model to establish the temporal chain of water conservation characteristics.

5. The method for optimizing the effectiveness of water conservation measures in power transmission and transformation projects according to claim 2, characterized in that, Each grid cell in the water conservation spatial response grid corresponds to a set of terrain, landform, soil, and vegetation attribute parameters.

6. The method for optimizing the effectiveness of water conservation measures in power transmission and transformation projects according to claim 5, characterized in that, The intervention feature time series chain and the water conservation feature time series chain are coupled and analyzed temporally, and then aligned temporally according to the coupling temporal relationship to obtain effect evaluation feature pairs, including: Cross-correlation analysis is performed on the intervention feature time series chain of each grid cell and the water conservation feature time series chain to determine the time crossover range between intervention changes and water conservation response. The time crossover range includes the lag time range and the lead time range. The maximum time delay threshold is set according to the time crossover range, and causal constraint rules are set according to the type of power transmission and transformation project. Specifically, for structural measures, the water conservation response time is limited to not being earlier than the intervention action time; for pretreatment measures, the response can be earlier than the intervention action time; and for biological measures, the response lag time is limited to not exceeding the maximum time delay threshold. Based on the terrain slope, runoff path, and grid adjacency of the construction area, a spatial propagation weight matrix is ​​constructed to describe the attenuation of the impact of upstream intervention on downstream response. Under the time constraints of the maximum delay threshold and the weights of the spatial propagation weight matrix, temporal alignment relationship matching is performed. The intervention feature time series chain and the water conservation feature time series chain are time-aligned according to the matched alignment relationship to obtain the intervention-water conservation effect evaluation feature pair.

7. The method for optimizing the effectiveness of water conservation measures in power transmission and transformation projects according to claim 6, characterized in that, Under the time constraint of the maximum delay threshold and the weight condition of the spatial propagation weight matrix, temporal alignment relationship matching is performed, including: A time series matching matrix is ​​constructed between the intervention feature time series chain and the water conservation feature time series chain. The matrix elements of the time series matching matrix are used to represent the matching cost between each time node. The matching cost is calculated based on the numerical difference, rate of change difference or trend difference at the corresponding time node, and is weighted and corrected by combining spatial propagation weights to obtain a comprehensive cost function. A dynamic programming search algorithm is used to minimize the comprehensive cost function to obtain the optimal alignment path between intervention and water conservation response; Based on the optimal alignment path, extract the corresponding time point set of intervention behavior and water conservation response to determine the time sequence alignment relationship.

8. The method for optimizing the effectiveness of water conservation measures in power transmission and transformation projects according to claim 7, characterized in that, Based on the optimal alignment path, extract the corresponding time point set of intervention behavior and water conservation response, and the time-series alignment relationship, including: Calculate the time difference between nodes in the set of time points and calculate the average lag time; The average lag time is used as a representative parameter of the time alignment relationship to determine the time alignment relationship, which is used to reflect the time coupling relationship between intervention and water conservation response within the grid cell.

9. The method for optimizing the effectiveness of water conservation measures in power transmission and transformation projects according to claim 1, characterized in that, Based on the aforementioned effect evaluation characteristics, water conservation deviation analysis is performed, and the water conservation deviation is optimized and compensated to obtain optimization compensation characteristics, which are used to optimize and adjust water conservation measures, including: The water conservation targets are used to perform a target evaluation traversal on the aforementioned effect evaluation features to identify water conservation deviation features that fail to achieve the water conservation targets. Based on the water conservation deviation characteristics and the corresponding target deviation, the parameters of water conservation measures or intervention parameters are compensated and adjusted to achieve the water conservation target, thereby obtaining the optimized compensation characteristics of each grid unit. Based on the spatial propagation weight matrix, the optimization compensation features of each grid cell are optimized by weight accumulation. The spatial smoothing adjustment is performed with the goal of maximizing the target and minimizing the cost of measures for all grid cells to obtain the final optimization compensation features.

10. A system for optimizing the effectiveness of water conservation measures in power transmission and transformation projects, characterized in that: The steps for implementing the method for optimizing the effectiveness of water conservation measures in power transmission and transformation projects according to any one of claims 1 to 9 include: The intervention feature time series chain establishment module is used to analyze the periodic water and soil intervention procedures of power transmission and transformation projects and establish the intervention feature time series chain. The water conservation feature time series chain construction module is used to extract the time series features of water conservation measures, such as measures behavior, measures incentives, and measures changes, and to construct the water conservation feature time series chain. The effect evaluation feature pair acquisition module is used to perform coupled temporal analysis on the intervention feature time series chain and the water conservation feature time series chain, and perform temporal alignment according to the coupled temporal relationship to obtain the effect evaluation feature pair; The deviation optimization and compensation module is used to perform water conservation deviation analysis based on the effect evaluation characteristics, optimize and compensate for the water conservation deviation, obtain optimization compensation characteristics, and use them to optimize and adjust water conservation measures.

Images