Power grid construction project water and soil conservation management system and method based on big data analysis

Abstract

The invention provides a power grid construction project water and soil conservation management system and method based on big data analysis, and relates to the field of power grid construction projects, the method is helpful to timely discover the influence of a power grid construction project on vegetation and soil, and corresponding protection measures are taken by pre-estimating the future growth condition of plants and the water and soil loss risk in advance, so that the water and soil conservation management of the power grid construction project is realized. The water and soil loss monitoring efficiency of each region of the power grid construction project can be reasonably adjusted by analyzing the abnormal soil growth and the water and soil loss, and the water and soil loss risk region can be accurately and quickly found; from the analysis of the influence of concrete pouring on soil adhesion, the analysis of regional soil growth abnormity, and the prediction of future growth of plants and the analysis of water and soil loss, a plurality of factors such as plant growth conditions, electric field stimulation, soil adhesion, soil nutrients and the like are comprehensively considered, and the influence of a power grid construction project on water and soil conservation is comprehensively evaluated.

Description

Technical Field

[0001] This invention relates to the field of power grid construction project technology, and in particular to a water and soil conservation management system and method for power grid construction projects based on big data analysis. Background Technology

[0002] With rapid socio-economic development, the demand for electricity is constantly increasing, leading to a rise in the number and scale of power grid construction projects. Power grid construction involves extensive land excavation, foundation pouring, and line erection, all of which inevitably impact the ecological environment of the project area, posing a significant challenge, particularly to soil and water conservation. In traditional power grid construction, the lack of comprehensive and systematic monitoring and analysis methods often makes it difficult to accurately assess the extent of the impact of construction activities on soil and vegetation. For example, during concrete pouring, while it is known that it will have some impact on the surrounding soil, it is impossible to precisely understand the specific effects of different types and volumes of concrete on soil physical properties such as cohesion, porosity, and permeability, nor is it easy to grasp the changing patterns of these effects over time.

[0003] Existing soil and water conservation monitoring methods suffer from significant shortcomings in the comprehensiveness and detail of data collection. Some monitoring focuses only on a few indicators such as vegetation cover, neglecting other important information such as vegetation species, root zone location, and chlorophyll content, leading to inaccurate assessments of vegetation growth. Furthermore, data collection methods are relatively limited, relying heavily on manual ground monitoring, making it difficult to obtain large-area, high-precision real-time data and promptly identify potential soil erosion risks during construction. Traditional data analysis methods often consider only single factors or the relationships between a few factors, lacking in-depth analysis of the combined effects of multiple factors. For example, when assessing plant growth, the combined effects of multiple factors such as electric field stimulation, soil cohesion, and soil nutrients are rarely considered simultaneously, resulting in inaccurate predictions of future plant growth trends. In addition, most existing prediction models are based on simple statistical methods, unable to effectively handle complex multi-physics coupling problems, resulting in low prediction accuracy for key indicators such as soil hardness.

[0004] To address the aforementioned issues, this invention provides a water and soil conservation management system and method for power grid construction projects based on big data analysis. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a water and soil conservation management system and method for power grid construction projects based on big data analysis. From the analysis of the impact of concrete pouring on soil bonding, to the analysis of regional soil growth anomalies, and then to the prediction of future plant growth and analysis of soil erosion, the system comprehensively considers multiple factors such as plant growth, electric field stimulation, soil bonding, and soil nutrients to fully assess the impact of power grid construction projects on water and soil conservation.

[0006] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0007] The first aspect of this invention illustrates a method for soil and water conservation management in power grid construction projects based on big data analysis, comprising the following specific steps:

[0008] S1. Obtain the plant growth status at the corresponding project location, as well as the concrete pouring status and soil and water conditions at the corresponding location.

[0009] S2. Based on the concrete pouring situation and the soil and water conditions at the corresponding location, analyze the impact of the concrete pouring process on soil bonding.

[0010] S3. Based on the analysis results of the regional soil bonding influence and soil nutrient status, conduct an analysis of regional soil growth anomalies;

[0011] S4. Based on the plant growth status of regional plants, the electric field stimulation effect in the corresponding direction, and the analysis results of regional soil growth anomalies, predict the future growth of plants.

[0012] S5. Soil and water loss analysis is conducted based on the predicted results of future plant growth and the analysis results of the impact of soil adhesion.

[0013] S6. Issue early warnings based on regional soil and water loss analysis results and generate a soil and water loss distribution map.

[0014] Specifically, S1 includes the following:

[0015] The project area was evenly divided into several fan-shaped areas with angles ranging from 30 to 60 degrees. UAV remote sensing or ground sensors were used to monitor vegetation coverage, chlorophyll content, and vegetation types in each area, as well as the location of the root systems of the corresponding vegetation types in the soil layer. Combined with historical data, the changes in vegetation in each area before and after construction were compared. Building information modeling or construction management systems were used to record the concrete pouring volume, location, time, and construction techniques. Combined with GPS / GIS positioning, a concrete distribution heat map was created to analyze its direct impact on the soil. Soil organic matter content, porosity, and permeability data were collected using soil moisture sensors, pH meters, and nutrient analyzers.

[0016] Specifically, the soil bonding influence analysis includes the following steps:

[0017] The system obtains the location, type, and volume of concrete at each location, as well as the soil porosity, moisture content, and permeability at the corresponding locations.

[0018] Based on the type of concrete, volume of concrete at the corresponding concrete distribution location, soil porosity, moisture and permeability, the soil hardness after concrete is implanted at the corresponding location is predicted and analyzed. The prediction and analysis of soil hardness after concrete is implanted at the corresponding location is performed by a deep learning neural network model.

[0019] Predictive analysis includes the following specific components:

[0020] The study acquires historical data on the type and location of concrete, as well as the volume, soil porosity, moisture, and permeability, and their impact on soil hardness changes before and after concrete implantation. This historical data is divided into an 85% weighted and biased training set and a 15% weighted and biased test set. The 85% weighted and biased training set is input into a deep learning neural network model for training, resulting in an initial deep learning neural network model. The 15% weighted and biased test set is used to test the initial deep learning neural network model, and the output of the initial deep learning neural network model that meets the maximum preset accuracy for predicting soil hardness changes is taken as the deep learning neural network prediction model.

[0021] The concrete type, volume, soil porosity, moisture, and permeability of the corresponding concrete distribution location are obtained and imported into the constructed deep learning neural network prediction model to predict soil bond hardness.

[0022] Obtain a comparison between the predicted soil bonding hardness and the maximum suitable soil hardness at plant roots in each region, and obtain a distribution map of the comparison results.

[0023] Specifically, the analysis of abnormal soil growth in the region includes the following steps:

[0024] The study compares the soil binding hardness at the corresponding plant root depth with the maximum suitable soil hardness at the plant root in each region, and also obtains the content of various elements in the soil of each region. By comparing the soil binding hardness at the plant root depth with the maximum suitable soil hardness, we can intuitively understand whether the soil compaction is suitable for plant root growth.

[0025] Soil element anomalies are obtained by weighting the importance of each element based on the relative deviations between the content of various elements in a region and the appropriate element content for corresponding plant growth. The formula for calculating the relative deviation is as follows: Where mi is the element content, mc is the median of the suitable element content for plant growth, max is the maximum of the suitable element content for plant growth, and min is the minimum of the suitable element content for plant growth; the importance of each element is obtained through experiments; by calculating the relative deviation, the content of various elements in the regional soil can be quantitatively compared with the suitable element content for plant growth, intuitively reflecting the degree of deviation of soil element content. Different elements have different importance to plant growth. By weighting the importance of each element, the impact of soil element anomalies on plant growth can be assessed more accurately. For example, macroelements such as nitrogen, phosphorus, and potassium have a greater impact on plant growth, and their importance weight may be relatively high.

[0026] The analysis results of regional soil growth anomalies are obtained by weighted summation of the obtained soil hardness comparison results and corresponding soil element anomalies. Combining soil hardness comparison results and soil element anomalies allows for a comprehensive assessment of the regional soil growth environment. The physical and chemical properties of soil influence each other, jointly determining plant growth. The results of regional soil growth anomaly analysis can provide accurate decision-making basis for agricultural production and ecological restoration. For example, if the analysis results indicate that soil growth anomalies in a certain area are mainly caused by excessive soil hardness and a deficiency of a certain element, integrating the information from both aspects through weighted summation can reduce the errors caused by single-factor analysis and improve the reliability of the analysis results.

[0027] Specifically, the plant's future growth forecast includes the following details:

[0028] A future vegetation cover prediction model is constructed. The vegetation cover, chlorophyll content, plant species, regional soil growth anomaly analysis results, future weather conditions, and electric field conditions generated by power supply equipment in the corresponding area are obtained and imported into the future vegetation cover prediction model to estimate the vegetation cover of the corresponding area in the future period.

[0029] Among them, the future vegetation cover prediction model is built based on LSTM. The pre-processed data of the future period (vegetation cover, chlorophyll content, plant species, regional soil growth anomaly analysis results, weather conditions of the future period and electric field conditions generated by power supply equipment in the corresponding area) are input into the trained model to obtain the vegetation cover prediction results of the corresponding area in the future period.

[0030] Specifically, the soil and water loss analysis includes the following steps:

[0031] The vegetation cover prediction results and soil bonding hardness prediction results for the corresponding area in the future cycle are obtained. The soil and water loss anomaly value for the corresponding area is obtained by weighted summation based on the standardized vegetation cover prediction results and soil bonding hardness prediction results for the corresponding area in the future cycle. The standardization is the process of dividing the corresponding parameter by the standard value of the corresponding parameter.

[0032] Specifically, the process of generating a soil erosion distribution map based on regional soil erosion analysis results includes the following steps:

[0033] The system obtains the abnormal values ​​of soil erosion in each region and compares them with the corresponding set abnormal values ​​of soil erosion. If the abnormal value of soil erosion in the corresponding region is greater than or equal to the set abnormal value of soil erosion, it indicates that the soil erosion risk in the corresponding region is relatively high, and it is necessary to strengthen the monitoring of soil erosion risk in the corresponding region and carry out soil erosion reinforcement and early warning in the corresponding region. If the abnormal value of soil erosion in the corresponding region is less than the set abnormal value of soil erosion, it indicates that the soil erosion risk in the corresponding region is relatively low, and the current soil erosion risk monitoring method in the corresponding region is maintained. The system then stitches together the areas with relatively high soil erosion risk to generate a soil erosion distribution map and sends it to the client.

[0034] A second aspect of this invention discloses a soil and water conservation management system for power grid construction projects based on big data analysis, used to implement a soil and water conservation management method for power grid construction projects based on big data analysis, including:

[0035] The data acquisition module is used to acquire information on plant growth at the corresponding project location, as well as concrete pouring and soil and water conditions at the corresponding location.

[0036] The Soil Bonding Impact Analysis Module analyzes the impact of the concrete pouring process on soil bonding based on the concrete pouring conditions and soil and water conditions at the corresponding locations.

[0037] The soil growth anomaly analysis module analyzes regional soil growth anomalies based on the results of regional soil bonding influence analysis and soil nutrient status.

[0038] The plant future growth prediction module predicts the future growth of plants based on the plant growth status of regional plants, the electric field stimulation effect in the corresponding direction, and the analysis results of regional soil growth anomalies.

[0039] The soil and water loss analysis module analyzes soil and water loss based on the predicted results of future plant growth and the results of soil binding influence analysis.

[0040] The early warning module provides early warnings based on the results of regional soil and water loss analysis and generates a soil and water loss distribution map.

[0041] A third aspect of the present invention discloses an electronic device, which includes a processor and a memory. The memory is used to store program code and data for analyzing complex high-altitude operation scenarios in substation engineering. The processor is used to call program instructions in the memory to execute the water and soil conservation management method for power grid construction projects based on big data analysis, as shown in the first aspect of the present invention.

[0042] A fourth aspect of the present invention discloses a storage medium comprising a stored program, wherein, when the program is executed, the device on which the storage medium is located executes the water and soil conservation management method for power grid construction projects based on big data analysis as shown in the first aspect of the present invention.

[0043] Based on the above embodiments of the present invention, the water and soil conservation management system and method for power grid construction projects based on big data analysis helps to promptly detect the impact of power grid construction projects on vegetation and soil. By predicting the future growth of plants and the risk of soil erosion in advance, corresponding protective measures can be taken to reduce damage to the ecological environment and promote the sustainable development of the ecosystem. Through the analysis of abnormal soil growth and soil erosion, the monitoring efficiency of soil erosion in various areas of the power grid construction project can be reasonably adjusted, and areas at risk of soil erosion can be quickly and accurately identified.

[0044] From analyzing the impact of concrete pouring on soil bonding, to analyzing regional soil growth anomalies, and then to predicting future plant growth and analyzing soil erosion, the study comprehensively considered multiple factors such as plant growth, electric field stimulation, soil bonding, and soil nutrients to fully assess the impact of power grid construction projects on soil and water conservation. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention 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 only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0046] Figure 1 This is a schematic diagram illustrating the process of a water and soil conservation management method for power grid construction projects based on big data analysis, as shown in an embodiment of the present invention.

[0047] Figure 2 This is a schematic diagram illustrating the soil adhesion impact analysis process in a water and soil conservation management method for power grid construction projects based on big data analysis, as shown in an embodiment of the present invention.

[0048] Figure 3 This is a schematic diagram of the water and soil conservation management system for power grid construction projects based on big data analysis, as shown in an embodiment of the present invention. Detailed Implementation

[0049] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] The terms "first," "second," "third," "fourth," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0051] It should be noted that the descriptions involving "first," "second," etc., in this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Furthermore, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed by this invention.

[0052] In this invention, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0053] Please see Figure 1 and Figure 2 The present invention provides an embodiment of a water and soil conservation management method for power grid construction projects based on big data analysis, which includes the following specific steps:

[0054] S1. Obtain the plant growth status at the corresponding project location, as well as the concrete pouring status and soil and water conditions at the corresponding location.

[0055] In this embodiment, S1 includes the following specific contents:

[0056] The project area was evenly divided into several fan-shaped zones with angles ranging from 30 to 60 degrees. UAV remote sensing or ground sensors were used to monitor vegetation cover, chlorophyll content, and vegetation species in each zone, as well as the soil layer location of the root systems of corresponding vegetation species. Combined with historical data, the vegetation changes in each zone before and after construction were compared. Building Information Modeling (BIM) or a construction management system was used to record concrete pouring volume, location, time, and construction techniques. GPS / GIS positioning was used to create a concrete distribution heat map to analyze its direct impact on the soil. Soil organic matter content, porosity, and permeability data were collected using soil moisture sensors, pH meters, and nutrient analyzers. Dividing the project area into several fan-shaped zones allows for systematic and comprehensive monitoring of the entire project area. Different fan-shaped zones may have differences in topography, sunlight, and moisture; this division helps to understand the vegetation and soil conditions of each zone in greater detail. By employing drone remote sensing or ground sensors to monitor vegetation cover, chlorophyll content, vegetation species, and root zone location, combined with data collection on soil moisture, pH, and nutrients, a comprehensive ecological environment data set for the project area can be obtained. This provides rich and comprehensive material for subsequent analysis, and the multi-angle, multi-indicator monitoring methods can mutually verify and supplement the data. For example, drone remote sensing can obtain large-area vegetation information from a macroscopic perspective, while ground sensors can provide more precise local data; combining the two can improve the accuracy and reliability of the data. Furthermore, comparing vegetation changes before and after construction with historical data allows for a more accurate assessment of the impact of construction activities on vegetation.

[0057] S2. Based on the concrete pouring situation and the soil and water conditions at the corresponding location, analyze the impact of the concrete pouring process on soil bonding.

[0058] In this embodiment, the soil bonding effect analysis includes the following specific steps:

[0059] The system obtains the location, type, and volume of concrete at each location, as well as the soil porosity, moisture content, and permeability at the corresponding locations.

[0060] Based on the concrete type, volume, soil porosity, moisture, and permeability at the corresponding concrete location, this study predicts and analyzes the soil hardness after concrete implantation. The prediction of soil hardness after concrete implantation is conducted using a deep learning neural network model. Predicting soil hardness after concrete implantation is a multi-physics coupling problem, and combining it with a deep learning model (such as a neural network) is feasible. For concrete type, its physical properties (such as density, porosity, and compressive strength) need to be quantified, which can be achieved through one-hot encoding or material parameters (such as elastic modulus). In the model, the following factors are considered: Distribution location and volume: This needs to be converted to volume ratio or equivalent thickness (e.g., concrete volume / soil unit volume) to reflect its spatial encroachment effect on soil structure; Porosity and permeability: These directly affect water migration and stress distribution, and it is necessary to distinguish between initial values ​​and dynamic changes (e.g., pore blockage caused by concrete curing); Humidity: This should be clearly defined as initial moisture content, using volumetric moisture content or matrix potential; Time factors: Concrete curing time and soil-concrete interface chemical interactions (e.g., pH changes) may affect hardness evolution; Stress history: Pre-compression stress caused by construction compaction or natural settlement; The soil mechanics equations are embedded as soft constraints in the loss function to improve prediction reliability.

[0061] Predictive analysis includes the following specific components:

[0062] The study acquires historical data on the type and location of concrete, as well as the volume, soil porosity, moisture, and permeability, and their impact on soil hardness changes before and after concrete implantation. This historical data is divided into an 85% weighted and biased training set and a 15% weighted and biased test set. The 85% weighted and biased training set is input into a deep learning neural network model for training, resulting in an initial deep learning neural network model. The 15% weighted and biased test set is used to test the initial deep learning neural network model, and the output of the initial deep learning neural network model that meets the maximum preset accuracy for predicting soil hardness changes is taken as the deep learning neural network prediction model.

[0063] The concrete type, volume, soil porosity, moisture, and permeability of the corresponding concrete distribution location are obtained and imported into the constructed deep learning neural network prediction model to predict soil bond hardness.

[0064] Obtain the comparison results between the predicted soil bonding hardness and the maximum suitable soil hardness at plant roots in each region, and obtain the distribution map of the comparison results;

[0065] S3. Based on the analysis results of the regional soil bonding influence and soil nutrient status, conduct an analysis of regional soil growth anomalies;

[0066] In this embodiment, the regional soil growth anomaly analysis includes the following specific steps:

[0067] The study compares the soil binding hardness at the corresponding plant root depth with the maximum suitable soil hardness at the plant root in each region, and also obtains the content of various elements in the soil of each region. By comparing the soil binding hardness at the plant root depth with the maximum suitable soil hardness, we can intuitively understand whether the soil compaction is suitable for plant root growth. If soil hardness exceeds a suitable value, it may hinder root extension and nutrient absorption, affecting normal plant growth. A comprehensive understanding of soil chemical properties and the content of various elements in soils of different regions allows for a clear grasp of soil fertility. Different plants have different requirements for various elements, and understanding soil element content helps determine whether the soil can provide the nutrients needed for plant growth, providing basic data for subsequent analysis. This data forms the basis for subsequent analysis of soil element anomalies and regional soil growth anomalies. Accurate data ensures the reliability of subsequent analysis results. The growth and function of plant roots are closely related to the physical and chemical properties of the soil. Soil compaction affects root penetration and oxygen supply, while various elements in the soil are essential nutrients for plant growth and development. Numerous studies have shown that the physical and chemical properties of soil have a significant impact on plant growth, yield, and quality. Therefore, monitoring soil hardness and element content is an important means of assessing soil quality and the plant growth environment.

[0068] Soil element anomalies are obtained by weighting the importance of each element based on the relative deviations between the content of various elements in a region and the appropriate element content for corresponding plant growth. The formula for calculating the relative deviation is as follows: Where mi is the element content, mc is the median of the suitable element content for plant growth, max is the maximum of the suitable element content for plant growth, and min is the minimum of the suitable element content for plant growth; the importance of each element is obtained through experiments; by calculating the relative deviation, the content of various elements in the regional soil can be quantitatively compared with the suitable element content for plant growth, intuitively reflecting the degree of deviation of soil element content. Different elements have different importance to plant growth. By weighting the importance of each element, the impact of soil element anomalies on plant growth can be assessed more accurately. For example, macroelements such as nitrogen, phosphorus, and potassium have a greater impact on plant growth, and their importance weight may be relatively high.

[0069] The analysis results of regional soil growth anomalies are obtained by weighted summation of the obtained soil hardness comparison results and corresponding soil element anomalies. Combining soil hardness comparison results and soil element anomalies allows for a comprehensive assessment of the regional soil growth environment. The physical and chemical properties of soil influence each other, jointly determining plant growth. The results of regional soil growth anomaly analysis can provide accurate decision-making basis for agricultural production and ecological restoration. For example, if the analysis results indicate that soil growth anomalies in a certain area are mainly caused by excessive soil hardness and a deficiency of a certain element, integrating the information from both aspects through weighted summation can reduce the errors caused by single-factor analysis and improve the reliability of the analysis results.

[0070] S4. Based on the plant growth status of regional plants, the electric field stimulation effect in the corresponding direction, and the analysis results of regional soil growth anomalies, predict the future growth of plants.

[0071] In this embodiment, the prediction of future plant growth includes the following specific details:

[0072] A future vegetation cover prediction model is constructed. The vegetation cover, chlorophyll content, plant species, regional soil growth anomaly analysis results, future weather conditions, and electric field conditions generated by power supply equipment in the corresponding area are obtained and imported into the future vegetation cover prediction model to estimate the vegetation cover of the corresponding area in the future period.

[0073] The future vegetation cover prediction model is built on LSTM and includes the following specific components: collecting historical data on vegetation cover, chlorophyll content, and plant species in the corresponding area; obtaining the results of regional soil growth anomaly analysis, which can be obtained based on the previously mentioned soil hardness comparison and element anomaly analysis; and collecting historical and future weather conditions, such as temperature, humidity, precipitation, and light. Weather data can be obtained from meteorological departments or relevant meteorological databases; the electric field conditions generated by power supply equipment in the corresponding area can be recorded and measured using professional electric field monitoring instruments. Check for missing values ​​and outliers in the data. For missing values, interpolation methods (such as linear interpolation and spline interpolation) can be used to fill them in; for outliers, they can be corrected or removed according to the distribution of the data. All data should be standardized to ensure that data with different characteristics have the same scale. For classification data such as plant species, encoding processing is required, such as using one-heat encoding to convert classification variables into numerical variables. Determine the input and output: Input: The preprocessed vegetation cover, chlorophyll content, plant species, regional soil growth anomaly analysis results, future weather conditions, and the electric field conditions generated by power supply equipment in the corresponding area are used as inputs to the model. The input data has an n×m dimension, where n is the number of samples and m is the number of features; Output: The model output is the vegetation cover of the corresponding area in the future period; Building the LSTM network structure: Importing relevant libraries: Use deep learning frameworks (such as TensorFlow, PyTorch) to import the libraries required to build the model; Defining the model architecture: Input layer: Receives the preprocessed input data; LSTM layer: Multiple LSTM units can be used to capture time series information in the data. Each LSTM unit contains an input gate, a forget gate, and an output gate, enabling efficient processing of long sequence data. Fully connected layers map the output of the LSTM layer to a single output node, whose output is the predicted vegetation cover. Activation functions can be used in the output layer, such as linear activation functions, because vegetation cover is a continuous value. The preprocessed dataset is divided into training, validation, and test sets, typically in a 70%, 15%, and 15% ratio. The training set is used for model training, the validation set for tuning hyperparameters, and the test set for evaluating model performance. The LSTM model is trained using the training set.During training, appropriate training parameters need to be set, such as learning rate, batch size, and number of training rounds. The trained model is evaluated using a test set, with common evaluation metrics including mean squared error (MSE), root mean square error (RMSE), and mean absolute error (MAE). Preprocessed data for future periods (vegetation cover, chlorophyll content, plant species, regional soil growth anomaly analysis results, future weather conditions, and electric field conditions generated by power supply equipment in the corresponding area) are input into the trained model to obtain the vegetation cover prediction results for the corresponding area in the future period.

[0074] S5. Soil and water loss analysis is conducted based on the predicted results of future plant growth and the analysis results of the impact of soil adhesion.

[0075] In this embodiment, the soil and water loss analysis includes the following specific steps:

[0076] This method obtains the predicted vegetation cover and soil bond hardness for the corresponding regions in future cycles. Based on the standardized predicted vegetation cover and soil bond hardness, a weighted sum is calculated to obtain the soil erosion anomaly value for the corresponding region. Standardization involves dividing the corresponding parameter by its standard value. Combining the projected future plant growth (vegetation cover prediction) and the soil bond impact analysis (soil bond hardness prediction) for soil erosion analysis allows for a more comprehensive and accurate assessment of soil erosion. Vegetation cover is a crucial factor influencing soil erosion, intercepting rainfall, slowing water flow, and stabilizing soil. Soil bond hardness reflects the soil's resistance to erosion. Considering both factors comprehensively avoids the limitations of single-factor assessments, making the soil erosion analysis results more reliable. By calculating soil erosion anomalies, the complex situation of soil erosion is quantified. This enables intuitive comparison and analysis of soil erosion risks in different regions, facilitating subsequent management and decision-making. Standardization makes different parameters comparable in calculations. Weighted summation allows for a reasonable comprehensive consideration of the impact of each parameter on soil erosion. Vegetation cover is closely related to soil erosion; vegetation reduces the direct impact of raindrops on the soil and lowers surface runoff velocity, thus reducing soil erosion. Soil cohesion hardness reflects the binding force between soil particles; the higher the cohesion hardness, the stronger the soil's resistance to external erosion. Therefore, analyzing soil erosion based on these two parameters aligns with the scientific principles of soil erosion. However, different parameters may have different dimensions and value ranges; direct summation can lead to inaccurate results. Standardization transforms each parameter into a value with the same dimensions and value range, allowing for weighted summation of different parameters on the same scale, thereby obtaining reasonable anomaly values ​​for soil erosion.

[0077] S6. Develop early warning based on the results of regional soil and water loss analysis and generate a soil and water loss distribution map;

[0078] In this embodiment, the following specific steps are included:

[0079] The system compares abnormal soil erosion values ​​in each region with corresponding set soil erosion thresholds. If the abnormal value is greater than or equal to the threshold, the region faces a relatively high risk of soil erosion, requiring enhanced monitoring and early warning for soil erosion reinforcement. Conversely, if the abnormal value is less than the threshold, the risk remains low, and the current monitoring method is maintained. A soil erosion distribution map is generated by stitching together areas with high risk and sent to the client. Comparing the abnormal values ​​with the thresholds allows for timely identification of high-risk areas. Strengthening monitoring and implementing appropriate measures in these high-risk areas effectively prevents and controls soil erosion, reducing its harmful effects. The generated distribution map visually represents the soil erosion risk in each region, helping managers quickly understand the overall soil erosion situation, pinpoint the location of high-risk areas, and provide a clear basis for developing targeted soil erosion prevention and control measures. Simultaneously, soil erosion distribution maps are sent to the client, facilitating timely information access for relevant personnel and improving decision-making efficiency. Based on the comparison results of soil erosion anomalies and thresholds, different monitoring methods are adopted for different areas, achieving dynamic management of soil erosion. For areas with relatively low risk, the current monitoring method is maintained to avoid resource waste caused by over-monitoring; for areas with relatively high risk, monitoring is strengthened to ensure timely understanding of changes in soil erosion.

[0080] In this embodiment, the weights, standard values, and thresholds are obtained experimentally by experts in the field. The acquisition steps include: obtaining the historical plant growth status of the corresponding project location, as well as the concrete pouring status and soil and water conditions of the corresponding location; obtaining the areas with relatively high actual risks; then substituting the data into the analysis model of this embodiment to select the areas with relatively high risks; and importing the actual acquired areas and the acquired areas obtained through analysis into MATLAB fitting software to obtain the weights, standard values, and thresholds with the highest accuracy in judging whether the conditions are met.

[0081] Please see Figure 3The water and soil conservation management system for power grid construction projects based on big data analysis is implemented based on the above-mentioned water and soil conservation management method for power grid construction projects based on big data analysis. It includes: a data acquisition module, which is used to acquire the plant growth status of the corresponding project location, as well as the concrete pouring status of the project and the water and soil conditions of the corresponding location.

[0082] The Soil Bonding Impact Analysis Module analyzes the impact of the concrete pouring process on soil bonding based on the concrete pouring conditions and soil and water conditions at the corresponding locations.

[0083] The soil growth anomaly analysis module analyzes regional soil growth anomalies based on the results of regional soil bonding influence analysis and soil nutrient status.

[0084] The plant future growth prediction module predicts the future growth of plants based on the plant growth status of regional plants, the electric field stimulation effect in the corresponding direction, and the analysis results of regional soil growth anomalies.

[0085] The soil and water loss analysis module analyzes soil and water loss based on the predicted results of future plant growth and the results of soil binding influence analysis.

[0086] The early warning module provides early warnings based on the results of regional soil and water loss analysis and generates a soil and water loss distribution map.

[0087] This invention provides an electronic device, which includes a processor and a memory. The memory stores program code and data for analyzing complex high-altitude operation scenarios in substation engineering, and the processor executes program instructions stored in the memory to implement the water and soil conservation management method for power grid construction projects based on big data analysis disclosed in the above embodiments.

[0088] This invention provides a storage medium, which includes the electronic device described in the above embodiments. The electronic device is used to execute the water and soil conservation management method for power grid construction projects based on big data analysis disclosed in the above embodiments.

[0089] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, they generate in whole or in part the flow or function according to the embodiments of the present invention. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired network and / or wireless network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more sets of available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be solid-state drives.

[0090] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on its differences from other embodiments. For system or system embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. The systems and system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. Components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0091] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0092] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. 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 the invention. Therefore, the invention 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.

Claims

1. A water and soil conservation management method for power grid construction projects based on big data analysis, characterized in that, The specific steps include the following: S1. Obtain the plant growth status at the corresponding project location, as well as the concrete pouring status and soil and water conditions at the corresponding location. S2. Based on the concrete pouring situation and the soil and water conditions at the corresponding location, analyze the impact of the concrete pouring process on soil bonding. S3. Based on the analysis results of the regional soil bonding influence and soil nutrient status, conduct an analysis of regional soil growth anomalies; S4. Based on the plant growth status of regional plants, the electric field stimulation effect in the corresponding direction, and the analysis results of regional soil growth anomalies, predict the future growth of plants. S5. Soil and water loss analysis is conducted based on the predicted results of future plant growth and the analysis results of the impact of soil adhesion. S6. Issue early warnings based on regional soil and water loss analysis results and generate a soil and water loss distribution map.

2. The method for water and soil conservation management of power grid construction projects based on big data analysis according to claim 1, characterized in that, The soil bonding effect analysis includes the following specific steps: The system obtains the location, type, and volume of concrete at each location, as well as the soil porosity, moisture content, and permeability at the corresponding locations. Based on the type of concrete, volume, soil porosity, moisture, and permeability at the corresponding concrete distribution location, the soil hardness after concrete implantation is predicted and analyzed. Specifically, the prediction and analysis of soil hardness after concrete implantation at the corresponding location is performed using a deep learning neural network model. The prediction and analysis include the following details: The system acquires historical data on concrete types, concrete distribution locations, volume, soil porosity, moisture, and permeability, as well as soil hardness changes before and after concrete implantation. This historical data is divided into an 85% weighted, biased training set and a 15% weighted, biased test set. The 85% weighted, biased training set is input into a deep learning neural network model for training, resulting in an initial deep learning neural network model. The 15% weighted, biased test set is used to test the initial deep learning neural network model, and the output of the initial deep learning neural network model that meets the maximum preset accuracy for predicting soil hardness changes is used as the deep learning neural network prediction model. The concrete type, volume, soil porosity, moisture, and permeability of the corresponding concrete distribution location are obtained and imported into the constructed deep learning neural network prediction model to predict soil bond hardness. Obtain a comparison between the predicted soil bonding hardness and the maximum suitable soil hardness at plant roots in each region, and obtain a distribution map of the comparison results.

3. The method for water and soil conservation management of power grid construction projects based on big data analysis according to claim 2, characterized in that, The analysis of abnormal soil growth in the region includes the following specific steps: The results of comparing the soil bonding hardness at the corresponding plant root depth with the maximum suitable soil hardness at the plant roots in each region were obtained, and the content of various elements in the soil of each region was also obtained. Soil element anomalies are obtained by weighting the importance of each element based on the relative deviations between the content of various elements in a region and the appropriate element content for corresponding plant growth. The formula for calculating the relative deviation is as follows: Where mi is the element content, mc is the median of the suitable element content for the corresponding plant growth, max is the maximum of the suitable element content for the corresponding plant growth, and min is the minimum of the suitable element content for the corresponding plant growth. The results of regional soil growth anomaly analysis were obtained by weighted summation of the hardness comparison results and the corresponding soil element anomalies.

4. The water and soil conservation management method for power grid construction projects based on big data analysis according to claim 3, characterized in that, The plant's future growth forecast includes the following specific details: A future vegetation cover prediction model is constructed. The vegetation cover, chlorophyll content, plant species, regional soil growth anomaly analysis results, future weather conditions, and electric field conditions generated by power supply equipment in the corresponding area are obtained and imported into the future vegetation cover prediction model to estimate the vegetation cover of the corresponding area in the future period. The future vegetation cover prediction model is based on LSTM.

5. The method for water and soil conservation management of power grid construction projects based on big data analysis according to claim 4, characterized in that, The soil and water loss analysis includes the following specific steps: The vegetation cover prediction results and soil bonding hardness prediction results for the corresponding area in the future cycle are obtained. The soil and water loss anomaly value for the corresponding area is obtained by weighted summation based on the standardized vegetation cover prediction results and soil bonding hardness prediction results for the corresponding area in the future cycle. The standardization is the process of dividing the corresponding parameter by the standard value of the corresponding parameter.

6. The method for water and soil conservation management of power grid construction projects based on big data analysis according to claim 5, characterized in that, The process of generating a soil erosion distribution map based on regional soil erosion analysis results includes the following specific steps: The system obtains the abnormal values ​​of soil erosion in each region and compares them with the corresponding set abnormal values ​​of soil erosion. If the abnormal value of soil erosion in the corresponding region is greater than or equal to the set abnormal value of soil erosion, it indicates that the soil erosion risk in the corresponding region is relatively high, and it is necessary to strengthen the monitoring of soil erosion risk in the corresponding region and carry out soil erosion reinforcement and early warning in the corresponding region. If the abnormal value of soil erosion in the corresponding region is less than the set abnormal value of soil erosion, it indicates that the soil erosion risk in the corresponding region is relatively low, and the current soil erosion risk monitoring method in the corresponding region is maintained. The system then stitches together the areas with relatively high soil erosion risk to generate a soil erosion distribution map and sends it to the client.

7. A water and soil conservation management system for power grid construction projects based on big data analysis, used to implement the water and soil conservation management method for power grid construction projects based on big data analysis as described in any one of claims 1-6, characterized in that, include: The data acquisition module is used to acquire information on plant growth at the corresponding project location, as well as concrete pouring and soil and water conditions at the corresponding location. The Soil Bonding Impact Analysis Module analyzes the impact of the concrete pouring process on soil bonding based on the concrete pouring conditions and soil and water conditions at the corresponding locations. The soil growth anomaly analysis module analyzes regional soil growth anomalies based on the results of regional soil bonding influence analysis and soil nutrient status. The plant future growth prediction module predicts the future growth of plants based on the plant growth status of regional plants, the electric field stimulation effect in the corresponding direction, and the analysis results of regional soil growth anomalies. The soil and water loss analysis module analyzes soil and water loss based on the predicted results of future plant growth and the results of soil binding influence analysis. The early warning module provides early warnings based on the results of regional soil and water loss analysis and generates a soil and water loss distribution map.

8. An electronic device, characterized in that, The electronic device includes a processor and a memory. The memory is used to store program code and data for analyzing complex high-altitude operation scenarios in substation engineering. The processor is used to call program instructions in the memory to execute the water and soil conservation management method for power grid construction projects based on big data analysis as described in any one of claims 1-6.

9. A storage medium, characterized in that, The storage medium includes a stored program, wherein, when the program is running, it controls the device where the storage medium is located to execute the water and soil conservation management method for power grid construction projects based on big data analysis as described in any one of claims 1-6.

Images