Comprehensive patrol unmanned aerial vehicle control method and system based on multi-source data analysis

Abstract

The invention discloses a comprehensive patrol unmanned aerial vehicle control method and system based on multi-source data analysis, and relates to the technical field of unmanned aerial vehicle control, and the method comprises the steps: obtaining a patrol region geographic map through a GIS, extracting elevation and ground coverage data, and constructing a three-dimensional ground model; power grid inspection point coordinates are determined and configured in a geographic map, and inspection contribution parameters are calculated in combination with a historical abnormal rate and a preset weight; collecting real-time wind power data, and predicting a wind power characteristic sequence; generating a plurality of initial inspection paths, and calculating energy consumption parameters based on wind power prediction and path length; and comprehensively evaluating the inspection contribution sum and the energy consumption sum of each path in the preset period, and selecting an optimal path. Through multi-source data fusion and dynamic path optimization, the method adapts to a complex environment, improves the power grid inspection efficiency, reduces the energy consumption, and shows relatively high innovativeness and practical value.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle (UAV) control, and in particular to an integrated inspection UAV control method and system based on multi-source data analysis. Background Art

[0002] In the field of UAV inspection, especially in the inspection of critical infrastructure such as power grids, the optimization of inspection paths is of crucial significance for improving efficiency and reducing costs. Traditional UAV inspection methods mostly adopt pre-set static path planning. In the face of complex and changeable environmental conditions (such as wind changes), this method often shows poor adaptability, resulting in increased energy consumption or insufficient inspection coverage of key areas. At the same time, there are defects in the priority evaluation of inspection points in the existing technology. Usually, the historical anomaly occurrence rates and importance differences of different inspection points are not fully considered, making it difficult to effectively focus on high-risk areas. In addition, although Geographic Information System (GIS), historical inspection data, and real-time environmental monitoring data have each been studied to a certain extent in UAV applications, the existing methods lack a systematic framework for integrating these multi-source data and using them for dynamic path optimization. This makes it difficult for UAVs to balance energy consumption efficiency and inspection effectiveness in actual inspections. To address the above problems, there is an urgent need for a UAV control method that can integrate multi-source data, dynamically adapt to environmental changes, and comprehensively consider energy consumption and inspection contributions. Summary of the Invention

[0003] The purpose of the present invention is to provide an integrated inspection UAV control method and system capable of optimizing UAV paths.

[0004] The present invention discloses an integrated inspection UAV control method based on multi-source data analysis, including: Step S100, using a GIS system to obtain a geographical map of the inspection area, determining the elevation data distribution and ground cover data of the geographical map of the inspection area, and constructing three-dimensional ground protrusions on the geographical map of the inspection area; Step S200, determining the coordinate positions of power grid inspection points, configuring the corresponding power grid inspection points on the geographical map of the inspection area, obtaining historical inspection records, determining the anomaly occurrence rates of different power grid inspection points from the historical inspection records, and combining the pre-set inspection weights of different power grid inspection points to determine the inspection contribution parameters of different power grid inspection points when triggered for inspection; Step S300, obtaining real-time wind monitoring data, and determining a wind feature prediction sequence based on the wind features of the real-time wind monitoring data; Step S400, constructing several initial inspection paths, and determining the energy consumption parameters of each initial inspection path based on the wind feature prediction sequence and path length; Step S500, comprehensively consider the total inspection contribution parameters and the total energy consumption parameters of each initial inspection path within a preset time period, and select the optimal inspection path.

[0005] In some embodiments of the present invention, the method for determining the wind characteristic prediction sequence based on the wind characteristics of real-time wind monitoring data includes: Step S301, construct a wind prediction model, and use the wind prediction model to analyze the wind characteristics of real-time wind monitoring data to determine the wind characteristic prediction sequence. Among them, the method for constructing the wind prediction model includes: Step S3011, arrange wind monitoring devices for the inspection area, and map the position nodes where the wind monitoring devices are arranged onto the geographical map of the inspection area to obtain a number of wind performance nodes; Step S3012, obtain the historical wind monitoring data of the wind monitoring devices, align the historical wind monitoring data on the time axis, and respectively map and represent the corresponding wind performance nodes to form the historical wind performance state of the wind performance nodes. The historical wind performance state includes dynamically changing wind performance frames, and each wind performance frame includes a wind direction line. The direction of the wind direction line is used to represent the monitored wind direction, and the length is used to represent the monitored wind force; Step S3013, obtain the historical weather forecast, align the historical wind forecast in the historical weather forecast and a number of historical wind monitoring data on the time axis, and map and represent the historical wind forecast on each wind performance node on the geographical map of the inspection area to form the historical wind forecast performance state. The historical wind forecast performance state includes dynamically changing wind forecast performance frames, and each wind forecast performance frame includes a wind forecast direction line. The direction of the wind forecast direction line is used to represent the forecast wind direction, and the length is used to represent the forecast wind force; Step S3014, compare the historical wind performance state and the historical forecast performance state, and based on the comparison result, classify the corresponding historical wind forecast and historical wind monitoring data, and construct a retrieval logic framework for the classified data set to obtain a wind prediction model.

[0006] In some embodiments of the present invention, the method for classifying the corresponding historical wind forecast and historical wind monitoring data includes: Step S3015, compare the historical wind performance state and the historical forecast performance state in the same time period, that is, compare several consecutive wind performance frames and wind forecast performance frames of each wind performance node, judge the difference characteristics of the direction lines of each frame, and determine the inter-state compliance parameter between the historical wind performance state and the historical forecast performance state. If the inter-state compliance parameter is greater than or equal to the preset value, it is determined that the corresponding historical wind forecast and historical wind monitoring data are equivalent in performance; Step S3016: Classify the historical wind force forecasts and historical wind force monitoring data with equivalent performances to obtain a dataset corresponding to equivalent historical wind forces, and classify the historical wind force forecasts and historical wind force monitoring data with non-equivalent performances to obtain a dataset corresponding to non-equivalent historical wind forces; Step S3017: Recognize each historical wind force forecast in the dataset corresponding to equivalent historical wind forces as the first retrieval condition, and its corresponding historical wind force monitoring data as the second retrieval condition, and construct a retrieval logic framework for the dataset corresponding to equivalent historical counterparts. Take each historical wind force monitoring data in the dataset corresponding to non-equivalent historical counterparts as the only retrieval condition, and construct a retrieval logic framework for the dataset corresponding to non-equivalent historical counterparts; Step S3018: Construct the datasets corresponding to equivalent historical counterparts and non-equivalent historical counterparts into a database of the wind force prediction model, and use the retrieval logic framework to retrieve the corresponding historical wind force monitoring data.

[0007] In some embodiments of the present invention, the method for analyzing the wind force characteristics of real-time wind force monitoring data using the wind force prediction model includes: Step S302: Dynamically map each wind force performance node of the real-time wind force monitoring data on the geographical map of the inspection area to form the real-time wind force performance state of the wind force performance node; Step S303: Substitute the real-time wind force monitoring data into the database of the wind force prediction model. First, compare the real-time wind force monitoring data corresponding to some time periods with the historical wind force forecasts. If there is a matching historical wind force forecast, determine the historical wind force monitoring data corresponding to the historical wind force forecast, and compare the historical wind force performance state corresponding to the historical wind force monitoring data with the corresponding real-time wind force performance state, and calculate the state matching parameter. If the state matching parameter is greater than or equal to the preset value, use the subsequent performance characteristics of the corresponding historical wind force performance state as the predicted wind force characteristics, and serialize the predicted wind force characteristics to obtain the wind force characteristic prediction sequence. If there is no matching historical wind force forecast, compare the real-time wind force performance state with the historical wind force performance states of different historical wind force monitoring data, and calculate the state matching parameter. If the state matching parameter is greater than or equal to the preset value, use the subsequent performance characteristics of the corresponding historical wind force performance state as the predicted wind force characteristics, and serialize the predicted wind force characteristics to obtain the wind force characteristic prediction sequence.

[0008] In some embodiments of the present invention, the expression for calculating the state matching parameter is: ; where F is the state matching parameter, is the sub-state matching parameter corresponding to the t-th time node, T is the total number of time nodes participating in the state matching comparison, and L is the influence adjustment coefficient of the sub-state matching parameter. The constant is adjusted for the influence of the sub-state matching parameter; Among them, the expression for calculating the sub-state matching parameter is: ; Among them, is the line matching parameter of the wind direction lines of the i-th wind performance node. If the included angle between the wind direction lines is less than or equal to the preset value and the length difference between the lines is less than or equal to the preset value, then output the first parameter value. If the included angle between the wind direction lines is less than or equal to the preset value and the length difference between the lines is greater than the preset value, then output the second parameter value. If the included angle between the wind direction lines is greater than the preset value and the length difference between the lines is greater than the preset value, then output 0. Among them, the first parameter value is greater than or equal to the second parameter value, the second parameter value is greater than 0, and n is the total number of wind performance nodes.

[0009] In some embodiments of the present invention, the method for determining the energy consumption parameter of each initial inspection path based on the wind power feature prediction sequence and the path length includes: Step S401: Construct a virtual mapping point of the unmanned aerial vehicle (UAV) on the geographical map of the inspection area, and drive the virtual mapping point of the UAV to perform a translation mapping according to the initial inspection path; Step S402: Determine the wind power features corresponding to the virtual mapping point of the UAV at different path nodes in the wind power feature prediction sequence, and determine the wind resistance energy consumption parameter corresponding to the virtual mapping point of the UAV based on the wind power features; Step S403: Calculate the sum of the wind resistance energy consumption parameters corresponding to all path nodes, calculate the sum of the basic energy consumption parameters corresponding to all path nodes, and calculate the sum of the sum of the wind resistance energy consumption parameters and the sum of the basic energy consumption parameters, which is recorded as the energy consumption parameter of the initial inspection path.

[0010] In some embodiments of the present invention, the method for determining the wind resistance energy consumption parameter corresponding to the UAV mapping point based on the wind power features includes: Step S4021: Based on the wind power features, determine the included angle between the wind direction and the initial inspection path and the wind power intensity, and determine the wind power influence coefficient based on the included angle. The wind power influence coefficient refers to the wind power energy consumption conversion ratio for increasing the energy consumption of the UAV mapping point by the wind power; Step S4022: Calculate the product of the wind power influence coefficient and the wind power intensity to obtain the wind resistance energy consumption parameter.

[0011] In some embodiments of the present invention, the method for comprehensively considering the sum of the inspection contribution parameters and the sum of the energy consumption parameters of each initial inspection path within a preset time period includes: Step S501: Set several parameter interval groups for the total inspection contribution parameters and the total energy consumption parameters. Each parameter interval group includes a total inspection contribution parameter interval and a total energy consumption parameter interval. Each parameter interval group is associated with a set inspection contribution consideration coefficient and an energy consumption consideration coefficient. Step S502: Determine the parameter intervals to which the total inspection contribution parameters and the total energy consumption belong respectively, and determine their corresponding consideration coefficients. Then, combine the total inspection contribution parameters and the total energy consumption to calculate the comprehensive consideration value of the initial inspection path. Based on the level of the comprehensive consideration value, determine the selected optimal inspection path. Among them, the expression for calculating the comprehensive consideration value is: ; Among them, Z is the comprehensive consideration value, is the inspection contribution consideration coefficient, G is the total inspection contribution parameter, is the energy consumption consideration coefficient, and H is the total energy consumption.

[0012] In some embodiments of the present invention, a comprehensive inspection UAV control system based on multi-source data analysis is also disclosed, including: The first module is used to obtain the geographical map of the inspection area by using the GIS system, determine the elevation data distribution and ground cover data of the geographical map of the inspection area, and construct a three-dimensional ground protrusion on the geographical map of the inspection area. The second module is used to determine the coordinate positions of the power grid inspection points, configure the corresponding power grid inspection points on the geographical map of the inspection area, obtain the historical inspection records, determine the abnormal occurrence rates of different power grid inspection points for the historical inspection records, and combine the preset inspection weights of different power grid inspection points to determine the inspection contribution parameters of different power grid inspection points when being triggered for inspection. The third module is used to obtain the real-time wind monitoring data and determine the wind characteristic prediction sequence based on the wind characteristics of the real-time wind monitoring data. The fourth module is used to construct several initial inspection paths and determine the energy consumption parameters of each initial inspection path based on the wind characteristic prediction sequence and the path length. The fifth module is used to comprehensively consider the total inspection contribution parameters and the total energy consumption parameters of each initial inspection path within a preset time period, and select the optimal inspection path.

[0013] The present invention discloses a comprehensive inspection UAV control method and system based on multi-source data analysis, which relates to the technical field of UAV control, and includes: using GIS to obtain the geographical map of the inspection area, extracting elevation and ground cover data, and constructing a three-dimensional ground model; determining the coordinates of the power grid inspection points and configuring them on the geographical map, and calculating the inspection contribution parameters by combining the historical anomaly rate and the preset weight; collecting real-time wind data and predicting the wind feature sequence; generating multiple initial inspection paths, and calculating the energy consumption parameters based on wind prediction and path length; comprehensively evaluating the total inspection contribution and the total energy consumption of each path within a preset period, and selecting the optimal path. Through multi-source data fusion and dynamic path optimization, the present invention adapts to complex environments, improves the power grid inspection efficiency and reduces energy consumption, showing high innovation and practical value.

[0014] The technical solution of the present invention will be further described in detail below through the accompanying drawings and embodiments. Brief Description of the Drawings

[0015] Figure 1 It is a method step diagram of the comprehensive inspection UAV control method based on multi-source data analysis disclosed in the embodiment of the present invention. Detailed Embodiments

[0016] The technical solution of the present invention will be further described below through the accompanying drawings and embodiments.

[0017] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and cannot be construed as limiting the protection scope of the present invention. Those skilled in the art can make some non-essential improvements and adjustments according to the content of the present invention described below. In the present invention, unless otherwise clearly defined and limited, the technical terms used in the present invention should have the ordinary meaning understood by those skilled in the art of the present invention.

[0018] Embodiment:

[0019] The present invention discloses a comprehensive inspection UAV control method based on multi-source data analysis. Refer to Figure 1 , including: Step S100, using the GIS system to obtain the geographical map of the inspection area, determining the elevation data distribution and ground cover data of the geographical map of the inspection area, and constructing a three-dimensional ground protrusion on the geographical map of the inspection area.

[0020] The core of this step is to use Geographic Information System (GIS) to obtain the geographical map of the inspection area, and extract the elevation data and ground cover data therein to construct a three-dimensional ground model. The elevation data reflects the undulating characteristics of the terrain, such as the height of a hillside or the depth of a valley, while the ground cover data reveals the surface coverage, such as the distribution of vegetation, the location of water bodies, or the presence of buildings. By integrating these data into the GIS system, a three-dimensional model containing ground convex features can be generated. This three-dimensional model provides intuitive and accurate environmental basic information for subsequent UAV path planning. For example, in a mountainous environment, the UAV needs to adjust its flight altitude according to the terrain height to avoid hitting the mountain; while in an urban area, protrusions such as high-rise buildings may require the UAV to detour or increase its flight altitude. In this way, step S100 provides the UAV inspection with the ability to dynamically adapt to the terrain. Compared with the two-dimensional plane maps often used in traditional technologies, this step uses three-dimensional modeling to significantly improve the accuracy and safety of path planning.

[0021] Step S200: Determine the coordinate positions of the power grid inspection points, configure the corresponding power grid inspection points on the geographical map of the inspection area, obtain historical inspection records, determine the abnormal occurrence rates of different power grid inspection points for the historical inspection records, and combine the preset inspection weights of different power grid inspection points to determine the inspection contribution parameters of different power grid inspection points when triggered by inspection.

[0022] This step aims to determine the accurate coordinates of the power grid inspection points, map them to the geographical map of the inspection area generated in step S100, and at the same time, by analyzing the historical inspection records, quantify the inspection contribution parameters of each inspection point. Specifically, first obtain the historical inspection data and calculate the abnormal occurrence rate of each inspection point, that is, the occurrence frequency of faults or problems; then combine the preset inspection weights (usually based on the importance of the inspection points, for example, the weight of a substation is higher than that of an ordinary electric pole) to calculate the inspection contribution parameters. This parameter comprehensively reflects the risk level and importance of the inspection point. For example, a power tower that often has faults may have a high abnormal occurrence rate, and a power supply core node has a high weight. After combining the two, its inspection contribution parameter will increase significantly, so it will be given priority in path planning. Compared with the methods of evenly distributing inspection points or static priorities often used in the existing technologies, this step dynamically quantifies the inspection requirements in a data-driven manner, making the inspection more targeted and efficient.

[0023] Step S300: Obtain real-time wind monitoring data, and determine the wind characteristic prediction sequence based on the wind characteristics of the real-time wind monitoring data.

[0024] Step S300 obtains real-time wind monitoring data, analyzes wind characteristics such as wind direction and wind speed, and predicts future wind changes based on this to generate a wind characteristic prediction sequence. This sequence provides dynamic environmental input for the UAV path planning. Wind has an important impact on UAV flight: the magnitude of the wind speed is directly related to the flight resistance. Flying with the wind can reduce energy consumption, while flying against the wind requires additional power support; changes in wind direction may require the UAV to adjust its heading to maintain stability. By predicting the wind trend, for example, predicting that the wind speed will increase or the wind direction will turn within the next hour, the UAV can adapt to these changes in advance when planning the path, thus optimizing the flight strategy. Compared with the static path planning in traditional technologies that mostly ignore dynamic wind factors, this step introduces a real-time monitoring and prediction mechanism, enabling the UAV to more intelligently cope with complex meteorological conditions and improve flight efficiency and safety.

[0025] Step S400 constructs several initial inspection paths and determines the energy consumption parameters of each initial inspection path based on the wind characteristic prediction sequence and the path length.

[0026] This step generates multiple initial inspection paths based on the aforementioned 3D model, inspection point configuration, and wind characteristic prediction, and evaluates the energy consumption parameters of each path. Specifically, the path length is a fundamental factor affecting flight time and energy consumption, and the wind characteristics (such as with the wind or against the wind) will further adjust the actual energy consumption. For example, a shorter path may have the lowest energy consumption under windless conditions, but in the case of strong headwinds, its energy consumption may be higher than that of a slightly longer but tailwind path. By comprehensively analyzing the path length and the wind characteristic prediction sequence, the energy consumption parameters of each path are calculated to provide data support for subsequent optimization. This process breaks through the limitation of generating paths only based on distance or fixed rules in traditional technologies and introduces the evaluation of energy consumption with dynamic environmental factors. For example, in areas with high wind speeds, the UAV may choose to bypass to take advantage of the tailwind, thus achieving the optimal balance of energy consumption.

[0027] Step S500 comprehensively considers the total inspection contribution parameters and the total energy consumption parameters of each initial inspection path within a preset time period and selects the optimal inspection path.

[0028] Step S500 is a crucial step for comprehensively evaluating the initial paths and selecting the optimal inspection path. The specific method is to conduct a trade-off analysis on the total inspection contribution parameters (reflecting the inspection effect) and the total energy consumption parameters (reflecting the energy consumption level) of each path within a preset time period, and finally determine the optimal path. The total inspection contribution parameters are accumulated from the contribution parameters of each inspection point in Step S200, reflecting the ability of the path to cover high-risk or important inspection points; the total energy consumption parameters are calculated in Step S400, reflecting the energy consumption level of the path. Comprehensive consideration can usually be achieved through methods such as weighted summation or Pareto optimization. For example, set the weight ratio of the inspection effect to the energy consumption, calculate the comprehensive score of each path, and select the one with the highest score. Compared with traditional technologies that often only focus on the path coverage range or a single energy consumption index, this step achieves a balance between the inspection effect and the energy consumption through multi-objective optimization. For example, in the case of limited resources, the drone may preferentially select a path that covers key inspection points and has lower energy consumption, thereby improving the overall inspection efficiency.

[0029] In some embodiments of the present invention, the method for determining the wind characteristic prediction sequence based on the wind characteristics of real-time wind monitoring data includes: Step S301, construct a wind prediction model and use the wind prediction model to analyze the wind characteristics of the real-time wind monitoring data to determine the wind characteristic prediction sequence, wherein the method for constructing the wind prediction model includes: Step S3011, arrange wind monitoring devices for the inspection area and map the position nodes of the arranged wind monitoring devices onto the geographical map of the inspection area to obtain a number of wind performance nodes.

[0030] The principle of arranging wind monitoring devices and mapping nodes is to reasonably set wind monitoring equipment within the inspection area, collect wind data at different positions in real time, and accurately map the positions of these devices onto the geographical map of the inspection area to form a number of "wind performance nodes". These nodes provide a geographical reference basis for subsequent spatial wind analysis. The arrangement of wind monitoring devices needs to consider factors such as the terrain and building distribution of the area to ensure the representativeness of the data. Compared with the single or small number of fixed monitoring points commonly used in traditional technologies, this step can capture the wind distribution characteristics within the area more comprehensively through multi-point distributed arrangement. For example, in complex terrains such as mountains or urban environments, the wind may change significantly due to local obstacles, and multi-point monitoring can effectively reflect these differences. This method breaks through the spatial limitations of traditional wind monitoring and provides a more accurate environmental basis for wind characteristic prediction based on real-time data.

[0031] Step S3012: Obtain the historical wind monitoring data of the wind monitoring device, align the historical wind monitoring data on the time axis, and respectively map and represent the corresponding wind performance nodes to form the historical wind performance state of the wind performance nodes. The historical wind performance state includes dynamically changing wind performance frames. Each wind performance frame includes a wind direction indicating line. The direction of the wind direction indicating line is used to represent the monitored wind direction, and the length is used to represent the monitored wind force.

[0032] The principle of forming the historical wind performance state is to utilize the historical wind data collected by the wind monitoring device, align it along the time axis, and map it to the corresponding wind performance nodes, thereby constructing a dynamic "historical wind performance state". This performance state consists of multiple "wind performance frames". Each frame contains a "wind direction indicating line", whose direction represents the monitored wind direction and the length reflects the wind force. This method converts scattered wind data into an intuitive spatio-temporal sequence, facilitating the analysis of the variation laws of wind force over time and space. In traditional technologies, wind data is usually stored in tabular or numerical forms, making it difficult to directly reflect dynamic characteristics. However, through frame serialization and visualization design in this step, the interpretability of the data is significantly improved. For example, when analyzing the monsoon changes in a certain region, the periodic patterns of wind direction and wind force can be clearly identified through the historical performance state, providing a reliable basis for subsequent predictions.

[0033] Step S3013: Obtain the historical weather forecast, align the historical wind forecast in the historical weather forecast and several historical wind monitoring data on the time axis, and map and represent the historical wind forecast at each wind performance node on the geographical map of the inspection area to form the historical wind forecast performance state. The historical wind forecast performance state includes dynamically changing wind forecast performance frames. Each wind forecast performance frame includes a wind forecast direction indicating line. The direction of the wind forecast direction indicating line is used to represent the forecast wind direction, and the length is used to represent the forecast wind force.

[0034] The principle of forming the historical wind forecast performance state is to extract the wind forecast data from the historical weather forecast, align it with the historical wind monitoring data on the time axis, and map it to each wind performance node in the inspection area to form the "historical wind forecast performance state". Similar to the historical wind performance state, this performance state is composed of "wind forecast performance frames". Each frame contains a "wind forecast direction indicating line", whose direction and length respectively represent the forecast wind direction and wind force magnitude. Through this design, the forecast data is integrated into the same framework as the monitoring data, facilitating subsequent comparison and analysis. In traditional technologies, wind forecast data is mostly used for post-event verification or independent analysis. However, in this step, it is transformed into a dynamic performance state, giving full play to the role of forecast data in pattern recognition. For example, if a certain historical forecast accurately predicted a strong wind event, this forecast pattern can be recorded and used to improve the accuracy of future predictions.

[0035] In some embodiments of the present invention, the method for classifying corresponding historical wind power forecasts and historical wind power monitoring data includes: Step S3015: Compare the historical wind power performance states and historical forecast performance states in the equivalent time periods, that is, compare several consecutive wind power performance frames and wind power forecast performance frames of each wind power performance node, determine the difference characteristics of the pointing lines of each frame, and determine the in-state matching parameter between the historical wind power performance state and the historical forecast performance state. If the in-state matching parameter is greater than or equal to the preset value, it is determined that the corresponding historical wind power forecast and historical wind power monitoring data are equivalent in performance.

[0036] The principle of comparing the historical performance state and the forecast performance state is to calculate the "in-state matching parameter" to quantify the similarity between the historical wind power monitoring data and the forecast data in the same time period. Specifically, for each wind power performance node, compare the consecutive wind power performance frames and wind power forecast performance frames, and analyze the direction and length differences of the pointing lines. If the differences are small (that is, the in-state matching parameter is greater than or equal to the preset value), it is considered that the historical forecast and monitoring data in this section are "equivalent in performance". This step identifies the scenarios with accurate historical forecasts through dynamic comparison and provides data support for the prediction model. In traditional technologies, the evaluation of forecast accuracy mostly relies on statistical indicators such as the mean square error, while this step uses the pattern matching method of frame sequences to more finely capture the spatio-temporal characteristics of wind power changes. For example, in a certain storm, if the forecast pointing line is highly consistent with the actual pointing line, this pattern can be used as a reference for predicting future similar events.

[0037] Step S3016: Classify the historical wind power forecasts and historical wind power monitoring data with equivalent performance to obtain an equivalent historical wind power corresponding data set, and classify the historical wind power forecasts and historical wind power monitoring data with non-equivalent performance to obtain a non-equivalent historical wind power corresponding data set.

[0038] The principle of data classification is to divide the historical wind power forecasts and monitoring data into two categories according to the comparison results: "equivalent historical wind power corresponding data set" (the forecast and monitoring performances are equivalent) and "non-equivalent historical wind power corresponding data set" (the forecast and monitoring performances are not equivalent). This classification lays a foundation for subsequent retrieval and prediction. The equivalent data set contains the scenarios with accurate historical forecasts and can be used as a priority reference for prediction, while the non-equivalent data set provides supplementary information for handling situations with large forecast deviations. In traditional technologies, historical data is often processed uniformly without targeted classification, while this step improves the accuracy of data utilization by distinguishing between equivalent and non-equivalent performances. For example, when predicting strong winds, preferentially using the patterns in the equivalent data set can effectively improve the reliability of the prediction results.

[0039] Step S3017: Consider each historical wind power forecast in the equivalent historical wind power corresponding dataset as the first retrieval condition, and its corresponding historical wind power monitoring data as the second retrieval condition. Construct a retrieval logic framework for the equivalent historical corresponding dataset. Consider each historical wind power monitoring data in the non - equivalent historical corresponding dataset as the only retrieval condition, and construct a retrieval logic framework for the non - equivalent historical corresponding dataset.

[0040] The principle of constructing the retrieval logic framework is to design different retrieval conditions and logics for the classified datasets to achieve rapid matching of historical patterns. For the equivalent historical wind power corresponding dataset, the historical wind power forecast is regarded as the "first retrieval condition", and the corresponding monitoring data is regarded as the "second retrieval condition"; for the non - equivalent historical wind power corresponding dataset, only the historical monitoring data is regarded as the "only retrieval condition". This design makes full use of the predictive value of the forecast data while retaining the authenticity of the monitoring data, ensuring the accuracy and applicability of the retrieval results. In traditional technologies, data retrieval is mostly based on simple time or location conditions, while in this step, through multi - condition combined retrieval, more efficient pattern matching is achieved. For example, in real - time prediction, if the current wind power characteristics are similar to a certain historical forecast, the corresponding monitoring data can be directly called as the prediction basis.

[0041] Step S3018: Construct the equivalent historical corresponding dataset and the non - equivalent historical corresponding dataset into the database of the wind power prediction model, and use the retrieval logic framework to retrieve the corresponding historical wind power monitoring data.

[0042] The principle of establishing the model database is to integrate the classified equivalent and non - equivalent datasets into the database of the wind power prediction model, and through the retrieval logic framework, extract the historical patterns matching the real - time wind power monitoring data from the database, and then predict the future wind power characteristics. This database provides support for dynamic wind power prediction through pattern matching of historical data. Compared with traditional wind power prediction methods based on statistical models or time - series analysis, this step combines pattern retrieval with historical data and can respond quickly in complex or emergency scenarios. For example, in drone patrol, if a sudden change in wind power is detected in real - time, the model can quickly retrieve similar historical scenarios and generate a wind power characteristic prediction sequence to optimize the flight path.

[0043] In some embodiments of the present invention, the method for analyzing the wind power characteristics of real - time wind power monitoring data using the wind power prediction model includes: Step S302: Dynamically map each wind power performance node of the real - time wind power monitoring data on the geographical map of the inspection area to form the real - time wind power performance state of the wind power performance node.

[0044] Step S303: Substitute the real-time wind power monitoring data into the database of the wind power prediction model. First, compare the real-time wind power monitoring data corresponding to some time periods with the historical wind power forecasts. If there is a matching historical wind power forecast, determine the historical wind power monitoring data corresponding to the historical wind power forecast, and compare the historical wind power performance state corresponding to the historical wind power monitoring data with the corresponding real-time wind power performance state, calculate the matching parameter between the states. If the matching parameter between the states is greater than or equal to the preset value, use the subsequent performance characteristics of the corresponding historical wind power performance state as the predicted wind power characteristics, and serialize the predicted wind power characteristics to obtain the wind power characteristic prediction sequence. If there is no matching historical wind power forecast, compare the real-time wind power performance state with the historical wind power performance states of different historical wind power monitoring data, and calculate the matching parameter between the states. If the matching parameter between the states is greater than or equal to the preset value, use the subsequent performance characteristics of the corresponding historical wind power performance state as the predicted wind power characteristics, and serialize the predicted wind power characteristics to obtain the wind power characteristic prediction sequence.

[0045] In some embodiments of the present invention, the expression for calculating the matching parameter between the states is: .

[0046] Where F is the matching parameter between the states, is the sub-matching parameter between the states corresponding to the t-th time node, T is the total number of time nodes participating in the matching comparison between the states, L is the influence adjustment coefficient of the sub-matching parameter between the states, is the influence adjustment constant of the sub-matching parameter between the states; Where the expression for calculating the sub-matching parameter between the states is: .

[0047] Where, is the line matching parameter between the wind direction lines of the i-th wind power performance node. If the included angle between the wind direction lines is less than or equal to the preset value and the length difference between the lines is less than or equal to the preset value, then output the first parameter value. If the included angle between the wind direction lines is less than or equal to the preset value and the length difference between the lines is greater than the preset value, then output the second parameter value. If the included angle between the wind direction lines is greater than the preset value and the length difference between the lines is greater than the preset value, then output 0. Where the first parameter value is greater than or equal to the second parameter value, the second parameter value is greater than 0, and n is the total number of wind power performance nodes.

[0048] In some embodiments of the present invention, the method for determining the energy consumption parameter of each initial inspection path based on the wind power characteristic prediction sequence and the path length includes: Step S401: Construct a virtual mapping point of the drone on the geographical map of the inspection area, and drive the virtual mapping point of the drone to perform a displacement mapping according to the initial inspection path.

[0049] Step S402: Determine the wind force characteristics corresponding to the virtual mapping point of the drone at different path nodes in the wind force characteristic prediction sequence, and based on the wind force characteristics, determine the wind resistance energy consumption parameters corresponding to the virtual mapping point of the drone.

[0050] Step S403: Calculate the sum of the wind resistance energy consumption parameters corresponding to all path nodes, calculate the sum of the basic energy consumption parameters corresponding to all path nodes, and calculate the sum of the sum of the wind resistance energy consumption parameters and the sum of the basic energy consumption parameters, which is recorded as the energy consumption parameter of the initial inspection path.

[0051] In some embodiments of the present invention, the method for determining the wind resistance energy consumption parameters corresponding to the drone mapping point based on the wind force characteristics includes: Step S4021: Based on the wind force characteristics, determine the angle between the wind direction and the initial inspection path and the wind force intensity, and based on the angle, determine the wind force influence coefficient, where the wind force influence coefficient refers to the wind energy consumption conversion ratio of the wind force to the energy consumption increase of the drone mapping point.

[0052] Step S4022: Calculate the product of the wind force influence coefficient and the wind force intensity to obtain the wind resistance energy consumption parameter.

[0053] In some embodiments of the present invention, the method for comprehensively considering the total inspection contribution parameter and the total energy consumption parameter of each initial inspection path within a preset time period includes: Step S501: Set several parameter interval groups for the total inspection contribution parameter and the total energy consumption parameter. Each parameter interval group includes a total inspection contribution parameter interval and a total energy consumption parameter interval, and each parameter interval group is associated with a set inspection contribution consideration coefficient and an energy consumption consideration coefficient.

[0054] Step S502: Determine the parameter intervals to which the total inspection contribution parameter and the total energy consumption belong respectively, and determine the corresponding consideration coefficients respectively. Combine the total inspection contribution parameter and the total energy consumption, calculate the comprehensive consideration value of the initial inspection path, and determine the selected optimal inspection path based on the level of the comprehensive consideration value.

[0055] Among them, the expression for calculating the comprehensive consideration value is: .

[0056] Among them, Z is the comprehensive consideration value, is the inspection contribution consideration coefficient, G is the total inspection contribution parameter, is the energy consumption consideration coefficient, and H is the total energy consumption.

[0057] In some embodiments of the present invention, there is also disclosed an integrated inspection UAV control system based on multi-source data analysis, including: A first module for obtaining a geographical map of the inspection area using a GIS system, determining the elevation data distribution and ground cover data of the geographical map of the inspection area, and constructing three-dimensional ground protrusions on the geographical map of the inspection area.

[0058] A second module for determining the coordinate positions of power grid inspection points, configuring the corresponding power grid inspection points on the geographical map of the inspection area, obtaining historical inspection records, determining the abnormal occurrence rates of different power grid inspection points for the historical inspection records, and combining the preset inspection weights of different power grid inspection points to determine the inspection contribution parameters when different power grid inspection points are triggered for inspection.

[0059] A third module for obtaining real-time wind monitoring data and determining a wind feature prediction sequence based on the wind features of the real-time wind monitoring data.

[0060] A fourth module for constructing a number of initial inspection paths and determining the energy consumption parameters of each initial inspection path based on the wind feature prediction sequence and the path length.

[0061] A fifth module for comprehensively considering the total inspection contribution parameters and the total energy consumption parameters of each initial inspection path within a preset time period and selecting the optimal inspection path.

[0062] The present invention discloses an integrated inspection UAV control method and system based on multi-source data analysis, relating to the technical field of UAV control, including: using GIS to obtain a geographical map of the inspection area, extracting elevation and ground cover data, and constructing a three-dimensional ground model; determining the coordinates of power grid inspection points and configuring them on the geographical map, and calculating inspection contribution parameters by combining historical abnormal rates and preset weights; collecting real-time wind data and predicting a wind feature sequence; generating multiple initial inspection paths and calculating energy consumption parameters based on wind prediction and path length; comprehensively evaluating the total inspection contribution and total energy consumption of each path within a preset period and selecting the optimal path. The present invention adapts to complex environments, improves the power grid inspection efficiency and reduces energy consumption through multi-source data fusion and dynamic path optimization, demonstrating high innovation and practical value.

[0063] Through the description of the above embodiments, those skilled in the art can clearly understand that the present invention can be implemented by hardware or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, and the software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various implementation scenarios of the present invention.

[0064] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that they can still modify or equivalently replace the technical solutions of the present invention, and these modifications or equivalent replacements cannot make the modified technical solutions deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. An integrated inspection UAV control method based on multi-source data analysis, characterized in that, Including: Step S100: Use the GIS system to obtain the geographical map of the inspection area, determine the elevation data distribution and ground cover data of the geographical map of the inspection area, and construct a three-dimensional ground bulge on the geographical map of the inspection area; Step S200: Determine the coordinate positions of the power grid inspection points, configure the corresponding power grid inspection points on the geographical map of the inspection area, obtain the historical inspection records, determine the abnormal occurrence rates of different power grid inspection points for the historical inspection records, and combine the preset inspection weights of different power grid inspection points to determine the inspection contribution parameters of different power grid inspection points when triggered by inspection; Step S300: Obtain the real-time wind monitoring data, and determine the wind characteristic prediction sequence based on the wind characteristics of the real-time wind monitoring data; Step S400: Construct several initial inspection paths, and determine the energy consumption parameters of each initial inspection path based on the wind characteristic prediction sequence and the path length; Step S500: Comprehensively consider the total inspection contribution parameters and the total energy consumption parameters of each initial inspection path within a preset time period, and select the optimal inspection path.

2. The integrated patrol UAV control method based on multi-source data analysis according to claim 1, wherein The method for determining the wind characteristic prediction sequence based on the wind characteristics of the real-time wind monitoring data includes: Step S301: Construct a wind prediction model, and use the wind prediction model to analyze the wind characteristics of the real-time wind monitoring data to determine the wind characteristic prediction sequence. Among them, the method for constructing the wind prediction model includes: Step S3011: Arrange wind monitoring devices for the inspection area, and map the position nodes where the wind monitoring devices are arranged onto the geographical map of the inspection area to obtain several wind performance nodes; Step S3012: Obtain the historical wind monitoring data of the wind monitoring devices, align the historical wind monitoring data on the time axis, and respectively map and represent the corresponding wind performance nodes to form the historical wind performance states of the wind performance nodes. The historical wind performance states include dynamically changing wind performance frames, and each wind performance frame includes a wind direction line. The direction of the wind direction line is used to represent the monitoring wind direction, and the length is used to represent the monitoring wind force; Step S3013: Obtain the historical weather forecast, align the historical wind forecast in the historical weather forecast and several historical wind monitoring data on the time axis, and map and represent the historical wind forecast at each wind performance node on the geographical map of the inspection area to form the historical wind forecast performance state. The historical wind forecast performance state includes dynamically changing wind forecast performance frames, and each wind forecast performance frame includes a wind forecast direction line. The direction of the wind forecast direction line is used to represent the forecast wind direction, and the length is used to represent the forecast wind force; Step S3014: Compare the historical wind performance state and the historical forecast performance state, and based on the comparison result, classify the corresponding historical wind forecast and historical wind monitoring data, and construct a retrieval logic framework for the classified data set to obtain the wind prediction model.

3. The integrated inspection UAV control method based on multi-source data analysis according to claim 2, wherein The method for classifying the corresponding historical wind forecast and historical wind monitoring data includes: Step S3015: Compare the historical wind power performance states and historical forecast performance states in equivalent time periods, that is, compare several consecutive wind power performance frames and wind power forecast performance frames at each wind power performance node, judge the difference characteristics of the pointing lines of each frame, and determine the inter-state compliance parameters between the historical wind power performance states and historical forecast performance states. If the inter-state compliance parameters are greater than or equal to the preset value, it is considered that the corresponding historical wind power forecast and historical wind power monitoring data are equivalent in performance; Step S3016: Classify the historical wind power forecasts and historical wind power monitoring data with equivalent performance to obtain an equivalent historical wind power corresponding data set, and classify the historical wind power forecasts and historical wind power monitoring data with non-equivalent performance to obtain a non-equivalent historical wind power corresponding data set; Step S3017: Take each historical wind power forecast in the equivalent historical wind power corresponding data set as the first retrieval condition, and its corresponding historical wind power monitoring data as the second retrieval condition to construct a retrieval logic framework for the equivalent historical corresponding data set. Take each historical wind power monitoring data in the non-equivalent historical corresponding data set as the only retrieval condition to construct a retrieval logic framework for the non-equivalent historical corresponding data set; Step S3018: Construct the equivalent historical corresponding data set and the non-equivalent historical corresponding data set into a database of the wind power prediction model, and use the retrieval logic framework to retrieve the corresponding historical wind power monitoring data.

4. The integrated inspection UAV control method based on multi-source data analysis according to claim 3, characterized in that The method for analyzing the wind power characteristics of real-time wind power monitoring data using the wind power prediction model includes: Step S302: Dynamically map each wind power performance node of the real-time wind power monitoring data on the geographical map of the inspection area to form the real-time wind power performance state of the wind power performance node; Step S303: Substitute the real-time wind power monitoring data into the database of the wind power prediction model. First, compare the real-time wind power monitoring data corresponding to some time periods with the historical wind power forecasts. If there is a matching historical wind power forecast, determine the historical wind power monitoring data corresponding to the historical wind power forecast, and compare the historical wind power performance state corresponding to the historical wind power monitoring data with the corresponding real-time wind power performance state, calculate the inter-state compliance parameters. If the inter-state compliance parameters are greater than or equal to the preset value, use the subsequent performance characteristics of the corresponding historical wind power performance state as the predicted wind power characteristics, and serialize the predicted wind power characteristics to obtain the wind power characteristic prediction sequence. If there is no matching historical wind power forecast, compare the real-time wind power performance state with the historical wind power performance states of different historical wind power monitoring data, and calculate the inter-state compliance parameters. If the inter-state compliance parameters are greater than or equal to the preset value, use the subsequent performance characteristics of the corresponding historical wind power performance state as the predicted wind power characteristics, and serialize the predicted wind power characteristics to obtain the wind power characteristic prediction sequence.

5. The integrated inspection UAV control method based on multi-source data analysis according to claim 3, characterized in that, The expression for calculating the inter-state compliance parameters is: ； where F is the state-to-state correspondence parameter, is the sub-state-to-state correspondence parameter corresponding to the t-th time node, T is the total number of time nodes participating in the state-to-state correspondence comparison, and L is the influence adjustment coefficient of the sub-state-to-state correspondence parameter, is the influence adjustment constant of the sub-state-to-state correspondence parameter; Among them, the expression for calculating the sub-inter-state compliance parameters is: ； Among them, is the line matching parameter of the wind direction lines of the i-th wind performance node. If the included angle between the wind direction lines is less than or equal to the preset value and the length difference between the lines is less than or equal to the preset value, then output the first parameter value. If the included angle between the wind direction lines is less than or equal to the preset value and the length difference between the lines is greater than the preset value, then output the second parameter value. If the included angle between the wind direction lines is greater than the preset value and the length difference between the lines is greater than the preset value, then output 0, where the first parameter value is greater than or equal to the second parameter value, the second parameter value is greater than 0, and n is the total number of wind performance nodes.

6. The integrated patrol drone control method based on multi-source data analysis according to claim 1, characterized in that, The method for determining the energy consumption parameters of each initial inspection path based on the wind power characteristic prediction sequence and the path length includes: Step S401: Construct virtual mapping points of unmanned aerial vehicles on the geographical map of the inspection area, and drive the virtual mapping points of unmanned aerial vehicles to perform displacement mapping according to the initial inspection path; Step S402: Determine the wind force characteristics corresponding to the virtual mapping point of the UAV at different path nodes in the wind force characteristic prediction sequence, and based on the wind force characteristics, determine the wind resistance energy consumption parameters corresponding to the virtual mapping point of the UAV; Step S403: Calculate the sum of the wind resistance energy consumption parameters corresponding to all path nodes, calculate the sum of the basic energy consumption parameters corresponding to all path nodes, and calculate the sum of the sum of the wind resistance energy consumption parameters and the sum of the basic energy consumption parameters, which is denoted as the energy consumption parameter of the initial inspection path.

7. The integrated inspection UAV control method based on multi-source data analysis according to claim 6, characterized in that, The method for determining the wind resistance energy consumption parameters corresponding to the UAV mapping point based on the wind force characteristics includes: Step S4021: Based on the wind force characteristics, determine the angle between the wind direction and the initial inspection path and the wind force intensity, and based on the angle, determine the wind force influence coefficient, where the wind force influence coefficient refers to the wind energy consumption conversion ratio of the wind force to the increase in the energy consumption of the UAV mapping point; Step S4022: Calculate the product of the wind force influence coefficient and the wind force intensity to obtain the wind resistance energy consumption parameter.

8. The integrated inspection UAV control method based on multi-source data analysis according to claim 1, characterized in that, The method for comprehensively considering the total inspection contribution parameter and the total energy consumption parameter of each initial inspection path within a preset time period includes: Step S501: Set a number of parameter interval groups for the total inspection contribution parameter and the total energy consumption parameter. Each parameter interval group includes an interval for the total inspection contribution parameter and an interval for the total energy consumption parameter. Each parameter interval group is associated with a set inspection contribution consideration coefficient and an energy consumption consideration coefficient; Step S502: Determine the parameter intervals to which the total inspection contribution parameter and the total energy consumption belong respectively, determine the corresponding consideration coefficients respectively, and combine the total inspection contribution parameter and the total energy consumption to calculate the comprehensive consideration value of the initial inspection path. Based on the level of the comprehensive consideration value, determine the selected optimal inspection path; Among them, the expression for calculating the comprehensive consideration value is: ； Among them, Z is the comprehensive consideration value, is the inspection contribution consideration coefficient, G is the total inspection contribution parameter, is the energy consumption consideration coefficient, H is the total energy consumption.

9. An integrated inspection UAV control system based on multi-source data analysis, characterized in that, The comprehensive inspection UAV control method for implementing any one of claims 1-8 includes: The first module is used to obtain the geographical map of the inspection area using the GIS system, determine the elevation data distribution and ground cover data of the geographical map of the inspection area, and construct a three-dimensional ground bulge on the geographical map of the inspection area; The second module is used to determine the coordinate positions of the power grid inspection points, configure the corresponding power grid inspection points on the geographical map of the inspection area, obtain the historical inspection records, determine the abnormal occurrence rates of different power grid inspection points from the historical inspection records, and combine the preset inspection weights of different power grid inspection points to determine the inspection contribution parameters of different power grid inspection points when triggered for inspection; The third module is used to obtain the real-time wind force monitoring data, and based on the wind force characteristics of the real-time wind force monitoring data, determine the wind force characteristic prediction sequence; The fourth module is used to construct a number of initial inspection paths, and based on the wind force characteristic prediction sequence and the path length, determine the energy consumption parameters of each initial inspection path; The fifth module is used to comprehensively consider the total inspection contribution parameter and the total energy consumption parameter of each initial inspection path within a preset time period, and select the optimal inspection path.

Images