An unmanned aerial vehicle intelligent flight method and system based on energy data analysis

Abstract

The application relates to an unmanned aerial vehicle intelligent flight method and system based on energy data analysis, and relates to the field of energy management technology.The method comprises the following steps: acquiring a required inspection position; constructing a monitoring time window and acquiring a monitoring wind receiving vector of a wind measuring point in the monitoring time window; determining a standard wind receiving vector according to the monitoring wind receiving vector; constructing a simulated inspection path according to a starting point and the required inspection position, and constructing a historical time window; determining a path single-point vector of each point on the simulated inspection path according to the standard wind receiving vector in the historical time window, and determining a required charging position according to the path single-point vector, and constructing a simulated inspection task according to the required charging position and the simulated inspection path; determining a task suitability coefficient according to the simulated inspection task, and defining the simulated inspection task with the largest task suitability coefficient as a use inspection task, and controlling the unmanned aerial vehicle to fly according to the use inspection task. The application has the function of improving the unmanned aerial vehicle inspection effect.

Description

Technical Field

[0001] This application relates to the field of energy management technology, and in particular to a method and system for intelligent flight of unmanned aerial vehicles based on energy data analysis. Background Technology

[0002] Mountainous terrain is complex and transportation is inconvenient. Drones, with their advantages of maneuverability, wide field of vision, and rapid response, can significantly reduce the safety risks of inspection personnel and improve operational efficiency. To ensure the continuous operation of drones in long-endurance, large-scale inspection missions in mountainous areas, engineering practice typically involves pre-distributing multiple charging points within the mountainous region. When the drone's battery is low, it can autonomously navigate to the nearest charging point to recharge, thus meeting the needs of continuous multi-segment inspections.

[0003] In practical applications, inspection needs may change dynamically due to seasonal factors, unforeseen events, or adjustments to maintenance plans, resulting in non-fixed inspection locations. Faced with inspection tasks in different batches and key areas, current practices generally involve comprehensive planning of the task, including the drone inspection path and the selection of intermediate charging points, using the shortest path to achieve effective drone inspections.

[0004] Among the aforementioned technologies, planning the shortest path is theoretically the most efficient and energy-saving solution. However, in actual inspections, environmental parameters in mountainous areas vary, and this solution may require long periods of headwind flight, resulting in low efficiency and high energy consumption. Consequently, the current drone inspection effect is poor, and there is still room for improvement. Summary of the Invention

[0005] To improve the effectiveness of drone inspections, this application provides a smart drone flight method and system based on energy data analysis.

[0006] Firstly, this application provides a method for intelligent flight of unmanned aerial vehicles (UAVs) based on energy data analysis, employing the following technical solution: A smart flight method for unmanned aerial vehicles (UAVs) based on energy data analysis includes: Obtain the required inspection locations; A monitoring window is constructed based on a preset monitoring duration, and the wind vector of the preset wind measurement point is obtained within the monitoring window. The standard wind vector is determined by calculation and analysis based on the monitored wind vector. The simulated inspection path is constructed by randomly sorting the locations based on the preset starting point and required inspection location, and a historical time window is constructed based on the preset historical duration. Within a historical time window, the path single-point vector of each point on the simulated inspection path is determined based on the standard wind vector. Energy consumption analysis is performed based on the path single-point vector to determine the charging location. The charging location and the simulated inspection path are then combined to construct the simulated inspection task. The inspection efficiency parameters and energy consumption parameters are determined by analyzing the simulated inspection tasks. The task suitability coefficient is then calculated based on these parameters. The simulated inspection task with the highest task suitability coefficient is defined as the inspection task, and the UAV is controlled to fly according to the inspection task.

[0007] Optionally, the steps for determining the standard wind vector through calculation and analysis based on the monitored wind vector include: The wind force value and wind angle are determined based on the monitored wind vector. The similar wind force range is determined by calculation based on the monitored wind force value and the preset similar wind force value, and the similar angle range is determined by calculation based on the monitored wind force angle and the preset similar angle. The number of wind units within a similar wind force range is determined by counting the monitored wind force values, and the monitored wind force value within a similar wind force range corresponding to the largest number of wind units within a wind force range is defined as the standard wind force value. The number of monitored wind angles within a similar angle range is determined by counting the monitored wind angles within that angle range. The monitored wind angle within a similar angle range corresponding to the largest number of wind angles is defined as the standard wind angle. The standard wind value and the standard wind angle are combined to determine the standard wind vector.

[0008] Optionally, after the path single-point vector is determined, the intelligent flight method for UAVs based on energy data analysis also includes: Points where the single-point vector of the path is empty are defined as missing points, and it is determined whether there is at least one missing point on both sides of the missing point on the simulated inspection path; If there is at least one missing point on both sides of the missing point on the simulated inspection path, then a missing signal is output. If there are no missing points on either side of a missing point on the simulated inspection path, then the path single-point vectors corresponding to the two side points are defined as adjacent single-point vectors. The degree of change between adjacent points is determined by calculation based on two adjacent single-point vectors, and it is then determined whether the degree of change between adjacent points is greater than the preset reasonable degree of change. If the adjacent degree of change is greater than the reasonable degree of change, then output the missing signal; If the adjacent variation is not greater than the reasonable variation, then the path vector of the missing point is updated based on the two adjacent single-point vectors.

[0009] Optionally, in the event of a missing signal output, the intelligent flight method for drones based on energy data analysis also includes: The deviation vector range is constructed by calculating based on the standard wind vector and the preset permissible deviation vector; The analysis is performed on each vector within the range of the deviation vector based on the missing point to determine the non-empty single-point deviation vector; The vector deviation degree is determined by calculating the vector within the deviation vector range corresponding to the deviation single-point vector and the standard wind-receiving vector, and the vector deviation weight corresponding to the vector deviation degree is determined according to the preset weight matching relationship. The single-point representative vector is determined by calculating the deviation single-point vector and the vector deviation weight, and the path single-point vector of the missing point is updated by calculating based on all the single-point representative vectors.

[0010] Optionally, after determining the non-empty deviation single-point vector, the intelligent flight method for UAVs based on energy data analysis also includes: The number of internal references is determined by counting the non-empty deviation single-point vectors. Determine whether the number of internal references is greater than the preset number of complex references; If the number of internal references is not greater than the number of complex references, then the path single-point vector of the missing point is updated based on the deviation single-point vector; If the number of internal references is greater than the number of complex references, a demand intervention signal will be output.

[0011] Optionally, the step of performing energy consumption analysis based on path point vectors to determine the location of required charging includes: Energy consumption analysis is performed based on the single-point vector of the path to determine the theoretical remaining power at each required inspection location; The first demand inspection location where the theoretical remaining power is no greater than the preset safety threshold power is defined as the power shortage point, and the demand inspection location in the simulated inspection path that is the position before the power shortage point is defined as the critical point. Construct charging path and charging fly-off path based on critical point, power shortage point and randomly selected preset available charging location; The path vector of each location point is determined within the charging path, and the remaining power at the critical point and the path vector are analyzed to determine the remaining power to be reached. The available charging location where the remaining power is greater than the preset required power is defined as the effective charging location. The analysis is performed based on the charging fly-off path corresponding to the effective charging location to retain the remaining power, and the effective charging location corresponding to the largest amount of retained remaining power is defined as the demand charging location.

[0012] Optionally, after determining the remaining battery power, the intelligent flight method for drones based on energy data analysis also includes: The time required for recharging is determined based on the remaining battery power. The path flight efficiency is determined by calculating the charging route and the charging departure route, and the overall detour efficiency is determined by calculating the charging time and the path flight efficiency. The preset correction matching relationship is used to determine the screening correction parameters corresponding to the overall detour efficiency, and the remaining power is updated according to the screening correction parameters.

[0013] Secondly, this application provides a smart flight system for unmanned aerial vehicles (UAVs) based on energy data analysis, employing the following technical solution: A smart flight system for unmanned aerial vehicles (UAVs) based on energy data analysis includes: The acquisition module is used to acquire the required inspection locations; The processing module, connected to the acquisition module, is used for information storage and processing; The processing module constructs a monitoring window based on a preset monitoring duration, and enables the acquisition module to acquire the wind vector of the preset wind measurement point within the monitoring window; The processing module performs calculations and analysis based on the monitored wind vector to determine the standard wind vector; The processing module randomly sorts the locations based on the preset starting point and required inspection locations to construct a simulated inspection path, and constructs a historical time window based on the preset historical duration. Within the historical time window, the processing module determines the path single-point vector of each point on the simulated inspection path based on the standard wind vector, performs energy consumption analysis based on the path single-point vector to determine the charging location, and combines the charging location and the simulated inspection path to construct the simulated inspection task. The processing module analyzes the simulated inspection task to determine the inspection efficiency parameters and inspection energy consumption parameters, and calculates the task suitability coefficient based on the inspection efficiency parameters and inspection energy consumption parameters. The simulated inspection task with the largest task suitability coefficient is defined as the inspection task and the UAV is controlled to fly according to the inspection task.

[0014] In summary, this application includes at least one of the following beneficial technical effects: When drones perform inspection tasks, the energy consumption caused by external environmental factors should be fully considered in order to rationally plan the drone flight path and improve the inspection effect. For locations without historical reference data, the environmental conditions of the location can be reasonably inferred through analysis of factors such as location, thereby improving the accuracy of data analysis. Attached Figure Description

[0015] Figure 1 This is a flowchart of a smart flight method for drones based on energy data analysis.

[0016] Figure 2 This is a flowchart of the modules for a smart drone flight method based on energy data analysis. Detailed Implementation

[0017] To make the purpose, technical solution, and advantages of this application clearer, the following is combined with Figures 1-2 The present application will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the application.

[0018] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0019] This application discloses a method for intelligent flight of unmanned aerial vehicles (UAVs) based on energy data analysis, referring to... Figure 1 The methodology for intelligent drone flight based on energy data analysis includes the following steps: Step S100: Obtain the required inspection location.

[0020] The required inspection location is the location where the drone needs to be moved to and inspected.

[0021] Step S101: Construct a monitoring window based on a preset monitoring duration, and obtain the monitoring wind vector of the preset wind measurement point within the monitoring window.

[0022] The monitoring duration is a set period of time set by staff to reflect short-term weather conditions, such as 2 hours. A monitoring window is constructed to facilitate the acquisition of data within the monitoring duration. The wind measurement point is a location in the mountainous area where wind monitoring equipment is installed. The monitored wind vector is the wind vector obtained at the wind measurement point, which includes the wind force and direction.

[0023] Step S102: Calculate and analyze based on the monitored wind vector to determine the standard wind vector.

[0024] The standard wind vector is a vector value that represents the wind force at the wind measurement point within the monitoring window. It is specifically determined through steps S200-S203.

[0025] Step S103: Randomly sort the locations according to the preset starting point and required inspection location to construct a simulated inspection path, and construct a historical time window according to the preset historical duration.

[0026] The starting point is the location where the drone begins its operation. The simulated inspection path is the drone's flight path from the starting point through each required inspection location in sequence. Since the order of the required inspection locations can be randomly determined, there are multiple simulated inspection paths. The historical duration is the duration set by the staff for acquiring historical inspection data from the drone. Historical time windows are constructed to facilitate the acquisition and analysis of data within the historical time windows.

[0027] Step S104: Within the historical time window, determine the path single-point vector of each point on the simulated inspection path based on the standard wind vector, and perform energy consumption analysis based on the path single-point vector to determine the charging location in demand. Combine the charging location in demand with the simulated inspection path to construct the simulated inspection task.

[0028] When the wind at the wind measurement point under the historical time window is the standard wind vector, the wind force vector received by the UAV at the position point on the simulated inspection path is used. When there are multiple wind force vectors, the method for determining the single-point vector of the path is the same as steps S200-S203, and will not be repeated here. For data analysis purposes, not all points on the simulated inspection path will be analyzed. Instead, a point can be set at a certain distance for analysis to reduce the amount of data analysis. The required charging position is the position point that the UAV needs to fly to for charging operations. The specific determination method is described in steps S600-S604, and will not be repeated here. Once the required charging position is determined, i.e., the required charging position for the UAV's flight sequence is between the two required inspection positions, the path can be replanned. The replanned path is the simulated inspection task that the UAV needs to perform.

[0029] Step S105: Analyze the simulated inspection task to determine the inspection efficiency parameters and inspection energy consumption parameters, and calculate the task suitability coefficient based on the inspection efficiency parameters and inspection energy consumption parameters. Define the simulated inspection task with the largest task suitability coefficient as the inspection task and control the UAV to fly according to the inspection task.

[0030] The inspection efficiency parameter is the efficiency value that the UAV can achieve when performing a simulated inspection task. It can be determined by analyzing the impact of wind on the UAV's flight and the UAV's charging status to determine the total time required for the overall operation, and then determining its efficiency based on this time. The inspection energy consumption parameter is the energy consumption parameter reflected by the UAV when performing a simulated inspection task, which can be determined by analyzing various power consumption conditions. The task suitability coefficient is the parameter value that reflects whether the simulated inspection task is suitable for the UAV's inspection operation. The larger the value, the more suitable the simulated inspection task is. This value is determined by dividing the inspection efficiency parameter by the inspection energy consumption parameter. At this time, the inspection task is defined to facilitate the control of the UAV's flight operation and improve the UAV's inspection effect.

[0031] The steps for determining the standard wind vector based on the monitored wind vector include: Step S200: Determine the monitored wind force value and the monitored wind angle based on the monitored wind vector.

[0032] The monitored wind force value is the magnitude of the wind force measured at the wind measuring point, and the monitored wind force angle is the direction of the wind force measured at the wind measuring point.

[0033] Step S201: Calculate the similar wind force range based on the monitored wind force value and the preset similar wind force value, and calculate the similar angle range based on the monitored wind force angle and the preset similar angle.

[0034] The similar wind force value is the maximum allowable difference between two wind force values ​​set by the staff when they are considered to be close. The similar angle is the maximum allowable offset angle set by the staff when two wind directions are considered to be relatively close. By monitoring the wind force value and adding and subtracting the similar wind force value, the similar wind force range can be constructed. By monitoring the wind angle and rotating the similar angle in different directions, the similar angle range can be determined.

[0035] Step S202: Count the monitored wind force values ​​within a similar wind force range to determine the number of wind force interiors, and define the monitored wind force value within a similar wind force range corresponding to the largest number of wind force interiors as the standard wind force value.

[0036] The number of wind force interiors refers to the number of monitored wind force values ​​within a single wind force range. The largest number of wind force interiors indicates that the corresponding monitored wind force value best reflects the wind force situation at that location, and it can be defined as the standard wind force value.

[0037] Step S203: Count the monitored wind angles within a similar angle range to determine the number of angles within the angle, and define the monitored wind angles within a similar angle range corresponding to the largest number of angles within the angle range as the standard wind angle. Combine the standard wind value and the standard wind angle to determine the standard wind vector.

[0038] Similarly, the number within an angle is the number of monitored wind angles within a range of similar single angles. At this point, a standard wind angle is defined to mark the situation that best represents the wind angle of the wind measurement point. The wind vector obtained by combining the standard wind value and the standard wind angle is the standard wind vector that can represent the wind situation of the wind measurement point.

[0039] After the path single-point vector is determined, the intelligent flight method for UAVs based on energy data analysis also includes: Step S300: Define the location point where the single-point vector of the path is empty as a missing point, and determine whether there is at least one missing point on both sides of the location point on the simulated inspection path.

[0040] An empty path vector means there is no historical data available for reference. Missing points are defined to identify and distinguish this situation, facilitating subsequent analysis. The purpose of the judgment is to determine whether the wind conditions of the current missing point can be determined by the wind conditions of adjacent locations.

[0041] Step S3001: If there is at least one missing point on both sides of the missing point on the simulated inspection path, then output a missing signal.

[0042] When there is at least one missing point on both sides of the missing point on the simulated inspection path, it means that the wind conditions of the current missing point cannot be inferred from the wind conditions of the two side points. Therefore, a missing signal is output to identify and distinguish this situation, which will facilitate further analysis.

[0043] Step S3002: If there are no missing points on the positions on both sides of the missing point on the simulated inspection path, then the path single-point vectors corresponding to the positions on both sides are defined as adjacent single-point vectors.

[0044] When there are no missing points on either side of a missing point on the simulated inspection path, it means that the wind conditions of the two sides can be analyzed. At this time, adjacent single-point vectors are defined to mark the required single-point vectors of the path, which will facilitate subsequent analysis.

[0045] Step S301: Calculate the degree of adjacent variation based on two adjacent single-point vectors, and determine whether the degree of adjacent variation is greater than the preset reasonable degree of variation.

[0046] The degree of adjacent variation is the change between two adjacent single-point vectors. It can be calculated and determined by the change in wind force and the angle between their directions. A weight can be set for wind force and an angle. The degree of adjacent variation is determined by multiplying each by its corresponding weight and adding them together. The reasonable degree of variation is the maximum degree of adjacent variation allowed when the wind conditions of two locations are considered to be similar. The purpose of this judgment is to further infer whether the data of the current missing points can be supplemented by the data of the locations on both sides.

[0047] Step S3011: If the adjacent change degree is greater than the reasonable change degree, then output the missing signal.

[0048] When the adjacent variation is greater than the reasonable variation, it indicates that there is a situation where the data changes significantly. In this case, it is impossible to supplement the data of the current missing point using the data of the position points on both sides. Therefore, a missing signal is output to identify this situation for the convenience of subsequent analysis.

[0049] Step S3012: If the adjacent change degree is not greater than the reasonable change degree, then calculate based on the two adjacent single-point vectors to update the path single-point vector of the missing point.

[0050] When the adjacent variation is not greater than the reasonable variation, it means that the wind condition of the current missing point can be determined by the data of the two position points. At this time, the intermediate value of the two can be used as the single point vector of the path. The wind force in the intermediate value is the average of the two wind force values, and the wind direction in the intermediate value is the center direction of the two directions.

[0051] In the event of a missing signal output, intelligent flight methods for unmanned aerial vehicles based on energy data analysis also include: Step S400: Calculate the deviation vector range based on the standard wind vector and the preset permissible deviation vector.

[0052] The permissible deviation vector is the deviation vector that is allowed when two wind conditions are considered to be relatively similar, as set by the staff. This permissible deviation vector includes the angle at which the wind direction can be adjusted and the wind force. By constructing the deviation vector range, the range within which the wind conditions are relatively consistent with the standard wind vector is determined, which facilitates subsequent analysis.

[0053] Step S401: Analyze the vectors within the deviation vector range based on the missing point to determine the non-empty single-point deviation vector.

[0054] The deviation single-point vector is the wind vector corresponding to the missing point when the wind measurement point in the historical time window is within the deviation vector range. A single-point deviation vector can be determined by a vector value within the deviation vector range. The determination method is the same as in step S104 above, and will not be repeated here. By determining the non-empty deviation single-point vector, it is convenient to identify and determine the reference data.

[0055] Step S402: Calculate the vector deviation degree by comparing the vector within the deviation vector range corresponding to the deviation single-point vector with the standard wind-receiving vector, and determine the vector deviation weight corresponding to the vector deviation degree according to the preset weight matching relationship.

[0056] The vector deviation is the deviation value between the vector within the deviation vector range and the standard windward vector, which can be determined by the calculation method in step S301; the vector deviation weight is a parameter value that reflects the importance of the data. The larger the vector deviation, the greater the deviation from the vector to be analyzed, that is, the lower the reference significance of the data. The weight matching relationship between the two is determined by the staff in advance through multiple experiments, which will not be elaborated here. It is necessary to ensure that the two are inversely proportional, and the vector deviation weight is between 0 and 1.

[0057] Step S403: Calculate the single-point representative vector based on the deviation single-point vector and the vector deviation weight, and calculate the path single-point vector of the missing point based on all the single-point representative vectors.

[0058] The vector length can be adjusted by multiplying the deviation single-point vector by the vector deviation weight, thus obtaining the single-point representative vector. By performing vector operations on all single-point representative vectors, the required path single-point vector can be obtained.

[0059] After determining the non-empty deviation single-point vector, the intelligent flight method for UAVs based on energy data analysis also includes: Step S500: Count the non-empty deviation single-point vectors to determine the number of internal references.

[0060] The internal reference quantity is the number of data points that have reference analysis significance, that is, the total number of non-empty deviation point vectors.

[0061] Step S501: Determine whether the number of internal references is greater than the preset number of complex references.

[0062] The number of complex references is the minimum number of internal references that staff set when they believe that the historical data of a location is too complex to be analyzed. The purpose of this judgment is to determine whether the historical data of that location is too complex.

[0063] Step S5011: If the number of internal references is not greater than the number of complex references, then update the path single-point vector of the missing point based on the deviation single-point vector.

[0064] When the number of internal references is not greater than the number of complex references, it means that the historical data of the location point is not complex and data analysis can be performed normally. In this case, the path single-point vector update can be performed normally.

[0065] Step S5012: If the number of internal references is greater than the number of complex references, then output a demand intervention signal.

[0066] When the number of internal references is greater than the number of complex references, it indicates that the historical data of the location point is more complex. Determining the single-point vector of the path using the methods in steps S402-S403 will result in a serious data deviation. Therefore, an intervention signal is output to identify the situation so that staff can be aware of it and handle it manually.

[0067] The steps for determining the location of charging demand based on energy consumption analysis using single-point vector paths include: Step S600: Perform energy consumption analysis based on the single-point vector of the path to determine the theoretical remaining power at each required inspection location.

[0068] The theoretical remaining power is the amount of power that the drone would have left when it reaches the required inspection location under theoretical conditions.

[0069] Step S601: Define the first demand inspection location where the theoretical remaining power is no greater than the preset safety threshold power as the power shortage point, and define the demand inspection location in the simulated inspection path that is the position before the power shortage point as the critical point.

[0070] The safe threshold power is the amount of remaining power that the staff sets when they believe the drone can fly to the charging location to recharge. By defining low power points and critical points, the situation where the drone needs to be recharged is identified and determined.

[0071] Step S602: Construct charging path and charging fly-off path based on critical point, power shortage point and randomly selected preset available charging location.

[0072] Available charging locations are locations in mountainous areas where drones can be charged. Charging path is the flight path of the drone moving from the critical point to an available charging location. Charging-away path is the flight path of the drone moving from an available charging location to a point where it is out of power.

[0073] Step S603: Determine the path single-point vector of each location point within the charging path, and analyze the theoretical remaining power at the critical point and the path single-point vector to determine the remaining power to be reached. Define the available charging location where the remaining power to be reached is greater than the preset required reserve power as the effective charging location.

[0074] The path single-point vector is the wind vector at each location point, and the specific determination method is the same as that of the path single-point vector in step S104 above; the remaining power is the theoretical remaining power of the drone when it flies to the charging position; the required reserve power is the remaining power value set by the staff when the drone flies to the available charging position. This value is set to overcome abnormal energy consumption that may occur during flight and improve the safety of charging analysis; the effective charging position is defined to mark the location where the drone can move to the charging position for subsequent analysis.

[0075] Step S604: Analyze the charging fly-off path corresponding to the effective charging location to retain the remaining power, and define the effective charging location corresponding to the largest retained remaining power as the required charging location.

[0076] The remaining power is the amount of power that the drone will have left after it has finished charging and is moved to the point where it is low on power. The maximum amount of remaining power will facilitate subsequent inspection operations. Therefore, the corresponding effective charging location can be defined as the charging location in need.

[0077] After determining the remaining battery power, the intelligent flight method for drones based on energy data analysis also includes: Step S700: Calculate the time required for recharging based on the remaining power.

[0078] The charging time is the time required to charge the drone, which is calculated based on the remaining battery level and the set charging rate.

[0079] Step S701: Calculate the path flight efficiency based on the charging to-go path and charging to-leave path, and calculate the overall detour efficiency based on the recharge consumption time and path flight efficiency.

[0080] Path flight efficiency refers to the efficiency of the drone flying on two paths, while overall detour efficiency refers to the efficiency of the drone reaching the point of low power during charging operations. The efficiency value corresponding to charging is determined by dividing a preset dimensionless coefficient by the charging time, and then adding this efficiency value to the path flight efficiency to determine the overall detour efficiency.

[0081] Step S702: Determine the filtering correction parameters corresponding to the overall detour efficiency according to the preset correction matching relationship, and update the remaining power based on the filtering correction parameters.

[0082] The filtering correction parameter is a parameter that updates the remaining battery power based on the drone's flight efficiency. The higher the overall detour efficiency, the larger the filtering correction parameter. The correction matching relationship between the two is determined in advance by the staff. The remaining battery power can be updated by adding the filtering correction parameter to the remaining battery power, so that the position selection based on the remaining battery power is more effective in the future.

[0083] Reference Figure 2 Based on the same inventive concept, embodiments of the present invention provide a smart flight system for unmanned aerial vehicles (UAVs) based on energy data analysis, comprising: The acquisition module is used to acquire the required inspection locations; The processing module, connected to the acquisition module, is used for information storage and processing; The processing module constructs a monitoring window based on a preset monitoring duration, and enables the acquisition module to acquire the wind vector of the preset wind measurement point within the monitoring window; The processing module performs calculations and analysis based on the monitored wind vector to determine the standard wind vector; The processing module randomly sorts the locations based on the preset starting point and required inspection locations to construct a simulated inspection path, and constructs a historical time window based on the preset historical duration. Within the historical time window, the processing module determines the path single-point vector of each point on the simulated inspection path based on the standard wind vector, performs energy consumption analysis based on the path single-point vector to determine the charging location, and combines the charging location and the simulated inspection path to construct the simulated inspection task. The processing module analyzes the simulated inspection task to determine the inspection efficiency parameters and inspection energy consumption parameters, and calculates the task suitability coefficient based on the inspection efficiency parameters and inspection energy consumption parameters. The simulated inspection task with the largest task suitability coefficient is defined as the inspection task and the UAV is controlled to fly according to the inspection task. The standard windward vector determination module is used to calculate and determine the standard windward vector. The path single-point vector update module is used to update empty path single-point vectors; The missing case analysis module is used to determine the single-point vector path in case of missing cases; The demand intervention analysis module is used to analyze and determine situations that require staff intervention. The demand charging location determination module is used to determine the demand charging location; The remaining battery level update module is retained, and the remaining battery level is updated according to efficiency.

[0084] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

Claims

1. A method for intelligent flight of unmanned aerial vehicles (UAVs) based on energy data analysis, characterized in that, include: Obtain the required inspection locations; A monitoring window is constructed based on a preset monitoring duration, and the wind vector of the preset wind measurement point is obtained within the monitoring window. The standard wind vector is determined by calculation and analysis based on the monitored wind vector. The simulated inspection path is constructed by randomly sorting the locations based on the preset starting point and required inspection location, and a historical time window is constructed based on the preset historical duration. Within a historical time window, the path single-point vector of each point on the simulated inspection path is determined based on the standard wind vector. Energy consumption analysis is performed based on the path single-point vector to determine the charging location. The charging location and the simulated inspection path are then combined to construct the simulated inspection task. The inspection efficiency parameters and energy consumption parameters are determined by analyzing the simulated inspection tasks. The task suitability coefficient is then calculated based on these parameters. The simulated inspection task with the highest task suitability coefficient is defined as the inspection task, and the UAV is controlled to fly according to the inspection task.

2. The intelligent flight method for unmanned aerial vehicles based on energy data analysis according to claim 1, characterized in that, The steps for determining the standard wind vector based on the monitored wind vector include: The wind force value and wind angle are determined based on the monitored wind vector. The similar wind force range is determined by calculation based on the monitored wind force value and the preset similar wind force value, and the similar angle range is determined by calculation based on the monitored wind force angle and the preset similar angle. The number of wind units within a similar wind force range is determined by counting the monitored wind force values, and the monitored wind force value within a similar wind force range corresponding to the largest number of wind units within a wind force range is defined as the standard wind force value. The number of monitored wind angles within a similar angle range is determined by counting the monitored wind angles within that angle range. The monitored wind angle within a similar angle range corresponding to the largest number of wind angles is defined as the standard wind angle. The standard wind value and the standard wind angle are combined to determine the standard wind vector.

3. The intelligent flight method for unmanned aerial vehicles based on energy data analysis according to claim 1, characterized in that, After the path single-point vector is determined, the intelligent flight method for UAVs based on energy data analysis also includes: Points where the single-point vector of the path is empty are defined as missing points, and it is determined whether there is at least one missing point on both sides of the missing point on the simulated inspection path; If there is at least one missing point on both sides of the missing point on the simulated inspection path, then a missing signal is output. If there are no missing points on either side of a missing point on the simulated inspection path, then the path single-point vectors corresponding to the two side points are defined as adjacent single-point vectors. The degree of change between adjacent points is determined by calculation based on two adjacent single-point vectors, and it is then determined whether the degree of change between adjacent points is greater than the preset reasonable degree of change. If the adjacent degree of change is greater than the reasonable degree of change, then output the missing signal; If the adjacent variation is not greater than the reasonable variation, then the path vector of the missing point is updated based on the two adjacent single-point vectors.

4. The intelligent flight method for unmanned aerial vehicles based on energy data analysis according to claim 3, characterized in that, In the event of a missing signal output, intelligent flight methods for unmanned aerial vehicles based on energy data analysis also include: The deviation vector range is constructed by calculating based on the standard wind vector and the preset permissible deviation vector; The analysis is performed on each vector within the range of the deviation vector based on the missing point to determine the non-empty single-point deviation vector; The vector deviation degree is determined by calculating the vector within the deviation vector range corresponding to the deviation single-point vector and the standard wind-receiving vector, and the vector deviation weight corresponding to the vector deviation degree is determined according to the preset weight matching relationship. The single-point representative vector is determined by calculating the deviation single-point vector and the vector deviation weight, and the path single-point vector of the missing point is updated by calculating based on all the single-point representative vectors.

5. The intelligent flight method for unmanned aerial vehicles based on energy data analysis according to claim 4, characterized in that, After determining the non-empty deviation single-point vector, the intelligent flight method for UAVs based on energy data analysis also includes: The number of internal references is determined by counting the non-empty deviation single-point vectors. Determine whether the number of internal references is greater than the preset number of complex references; If the number of internal references is not greater than the number of complex references, then the path single-point vector of the missing point is updated based on the deviation single-point vector; If the number of internal references is greater than the number of complex references, a demand intervention signal will be output.

6. The intelligent flight method for unmanned aerial vehicles based on energy data analysis according to claim 1, characterized in that, The steps for determining the location of charging demand based on energy consumption analysis using single-point vector paths include: Energy consumption analysis is performed based on the single-point vector of the path to determine the theoretical remaining power at each required inspection location; The first demand inspection location where the theoretical remaining power is no greater than the preset safety threshold power is defined as the power shortage point, and the demand inspection location in the simulated inspection path that is the position before the power shortage point is defined as the critical point. Construct charging path and charging fly-off path based on critical point, power shortage point and randomly selected preset available charging location; The path vector of each location point is determined within the charging path, and the remaining power at the critical point and the path vector are analyzed to determine the remaining power to be reached. The available charging location where the remaining power is greater than the preset required power is defined as the effective charging location. The analysis is performed based on the charging fly-off path corresponding to the effective charging location to retain the remaining power, and the effective charging location corresponding to the largest amount of retained remaining power is defined as the demand charging location.

7. The intelligent flight method for unmanned aerial vehicles based on energy data analysis according to claim 6, characterized in that, After determining the remaining battery power, the intelligent flight method for drones based on energy data analysis also includes: The time required for recharging is determined based on the remaining battery power. The path flight efficiency is determined by calculating the charging route and the charging departure route, and the overall detour efficiency is determined by calculating the charging time and the path flight efficiency. The preset correction matching relationship is used to determine the screening correction parameters corresponding to the overall detour efficiency, and the remaining power is updated according to the screening correction parameters.

8. A smart flight system for unmanned aerial vehicles (UAVs) based on energy data analysis, used to implement the smart flight method for UAVs based on energy data analysis as described in any one of claims 1-7, characterized in that, include: The acquisition module is used to acquire the required inspection locations; The processing module, connected to the acquisition module, is used for information storage and processing; The processing module constructs a monitoring window based on a preset monitoring duration, and enables the acquisition module to acquire the wind vector of the preset wind measurement point within the monitoring window; The processing module performs calculations and analysis based on the monitored wind vector to determine the standard wind vector; The processing module randomly sorts the locations based on the preset starting point and required inspection locations to construct a simulated inspection path, and constructs a historical time window based on the preset historical duration. Within the historical time window, the processing module determines the path single-point vector of each point on the simulated inspection path based on the standard wind vector, performs energy consumption analysis based on the path single-point vector to determine the charging location, and combines the charging location and the simulated inspection path to construct the simulated inspection task. The processing module analyzes the simulated inspection task to determine the inspection efficiency parameters and inspection energy consumption parameters, and calculates the task suitability coefficient based on the inspection efficiency parameters and inspection energy consumption parameters. The simulated inspection task with the largest task suitability coefficient is defined as the inspection task and the UAV is controlled to fly according to the inspection task.

Images