Intelligent driving control method and system based on brushless motor

Abstract

The invention discloses an intelligent driving control method and system based on a brushless motor, and relates to the technical field of driving control. According to the intelligent driving control method based on the brushless motor, running state data, motor running data and environment three-dimensional point cloud data of a set unmanned aerial vehicle are obtained in real time; analyzing a flight reliability characteristic value and a motor response sensitivity characteristic value of the set unmanned aerial vehicle based on the running state data and the motor running data of the set unmanned aerial vehicle; obtaining a current three-dimensional position coordinate of the set unmanned aerial vehicle, and analyzing a flight fault-tolerant characteristic value of the set unmanned aerial vehicle based on a pre-trained flight environment perception model in combination with the corresponding environment three-dimensional point cloud data; according to the method, the brushless motor is jointly driven to control the set unmanned aerial vehicle based on the flight reliable characteristic value, the motor response sensitivity characteristic value and the flight fault-tolerant characteristic value, so that the flight safety is improved, the unmanned aerial vehicle can flexibly respond in a complex environment, and the flight control accuracy is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of drive control, in particular to an intelligent drive control method and system based on a brushless motor. BACKGROUND

[0002] With the rapid development of unmanned aerial vehicle technology, especially in the fields of industrial application, logistics distribution, agricultural monitoring, environmental monitoring, etc., unmanned aerial vehicles have gradually become important intelligent tools. Whether it is task execution or autonomous flight control, the flight performance and stability of unmanned aerial vehicles are directly related to their application effect and reliability. As the core power system of unmanned aerial vehicles, brushless motors have become the mainstream driving method in the current unmanned aerial vehicle field due to their high efficiency, long service life and low maintenance characteristics. However, with the diversification of flight tasks and the complexity of the environment, traditional motor control methods have been difficult to meet the growing demand, especially in the face of dynamic flight environments, it is difficult to ensure efficient and safe execution of tasks by the aircraft.

[0003] The prior art, such as the patent application with publication number CN114625168B, discloses a brushless motor driving method, device, storage medium and flight equipment. The brushless motor driving method obtains the current flight parameters of the flight equipment; performs flight simulation according to the received flight instructions to obtain theoretical flight parameters; determines the current operating state of the flight equipment according to the current flight parameters and the theoretical flight parameters; when the current operating state is in an out-of-control state, drives the brushless motor of the flight equipment to control the safe landing of the flight equipment according to the current flight parameters. The present application determines the current operating state of the flight equipment by comparing the current flight parameters of the flight equipment with the theoretical flight parameters, and drives the brushless motor of the flight equipment to control the safe landing of the flight equipment when the current operating state is in an out-of-control state, thereby achieving active driving to avoid the direct falling of the flight equipment and causing serious damage when the flight equipment is out of control.

[0004] Based on the above-mentioned scheme, the limitations of the prior art at least include the following problems: the prior art has certain limitations in the intelligent control capability of unmanned aerial vehicles, especially in the face of complex and dynamic environments, it is difficult to effectively realize real-time analysis and dynamic adjustment of multiple characteristics, which leads to unstable flight of unmanned aerial vehicles in complex environmental changes or difficulty in timely responding to external disturbances. When the unmanned aerial vehicle encounters sudden environmental changes such as the appearance of obstacles or temperature changes, the prior art is difficult to quickly and accurately adjust, thereby affecting the safety and stability of flight. Moreover, the prior art is difficult to fully capture the complex changes of the flight environment and effectively respond to multiple interference sources. Therefore, when the unmanned aerial vehicle enters complex environments such as urban airspace or mountainous areas, the prior art is often difficult to adapt to the rapid changes of the environment, resulting in difficulty in flexible adjustment of flight strategies by the unmanned aerial vehicle. SUMMARY

[0005] In view of the deficiencies of the prior art, the present application provides an intelligent driving control method and system based on a brushless motor, which solves the problem of lack of real-time multi-feature analysis and adjustment capability in a complex dynamic environment in the prior art, resulting in unstable flight of a UAV.

[0006] To achieve the above object, the present application is implemented by the following technical scheme: an intelligent driving control method based on a brushless motor, comprising the following steps: acquiring real-time operation state data of a set UAV, motor operation data, and environment three-dimensional point cloud data; analyzing flight reliable characteristic values of the set UAV and motor response sensitive characteristic values based on the operation state data of the set UAV and the motor operation data; acquiring current three-dimensional position coordinates of the set UAV, and combining the corresponding environment three-dimensional point cloud data, analyzing flight fault-tolerant characteristic values of the set UAV based on a pre-trained flight environment perception model; and jointly driving the brushless motor to control the set UAV based on the flight reliable characteristic values, the motor response sensitive characteristic values, and the flight fault-tolerant characteristic values.

[0007] Further, the operation state data includes an attitude aggregation deviation value, a flight speed value, a flight height value, a rotational inertia force value, a surface static charge value, and a surface electromagnetic radiation value, and the specific steps of analyzing the flight reliable characteristic values of the set UAV are as follows: analyzing an operation characteristic set of the set UAV based on the operation state data of the set UAV, including flight stability characteristic values and function failure risk characteristic values; and analyzing the flight reliable characteristic values of the set UAV based on the operation characteristic set of the set UAV.

[0008] Further, the specific steps of analyzing the operation characteristic set of the set UAV are as follows: analyzing the flight stability characteristic values of the set UAV based on the attitude aggregation deviation value, the flight speed value, and the flight height value of the set UAV; and analyzing the function failure risk characteristic values of the set UAV based on the rotational inertia force value, the surface static charge value, and the surface electromagnetic radiation value of the set UAV.

[0009] Further, the motor operation data includes a torque value, a magnetic force distribution value, a temperature gradient value, an electromagnetic field saturation value, a motor thermal resistance value, and a motor amplitude value, and the specific steps of analyzing the motor response sensitive characteristic values of the set UAV are as follows: analyzing a motor response characteristic set of the set UAV based on the motor operation data of the set UAV, including electromagnetic response efficiency characteristic values and thermal mechanical response stability characteristic values; and analyzing the motor response sensitive characteristic values of the set UAV based on the motor response characteristic set of the set UAV.

[0010] Further, the specific steps of analyzing the motor response characteristic set of the set unmanned aerial vehicle are as follows: based on the torque value, magnetic force distribution value, and electromagnetic field saturation value of the set unmanned aerial vehicle, analyzing the electromagnetic response efficiency characteristic value of the set unmanned aerial vehicle; based on the temperature gradient value, motor thermal resistance value, and motor amplitude value of the set unmanned aerial vehicle, analyzing the thermal mechanical response stability characteristic value of the set unmanned aerial vehicle.

[0011] Further, the specific steps of analyzing the flight fault-tolerant characteristic value of the set unmanned aerial vehicle are as follows: inputting the environment three-dimensional point cloud data of the set unmanned aerial vehicle into the pre-trained flight environment perception model, analyzing the environment characteristic set of the set unmanned aerial vehicle, including the environment obstacle characteristic value and the flight adaptation characteristic value; based on the environment characteristic set of the set unmanned aerial vehicle, analyzing the flight fault-tolerant characteristic value of the set unmanned aerial vehicle.

[0012] Further, the flight environment perception model includes an input layer, a feature extraction layer, and an output layer, and the specific steps of analyzing the environment characteristic set of the set unmanned aerial vehicle are as follows: in the input layer of the flight environment perception model, receiving and preprocessing the current three-dimensional position coordinates and environment three-dimensional point cloud data of the set unmanned aerial vehicle; in the feature extraction layer of the flight environment perception model, based on the preprocessed current three-dimensional position coordinates and environment three-dimensional point cloud data of the set unmanned aerial vehicle, extracting the environment perception feature vector of the set unmanned aerial vehicle; in the output layer of the flight environment perception model, outputting the environment perception feature vector of the set unmanned aerial vehicle to obtain the environment characteristic set of the set unmanned aerial vehicle.

[0013] Further, the specific formula for calculating the flight fault-tolerant characteristic value of the set unmanned aerial vehicle is as follows: ; wherein, is the flight fault-tolerant characteristic value of the set unmanned aerial vehicle, is the environment obstacle characteristic value of the set unmanned aerial vehicle, is the obstacle coefficient in the database, is the flight adaptation characteristic value of the set unmanned aerial vehicle, is the adaptation coefficient in the database, is the adjustment coefficient in the database, is the smoothing coefficient in the database.

[0014] Further, based on the flight reliability characteristic value, the motor response sensitivity characteristic value and the flight fault tolerance characteristic value, the specific steps of controlling the set unmanned aerial vehicle by the brushless motor are as follows: the flight reliability characteristic value, the motor response sensitivity characteristic value and the flight fault tolerance characteristic value of the set unmanned aerial vehicle are respectively analyzed and judged in a plurality of preset motor driving intervals, each motor driving interval includes a flight reliability interval, a motor response sensitivity interval and a flight fault tolerance interval, and each motor driving interval corresponds to a control strategy; based on the control strategy corresponding to the flight reliability characteristic value, the motor response sensitivity characteristic value and the flight fault tolerance characteristic value of the set unmanned aerial vehicle within the preset motor driving interval, the brushless motor controls the set unmanned aerial vehicle.

[0015] An intelligent driving control system based on a brushless motor, comprising: a data acquisition module for acquiring real-time operation state data, motor operation data and environment three-dimensional point cloud data of a set unmanned aerial vehicle; an operation analysis module for analyzing flight reliability characteristic values and motor response sensitivity characteristic values of the set unmanned aerial vehicle based on the operation state data and the motor operation data; a flight environment analysis module for acquiring current three-dimensional position coordinates of the set unmanned aerial vehicle, combining corresponding environment three-dimensional point cloud data, and analyzing flight fault tolerance characteristic values of the set unmanned aerial vehicle based on a pre-trained flight environment perception model; and a driving control module for controlling the set unmanned aerial vehicle by the brushless motor based on the flight reliability characteristic values, the motor response sensitivity characteristic values and the flight fault tolerance characteristic values.

[0016] The present application has the following advantages: (1) The intelligent driving control method based on a brushless motor can realize real-time multi-feature analysis and intelligent adjustment of the unmanned aerial vehicle in a complex dynamic environment by deeply analyzing the flight reliability characteristic value, the motor response sensitivity characteristic value and the flight fault tolerance characteristic value, can effectively capture the details of the state and environmental changes of the unmanned aerial vehicle during flight, accurately judge the adaptability of the unmanned aerial vehicle, and on this basis, can adjust the motor drive in real time in combination with the motor response sensitivity characteristic value, enhance the ability of the unmanned aerial vehicle to respond to environmental changes, for example, when an obstacle suddenly appears during flight, the unmanned aerial vehicle can quickly adjust the flight state to avoid flight instability, thereby improving flight safety, and ensuring that the unmanned aerial vehicle can flexibly respond in a complex environment, improving the accuracy of flight control.

[0017] (2) The intelligent driving control method based on the brushless motor can detect and evaluate the flight state of the unmanned aerial vehicle in a complex environment in real time, especially when a sudden event occurs, so as to effectively judge and adjust the flight strategy. The flight fault-tolerant characteristic value is obtained based on the environment perception model and three-dimensional point cloud data analysis, which helps the unmanned aerial vehicle to maintain flight stability through feedback control when external interference occurs, thereby enhancing the adaptability of the unmanned aerial vehicle in extreme environments and ensuring the safety of the unmanned aerial vehicle in high-risk tasks, thereby greatly reducing the risk of unmanned aerial vehicle loss of control or task failure, and even in the case of sudden environmental interference, the unmanned aerial vehicle can be recovered in time.

[0018] (3) The intelligent driving control method based on the brushless motor optimizes the matching between the motor response and the aircraft control by deeply analyzing the motor operation data and the aircraft state data, thereby realizing the dynamic cooperative control of the unmanned aerial vehicle and the motor, improving the stability of flight, and continuously maintaining high flight performance in complex environments and high-load flight, thereby realizing flight efficiency maximization, and ensuring stronger energy efficiency and reliability in actual flight tasks.

[0019] (4) The intelligent driving control system based on the brushless motor improves the self-adaptability and intelligent control precision of the unmanned aerial vehicle in a complex environment through the cooperation between the modules. The system can collect and analyze the operation state data of the unmanned aerial vehicle and the motor operation data and the three-dimensional point cloud data of the environment, generate corresponding characteristic values, and drive the brushless motor to control the unmanned aerial vehicle based on the generated characteristic values, thereby ensuring the accurate adaptation of the unmanned aerial vehicle to external environmental changes during flight, effectively reducing the error accumulation of the unmanned aerial vehicle in dynamic flight tasks, improving the flight precision, and thereby enhancing the safety of the unmanned aerial vehicle in task execution.

[0020] Of course, implementing any product of the present application does not necessarily require all the advantages described above. BRIEF DESCRIPTION OF DRAWINGS

[0021] Figure 1 A flowchart of the intelligent driving control method based on the brushless motor.

[0022] Figure 2 A flowchart of the specific steps of analyzing and setting the environmental feature set of the unmanned aerial vehicle in the intelligent driving control method based on the brushless motor.

[0023] Figure 3 A schematic diagram of setting the feature data of the unmanned aerial vehicle in the intelligent driving control method based on the brushless motor.

[0024] Figure 4 A block diagram of an intelligent driving control system based on a brushless motor. DETAILED DESCRIPTION

[0025] Referring to Figure 1 The embodiment of the present application provides a technical scheme: an intelligent driving control method based on a brushless motor, comprising the following steps: acquiring running state data of a set unmanned aerial vehicle, motor running data, and environment three-dimensional point cloud data in real time; analyzing flight reliable characteristic values and motor response sensitive characteristic values of the set unmanned aerial vehicle based on the running state data of the set unmanned aerial vehicle and the motor running data; acquiring current three-dimensional position coordinates of the set unmanned aerial vehicle, and combining the corresponding environment three-dimensional point cloud data, analyzing flight fault-tolerant characteristic values of the set unmanned aerial vehicle based on a pre-trained flight environment perception model; and controlling the set unmanned aerial vehicle based on the joint driving of the brushless motor based on the flight reliable characteristic values, the motor response sensitive characteristic values, and the flight fault-tolerant characteristic values.

[0026] Specifically, the running state data includes an attitude aggregation deviation value, a flight speed value, a flight height value, a rotational inertia force value, a surface static charge value, and a surface electromagnetic radiation value, and the specific steps of analyzing the flight reliable characteristic values of the set unmanned aerial vehicle are as follows: analyzing a running characteristic set of the set unmanned aerial vehicle based on the running state data of the set unmanned aerial vehicle, including flight stability characteristic values and function failure risk characteristic values; and analyzing the flight reliable characteristic values of the set unmanned aerial vehicle based on the running characteristic set of the set unmanned aerial vehicle.

[0027] The attitude aggregation deviation value is the degree of comprehensive deviation of the flight attitude angle in the flight process of the unmanned aerial vehicle, which can acquire the pitch angle, the roll angle, and the yaw angle of the unmanned aerial vehicle through an IMU sensor (inertial measurement unit), and perform weighted processing on the squares of the pitch angle, the roll angle, and the yaw angle, i.e., weighting the squares of the pitch angle, the roll angle, and the yaw angle, and taking the square root of the result as the attitude aggregation deviation value.

[0028] The flight speed value is the instantaneous flight speed of the unmanned aerial vehicle relative to the ground, which can be acquired through a GPS sensor.

[0029] The flight height value is the current flight height of the unmanned aerial vehicle, indicating the vertical distance relative to the ground, which can be acquired through an ultrasonic sensor.

[0030] The rotating inertia force value is the inertia load caused by the angular acceleration when the UAV is in high-speed maneuver, i.e. the destructive force resisting the attitude change, which can be obtained by a piezoelectric force sensor (embedded in the motor support and connected with the arm, the polarization direction is parallel to the arm axis, and the piezoelectric sheet is normal to the direction of the rotating inertia force, when the rotating inertia force acts on the piezoelectric sheet, the internal lattice deformation generates electric charge), i.e. when the rotating inertia force acts on the piezoelectric sheet, the internal lattice deformation generates electric charge, the rotating inertia force is directly calculated by measuring the electric charge amount, i.e. the output charge amount = piezoelectric constant (such as 593 pC / N, which can be obtained by the technical specification stored in the database) x acting force (i.e. rotating inertia force), and the result is taken as the rotating inertia force value based on the inversion.

[0031] The surface static charge value is the total amount of static charge on the surface of the UAV, and the accumulation of static charge on the surface of the UAV can affect the normal operation of its electronic equipment, leading to failure of the UAV control or distortion of data transmission, which can be obtained by an electrostatic sensor. The electrostatic sensor uses piezoelectric effect or electric field induction principle, when static charge accumulates on the surface of the aircraft, the sensor can sense the change of the surface electric field, and the total amount of static charge is calculated by the change of the electric field.

[0032] The surface electromagnetic radiation value is the electromagnetic radiation intensity released by the UAV when it is running, which can be obtained by an electromagnetic radiation sensor (such as an EMI sensor). The electromagnetic radiation sensor can sense the electromagnetic field intensity on the surface of the aircraft, and calculate the intensity of the electromagnetic radiation according to the sensing signal.

[0033] The specific formula for calculating the flight reliability characteristic value of the set UAV is as follows: ; wherein, is the flight reliability characteristic value of the set UAV, is the flight stability characteristic value of the set UAV, is the stability coefficient stored in the database, and in this embodiment example, the value is 0.637, is the functional failure risk characteristic value of the set UAV, is the risk coefficient stored in the database, and in this embodiment example, the value is 0.363, .

[0034] The specific steps of analyzing the operation characteristic set of the set unmanned aerial vehicle are as follows: based on the attitude aggregation deviation value, the flight speed value and the flight height value of the set unmanned aerial vehicle, the flight stability characteristic value of the set unmanned aerial vehicle is analyzed, which is specifically: the attitude aggregation deviation value, the flight speed value and the flight height value of the set unmanned aerial vehicle are standardized, and the standardized results are weighted, and in the weighting process, the standardized attitude aggregation deviation value is taken as the reciprocal, that is, 1 / (1+standardized attitude aggregation deviation value), and the result is taken as the flight stability characteristic value (used to measure the stability of the unmanned aerial vehicle in flight); based on the rotational inertia force value, the surface static charge value and the surface electromagnetic radiation value of the set unmanned aerial vehicle, the functional failure risk characteristic value of the set unmanned aerial vehicle is analyzed, which is specifically: the rotational inertia force value, the surface static charge value and the surface electromagnetic radiation value of the set unmanned aerial vehicle are standardized, and the standardized results are weighted, and after the weighting, the result is mapped to 0-1 through the Sigmoid function, and the result is taken as the functional failure risk characteristic value (used to measure the functional failure risk degree of the unmanned aerial vehicle in flight due to external environmental factors).

[0035] In the embodiment, by comprehensively analyzing the flight stability characteristic value and the functional failure risk characteristic value, the flight reliability of the unmanned aerial vehicle can be comprehensively evaluated and optimized to ensure that the unmanned aerial vehicle can maintain high efficient and stable flight performance in flight, especially in the face of complex environmental changes. Secondly, by standardizing and weighting the operation state data, the flight stability of the unmanned aerial vehicle can be measured in real time, and by taking the reciprocal of the attitude aggregation deviation value, the flight control response is more sensitive when the instability is high, thereby improving the accuracy of flight. Finally, the standardization and weighting analysis of the rotational inertia force value, the surface static charge value and the surface electromagnetic radiation value effectively reflect the influence of external environmental factors on the functional failure of the unmanned aerial vehicle. The result is mapped to the 0-1 interval through the Sigmoid function, and the functional failure risk of the unmanned aerial vehicle in complex environment is accurately evaluated, so that the control strategy of the unmanned aerial vehicle can be dynamically adjusted, and the unmanned aerial vehicle can be adjusted in time when encountering external interference, thereby ensuring the stable operation of the unmanned aerial vehicle and improving the reliability of the unmanned aerial vehicle.

[0036] Specifically, the motor operation data includes torque value, magnetic force distribution value, temperature gradient value, electromagnetic field saturation value, motor thermal resistance value and motor amplitude value. The specific steps of analyzing the motor response sensitivity characteristic value of the set unmanned aerial vehicle are as follows: based on the motor operation data of the set unmanned aerial vehicle, the motor response characteristic set of the set unmanned aerial vehicle is analyzed, including electromagnetic response efficiency characteristic value and thermal mechanical response stability characteristic value; based on the motor response characteristic set of the set unmanned aerial vehicle, the motor response sensitivity characteristic value of the set unmanned aerial vehicle is analyzed.

[0037] The torque value is the rotating torque generated by the motor during operation, which can be obtained by a torque sensor.

[0038] The magnetic force distribution value is the magnetic field strength distribution of the motor at different positions, which is used to reflect the uniformity and stability of the magnetic field of the motor during operation. Non-uniform magnetic field may lead to reduced motor efficiency. The magnetic field strength at each position of the motor can be obtained by a Hall sensor array, and the magnetic force skewness value of the motor is analyzed based on the sample skewness formula, and a ratio processing is performed, i.e. 1 / (1+force skewness value), and the result is taken as the magnetic force distribution value.

[0039] The temperature gradient value is the temperature difference change rate between each part (such as stator, rotor, bearing, etc.) of the motor, which reflects the non-uniformity of heat distribution of the motor during operation. The greater the temperature gradient value, the more likely it is to affect the performance of the motor and lead to reduced efficiency. The temperature values of each part can be obtained by a high-precision temperature sensor, and a standard deviation processing is performed, and the result is taken as the temperature gradient value.

[0040] The electromagnetic field saturation value is the saturation degree of the electromagnetic field inside the motor. Magnetic saturation makes it difficult for the motor to effectively respond to load changes. The magnetic field strength at each position of the motor can be obtained by a Hall sensor array, and the saturation magnetic field strength of each position (obtained from the technical specifications of the materials stored in the database) is obtained, and a ratio processing is performed, such as magnetic field strength / saturation magnetic field strength, and a weighted average processing is performed based on the ratio processing result, and the result is taken as the electromagnetic field saturation value.

[0041] The motor thermal resistance value is the degree of hindering heat transfer of the motor material, which reflects the heat dissipation capacity of the motor. Higher thermal resistance value may cause the motor to overheat, reducing its performance. The temperature values of each part can be obtained by a high-precision temperature sensor, and the maximum temperature value and the minimum temperature value are counted, a difference processing is performed to obtain the temperature difference value, and a ratio processing is performed with the motor thermal power (the absolute value of the difference between the input power and the output power, and the input power can be obtained by multiplying the input voltage and current of the motor obtained by the voltage sensor and the current sensor, and the output power can be obtained by multiplying the output torque and speed of the motor obtained by the torque sensor and the speed sensor), and the result is taken as the motor thermal resistance value.

[0042] The motor amplitude value is the vibration intensity of the motor during operation, which reflects the stability of the motor. Higher vibration value may lead to poor control accuracy, mechanical damage and energy waste. It can be obtained by a vibration sensor.

[0043] The specific formula for calculating the motor response sensitivity characteristic value of the set unmanned aerial vehicle is as follows: ; wherein, is the motor response sensitivity characteristic value of the set unmanned aerial vehicle, is the electromagnetic response efficiency characteristic value of the set unmanned aerial vehicle, is a thermal-mechanical coefficient stored in the database and takes a value of 0.612 in the present embodiment, is a thermal-mechanical response stability characteristic value of the unmanned aerial vehicle, is a thermal-mechanical coefficient stored in the database and takes a value of 0.612 in the present embodiment, is an adjustment coefficient stored in the database and takes a value of 2.000 in the present embodiment.

[0044] The specific steps of analyzing the motor response characteristic set of the unmanned aerial vehicle are as follows: based on the torque value, magnetic force distribution value, and electromagnetic field saturation value of the unmanned aerial vehicle, the electromagnetic response efficiency characteristic value of the unmanned aerial vehicle is analyzed, which is specifically: the torque value, magnetic force distribution value, and electromagnetic field saturation value of the unmanned aerial vehicle are standardized, and the standardized results are weighted (and the reciprocal of the standardized electromagnetic field saturation value is taken in the weighting process), and after weighting, the results are mapped between 0 and 1 through a Sigmoid function to obtain the electromagnetic response efficiency characteristic value (used to evaluate the electromagnetic response efficiency of the unmanned aerial vehicle motor); based on the temperature gradient value, motor thermal resistance value, and motor amplitude value of the unmanned aerial vehicle, the thermal-mechanical response stability characteristic value of the unmanned aerial vehicle is analyzed, which is specifically: the temperature gradient value, motor thermal resistance value, and motor amplitude value of the unmanned aerial vehicle are standardized, the standardized results are weighted, and the reciprocal of the weighted results is taken as the thermal-mechanical response stability characteristic value (used to evaluate the thermal stability and mechanical stability of the unmanned aerial vehicle motor in a complex environment).

[0045] In the present embodiment, the motor response sensitivity can be comprehensively evaluated through multi-dimensional analysis of the motor operation data, thereby achieving precise control. In addition, the electromagnetic response efficiency characteristic value of the motor is analyzed using data such as the torque value, magnetic force distribution value, and electromagnetic field saturation value, which helps to optimize the electromagnetic response efficiency of the motor to ensure that the motor can quickly respond when the load changes. These data are standardized and weighted, and the results are mapped to between 0 and 1 through a Sigmoid function, thereby ensuring that the calculation of the electromagnetic response efficiency characteristic value has high precision and reliability, thereby improving the adaptability of the motor in flight. Finally, the analysis of the temperature gradient value, motor thermal resistance value, and motor amplitude value helps to extract the thermal-mechanical response stability characteristic value, which can effectively reflect the thermal stability and mechanical stability of the motor under high load and extreme environment, and through standardization and weighted average, combined with reciprocal processing, the stability of the motor under temperature changes, thermal expansion, and vibration interference can be more accurately measured to ensure the long-term reliability of the unmanned aerial vehicle in a complex environment.

[0046] Specifically, as Figure 3As shown, the environment three-dimensional point cloud data includes the voxel value, three-dimensional coordinates of each voxel point, and the specific steps of analyzing the flight fault tolerance characteristic value of the set unmanned aerial vehicle are as follows: inputting the environment three-dimensional point cloud data of the set unmanned aerial vehicle into the pre-trained flight environment perception model, analyzing the environment characteristic set of the set unmanned aerial vehicle, including the environment obstacle characteristic value and the flight adaptation characteristic value; based on the environment characteristic set of the set unmanned aerial vehicle, analyzing the flight fault tolerance characteristic value of the set unmanned aerial vehicle.

[0047] The flight environment perception model includes an input layer, a feature extraction layer, and an output layer, and the specific steps of analyzing the environment characteristic set of the set unmanned aerial vehicle are as follows: in the input layer of the flight environment perception model, receiving the current three-dimensional position coordinates and the environment three-dimensional point cloud data of the set unmanned aerial vehicle and performing preprocessing; in the feature extraction layer of the flight environment perception model, based on the preprocessed current three-dimensional position coordinates and the environment three-dimensional point cloud data of the set unmanned aerial vehicle, extracting the environment perception feature vector of the set unmanned aerial vehicle; in the output layer of the flight environment perception model, performing output processing on the environment perception feature vector of the set unmanned aerial vehicle to obtain the environment characteristic set of the set unmanned aerial vehicle, which is specifically: inputting the environment perception feature vector of the set unmanned aerial vehicle into a fully connected layer, processing through an activation function (such as Sigmoid), and outputting the environment obstacle feature and the flight adaptation feature in the environment perception feature vector as the environment obstacle characteristic value and the flight adaptation characteristic value.

[0048] The specific steps of extracting the feature vector of the set unmanned aerial vehicle are as follows: Based on a three-dimensional segmentation network (such as 3D-U-Net or 3D-CNN), obstacles are extracted from the environment three-dimensional point cloud data of the set unmanned aerial vehicle to obtain a plurality of obstacle regions (including but not limited to buildings, trees, rocks, pedestrians, vehicles, and birds) and a plurality of empty regions (i.e. non-obstacle regions), as well as corresponding obstacle point sets (including a plurality of obstacle voxel points obstacle voxel values, obstacle three-dimensional coordinates) and empty point sets (including a plurality of empty voxel points empty voxel values, empty three-dimensional coordinates) The obstacle three-dimensional coordinates of each obstacle voxel point in each obstacle region are processed by mean value to obtain the centroid obstacle three-dimensional coordinates of each obstacle region, and the Euclidean distance analysis is performed with the current three-dimensional position coordinates of the set unmanned aerial vehicle to obtain the Euclidean distance value between the set unmanned aerial vehicle and each obstacle region, to determine whether it is lower than the preset safety distance threshold, and to count the number of obstacle regions lower than the preset safety distance threshold and the total number of obstacle regions, and to process the ratio to obtain the collision risk feature, based on the Euclidean distance formula to analyze the distance value between each obstacle region and each remaining obstacle region (i.e. all remaining obstacle regions excluding the obstacle region), and to process by mean value to obtain the obstacle distribution feature; The obstacle voxel values of each obstacle voxel point of each obstacle region are processed by mean value, and the results are processed by standard deviation to obtain a reflection feature. The centroid obstacle three-dimensional coordinates of each obstacle region and the obstacle three-dimensional coordinates of each obstacle voxel point are processed by PCA (i.e., a covariance matrix is constructed based on the centroid obstacle three-dimensional coordinates of each obstacle region and the obstacle three-dimensional coordinates of each obstacle voxel point, and the covariance matrix is solved, and the vector corresponding to the maximum eigenvalue of the covariance matrix is taken as the orientation vector), to extract the orientation vector of the corresponding obstacle region, and analyze the current three-dimensional position coordinates of the set unmanned aerial vehicle (i.e., based on the dot product formula of the vector, the cosine angle value of the set unmanned aerial vehicle and each obstacle region is extracted, and based on the inverse cosine function, the relative angle of the set unmanned aerial vehicle and each obstacle region is extracted), to extract the relative angle of the set unmanned aerial vehicle and each obstacle region, judge whether it is lower than the preset angle threshold, count the number of obstacle regions of the preset angle threshold, and process the ratio of the total number of obstacle regions, and the ratio processing result is standardized with the collision risk feature, the reflection feature, and the obstacle distribution feature, based on the standardized processing result, the environmental obstruction feature (for) is extracted; The number of empty voxel points of each empty area of the unmanned aerial vehicle is counted and summed to obtain an empty volume feature. For each empty voxel point of each empty area, a corresponding empty neighborhood (e.g., 5x5x5, and each empty voxel point in the range is marked as a corresponding neighborhood voxel point) is set. The least square method is used to fit each neighborhood voxel point in the set empty neighborhood range of each empty voxel point to obtain the maximum curvature and minimum curvature of the corresponding empty voxel point, i.e., the centroid coordinates of the neighborhood point set are calculated, i.e., the average value of the empty three-dimensional coordinates of each neighborhood voxel point in the empty neighborhood range is obtained to obtain the neighborhood centroid three-dimensional coordinates of the empty neighborhood. The three-dimensional coordinates of each neighborhood voxel point in the empty neighborhood range are translated to the neighborhood centroid three-dimensional coordinates as the coordinate origin, the covariance matrix of the translated empty neighborhood is calculated, and the eigenvalue decomposition of the covariance matrix is performed to obtain three eigenvalues and their corresponding eigenvectors. The eigenvector corresponding to the minimum eigenvalue is used as the normal vector, and the other two eigenvectors are used as the base vectors of the tangent plane, thereby establishing a local tangent plane coordinate system. The three-dimensional coordinates of each neighborhood voxel point in the empty neighborhood range are projected onto the local tangent plane to obtain the two-dimensional coordinates of each neighborhood voxel point on the tangent plane and the height value of the neighborhood voxel point relative to the tangent plane (i.e., the directed distance of the neighborhood voxel point to the tangent plane along the normal vector direction). The least square method is used to express the height value as a quadratic polynomial function of the two-dimensional coordinates, and the corresponding coefficients are obtained by solving the linear equation system, and a second basic form matrix (Weingarten matrix) is constructed. The maximum eigenvalue and the minimum eigenvalue of the matrix are solved and are used as the maximum curvature and the minimum curvature, respectively. The curvature values of the empty voxel points are obtained by mean value processing, and the weighted average processing is performed based on the mean value processing result to extract the empty complex feature. The empty distance values between each empty area and each remaining empty area (i.e., all remaining empty areas except the empty area) are analyzed based on the Euclidean distance formula, and the mean value processing is performed to obtain the empty distribution feature. The empty volume feature, the empty complex feature, and the empty distribution feature are standardized, and the weighted processing is performed based on the result (and the inverse of the standardized empty complex feature is taken in the weighted processing process) to extract the flight adaptation feature. The environmental obstacle feature and the flight adaptation feature are spliced into an environmental perception feature vector.

[0049] The pre-training steps of the flight environment perception model are as follows: First, obtain the environmental three-dimensional point cloud data sample set in the set area (including the annotated obstacle area, open area, and corresponding obstacle point set and open point set, such as the voxel point coordinates, obstacle voxel value, open voxel point coordinates and open voxel value of each obstacle area), and perform dataset division and format specification processing, such as cleaning the original three-dimensional point cloud data, removing invalid points (such as empty points with intensity of 0, duplicate points, etc.), and filling in missing voxel attributes by interpolation or padding.

[0050] The preprocessed three-dimensional point cloud sample set is divided into a training set, a validation set and a test set, the training set accounts for about 80%, the validation set accounts for 10%, and the test set accounts for 10%. When dividing, ensure that the samples contain different obstacle types, sizes, materials and positions, guarantee the representativeness of the dataset, and enhance the generalization ability of the model.

[0051] Functional layer training: taking the feature extraction layer as an example, the network is trained to extract the spatial structure features of the point cloud from the voxelized sparse spatial tensor layer by layer, and a multi-scale spatial feature map is constructed. Center point regression mechanism: using the regression mechanism, the center position and size vector of the potential obstacle target in the point cloud are predicted, for example, by the centroid coordinates of the obstacle and the coordinates of the obstacle voxel points, the spatial position and shape of the target are estimated, and the corresponding feature values are generated. Calculate the classification loss (such as Focal Loss), regression loss (such as L1 loss or Smooth L1 loss) and direction loss, and train the network parameters through error back propagation.

[0052] Use the training set to perform multiple rounds of iterative training, update the model parameters through the optimizer (such as AdamW), and improve the fitting effect of feature extraction. After each round of training, use the validation set to evaluate the model performance, calculate the obstacle detection accuracy, F1-score and other indicators, and adjust the model hyperparameters such as voxel scale, anchor parameter and non-maximum suppression (NMS) threshold through the validation set to improve the accuracy and recall rate of the model.

[0053] If the model performs poorly on the validation set, overfitting may occur, in which case methods such as Dropout and regularization can be used to suppress overfitting and improve the generalization ability of the model. The model that performs best on the validation set will be used as the formal training model, and its obstacle detection ability and feature extraction accuracy will be verified on the test set to ensure the reliability of the model.

[0054] The specific formula for calculating the flight fault tolerance feature value of the set unmanned aerial vehicle is as follows: ; wherein, is the flight fault tolerance feature value of the set unmanned aerial vehicle, is the environmental obstacle feature value of the set unmanned aerial vehicle, is an obstacle coefficient in the database, and in the present embodiment has a value of 0.648, is a flight adaptability characteristic value of the setting UAV, is an adaptability coefficient in the database, and in the present embodiment has a value of 0.718, is an adjustment coefficient in the database, and in the present embodiment has a value of 0.437, is a smoothing coefficient in the database, and in the present embodiment has a value of 2.000.

[0055] In the present embodiment, by precisely analyzing the three-dimensional point cloud data of the environment in which the UAV is located, and in combination with the flight environment perception model, the adaptability and fault tolerance of the aircraft in a complex environment can be comprehensively evaluated. Secondly, by effectively distinguishing and analyzing the obstacle region and the open region, the model can evaluate the relative distance between the obstacle and the UAV and the possible collision risk in real time, thereby avoiding the UAV from colliding or deviating in flight due to sudden obstacles in a complex environment. Moreover, the extraction of the flight fault tolerance characteristic value combines the environmental obstacle characteristic value and the flight adaptability characteristic value, enabling the UAV to flexibly control the strategy. Finally, by precisely modeling the orientation and position distribution of the obstacles in the flight environment and the morphological characteristics of the open region, the strain ability of the UAV in complex terrain and sudden environmental changes is enhanced, and the flight safety and stability are improved, thereby enabling the UAV to quickly respond and make reasonable adjustments when facing a variable environment, to ensure the smooth execution of the flight mission.

[0056] Specifically, the specific steps of driving the brushless motor to control the setting UAV based on the flight reliability characteristic value, the motor response sensitivity characteristic value, and the flight fault tolerance characteristic value are as follows: the flight reliability characteristic value, the motor response sensitivity characteristic value, and the flight fault tolerance characteristic value of the setting UAV are respectively analyzed and judged in a plurality of preset motor driving intervals, each motor driving interval includes a flight reliability interval, a motor response sensitivity interval, and a flight fault tolerance interval, and each motor driving interval corresponds to a control strategy; based on the control strategy corresponding to the flight reliability characteristic value, the motor response sensitivity characteristic value, and the flight fault tolerance characteristic value of the setting UAV being within the preset motor driving interval, the brushless motor performs control processing on the setting UAV, including but not limited to the following examples: Motor driving interval 1 (high reliability, high sensitivity, and low fault tolerance); Flight reliability interval: 0.8-1.0 (indicating high flight reliability); Motor response sensitivity interval: 0.7-1.0 (indicating very sensitive motor response); Flight fault tolerance interval: 0.0-0.3 (indicating low flight fault tolerance); Corresponding driving control strategy example: Due to high flight reliability and strong sensitivity, the focus is to ensure accurate and efficient motor response. By optimizing the speed and torque output of the brushless motor, the motor can quickly and accurately respond to flight instructions, ensuring stable performance of the UAV in high-precision tasks. For low fault tolerance, the motor overload protection system needs to be adjusted, such as setting current limit value and temperature protection threshold, to prevent the motor from overheating or damage in high response situations; Motor driving interval 2 (medium reliability, medium sensitivity, medium fault tolerance); Flight reliability interval: 0.5-0.7 (indicating medium flight reliability); Motor response sensitivity interval: 0.4-0.6 (indicating moderate motor response sensitivity); Flight fault tolerance interval: 0.4-0.6 (indicating medium flight fault tolerance); Corresponding driving control strategy example: In this interval, the motor needs to ensure moderate response speed, while appropriately reducing sensitivity to avoid unnecessary over-adjustment, such as optimizing the PWM (Pulse Width Modulation) signal control of the motor to make the motor speed more stable during flight; Motor driving interval 3 (low reliability, high sensitivity, high fault tolerance); Flight reliability interval: 0.0-0.4 (indicating low flight reliability); Motor response sensitivity interval: 0.6-0.9 (indicating high motor response sensitivity); Flight fault tolerance interval: 0.7-1.0 (indicating high flight fault tolerance); Corresponding driving control strategy example: In this interval, due to low flight reliability, the fault tolerance mechanism of the flight control system needs to be strengthened, such as through a redundant system of motor control, to ensure that the motor can still provide continuous power within a certain time even if there is a partial control error. The sensitivity of the motor is set to be high to quickly respond to the instructions of the flight control system and ensure real-time adjustment during flight. However, due to high fault tolerance, the load and temperature of the motor can fluctuate within a certain range, so the control strategy should focus on improving the motor power output without affecting stability to cope with unpredictable factors in the flight environment; Motor driving interval 4 (high reliability, low sensitivity, high fault tolerance); Flight reliability interval: 0.8-1.0 (indicating high flight reliability); Motor response sensitivity interval: 0.0-0.3 (indicating low motor response sensitivity); Flight fault tolerance interval: 0.7-1.0 (indicating high flight fault tolerance); Corresponding driving control strategy example: In the case of high reliability and high fault tolerance, the focus is to improve the stability of the motor's continuous output. The motor's response sensitivity is low, which means the response to control instructions should be moderate (i.e., the motor's reaction to control instructions is slow, and it will not react sharply to input changes). Avoid over-regulation, adjust the motor's driving strategy, and maintain stable speed output, especially to reduce motor load fluctuations during long flights. To ensure high fault tolerance, set a higher motor speed tolerance and temperature tolerance to ensure that the motor can work stably even if it encounters disturbances during flight. Motor driving interval 5 (low reliability, low sensitivity, low fault tolerance); Flight reliability interval: 0.0-0.2 (indicating low flight reliability); Motor response sensitivity interval: 0.0-0.3 (indicating low motor response sensitivity); Flight fault tolerance interval: 0.0-0.2 (indicating low flight fault tolerance); Corresponding driving control strategy example: In the case of low reliability, low sensitivity, and low fault tolerance, the motor control strategy needs to enhance stability and safety, such as strengthening the starting stability control of the motor and the smooth transition during acceleration to avoid risks caused by drastic changes. In addition, the control system needs to monitor the motor's load in real time, adjust the current and output power to avoid motor overload, and set a more stringent temperature control strategy to ensure that the motor can work reliably in unstable environments. Motor driving interval 6 (high reliability, high sensitivity, high fault tolerance) Flight reliability interval: 0.8-1.0 (indicating high flight reliability) Motor response sensitivity interval: 0.7-1.0 (indicating high motor response sensitivity) Flight fault tolerance interval: 0.7-1.0 (indicating high flight fault tolerance) Corresponding driving control strategy example: In this group, flight reliability, sensitivity, and fault tolerance are all high. For example, precisely adjust the motor's speed and torque output to enable the motor to respond quickly to the instructions of the flight control system, especially when performing high-precision flight tasks, to ensure the consistency of instructions and actions. Due to high fault tolerance, the motor can provide more redundancy support in load and environmental changes. In this case, the control system can appropriately increase the motor power output to improve flight stability and adaptability to sudden situations. Despite high fault tolerance, it is still necessary to ensure that overload protection measures are in place, such as adjusting current limits and setting temperature protection thresholds, to ensure that the motor will not be damaged under maximum load conditions and maintain long-term reliability.

[0057] The specific implementation example of controlling the set unmanned aerial vehicle by the brushless motor driven by the flight reliability characteristic value, the motor response sensitivity characteristic value, and the flight fault-tolerant characteristic value is as follows, and the following data are provided, including: The flight stability characteristic value, the functional failure risk characteristic value, the electromagnetic response efficiency characteristic value, the thermal mechanical response stability characteristic value, the environmental obstruction characteristic value, and the flight adaptation characteristic value of the set unmanned aerial vehicle are specifically shown in Table 1 and Figure 3

[0058] The stability coefficient stored in the data is 0.637; The risk coefficient stored in the database is 0.363; The electromagnetic coefficient stored in the data is 0.584; The thermal mechanical coefficient stored in the database is 0.612; The adjustment coefficient stored in the database is 2.000; The obstruction coefficient stored in the data is 0.648; The adaptation coefficient stored in the database is 0.718; The adjustment coefficient stored in the database is 0.437; The smoothing coefficient stored in the database is 2.000; The data in Table 1 and the above coefficients are respectively substituted into the specific formula for calculating the flight reliability characteristic value, the motor response sensitivity characteristic value, and the flight fault-tolerant characteristic value of the set unmanned aerial vehicle to obtain: The flight reliability characteristic value of the set unmanned aerial vehicle is 0.637*0.816+0.363*(1 / (1+0.238))≈0.812; The motor response sensitivity characteristic value of the set unmanned aerial vehicle is ((0.736^0.584+0.687^0.612) / 2.000)^1 / (0.584+0.612)≈0.848; The flight fault-tolerant characteristic value of the set unmanned aerial vehicle is ((exp(-0.648*0.246)+0.769^0.718) / 2.000)*ln(1+0.437*(0.769 / 0.246))≈0.723.

[0059] ​At this time, the flight reliability characteristic value, the motor response sensitivity characteristic value and the flight fault tolerance characteristic value are in the motor driving interval 6, that is, the motor power output can be appropriately increased to improve the flight stability and the adaptability to sudden situations, and the overload protection measures are ensured to be in place, such as adjusting the current limit and setting the temperature protection threshold, so that the motor is not damaged under the maximum load condition and the long-term reliability is maintained.

[0060] In the embodiment, by combining the flight reliability characteristic value, the motor response sensitivity characteristic value and the flight fault tolerance characteristic value, an intelligent control framework is provided for the unmanned aerial vehicle, and by presetting the motor driving interval, the unmanned aerial vehicle can adjust the motor control strategy accurately to ensure the stability and safety of the unmanned aerial vehicle. Specifically, based on different motor driving intervals, the motor is accurately adjusted to realize efficient flight control. Secondly, in the case of high flight reliability and strong sensitivity, the motor control focuses on accurate and efficient response to ensure that the detailed operation in the flight task can be smoothly completed. In the case of low sensitivity but high fault tolerance, the motor stability is emphasized by reducing the excessive response to input changes, so that the unmanned aerial vehicle can still maintain stable operation when encountering external disturbances, thereby greatly improving the adaptability of the unmanned aerial vehicle in complex environments. Finally, by combining the flight fault tolerance characteristic value, redundancy protection is provided during the operation of the motor to reduce the risk of motor failure and improve the reliability of the unmanned aerial vehicle in variable environments, thereby improving the adaptability of the unmanned aerial vehicle in different flight tasks and enabling the unmanned aerial vehicle to realize efficient and safe flight under various working conditions.

[0061] Please refer to Figure 4 The embodiment of the present application provides a technical solution: an intelligent driving control system based on a brushless motor, comprising: a data acquisition module for acquiring real-time running state data of a set unmanned aerial vehicle, motor running data and environment three-dimensional point cloud data; an operation analysis module for analyzing flight reliability characteristic values and motor response sensitivity characteristic values of the set unmanned aerial vehicle based on the running state data and the motor running data of the set unmanned aerial vehicle; a flight environment analysis module for acquiring the current three-dimensional position coordinates of the set unmanned aerial vehicle, combining the corresponding environment three-dimensional point cloud data, and analyzing the flight fault tolerance characteristic values of the set unmanned aerial vehicle based on a pre-trained flight environment perception model; and a driving control module for jointly driving the brushless motor to control the set unmanned aerial vehicle based on the flight reliability characteristic values, the motor response sensitivity characteristic values and the flight fault tolerance characteristic values.

[0062] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications to the embodiments once they know the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0063] Obviously, many modifications and variations of the present application are possible in light of the above teachings. It is, therefore, to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A method for intelligent drive control based on a brushless motor, characterized in that, The method comprises the following steps: Real-time acquisition of the running state data of the unmanned aerial vehicle, motor running data, and environmental three-dimensional point cloud data; Based on the running state data of the unmanned aerial vehicle and the motor running data, the flight reliability characteristic value and the motor response sensitivity characteristic value of the unmanned aerial vehicle are analyzed; The current three-dimensional position coordinates of the unmanned aerial vehicle are acquired, and the corresponding environmental three-dimensional point cloud data are combined to analyze the flight fault tolerance characteristic value of the unmanned aerial vehicle based on a pre-trained flight environment perception model; The brushless motor is jointly driven based on the flight reliability characteristic value, the motor response sensitivity characteristic value, and the flight fault tolerance characteristic value to control the unmanned aerial vehicle.

2. The intelligent drive control method based on a brushless motor according to claim 1, characterized in that, The running state data includes attitude aggregation deviation value, flight speed value, flight height value, rotational inertia force value, surface static charge value, and surface electromagnetic radiation value, and the specific steps of analyzing the flight reliability characteristic value of the unmanned aerial vehicle are as follows: Based on the running state data of the unmanned aerial vehicle, the operating characteristic set of the unmanned aerial vehicle is analyzed, including the flight stability characteristic value and the functional failure risk characteristic value; Based on the operating characteristic set of the unmanned aerial vehicle, the flight reliability characteristic value of the unmanned aerial vehicle is analyzed.

3. The intelligent drive control method based on a brushless motor according to claim 2, characterized in that, The specific steps of analyzing the operating characteristic set of the unmanned aerial vehicle are as follows: Based on the attitude aggregation deviation value, flight speed value, and flight height value of the unmanned aerial vehicle, the flight stability characteristic value of the unmanned aerial vehicle is analyzed; Based on the rotational inertia force value, surface static charge value, and surface electromagnetic radiation value of the unmanned aerial vehicle, the functional failure risk characteristic value of the unmanned aerial vehicle is analyzed.

4. The intelligent drive control method based on a brushless motor according to claim 1, wherein, The motor running data includes torque value, magnetic force distribution value, temperature gradient value, electromagnetic field saturation value, motor thermal resistance value, and motor amplitude value, and the specific steps of analyzing the motor response sensitivity characteristic value of the unmanned aerial vehicle are as follows: Based on the motor running data of the unmanned aerial vehicle, the motor response characteristic set of the unmanned aerial vehicle is analyzed, including the electromagnetic response efficiency characteristic value and the thermal mechanical response stability characteristic value; Based on the motor response characteristic set of the unmanned aerial vehicle, the motor response sensitivity characteristic value of the unmanned aerial vehicle is analyzed.

5. The intelligent drive control method based on a brushless motor according to claim 4, characterized in that, The specific steps of analyzing the motor response characteristic set of the unmanned aerial vehicle are as follows: Based on the torque value, magnetic force distribution value, and electromagnetic field saturation value of the unmanned aerial vehicle, the electromagnetic response efficiency characteristic value of the unmanned aerial vehicle is analyzed; Based on the temperature gradient value, motor thermal resistance value, and motor amplitude value of the unmanned aerial vehicle, the thermal mechanical response stability characteristic value of the unmanned aerial vehicle is analyzed.

6. The intelligent drive control method based on a brushless motor according to claim 1, wherein, The specific steps of analyzing the flight fault tolerance characteristic value of the unmanned aerial vehicle are as follows: The environmental three-dimensional point cloud data of the unmanned aerial vehicle are input into the pre-trained flight environment perception model to analyze the environmental characteristic set of the unmanned aerial vehicle, including the environmental obstruction characteristic value and the flight adaptation characteristic value; Based on the environmental characteristic set of the unmanned aerial vehicle, the flight fault tolerance characteristic value of the unmanned aerial vehicle is analyzed.

7. The intelligent drive control method based on a brushless motor according to claim 6, wherein, The flight environment perception model includes an input layer, a feature extraction layer, and an output layer, and the specific steps of analyzing the environmental characteristic set of the unmanned aerial vehicle are as follows: In the input layer of the flight environment perception model, the current three-dimensional position coordinates and the environmental three-dimensional point cloud data of the unmanned aerial vehicle are received and preprocessed; In the feature extraction layer of the flight environment perception model, based on the pre-processed current three-dimensional position coordinates of the set unmanned aerial vehicle and the environment three-dimensional point cloud data, the environment perception feature vector of the set unmanned aerial vehicle is extracted; In the output layer of the flight environment perception model, the environment perception feature vector of the set unmanned aerial vehicle is output processed to obtain the environment feature set of the set unmanned aerial vehicle.

8. The intelligent drive control method based on a brushless motor according to claim 6, wherein, The specific formula for calculating the flight fault tolerance feature value of the set unmanned aerial vehicle is as follows: ； wherein, to set a flight fault characteristic value of the UAV, to set an environmental obstruction characteristic value of the UAV, to set an obstruction coefficient in the database, to set a flight adaptation characteristic value of the UAV, to set an adaptation coefficient in the database, to set a regulation coefficient in the database, to set a smoothing coefficient in the database.

9. The intelligent drive control method based on a brushless motor according to claim 1, wherein, The specific steps of controlling the set unmanned aerial vehicle based on the flight reliability feature value, the motor response sensitivity feature value and the flight fault tolerance feature value jointly driving the brushless motor are as follows: The flight reliability feature value, the motor response sensitivity feature value and the flight fault tolerance feature value of the set unmanned aerial vehicle are respectively analyzed by judging a plurality of preset motor driving intervals, each motor driving interval includes a flight reliability interval and a motor response sensitivity interval and a flight fault tolerance interval, and each motor driving interval corresponds to a control strategy; Based on the control strategy corresponding to the flight reliability feature value, the motor response sensitivity feature value and the flight fault tolerance feature value of the set unmanned aerial vehicle within the preset motor driving interval, the brushless motor drives the set unmanned aerial vehicle to perform control processing.

10. A brushless motor-based intelligent drive control system, applying the brushless motor-based intelligent drive control method according to any one of claims 1-9, characterized in that, It includes: The data acquisition module is used for real-time acquisition of the running state data, motor running data and environment three-dimensional point cloud data of the set unmanned aerial vehicle; The running analysis module is used for analyzing the flight reliability feature value and the motor response sensitivity feature value of the set unmanned aerial vehicle based on the running state data and the motor running data of the set unmanned aerial vehicle; The flight environment analysis module is used for acquiring the current three-dimensional position coordinates of the set unmanned aerial vehicle, combining the corresponding environment three-dimensional point cloud data, and analyzing the flight fault tolerance feature value of the set unmanned aerial vehicle based on the pre-trained flight environment perception model; The driving control module is used for controlling the set unmanned aerial vehicle based on the flight reliability feature value, the motor response sensitivity feature value and the flight fault tolerance feature value jointly driving the brushless motor.

Images