Control method for synchronous rectification of starting generator of unmanned aerial vehicle

Abstract

The invention provides a control method for synchronous rectification of a starting generator of an unmanned aerial vehicle, and relates to the technical field of unmanned aerial vehicle power electronics, and the control method comprises the steps: obtaining multi-sensor data of a starting generator system, and calculating and generating state parameters; reasoning by using the fuzzy control node and a preset fuzzy rule in combination with multi-sensor data to generate a preliminary PWM adjustment signal; smoothing the preliminary PWM adjustment signal by using an adaptive filter; transmitting the smoothed initial PWM adjustment signal and the state parameter to a pre-trained neural network model by taking the smoothed initial PWM adjustment signal and the state parameter as input, and adjusting the initial PWM adjustment signal through the pre-trained neural network model; and a final PWM control signal is generated according to the adjusted preliminary PWM adjustment signal, and the final PWM control signal is transmitted to the generator system of the unmanned aerial vehicle, the state of the generator system of the unmanned aerial vehicle can be sensed in real time, and accurate control is performed based on multi-sensor data, so that the stability of synchronous rectification control is improved.

Description

Technical Field

[0001] The present invention relates to the field of UAV power electronics technology, and in particular to a control method for synchronous rectification of a UAV starter generator. Background Art

[0002] With the rapid development of drone technology, drones are increasingly used in many fields. As one of the core components of drones, the generator system is not only responsible for providing power support for drones, but also serves as a generator to recover energy during the landing and recovery process of drones to improve energy efficiency. However, the drone generator system faces a complex and changeable operating environment during operation, such as sudden load changes, voltage fluctuations, and temperature increases. These factors may cause the performance of the generator system to deteriorate and even affect the stable flight of the drone.

[0003] Traditional UAV generator control methods mostly use simple open-loop control or PID (proportional-integral-differential) control. These methods are unable to cope with complex and changeable operating environments and it is difficult to achieve high-precision synchronous rectification control.

[0004] Therefore, it is necessary to provide a control method for synchronous rectification of a UAV generator to solve the above technical problems. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a control method for synchronous rectification of a UAV starting generator, which can sense the system status of the UAV starting generator in real time and perform precise control based on multi-sensor data, so as to improve the accuracy and stability of synchronous rectification control.

[0006] The present invention provides a control method for synchronous rectification of a UAV generator, which is applied to a UAV generator system. The control method comprises the following steps:

[0007] Acquire multi-sensor data of a generator system of the UAV, and calculate and generate state parameters based on the multi-sensor data;

[0008] Using pre-built fuzzy control nodes and preset fuzzy rules, and combining the multi-sensor data for reasoning, to generate a preliminary PWM adjustment signal;

[0009] Using an adaptive filter to smooth the preliminary PWM adjustment signal;

[0010] The smoothed preliminary PWM adjustment signal and the state parameter are used as inputs and transmitted to a pre-trained neural network model, and the preliminary PWM adjustment signal is adjusted by the pre-trained neural network model;

[0011] A final PWM control signal is generated according to the adjusted preliminary PWM adjustment signal, and the final PWM control signal is transmitted to the generator system of the UAV for realizing synchronous rectification control.

[0012] Preferably, the multi-sensor data includes voltage sensor data, current sensor data, rotation speed sensor data and temperature sensor data of the generator system of the drone.

[0013] Preferably, the calculating and generating of the state parameters includes:

[0014] Calculating the real-time output power of the generator system of the drone based on the voltage sensor data and the current sensor data;

[0015] Determine the current speed of the generator system using the speed sensor data;

[0016] Monitoring the temperature status of the generator system through temperature sensor data;

[0017] The real-time output power, current speed and temperature status are integrated to generate status parameters reflecting the current operating status of the generator system.

[0018] Preferably, the method of utilizing the pre-built fuzzy control nodes and preset fuzzy rules and combining the multi-sensor data for reasoning to generate a preliminary PWM adjustment signal includes:

[0019] Define multiple fuzzy sets, each fuzzy set corresponds to a single control dimension of the UAV generator system, and set a corresponding membership function for each fuzzy set, wherein the control dimension includes real-time output power, current speed and temperature state;

[0020] The real-time output power, current speed and temperature state acquired in real time are mapped to the corresponding fuzzy sets, and the membership function set for each fuzzy set is used to calculate the membership of each sensor data in the corresponding fuzzy set;

[0021] Using a preset fuzzy rule base, fuzzy reasoning is performed according to the membership degree of each fuzzy set, wherein the fuzzy rule base contains a plurality of rules for describing the changing law of the PWM adjustment signal under different states;

[0022] According to the result of the fuzzy reasoning, the duty cycle and frequency of the preliminary PWM adjustment signal are calculated.

[0023] Preferably, the smoothing process of the preliminary PWM adjustment signal by using an adaptive filter includes:

[0024] The preliminary PWM adjustment signal is input as an input signal into the adaptive filter, and the adaptive filter dynamically adjusts the parameters of the adaptive filter according to a preset filtering algorithm and the current input signal, and finally outputs a smooth PWM adjustment signal.

[0025] Preferably, the process of taking the smoothed preliminary PWM adjustment signal and the state parameter as input and transmitting them to the pre-trained neural network model for signal adjustment includes:

[0026] The preliminary PWM adjustment signal after smoothing by the adaptive filter is integrated with the state parameter to form a multi-dimensional input vector;

[0027] The multidimensional input vector is used as input layer data and transmitted to a pre-trained neural network model. After being processed layer by layer by the neural network model, an adjusted PWM adjustment signal is output, wherein the neural network model has been trained based on historical data and expert knowledge.

[0028] Preferably, generating a final PWM control signal according to the adjusted preliminary PWM adjustment signal, and transmitting the final PWM control signal to the generator system of the UAV, comprises:

[0029] Performing signal conversion and formatting processing on the duty cycle and frequency of the adjusted PWM adjustment signal to generate a final PWM control signal that meets the requirements of the generator system of the UAV;

[0030] The generated final PWM control signal is transmitted to the UAV's starting generator system, and when the starting generator system is in generator mode, the received final PWM control signal is used to control the output voltage and current waveforms to achieve synchronous rectification control with the UAV load.

[0031] Compared with the related art, the control method for synchronous rectification of a UAV generator provided by the present invention has the following beneficial effects:

[0032] The present invention realizes efficient and precise control of the UAV generator system by integrating advanced technologies such as multi-sensor data fusion, fuzzy control, adaptive filtering and neural network optimization. This method not only significantly improves the system's adaptability and intelligence level, but also can dynamically adjust the PWM control signal according to the real-time operating conditions to ensure accurate matching of the output voltage and current waveforms and efficient synchronous rectification. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 A flow chart of a control method for synchronous rectification of a UAV generator provided by the present invention. DETAILED DESCRIPTION

[0034] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only the parts related to the present invention, rather than all structures, are shown in the accompanying drawings. In addition, the embodiments of the present invention and the features in the embodiments may be combined with each other without conflict.

[0035] It should also be noted that, for ease of description, only the part relevant to the present invention but not all the content is shown in the accompanying drawings. It should be mentioned before discussing the exemplary embodiments in more detail that some exemplary embodiments are described as the processing or method described as a flow chart. Although the flow chart describes each operation (or step) as being processed sequentially, many operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of each operation can be rearranged. When its operation is completed, the processing can be terminated, but it can also have additional steps not included in the accompanying drawings. The processing can correspond to a method, a function, a procedure, a subroutine, a subprogram, etc.

[0036] The present invention provides a control method for synchronous rectification of a UAV generator, which is applied to a UAV generator system. Figure 1 As shown, the control method comprises the following steps:

[0037] S1: Acquire multi-sensor data of the generator system of the UAV, and calculate and generate state parameters based on the multi-sensor data.

[0038] In step S1, the multi-sensor data includes voltage sensor data, current sensor data, rotation speed sensor data and temperature sensor data of the generator system of the drone.

[0039] In the UAV's starting and power generation system, in order to ensure the stability and reliability of the starting and power generation system, multiple key parameters must be monitored in real time. These parameters include voltage, current, speed and temperature. Through these sensor data, potential problems can be discovered in time and measures can be taken in advance to avoid failures, thereby improving the overall performance and safety of the system.

[0040] For voltage sensor data, the output voltage of the generator is monitored by a voltage sensor installed at the output end of the generator. The voltage sensor converts the voltage signal into an electrical signal, which is then processed by the data acquisition unit and transmitted to the control system.

[0041] For current sensor data, current is indirectly measured using a current sensor based on a Hall effect sensor, which converts current changes into a measurable signal.

[0042] For the speed sensor data, the speed sensor installed on the motor shaft detects the magnetic changes on the rotating parts to calculate the speed.

[0043] For temperature sensor data, the temperature of the generator and its components is monitored by temperature sensors installed inside the motor windings.

[0044] These sensor data are collected continuously and transmitted to the central control system of the UAV through communication interfaces (including but not limited to CAN bus, RS-485, etc.). The central control system uses these data to calculate and evaluate the status parameters of the generator, and then decides how to adjust the operating parameters of the system to maintain optimal performance.

[0045] In step S1, the step of generating state parameters includes:

[0046] S11: Calculate the real-time output power of the generator system of the drone based on the voltage sensor data and the current sensor data.

[0047] In this embodiment, the collected analog voltage and current signals are converted into digital signals through an analog-to-digital converter (ADC), and the voltage and current values ​​output by the ADC are read in real time, and then the instantaneous power, that is, the real-time output power, is calculated according to the power calculation formula.

[0048] S12: Determine the current rotation speed of the generator system using the rotation speed sensor data.

[0049] In this embodiment, a rotation speed sensor is installed on a rotating component (such as a motor shaft) of the generator. Generally, such a sensor can detect magnetic changes of the rotating component.

[0050] Each time the rotating part rotates a certain angle, the sensor generates a pulse signal. The number of pulses generated per unit time is recorded using a timer / counter, and the rotation speed is calculated based on the number of pulses per unit time. Specifically, the number of pulses generated within 60 seconds is divided by the measurement time (seconds), and the result is the rotation speed (RPM).

[0051] S13: Monitoring the temperature status of the generator system through temperature sensor data.

[0052] In this embodiment, a temperature sensor is installed at the key heat-generating part of the generator, namely, inside the motor winding. The temperature sensor includes but is not limited to thermistors and thermocouples. These sensors can feedback the temperature value in real time. The signal output by the temperature sensor is converted into a digital signal through an analog-to-digital converter to obtain the temperature value.

[0053] S14: Integrate the real-time output power, current speed and temperature status to generate status parameters reflecting the current operating status of the generator system.

[0054] In this embodiment, the state parameter is a comprehensive assessment of the overall health of the generator system. By combining multiple key parameters, a more comprehensive understanding of the system's operating status can be obtained, providing a basis for subsequent control decisions.

[0055] Specifically, the real-time output power, rotation speed and temperature status data obtained in steps S11 to S13 are integrated together, and weights are assigned to each parameter according to actual conditions. These weights reflect the importance of each parameter in evaluating the system status. Specifically, weights are assigned to each parameter based on past experience and in-depth understanding of the system. For example, if engineers find that in some cases, temperature has a greater impact on the system than output power, then a higher weight can be given to temperature. Finally, the real-time output power, rotation speed and temperature status are weighted and calculated according to their respective weights.

[0056] S2: Utilizing the pre-built fuzzy control nodes and preset fuzzy rules, and combining the multi-sensor data for reasoning, a preliminary PWM adjustment signal is generated.

[0057] Specifically, step S2 specifically includes the following steps:

[0058] S21: Define multiple fuzzy sets, each fuzzy set corresponds to a single control dimension of the UAV generator system, and set a corresponding membership function for each fuzzy set, wherein the control dimension includes real-time output power, current speed and temperature status.

[0059] In this embodiment, fuzzy sets and membership functions are the core components of the fuzzy logic control system. By defining fuzzy sets and membership functions, accurate sensor data can be converted into fuzzy language variables, so that the control system can better handle uncertainty and fuzzy information.

[0060] Specifically, a fuzzy set is first defined. For the real-time output power, a fuzzy set such as "low power", "medium power" and "high power" can be defined.

[0061] For the current speed, fuzzy sets such as "low speed", "medium speed" and "high speed" can be defined.

[0062] For temperature status, fuzzy sets such as "low temperature", "suitable temperature" and "high temperature" can be defined.

[0063] Secondly, a corresponding membership function is set for each fuzzy set, and a triangular function is selected to define the membership function. The triangular function reaches the maximum membership (usually 1) at a certain point and gradually decreases to 0 on both sides of this point.

[0064] Exemplarily, assuming that the range of the real-time output power is [0, 2000] W, the following triangular membership functions can be defined:

[0065] Low power (LP): The vertex of the triangular function is located between P min and P mid where P min is the minimum value of the power, and P mid is the boundary value between low power and medium power.

[0066] Assume P min = 0 W and P mid = 500 W.

[0067] The membership function is defined as μ LP (P), where P is the real-time output power.

[0068] If P < 0 or P > 500, then μ LP (P) = 0;

[0069] If 0 ≤ P ≤ 500, then μ LP (P) is a linearly increasing function from 0 to 1;

[0070] If 500 < P ≤ 1000, then μ LP (P) is a linearly decreasing function from 1 to 0.

[0071] Medium power (MP): The vertex of the triangular function is located between P mid and P max where P max is the maximum value of the power.

[0072] Assume P mid = 500 W and P max = 2000 W.

[0073] The membership function is defined as μ MP (P).

[0074] If P < 500 or P > 2000, then μ MP (P) = 0;

[0075] If 500 ≤ P ≤ 1000, then μ MP (P) is a linearly increasing function from 0 to 1;

[0076] If 1000 < P ≤ 2000, then μMP (P) is a linearly decreasing function from 1 to 0.

[0077] High power (HP): The vertex of the triangular function is located between P mid and P max between.

[0078] Assume P mid = 1500W, P max = 2000W.

[0079] The membership function is defined as μ HP (P).

[0080] If P < 1500 or P > 2000, then μ HP (P) = 0;

[0081] If 1500 ≤ P ≤ 2000, then μ HP (P) is a linearly increasing function from 0 to 1;

[0082] If 2000 < P ≤ 2500, then μ HP (P) is a linearly decreasing function from 1 to 0.

[0083] S22: Map the real-time output power, current rotational speed, and temperature status obtained in real time into the corresponding fuzzy sets, and use the membership functions set for each fuzzy set to calculate the membership degrees of each sensor data in the corresponding fuzzy sets.

[0084] In this embodiment, mapping the accurate sensor data into fuzzy sets can convert continuous numerical values into fuzzy language variables, facilitating the subsequent fuzzy reasoning process.

[0085] Map the real-time output power into fuzzy sets such as "low power", "medium power", "high power", etc.

[0086] Map the current rotational speed into fuzzy sets such as "low rotational speed", "medium rotational speed", "high rotational speed", etc.

[0087] Map the temperature status into fuzzy sets such as "low temperature", "suitable temperature", "high temperature", etc.

[0088] Use the membership functions defined in step S21 to calculate the membership degrees of the real-time output power, current rotational speed, and temperature status in the corresponding fuzzy sets.

[0089] The membership degree values are between 0 and 1, indicating the degree to which the data belongs to a certain fuzzy set.

[0090] S23: using a preset fuzzy rule base to perform fuzzy reasoning according to the membership of each fuzzy set, wherein the fuzzy rule base includes a plurality of rules for describing the changing rules of the PWM adjustment signal under different states.

[0091] In this embodiment, fuzzy reasoning is a process of inferring a preliminary value of the PWM adjustment signal based on the rules in the fuzzy rule base and the membership degree of the sensor data.

[0092] A fuzzy rule base is pre-built, including multiple fuzzy rules, such as: "If the real-time output power is 'low power', and the speed is 'low speed', the PWM adjustment signal should be 'increase'".

[0093] The form of the rule is: "If A and B, then C", where A and B are input conditions and C is the output adjustment signal.

[0094] According to the membership value calculated in step S22, fuzzy rules are applied to perform reasoning.

[0095] For each fuzzy rule, calculate its activation degree, that is, the minimum membership degree of the input condition.

[0096] Based on the most active rule, a preliminary value for the PWM adjustment signal is inferred.

[0097] S24: According to the result of the fuzzy reasoning, the duty cycle and frequency of the preliminary PWM adjustment signal are calculated.

[0098] In this embodiment, the calculation of the preliminary PWM adjustment signal is to convert the result of fuzzy reasoning into specific PWM signal parameters (such as duty cycle and frequency) to facilitate subsequent signal processing and control applications.

[0099] The result of fuzzy reasoning is converted into a specific numerical value using defuzzification technology (including but not limited to the centroid method and the maximum membership method). The purpose of defuzzification is to extract a clear PWM adjustment signal value from the result of fuzzy reasoning.

[0100] The duty cycle and frequency of the preliminary PWM adjustment signal are calculated based on the results of defuzzification. The duty cycle determines the proportion of the high level of the PWM signal in one cycle, and the frequency is the number of cycles completed by the PWM signal per second.

[0101] S3: Using an adaptive filter to smooth the preliminary PWM adjustment signal.

[0102] Specifically, step S3 is as follows:

[0103] The preliminary PWM adjustment signal is input as an input signal into the adaptive filter, and the adaptive filter dynamically adjusts the parameters of the adaptive filter according to a preset filtering algorithm and the current input signal, and finally outputs a smooth PWM adjustment signal.

[0104] After the initial PWM adjustment signal is generated, the signal may have noise or fluctuations, which will affect the stability and efficiency of the system. Using LMS adaptive filter can effectively remove these noise and fluctuations, making the PWM signal smoother, thereby improving the reliability and performance of the system.

[0105] An adaptive filter is a filter that can automatically adjust its parameters according to the input signal. It can continuously learn and update the filter parameters during the processing process to better adapt to the changes of the input signal.

[0106] The preliminary PWM adjustment signal obtained in step S24 is input as an input signal to the LMS adaptive filter. This signal includes the duty cycle and frequency information of the PWM.

[0107] Among them, the working process of LMS adaptive filter is:

[0108] Initialization: Set the initial parameters of the adaptive filter, including the filter order and step factor.

[0109] Filtering: The preliminary PWM adjustment signal is sent to the filter, and the filter dynamically adjusts the filter parameters according to the preset filtering algorithm and the current input signal.

[0110] Parameter update: The filter adjusts its parameters based on changes in the input signal to minimize the error between the output signal and the ideal signal.

[0111] Output smooth signal: The final output is a smooth PWM adjustment signal after filtering.

[0112] S4: taking the smoothed preliminary PWM adjustment signal and the state parameter as input and transmitting them to a pre-trained neural network model, and adjusting the preliminary PWM adjustment signal through the pre-trained neural network model.

[0113] Specifically, step S4 specifically includes the following steps:

[0114] S41: Integrate the preliminary PWM adjustment signal after smoothing by the adaptive filter with the state parameter to form a multi-dimensional input vector.

[0115] In the control of the UAV generator system, although the preliminary PWM adjustment signal has been fuzzy logic controlled and smoothed, there may still be some slight fluctuations or uncertainties. In order to further optimize the control effect, the preliminary PWM adjustment signal is input into the pre-trained neural network model together with the state parameters to obtain a more accurate and stable adjustment signal.

[0116] The preliminary PWM adjustment signal after smoothing by the adaptive filter and the state parameters calculated in step S1 are obtained, including the real-time output power, the current speed and the temperature state.

[0117] The preliminary PWM adjustment signal (including duty cycle and frequency) is combined with the state parameters (real-time output power, speed, temperature) to form a multi-dimensional input vector. The input data of the neural network model is standardized to ensure that each feature is at the same level.

[0118] Normalization can be performed by methods including but not limited to normalization or standardization, for example, scaling all input features to between 0 and 1 or to have a mean of 0 and a variance of 1.

[0119] S42: transmitting the multidimensional input vector as input layer data to a pre-trained neural network model, and outputting an adjusted PWM adjustment signal after layer-by-layer processing by the neural network model, wherein the neural network model has been trained based on historical data and expert knowledge.

[0120] In this embodiment, the pre-trained neural network model can learn more complex nonlinear relationships, so that more influencing factors can be taken into account when processing the preliminary PWM adjustment signal, providing a more accurate and robust control effect.

[0121] The multi-dimensional input vector formed in step S41 is input into the pre-trained neural network model as input layer data.

[0122] Neural network structure: The neural network model includes an input layer, a hidden layer, and an output layer. The input layer receives a multi-dimensional input vector, the hidden layer has multiple layers, each layer has several neurons, and the ReLU activation function is used to process the input data. The output layer outputs the adjusted PWM adjustment signal.

[0123] The data is linearly transformed through the weight matrix and bias term in each layer of the neural network, and then nonlinearly processed through the activation function. The activation function is ReLU. By introducing nonlinearity, the model has stronger learning ability. After layer-by-layer processing of the neural network model, the output layer generates a new PWM adjustment signal. The output signal includes the adjusted duty cycle and frequency, which is used to more accurately control the output of the generator.

[0124] S5: Generate a final PWM control signal according to the adjusted preliminary PWM adjustment signal, and transmit the final PWM control signal to the generator system of the UAV for realizing synchronous rectification control.

[0125] Specifically, step S5 specifically includes the following steps:

[0126] S51: performing signal conversion and formatting processing on the duty cycle and frequency of the adjusted PWM adjustment signal to generate a final PWM control signal that meets the requirements of the generator system of the UAV.

[0127] PWM (Pulse Width Modulation) signals are a common way to control motor drives and other power electronic devices. By adjusting the duty cycle and frequency of the PWM signal, the speed and torque of the motor can be controlled. In this step, the adjusted and optimized PWM signal needs to be converted into the final control signal format suitable for the generator system.

[0128] Signal conversion:

[0129] Convert the duty cycle and frequency of the adjusted PWM signal to a signal format suitable for the generator system. This usually involves converting the digital signal to an analog or digital signal suitable for the motor drive.

[0130] For example, if the generator system uses digital signals, the digital PWM signal needs to be converted into a digital format that the motor driver can directly use.

[0131] Formatting:

[0132] Make sure the format of the PWM signal complies with the communication protocol and electrical characteristics of the generator system. For example, if the system uses a specific pulse width or frequency range, the signal needs to be adjusted accordingly.

[0133] Perform necessary signal conditioning, such as filtering and shaping, to ensure signal quality and reliability.

[0134] Signal compatibility check:

[0135] Confirm that the converted PWM signal is compatible with the interface of the generator system in terms of physical connection and electrical characteristics.

[0136] Test the integrity and correctness of the signal to ensure there is no signal distortion or interference.

[0137] S52: The generated final PWM control signal is transmitted to the starting generator system of the UAV, and when the starting generator system is in the generator mode, the output voltage and current waveforms are controlled using the received final PWM control signal to achieve synchronous rectification control with the UAV load.

[0138] In the UAV's starting and generating system, the final PWM control signal is used to adjust the output voltage and current waveform of the starting and generating generator to achieve effective matching with the UAV load. Through synchronous rectification control, the efficiency and stability of the system can be improved.

[0139] The final PWM control signal generated is transmitted to the control unit of the generator system through an appropriate communication interface to ensure the real-time and accuracy of signal transmission and avoid signal delay or loss.

[0140] After receiving the PWM control signal, the control unit of the generator system parses and processes it, and adjusts the output of the inverter or converter according to the duty cycle and frequency of the PWM signal to change the waveform of the output voltage and current.

[0141] The PWM signal is used to control the output of the generator system to match the UAV load and achieve synchronous rectification, that is, the output voltage and current waveforms are synchronized with the load requirements to ensure efficient and stable power transmission.

[0142] The working principle of a control method for synchronous rectification of a UAV generator provided by the present invention is as follows:

[0143] First, by integrating the multi-sensor data (including voltage, current, speed and temperature) of the UAV generator system, this method can accurately calculate and generate state parameters that reflect the current operating status of the system in real time. These state parameters provide a comprehensive and accurate information basis for subsequent control decisions, thereby significantly improving the stability and response speed of the system. During the flight of the UAV, facing complex and changing environmental conditions, this method can quickly adjust the PWM control signal to ensure the stability of the generator output voltage and current, and achieve precise synchronous rectification with the UAV load.

[0144] Secondly, the use of fuzzy control nodes and preset fuzzy rules to generate preliminary PWM adjustment signals not only simplifies the complexity of control logic, but also improves the accuracy and flexibility of control. Fuzzy control can handle the uncertainty and nonlinear factors in the system, generate appropriate PWM adjustment signals through fuzzy reasoning, and effectively respond to the changes of the UAV generator system under different working conditions. In addition, combined with the use of adaptive filters, the PWM adjustment signal is further smoothed, the signal fluctuation is reduced, and the stability and reliability of the control signal are improved.

[0145] Then, the preliminary PWM adjustment signal is further adjusted by introducing a pre-trained neural network model. This method can make full use of the powerful learning and generalization capabilities of the neural network to continuously optimize the PWM control signal to make it more in line with the actual operation requirements of the UAV generator system.

[0146] Finally, by real-time monitoring of the key parameters of the UAV generator system (such as voltage, current, speed, and temperature, etc.), potential safety hazards can be discovered and handled in a timely manner, effectively preventing system failures and accidents. At the same time, through fine PWM control, the stable regulation of the generator output voltage and current is achieved, avoiding damage to the UAV load and the entire system caused by voltage fluctuations or current overloads, which greatly improves the reliability and safety of the UAV generator system.

[0147] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0148] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0149] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

Claims

1. A control method for synchronous rectification of a UAV generator, applied to a UAV generator system, characterized in that: The control method comprises the following steps: Acquire multi-sensor data of a generator system of the UAV, and calculate and generate state parameters based on the multi-sensor data; Using pre-built fuzzy control nodes and preset fuzzy rules, and combining the multi-sensor data for reasoning, to generate a preliminary PWM adjustment signal; Using an adaptive filter to smooth the preliminary PWM adjustment signal; The smoothed preliminary PWM adjustment signal and the state parameter are used as inputs and transmitted to a pre-trained neural network model, and the preliminary PWM adjustment signal is adjusted by the pre-trained neural network model; A final PWM control signal is generated according to the adjusted preliminary PWM adjustment signal, and the final PWM control signal is transmitted to the generator system of the UAV for realizing synchronous rectification control.

2. A control method for synchronous rectification of a UAV generator according to claim 1, characterized in that: The multi-sensor data includes voltage sensor data, current sensor data, rotation speed sensor data and temperature sensor data of the generator system of the drone.

3. A control method for synchronous rectification of a UAV generator according to claim 2, characterized in that: The calculating and generating of the state parameters comprises: Calculating the real-time output power of the generator system of the drone based on the voltage sensor data and the current sensor data; Determine the current speed of the generator system using the speed sensor data; Monitoring the temperature status of the generator system through temperature sensor data; The real-time output power, current speed and temperature status are integrated to generate status parameters reflecting the current operating status of the generator system.

4. A control method for synchronous rectification of a UAV generator according to claim 3, characterized in that: The method of utilizing the pre-built fuzzy control nodes and the preset fuzzy rules and combining the multi-sensor data for reasoning to generate a preliminary PWM adjustment signal includes: Define multiple fuzzy sets, each fuzzy set corresponds to a single control dimension of the UAV generator system, and set a corresponding membership function for each fuzzy set, wherein the control dimension includes real-time output power, current speed and temperature state; The real-time output power, current speed and temperature state acquired in real time are mapped to the corresponding fuzzy sets, and the membership function set for each fuzzy set is used to calculate the membership of each sensor data in the corresponding fuzzy set; Using a preset fuzzy rule base, fuzzy reasoning is performed according to the membership degree of each fuzzy set, wherein the fuzzy rule base contains a plurality of rules for describing the changing law of the PWM adjustment signal under different states; According to the result of the fuzzy reasoning, the duty cycle and frequency of the preliminary PWM adjustment signal are calculated.

5. A control method for synchronous rectification of a UAV generator according to claim 4, characterized in that: The step of smoothing the preliminary PWM adjustment signal by using an adaptive filter comprises: The preliminary PWM adjustment signal is input as an input signal into the adaptive filter, and the adaptive filter dynamically adjusts the parameters of the adaptive filter according to a preset filtering algorithm and the current input signal, and finally outputs a smooth PWM adjustment signal.

6. A control method for synchronous rectification of a UAV generator according to claim 5, characterized in that: The process of taking the smoothed preliminary PWM adjustment signal and the state parameter as input and transmitting them to the pre-trained neural network model for signal adjustment includes: The preliminary PWM adjustment signal after smoothing by the adaptive filter is integrated with the state parameter to form a multi-dimensional input vector; The multidimensional input vector is used as input layer data and transmitted to a pre-trained neural network model. After being processed layer by layer by the neural network model, an adjusted PWM adjustment signal is output, wherein the neural network model has been trained based on historical data and expert knowledge.

7. A control method for synchronous rectification of a UAV generator according to claim 6, characterized in that: The method of generating a final PWM control signal according to the adjusted preliminary PWM adjustment signal and transmitting the final PWM control signal to the generator system of the UAV includes: Performing signal conversion and formatting processing on the duty cycle and frequency of the adjusted PWM adjustment signal to generate a final PWM control signal that meets the requirements of the generator system of the UAV; The generated final PWM control signal is transmitted to the UAV's starting generator system, and when the starting generator system is in generator mode, the received final PWM control signal is used to control the output voltage and current waveforms to achieve synchronous rectification control with the UAV load.

Images