239 results about "Gain parameter" patented technology

The invention belongs to the technical field of ship path tracking, and discloses a ship path tracking method based on adaptive line-of-sight guidance and fuzzy adaptive PID, and the method comprises the steps: presetting a path point, and obtaining a real-time coordinate; obtaining an actual expected heading angle # imgabs0 # and a ship observation heading angle # imgabs1 #, subtracting the actual expected heading angle # imgabs0 # and the ship observation heading angle # imgabs1 # to obtain a heading deviation # imgabs2 #, and calculating a heading deviation rate # imgabs3 #; the course deviation and the course deviation rate are input into a fuzzy self-adaptive PID motion control module, and gain parameters are output through a fuzzy control algorithm; the gain parameter and # imgabs4 # are input into a PID controller to calculate a ship rudder angle # imgabs5 #; inputting # imgabs6 # into the motion mathematical model to update the motion state, and forming a closed-loop updated motion state to enable the ship to approach a preset path point; and judging a ship path after the state information is updated. The expected course of the ship is calculated in real time and the sideslip angle of the ship and the control parameters of the ship are adjusted in real time through self-adaptive sight guidance, and the control parameters are automatically adjusted in real time by means of the fuzzy self-adaptive PID motion control module to achieve accurate motion control, so that the ship travels according to a preset planned path.

The invention provides an unmanned aerial vehicle motor rotating speed control method based on active disturbance rejection. The method comprises the following steps: 1) measuring the rotating speed of a motor by adopting a high-precision rotating speed sensor based on a quantum effect; 2) designing a tracking differentiator TD to smooth an expected rotating speed, and outputting a rotating speed tracking signal and a rotating speed tracking signal change rate; 3) introducing a dynamic weight matrix to form a dynamic weight expansion state observer DWESO, and taking an output state variable estimation value and a total disturbance estimation value as the input of the NLSEF; 4) automatically searching the optimal combination of the gain parameters of the DWESO by adopting an ALA (artificial Louver Mouse Algorithm), so that the optimal state variable estimation value and the optimal total disturbance estimation value are output to the NLSEF; compared with the prior art, the method for controlling the rotating speed of the unmanned aerial vehicle has the advantages that the dynamic response speed, the anti-jamming capability and the parameter adaptability of the system are remarkably improved, and the flight performance and the robustness of the unmanned aerial vehicle are improved.

The invention discloses a control method for adjusting the tunneling attitude of a shield tunneling machine, particularly relates to the field of attitude control of the shield tunneling machine, and aims to solve the problem that attitude deviation caused by underground environment change cannot be timely and effectively corrected in the tunneling process of the shield tunneling machine. The method comprises the following steps of: calculating membership degrees of horizontal deviation, vertical deviation and change rates of the horizontal deviation and the vertical deviation, extracting high-frequency and low-frequency characteristics, generating independent phase signals, and calculating a judgment coefficient by using a multi-dimensional data fusion and high-dimensional exponential integration method so as to dynamically adjust the weight of a fuzzy control rule base and realize adaptive optimization of PID (Proportion Integration Differentiation) gain parameters; a master control output signal is generated based on the updated PID parameters, the thrust of the partition oil cylinders is accurately adjusted, it is ensured that the posture of the shield tunneling machine is rapidly, accurately and stably adjusted under the complex environment condition, the control precision of the tunneling direction and the construction safety are improved, and the working efficiency is improved. And meanwhile, the overall posture correction capability of the shield tunneling machine is further enhanced through dynamic adjustment of the rolling angle.

The invention provides an intelligent control method and system based on electro-hydraulic linkage. The method comprises the steps that multi-mode environment parameters are collected, a digital twin environment model is constructed, and data are synchronized with an electro-hydraulic servo system in real time. And establishing a nonlinear model, identifying parameters by using a least square method and a recursive least square method, verifying the precision through a step response test, and updating. And constructing an adaptive LSTM neural network inverse model to output a control voltage signal. And the signal is subjected to weighted fusion with the output of a PID controller, and the PID controller dynamically adjusts a gain parameter according to an error integral term to generate a control instruction to drive the system. According to the invention, the LSTM inverse model provides feed-forward compensation, the PID controller realizes feedback correction, and the LSTM inverse model and the PID controller are complementary. Meanwhile, based on a related nonlinear model and a parameter self-adaptive updating mechanism, the influence of working condition change is accurately described, and high-precision control of the electro-hydraulic servo system under the complex working condition is achieved.

The invention discloses a control method applied to self-piercing riveting, and relates to the technical field of self-piercing riveting control. According to the method, riveting material data are collected in real time through a multi-source data fusion interface, the high-dynamic deformation process of a riveting head is captured, deformation rate and rebound value characteristic values are extracted, and a multi-dimensional process parameter set is constructed. And comprehensively analyzing the hardness, thickness and plastic dissipation characteristics of the material, and establishing an anti-deformation capability evaluation function. By introducing the fluctuation characteristics of the punching force, the nonlinear relation between the punching force and the elastic deformation of the riveting rod is analyzed, a hybrid compensation model is constructed, and a riveting dynamic coupling compensation vector is output. And generating a compensation weight matrix through an adaptive optimization algorithm, and dynamically adjusting the stamping force and the displacement of the riveting rod in combination with an anti-saturation control strategy. And dynamically adjusting a gain parameter through multi-scale filtering and a Lyapunov stability criterion, and triggering iterative updating of a compensation weight parameter during out-of-tolerance so as to optimize a control effect. Riveting precision and stability are improved, and the service life of equipment is prolonged.

The invention belongs to the technical field of phase control cabinet phase regulation and control, and particularly relates to a phase control cabinet regulation and control system and method based on multistage phase compensation. According to the method, the voltage waveform and the current waveform output by the phase control cabinet are preliminarily compensated so as to reduce the initial phase deviation, environmental parameters are matched with a pre-stored interference feature library, the type of an interference source can be identified, and the interference source is quantified as a thermal noise contribution value to calculate an interference intensity prediction value in a prediction window, so that the prediction accuracy is improved. And then providing data support for secondary compensation through a phase residual error output by an interference intensity predicted value, determining a compensation gain parameter according to a dynamic error coefficient during secondary compensation, performing secondary compensation on a voltage waveform and a current waveform to enable a phase deviation to be converged to a preset range, and according to the phase convergence information after secondary compensation, determining the interference intensity predicted value according to the phase convergence information after secondary compensation. And the sampling frequency and the compensation weight factor of the sensor array are reversely adjusted to form a closed-loop compensation control link, so that continuous optimization and improvement of the compensation process are realized.

The invention relates to the technical field of flight control, in particular to a hybrid control FPV unmanned aerial vehicle flight control system and method. The method comprises the following steps: acquiring triaxial angular velocity data of the unmanned aerial vehicle in real time by using an inertial navigation system, eliminating high-frequency noise and performing zero offset calibration; constructing a corresponding linear extended state observer to adjust a gain parameter in real time based on an absolute value of an observation error, and filtering tiny noise disturbance through a dead zone function to realize high-precision estimation of the system state and total disturbance of the unmanned aerial vehicle so as to obtain an error and an error change rate; and designing a self-adaptive PID control law to dynamically adjust PID control quantities corresponding to proportion, integral and differential gains, carrying out dynamic weighted stacking according to a flight mode, generating a three-axis control quantity, carrying out flight control on the FPV unmanned aerial vehicle, and meanwhile, realizing real-time visual verification of a control effect corresponding to the flight control. According to the invention, high-precision and high-robustness attitude control can be realized.

The invention relates to the technical field of high-precision positioning, and discloses a linear module high-precision positioning control method and system, and the method comprises the steps: carrying out the feature point extraction and feature point tracking of a motion image sequence of a linear module, and obtaining displacement measurement data and vibration feature data; performing nonlinear compensation on a linear module according to the displacement measurement data and the vibration characteristic data, and constructing a standard linear state equation; performing sliding mode surface design and gain parameter calculation based on the standard linear state equation to obtain an initial sliding mode controller parameter; track interpolation and motion feedback are carried out on the linear module according to the initial sliding mode controller parameters, and real-time position deviation data are obtained; the initial sliding mode controller parameters are iteratively optimized based on the real-time position deviation data, and target sliding mode controller parameters are obtained.According to the method, impact in the acceleration and deceleration process is reduced, system vibration is effectively reduced, and the positioning precision is improved.

The invention relates to the field of machining and automatic control, in particular to a pressure-sensing precision mechanical part polishing brush system and method. Comprising the following steps: converting and processing pressure data to obtain processed pressure data; calculating the difference between the current pressure and the target pressure based on the processed pressure data, and mapping the target pressure into the path track; optimizing the path through the path optimization objective function and the constraint condition to obtain an optimized path; based on the optimized path, obtaining a torque variation; a path adjustment amount is obtained through the torque variation; and correcting the optimized path through the gain parameter and the path adjustment amount to obtain a corrected path. The problems that the relation between the motion trail of the brush and the contact pressure is not accurately processed, and the motion trail of the brush is difficult to accurately control are solved.

The invention discloses an open-phase self-fault-tolerant control method for a phase-shift-free dual three-phase permanent magnet synchronous motor. The method can automatically adjust a current distribution relation in the case of an open-phase fault and suppress torque pulsation in combination with neutral point voltage compensation. Comprising the following steps: driving two pairs of three-phase winding modules of the phase-shift-free DTP-PMSM in parallel by adopting two two-level three-phase voltage source inverters, and providing a mathematical model of the motor; current distribution is automatically adjusted; compensating the voltage of the neutral point, and calculating the offset of the fault module; the current is redistributed to suppress the torque ripple after the fault, and the secondary oblique wave component generated by the phase failure fault is eliminated; a current loop controller is improved through dead-beat predictive control; the speed ring controller is optimally designed into an improved sliding mode controller; an improved double-loop controller system is formed by combining improved sliding mode control and dead-beat prediction control, high-gain parameters are set to improve the dynamic response performance of the system, and a new self-fault-tolerant control system is formed.

The invention discloses a wind power generation system control method and system based on an improved recurrent neural network (RNN), and belongs to the field of wind power generation system control. The method comprises the following steps: training an improved RNN model by adopting a training data set, and carrying out forward propagation on an input vector to obtain gain data; quantizing a loss value between the gain parameter and an ideal gain parameter, constructing a loss function according to the loss value, obtaining a weight gradient of each layer by using a gradient back propagation algorithm, updating a network weight according to the weight gradient and in combination with a momentum gradient descent algorithm, applying amplitude constraint to a recursive weight, and performing iterative training to obtain an ideal gain parameter. A trained RNN network model is obtained; obtaining a gain parameter of the wind power generation system according to the trained RNN network model, and controlling the operation state of the wind power generation system according to the gain parameter; according to the method, PI controller self-adaption is achieved by introducing the recurrent neural network, the system response time, static errors and overshoot can be remarkably reduced, and therefore the system performance is improved.

The invention discloses a primary frequency modulation optimization control method and system based on adaptive gain adjustment, and the method comprises the steps: obtaining and preprocessing the operation state parameters of a power grid and the historical data of the frequency of the power grid, and constructing a power grid frequency stability classification model; power grid operation parameters are obtained in real time and normalized, and a power grid operation state classification result is obtained according to normalized data; preliminarily judging the stability based on the power grid operation parameters and the classification model, and if not, calculating a power grid frequency stability index and judging whether the power grid frequency stability index is lower than a threshold value; and a self-adaptive gain adjustment model is constructed, if the power grid operation state classification result does not meet the requirement or is lower than a threshold value, the optimal gain parameter of primary frequency modulation control is obtained based on the power grid frequency stability index and the self-adaptive gain adjustment model, and optimization control is realized according to the optimal gain parameter. Accurate adaptive control of the power grid frequency is realized, and a powerful guarantee is provided for safe and stable operation of a power system.

The invention relates to the field of data processing, in particular to a rapid temperature change test box temperature control method and system, and the method comprises the steps: collecting the internal temperature and external temperature of a test box in real time; calculating the internal and external temperature change consistency of the local time period at the current moment; calculating a correction value of the internal temperature at the current moment by using the internal and external temperature change consistency; and presetting a gain parameter vector, calculating an adjustment value of the gain parameter vector at the current moment, inputting the adjustment value of the gain parameter vector at the current moment and an error between the correction value of the corresponding internal temperature and the target temperature in the test box into a PID controller, outputting a control signal, and performing temperature control on the test box according to the control signal. According to the invention, by adaptively adjusting the gain parameter, the overshoot caused by too fast system response speed and the oscillation phenomenon caused by the overshoot can be effectively avoided, so that the temperature change in the test box is more stable, and the stability of the temperature control process is ensured.

The invention relates to the technical field of vehicles, in particular to a vehicle driving warning sound generation method and device, equipment and a storage medium. Environment bottom noise data is obtained through real-time collection and analysis, and a frequency band possibly generating a masking effect on the generated warning sound is judged according to the data; in particular, the system recognizes the frequency bands influenced by the masking effect according to the spectral characteristics of the environmental noise, and increases the volume of the frequency bands in a targeted manner to ensure that the warning sound can be effectively transmitted to pedestrians, and in addition, the system also can give the warning sound to the pedestrians according to the actual driving scene of the vehicle. According to the method, the most appropriate warning sound frequency band and gain parameters can be intelligently selected to adapt to different acoustic environments, such as an underground garage or an open parking lot, so that the pedestrian warning effect when the electric vehicle runs at a low speed is remarkably improved.

The invention discloses an IMU attitude calculation method, device and equipment and a storage medium, and the method comprises the steps: obtaining IMU original data which comprises a three-axis acceleration measurement value and a three-axis angular velocity measurement value; dynamically updating gain parameters of a Mahony complementary filtering algorithm based on the three-axis acceleration measurement value, the gain parameters including a proportional gain parameter and an integral gain parameter; based on the gain parameter, correcting the triaxial angular velocity measurement value to obtain a target triaxial angular velocity value; and calculating body attitude information based on the three-axis acceleration measurement value and the target three-axis angular velocity value. Compared with a traditional Mahony algorithm adopting fixed gain parameters, the method can reduce error fluctuation of the airframe under rapid movement and improve the accuracy of attitude calculation.

A hybrid controller and method for mitigating frequency disturbances in a multi-area power plant including multiple thermal energy generators and renewable energy sources includes a cascaded fractional model predictive controller (CFMPC), first and second fractional-order proportional-integral-derivative controllers (FOPID-1 and FOPID-2) and a sooty terns controller. The CFMPC generates a minimized area central error (ACE) signal based on minimizing a controlled fitness equation, an ACE signal and a load power disturbance signal (ΔPL). The FOPID-1 generates a frequency disturbance correction signal based on the frequency disturbance value (Δfi). A combined frequency correction signal is generated by adding negative values of the minimized ACE signal and the frequency disturbance correction signal. The FOPID-2 receives the combined frequency correction signal and generates a frequency error correction signal. The sooty terns controller generates optimized gain parameters and transmits the optimized parameters to the FOPID-1 and the FOPID-2 to mitigate the frequency disturbances.

The invention discloses a double-feedback control debugging method of an ultra-precision servo system, and relates to the technical field of semiconductor manufacturing equipment. In order to solve the defects that in the prior art, coupling interference is serious in the debugging process, frequency domain performance optimization is insufficient, filter configuration does not have adaptivity, and an efficient anti-interference debugging mechanism under multi-source disturbance is lacked, the technical scheme provided by the invention comprises the steps that a double-feedback servo system comprising a speed ring and a position ring is constructed; debugging a speed feedback loop, optimizing controller gain parameters based on frequency domain analysis, and outputting speed loop response characteristics; a position feedback loop is debugged, and position loop controller parameters are configured in combination with speed loop response and acceleration sensor signals; the notch filter is automatically adjusted according to the dynamic vibration characteristics; and frequency domain self-adaptive debugging of the double-feedback controller is completed. The method is suitable for servo control debugging work of high-precision motion systems such as a wafer carrying table in semiconductor manufacturing equipment, and is especially suitable for nanoscale positioning scenes such as a photoetching machine and measuring equipment.

The invention discloses a gain adjustment method, electronic equipment and a readable storage medium, and the method comprises the steps: obtaining a feedback signal of a motor under a preset control signal when a motor control system is in a speed open-loop mode; determining speed loop delay time of the motor control system in a speed closed-loop mode based on the feedback signal; a first speed loop gain parameter is determined using the speed loop delay time. According to the method, the repeated manual trial and error process can be avoided, the time required for parameter adjustment is remarkably shortened, and the speed loop gain parameter setting is quicker and more accurate, so that the method is suitable for more application scenes.

The invention discloses a periodic torque disturbance suppression method of a permanent magnet synchronous motor, and belongs to the field of permanent magnet synchronous motors. In order to solve the problem that a low-frequency periodic load is introduced due to the fact that a motor continuously drives a complex mechanical structure to move periodically and repeatedly, a novel rotating speed controller is designed, and a four-order expansion state observer is introduced into a permanent magnet synchronous motor control system considering disturbance. A bandwidth tuning method is adopted to set observer gain parameters to achieve observation of torque disturbance, a frequency analysis method is adopted to optimize and design an observer gain matrix, an optimized four-order extended state observer is obtained, and torque disturbance compensation is achieved in the mode that estimated torque is converted into feed-forward current. According to the method, the influence of torque disturbance on the rotating speed stability is effectively suppressed, and the anti-interference performance and the anti-noise performance of the four-order extended state observer are synchronously improved.

The invention provides a signal gain self-adaptive control method based on dynamic feedback, which relates to the technical field of self-adaptive control, and comprises the following steps: carrying out initial gain control on an input signal to obtain a system output signal; the feedback quantity of the system output signal is collected, and the filtered actual output signal is obtained through filtering processing; based on the expected output signal and the actual output signal, calculating multi-order errors, including an amplitude error, a first-order derivative error and a second-order derivative error; calculating a collaborative weighting function according to the multi-order error; constructing a comprehensive error cost function based on the multi-order error and the collaborative weighting function; according to gradient information of the comprehensive error cost function and a product term of a second derivative error and a collaborative weighting function, updating a gain parameter by adopting a dynamic step length; and performing gain control on the input signal by using the updated gain parameter to obtain a new system output signal. According to the invention, dynamic self-adaptive adjustment of signal gain parameters can be realized, so that the response capability of the system to rapid dynamic change is improved.

The invention discloses a method and equipment for controlling the virtual precession rotating speed of a micro-hemisphere gyroscope in a full-angle mode and a medium. The method comprises the following steps: enabling the micro-hemisphere gyroscope to be in the full-angle mode through three loops of amplitude, orthogonality and frequency tracking; applying a control force in the angle control equation to force the standing wave to self-rotate at a corresponding virtual angular velocity; in a standing wave precession state, identifying a total loop gain parameter in real time by using an adaptive identification technology; and the excitation voltage is multiplied by an external given excitation voltage to obtain a compensated excitation voltage, so that on-line compensation of the standing wave virtual procession is realized, and the accuracy and stability of the rotating speed of the virtual procession are improved.

The invention discloses an aviation electric fuel pump design method based on structure optimization and intelligent control, belongs to the field of intelligent optimization design and control, and aims to optimize the structure of a gear pump, simplify the bearing design and neglect a diffusion area and an unloading groove, so that the gear pump better meets the quality requirement in practical application, and the gear pump design method is suitable for large-scale popularization and application. And a sparrow search algorithm is used for optimizing structural parameters, so that the quality and efficiency of the gear pump are improved. The spline is additionally arranged between the motor end and the gear pump end of the gear shaft, rotation isolation of the two ends is achieved, and the problem that the electric fuel pump is stuck in the to-be-loaded starting stage is effectively solved. By redesigning the shell and comprehensively considering the problems of weight, leakage, torque and the like, the overall design of the electric fuel pump is optimized. By adopting a super-spiral direct torque control method, rapid torque response and accurate flow control of the electric fuel pump are realized. According to the method, the gain parameters of the controller are optimized through the sparrow search algorithm, and the control precision and the steady-state performance of the system are improved.

The invention discloses a robot joint dynamic precision control method. The method comprises the following steps that the interaction torque, the angle and the angular speed of a robot joint are obtained; based on the interaction torque, the angle and the angular velocity of the robot joint, a robot joint dynamic model containing friction and external disturbance is constructed; designing a super-spiral sliding mode control law based on the robot joint kinetic model; optimizing a sliding mode gain parameter in the super-spiral sliding mode control law based on a PPO algorithm to obtain an optimized super-spiral sliding mode control law; and controlling the dynamic precision of the robot joint based on the optimized super-spiral sliding mode control law. According to the method, the MEMS torque sensor and deep reinforcement learning are combined, and a new effective method is provided for robot joint dynamic precision control.

The invention belongs to the technical field of aircraft wind tunnel virtual free flight tests, and particularly relates to an aircraft wind tunnel virtual free flight lateral course stability augmentation control system design method and system.The aircraft wind tunnel virtual free flight lateral course stability augmentation control system design method comprises the steps that 1, a scale model lateral course linearization dynamics mathematical model is established; step 2, calculating a scaling coefficient of the scaling model; 3, determining the design requirement of the transverse flight quality of the scaling model; step 4, establishing a scale model transverse course stability augmentation control law; 5, establishing a scaling model closed-loop control system; step 6, optimizing control law gain parameters in a scaling model closed-loop control system; and 7, verifying the scale model closed-loop control system.

The invention relates to a Markov jump network system control method under DoS attack based on a phototropic growth algorithm. The method comprises the following steps: establishing a networked system model with Markov jump parameters; an energy-limited DoS attack model is constructed; introducing a dynamic event triggering mechanism, and determining a triggering moment based on a measurement error, a weighting coefficient, a design parameter and an internal dynamic variable; based on a networked system model and an energy-limited DoS attack model, a dynamic event triggering mechanism is fused to construct a closed-loop system dynamic model; establishing a hybrid anti-interference performance index; performing global optimization on gain parameters of the closed-loop system dynamic model by adopting a phototropic growth algorithm to obtain an optimal controller gain; and constructing a controller under the energy-limited DoS attack, and realizing the control of the Markov jump network system under the DoS attack. The finally constructed controller can realize high robustness, low communication burden and excellent dynamic performance control of the Markov hopping network system in an energy limited DoS attack scene.

The invention provides an attitude control system for a short-wave satellite, and relates to the technical field of data processing, and the attitude control system comprises the steps: inputting a three-axis synthesis control torque instruction into a reaction flywheel controller, converting the instruction into a flywheel motor rotating speed adjustment instruction, and driving a reaction flywheel to execute; adjusting and analyzing the continuously updated attitude deviation angle based on the actual attitude change after the execution of the driving reaction flywheel, obtaining the updated gain parameter of the sliding mode controller, and feeding back the parameter of the updated sliding mode controller; performing control based on the updated parameters of the sliding mode controller, performing direction consistency verification on a newly output sun direction vector measurement value, and verifying an actual included angle; if the actual included angle is smaller than the preset precision threshold value, a new round of data acquisition cycle is triggered, and closed-loop control is achieved. According to the invention, the timeliness and effectiveness of attitude control are ensured, and the control efficiency and reliability are improved.

The invention discloses a reinforcement learning-based PID (Proportion Integration Differentiation) control method for a hydraulic mechanical arm, which belongs to the technical field of heavy-load hydraulic mechanical arm control and comprises the following steps of: S1, acquiring hydraulic cylinder displacement data of the hydraulic mechanical arm in an experiment process by utilizing a displacement sensor; s2, designing a PID-like controller based on the obtained hydraulic cylinder displacement signal and the hydraulic cylinder instruction displacement signal; s3, automatically adjusting a time-varying gain by using an evaluation neural network-execution neural network architecture, and correcting a gain parameter of the PID controller in real time to obtain an optimal gain parameter of the PID controller; and S4, realizing high-precision tracking control of the hydraulic cylinder based on the optimal control parameters of the PID controller. The method is used for compensating for strong nonlinearity, unknown disturbance, multi-joint coupling and the like existing in mechanical and hydraulic systems, the tracking precision of a hydraulic mechanical arm system is improved, the complex and time-consuming manual parameter adjusting process in traditional PID control is avoided, the structure is simple, and meanwhile the strong self-adaption and learning capacity is achieved.

The invention discloses a self-adaptive fuzzy PID flow field control method and device, and the method comprises the steps: generating an initial PID gain parameter in real time through a fuzzy reasoning module, introducing an RBF neural network module to carry out the dynamic optimization compensation of the initial parameter, and generating a correction gain. And a final PID parameter is dynamically synthesized by adopting a weighted fusion formula, and a weight coefficient is adjustable so as to balance the contribution of fuzzy rules and neural network learning. The nonlinear approximation capability of the RBF network is utilized, network parameters are updated in real time through a gradient descent method, a Jacobian matrix of a controlled system is output, and the sensitivity of the control quantity to input changes is accurately recognized. The parameter updating rate is dynamically adjusted through a momentum item and an exponential decay function in combination with environmental sensor data, flow feedback and historical deviation, and a closed-loop control loop of monitoring, fuzzy reasoning, RBF optimization, PID output and feedback is formed. The accuracy of flow field control is improved.

The invention relates to the technical field of resonance suppression, in particular to a direct-drive fan grid-connected inverter high-frequency resonance dynamic suppression method and system, and the method comprises the steps: obtaining a preliminary damping value according to extracted high-frequency resonance natural frequency oscillation distribution data; based on the initial damping value and a power grid voltage fluctuation influence factor, performing dynamic compensation adjustment on the active resonance suppression time delay factor to obtain a high-frequency resonance characteristic value; calculating a frequency drift offset according to the high-frequency resonance characteristic value and a bandwidth upper limit value of a grid-connected inverter controller; and when the frequency drift offset exceeds a preset drift threshold range, optimizing the active damping gain parameter by taking minimization of a resonance peak value and maximization of a dynamic response margin as optimization targets, outputting a high-frequency resonance active suppression parameter optimization set, and completing high-frequency resonance active suppression of the direct-drive fan grid-connected inverter system. By optimizing the active damping gain parameters, high-frequency resonance of the direct-drive fan grid-connected inverter system is effectively suppressed, and stable operation of the system is guaranteed.

The invention relates to a full-link differentiable physical enhancement type automatic driving control method and a full-link differentiable physical enhancement type automatic driving control system. The method comprises the following steps: constructing a full-link differentiable PERL dynamical model to reconstruct real vehicle dynamics in a high-fidelity manner; establishing a micro-preview PID execution layer, calculating a transverse error and a longitudinal speed error based on a dynamic preview distance, and generating a steering wheel angle instruction and an automobile longitudinal acceleration instruction by using a PID control law supporting gradient return; and the PID gain parameter and the preview distance are adaptively adjusted in real time by using the SAC network according to the current vehicle state. According to the full-link micro closed-loop training architecture designed by the invention, end-to-end optimization of control parameters is directly guided by utilizing gradient information of dynamic residual errors, the problem of distortion of a Sim2Real model is effectively solved, the physical interpretability and smoothness of a control strategy are ensured, and meanwhile, the optimal optimization of the control parameters is realized. The trained strategy network significantly improves the path tracking precision and robustness of the vehicle under a complex working condition.