438 results about "Linear system" patented technology

The invention discloses a GNSS (Global Navigation Satellite System) / INS (Inertial Navigation Satellite System) anti-deception navigation method based on ESKF (Enhanced Shift Keying Function) and dynamic window detection, which comprises the following steps of: 1, acquiring observation data of an INS and a GNSS, performing time synchronization and coordinate system unification on the observation data of the INS and the GNSS, and respectively eliminating a time error and a coordinate difference; 2, a dynamic window detection mechanism is designed, an error state dynamical model is constructed, the dynamic window detection mechanism is used for detecting whether GNSS cheating exists or not, and meanwhile the error state dynamical model can output stable navigation parameters; and 3, outputting a final high-precision navigation result according to the stable navigation parameters. According to the method, the problems of error accumulation and covariance distortion of nonlinear system model linearization are effectively solved, pollution of GNSS deception signals can be effectively inhibited, high-precision positioning and anti-deception capability are kept in complex environments (such as urban shielding and electromagnetic interference), and a navigation system with high precision and high reliability is formed.

A hybrid quantum-classical (HQC) computer system, which includes a classical computer and a quantum computer, solves linear systems. The HQC computer system splits the linear system to be solved into subsystems that are small enough to be solved by the quantum computer, under control of the classical computer. The classical computer synthesizes the outputs of the quantum computer to generate the complete solution to the linear system.

The invention relates to the technical field of geophysical exploration, and particularly provides a three-dimensional finite element transient electromagnetic forward modeling calculation method based on an iterative solution method.The method comprises the steps that tetrahedron space discretization is carried out based on a vector finite element method, and an electric field is given to six edges of a space tetrahedron; constructing a back-pushing Euler finite element equation set, and assembling a linear system formed by a large sparse matrix based on the equation set; performing iterative solution on the linear system based on an FGMRES algorithm to obtain an electric field value corresponding to a spatial tetrahedron unit edge; optimizing a spatial tetrahedral mesh based on a quadratic nesting method, and optimizing a time step length based on a third-order backward Euler difference format; a grid pre-encryption method is adopted, the calculation error of iterative solution is reduced, a region decomposition method is used for achieving parallel calculation, and the calculation efficiency is greatly improved. According to the method, the requirements of high precision and high efficiency in three-dimensional transient electromagnetic forward modeling calculation can be met, and an advanced calculation tool is provided for resource exploration in a complex geological environment.

The invention provides a train operation state estimation method and system based on a high-order extended Kalman filter considering noise correlation, and belongs to the technical field of rail transit train operation management. According to the method, correlation analysis between high-order terms is introduced, the filtering precision is remarkably improved, and particularly, excellent performance is shown under a strong nonlinear system; by establishing a multi-mode train state model, the dynamic characteristics of a train in operation modes such as traction, cruising, sliding and braking are comprehensively covered, and a more accurate input basis is provided for a filtering algorithm; by introducing a sliding window error criterion, the filter can quickly switch operation modes according to real-time errors, so that the filter is ensured to keep high adaptability in a complex and changeable operation environment; the comprehensive performance evaluation framework based on the error covariance matrix not only evaluates the mean square error and the mean absolute error, but also quantifies the contribution of the high-order correlation to the precision of the filter, and provides a more scientific and comprehensive evaluation system.

The invention relates to the field of heat supply network analogue simulation, and particularly discloses a regional heat supply network dynamic simulation method and system, a terminal and a medium, the method comprises the following steps: constructing a hydraulic model semi-analytical expression and a thermal model semi-analytical expression of a pipeline in a regional heat supply network, and according to the pipeline momentum conservation and the node mass conservation, calculating the thermal model semi-analytical expression of the pipeline in the regional heat supply network; constructing semi-analytic coefficient recursive relation linear equations, and respectively calculating semi-analytic coefficients of a hydraulic model semi-analytic expression and a thermal model semi-analytic expression through the two semi-analytic coefficient recursive relation linear equations according to initial conditions and boundary conditions of the pipe section; the calculated semi-analytic coefficient meets the condition that the truncation error is not greater than a truncation error threshold value; and substituting the semi-analytic coefficient into the semi-analytic expression to obtain a semi-analytic calculation result of each pipe section of each pipeline under all time steps. According to the method, non-iterative calculation of the PDAEs is realized, the calculation complexity is reduced, the simulation efficiency is improved, and the solution continuity can be ensured.

The invention provides an efficient privacy set intersection method and device based on bucket coding, and the method comprises the steps: obtaining an input set and a target value set, the input set comprises a private set of a sender and a private set of a receiver, and the target value set is generated based on the private set of the receiver; encoding the private set of the receiver into a sparse matrix composed of a plurality of buckets through a hash function; determining a linear system of the sparse matrix; performing ascending sorting and re-labeling on the linear system according to the initial bit position set to obtain a target linear system; according to a bucket-based Gaussian elimination algorithm, based on a target linear system, through exclusive-or operation, determining oblivious key value pairs for storage; an intersection of the private set of the sender and the private set of the receiver is determined based on the oblivious key-value pair storage according to an oblivious linear evaluation protocol. According to the invention, communication resources required by privacy set intersection in an actual production environment can be further reduced.

The invention relates to the technical field of mechanical transmission, in particular to a reinforcement learning compensation method and system for gear multi-body dynamics constraint, and the method comprises the steps: building a multi-body dynamics digital twinborn model containing bearing rigidity and gear meshing force; constructing an adaptive reward function based on nonlinear manifold mapping, and dividing a system state space into a small deviation domain and a large deviation domain according to an angle deviation threshold value; training the multi-body dynamic model based on a depth deterministic strategy gradient algorithm to obtain a compensation strategy; the obtained compensation strategy is applied to a multi-body dynamic model, and an optimal compensation signal is obtained through self-adaptive fusion of static compensation and dynamic compensation, so that the training efficiency of a reinforcement learning algorithm in a complex nonlinear system is improved, the adaptability of the system to working condition changes is enhanced, the vibration of a gear system is remarkably reduced, and the reliability of the system is improved. The angle control precision is improved, and the service life of equipment is prolonged.

The invention discloses a novel model-free super-spiral sliding mode control method based on a sliding mode disturbance observer, and the method comprises the steps: designing a novel model-free super-spiral sliding mode controller of a rotating speed ring based on the combination of a novel super-local model and a second-order super-spiral law; meanwhile, a sliding mode disturbance observer is designed to estimate uncertain and unknown disturbance parts of system parameters in real time and feed back to a novel model-free super-spiral sliding mode controller of a rotating speed ring, so that the rotating speed of the motor is controlled; the controller introduces a linear system state item and a nonlinear disturbance item according to the novel super-local model, establishes a novel super-local model of the system, combines the novel super-local model of the system with a rotating speed ring state equation of the motor, establishes a novel super-local model of a rotating speed ring, and performs the super-local model of the rotating speed ring; and establishing a novel model-free super-spiral sliding mode control law of the rotating speed ring based on the novel super-local model of the rotating speed ring and an observation result of the sliding mode disturbance observer. The influence of external disturbance on the motor is effectively solved, buffeting is weakened, and effective tracking of the given rotating speed can be achieved.

The invention relates to the technical field of inverter control, and discloses a micro inverter control method and system in a photovoltaic system and a storage medium. The method comprises the following steps: carrying out parameter acquisition and processing on the photovoltaic micro inverter to obtain an initial parameter set; designing a radial basis function neural network compensation uncertainty parameter based on the initial parameter set; inputting the compensation parameter set into a particle swarm optimization algorithm to optimize control parameters; and training a back propagation neural network based on the optimized parameter set to realize maximum power point tracking control. According to the method, the uncertainty of the system is compensated by introducing the radial basis function neural network, the control parameters are optimized in combination with the particle swarm optimization algorithm, and the real-time prediction and adjustment of the parameters are realized by using the back propagation neural network; the technical problems that a traditional control method is low in control precision and poor in adaptability when facing nonlinear system characteristics, environmental condition changes and parameter uncertainty are effectively solved.

The invention relates to the technical field of CPU card chips, and discloses a self-adaptive power consumption control method and system of a CPU card chip. The method comprises the following steps: collecting power consumption characteristic data of a CPU card chip in different working load states, and constructing a power consumption signal model; creating a generalized power consumption control operator, and performing matrix decomposition on the power consumption characteristic data of the CPU card chip to obtain a power consumption weight vector; performing dual-state monitoring and feature selection on the power consumption state vector and the performance state vector which are acquired in real time to obtain a low-power-consumption sparse control matrix; performing parameter optimization training through a five-layer fuzzy neural network to obtain a target inverse system model; the target inverse system model and the original power consumption control system are connected in series to form a pseudo-linear system, a linear closed-loop controller is added, and the decoupling control system is obtained, compared with a traditional method, the decoupling control system has the advantages that the energy efficiency ratio of a CPU card chip is remarkably increased, and guarantee is provided for efficient operation in various working environments.

The invention belongs to the field of automatic control, and particularly relates to a nonlinear system dynamic gain global trajectory tracking control method based on a self-adaptive neural network observer, which comprises the following steps: converting an uncertain nonlinear system model with unknown interference according to the requirement of output feedback control to obtain a first nonlinear system model; enabling an unknown nonlinear continuous function in the first nonlinear system model to be expressed as a function only containing an output signal and other system state estimation values; performing approximate approximation on an unknown nonlinear continuous function in the first nonlinear system model by using the first radial basis function neural network vector to obtain a second nonlinear system model; designing a second radial basis function neural network vector to construct a dynamic gain state observer of the second nonlinear system model, and obtaining an estimated value of a system state and an estimated value of an unknown nonlinear continuous function in the model; according to an inversion control method, defining a dynamic system tracking error index containing an intermediate virtual control signal, designing a Lyapunov function, and obtaining a change rate of a dynamic gain, a weight adaptive update rate of a second radial basis function neural network vector, and a control rate of the intermediate virtual control signal and a system input signal; different from most existing nonlinear system control methods, the method combines a novel dynamic gain neural network observer with an inversion controller with dynamic gain, and provides a robust global trajectory tracking control solution for a dynamic system operating under uncertain conditions.

The invention discloses an armored vehicle diesel engine digital twin model reduction method and system, and the method comprises the steps: building a diesel engine twin model which is a high-dimensional nonlinear system and comprises a thermodynamic equation of a diesel engine; operating the diesel engine twin model under different working conditions, collecting input and output data of variables, and performing standardization processing on the input and output data of the variables to obtain simulation data; a neural network is used for constructing a nerve differential equation model, simulation data is used for training the nerve differential equation model to obtain a reduced-order model, and the output of the diesel engine is predicted based on the obtained reduced-order model. Through Simulink modeling, neural network training, incremental learning and real-time data updating, a dynamic model of the diesel engine is effectively simplified, and it is ensured that high-precision prediction capacity is kept under different working conditions and operation environments. The system architecture supports real-time monitoring, online learning and self-adaptive adjustment, and high efficiency and stability of the diesel engine control system in practical application are guaranteed.

The invention provides a linear equation set of a diffusion equation diagram neural network model for water quality prediction, an F-GNN method and a system, and the F-GNN method comprises the steps: S1, collecting the monitoring historical data of each station, and constructing a space-time diagram; s2, on the basis of the space-time diagram, calculating a diffusion equation calculation formula by adopting a finite difference method, constructing an overdetermined linear equation set according to the diffusion equation calculation formula, and estimating parameters of the diffusion equation of each river reach by applying a least square method; and S3, if the parameters of the diffusion equation of each river reach are positive numbers, performing F-GNN prediction to obtain feature prediction of each station. According to the method, the defect that a water quality prediction model lacks space-time joint modeling is overcome, the problem that a traditional data driving model is prone to overfitting under the small sample condition is solved, diffusion equation constraints are introduced, the defect is effectively overcome, meanwhile, physical constraints are introduced, prediction precision and reliability are improved, and the method is suitable for large-scale popularization and application. The method is suitable for various environment monitoring scenes.

The invention discloses a fault-tolerant control method and device for a faulty unmanned aerial vehicle based on incremental nonlinear dynamic inverse terminal sliding-mode control, and the method comprises the steps: determining an incremental expression based on a terminal sliding-mode control law, determining a sliding-mode control law of the faulty unmanned aerial vehicle based on an attitude control algorithm of incremental nonlinear dynamic inverse nonsingular terminal sliding-mode control, and carrying out the fault-tolerant control of the faulty unmanned aerial vehicle. The method comprises the steps of calculating the rotating speed of a rotor wing based on a sliding-mode control law and incremental expression, calculating the acceleration required to be applied by a faulted unmanned aerial vehicle based on the rotating speed of the rotor wing, and controlling the attitude and position of the faulted unmanned aerial vehicle based on the acceleration, and comprises the steps of converting a nonlinear system of the faulted unmanned aerial vehicle into a linear system, and designing a terminal sliding-mode control law; and determining an incremental expression according to the sliding-mode control law to calculate the acceleration required to be applied by the faulted unmanned aerial vehicle, thereby solving the problems that the fault-tolerant control cost is high and an expected index is not easy to reach under a relatively serious fault condition that the faulted unmanned aerial vehicle fails in a single-rotor or double-rotor mode.

This disclosure describes a computing module for reducing communication burden between a controller and a physical system comprising a non-linear system by which only a m-length string is transmitted between the controller and the physical system. Further, the computing module introduces a self-adjustable performance mechanism that flexibly adjusts symmetric or asymmetric performance boundaries of the nonlinear system to accommodate various type of initial conditions, providing a solution to an underlying tracking problem.

The invention belongs to the technical field of airplane nonlinear system control, and discloses a deicing vehicle hierarchical control method and system under an airplane idling condition. According to the method, a deicing vehicle overall dynamic model under incomplete constraint is constructed based on a Lagrange equation, a vehicle-arm combined trajectory tracking error state model is constructed, a cost function of a model prediction controller is designed according to a control target of deicing vehicle combined trajectory tracking, a quadratic programming problem is constructed on an upper layer to solve an optimal virtual control quantity, and the optimal virtual control quantity is calculated. And the lower layer analyzes the virtual control quantity into control input which can actually act on an execution mechanism by designing a self-adaptive fuzzy logic strategy so as to realize trajectory tracking control. According to the invention, a hierarchical control strategy is provided by combining model predictive control and an adaptive fuzzy logic system (FLS), the stability and high efficiency of system operation are ensured, and the deicing vehicle is ensured to always maintain a stable operation state in a complex and changeable operation environment.

The invention discloses an EMB system modeling and estimation integration method and device based on a Koopman operator, and relates to the technical field of automatic driving and intelligent chassis, and the method comprises the steps: obtaining an EMB system input and output offline data set, constructing a clamping force estimation high-dimensional linearization model through the Koopman operator, and carrying out the offline training of a clamping force estimation-oriented high-dimensional linear system matrix set; inputting the matrix set into a clamping force estimator based on a Koopman operator to obtain a real-time clamping force; the real-time clamping force is combined with a pre-established EMB system dynamic model to obtain a unified linearization model of the EMB system, and an adaptive estimation algorithm based on minimum recursion is adopted to obtain an estimation result of time-varying parameters of the EMB system. And dynamic online unified linear modeling and self-adaptive parameter updating of the electro-mechanical braking EMB system are realized.

A system and method include dividing training data into training data blocks, determining a support vector subset, distributing the training data blocks and the support vector subset to worker machines, receiving a first set of sub-results from worker machines, combining the first set of sub-results, solving a linear system, distributing a first set of variables to worker machines, receiving a second set of sub-results from worker machines, selecting a step size value and sending the selected step size value to worker machines, receiving updated values of the first set of variables and second set of variables from worker machines, receiving a maximum residual error value from worker machines, selecting a maximum value of the maximum residual error values, responsive to determining that selected maximum value satisfies an optimality condition, outputting a weight value and a bias value, and predicting a label using the weight value and the bias value.

The invention provides a trajectory planning method and device of a mechanical arm, a storage medium and a computer program product. The trajectory planning method comprises the following steps: an information acquisition step: acquiring environment information around the mechanical arm and state information of the mechanical arm; a path planning step: according to the acquired environment information and the state information of the mechanical arm, performing path planning by adopting a fast random tree extension method so as to generate a running path of the mechanical arm, and smoothing and optimizing the running path by using a gradient descent method; and track control: converting a control system of the mechanical arm from a nonlinear system into a linear system by using a feedback linearization method, optimizing the control gain of the linear system by using a linear quadratic regulation controller according to the state information and the environment information of the mechanical arm, and generating a control instruction for controlling the mechanical arm to track a running path. According to the invention, the control instruction is dynamically adjusted through real-time sensing information, so that the robot can more flexibly and accurately avoid obstacles in a dynamic environment.

The invention discloses a method for designing a double-iteration Turbo equalizer of an OTFS-MIMO-ISAC system, and the method comprises the steps: carrying out the sparse processing of covariance matrix inversion, and reducing the matrix inversion cost of conventional MMSE equalization through linear complexity derivation; the sparse linear system is solved through the TFQMR algorithm to reduce the complexity of the first iteration, and a sparse approximate inverse matrix is generated in the subsequent iteration through the FSPAI algorithm to further realize the balance between the calculation efficiency and the performance; and dynamically optimizing channel information by adopting an iterative channel estimation method and utilizing MMSE (Minimum Mean Square Error) equilibrium feedback. Through outer iteration and inner iteration, the symbol estimation precision is gradually improved, meanwhile, the calculation complexity is reduced, and a low-complexity and high-precision equalization and channel estimation solution is provided for a high-mobility wireless communication system.

The invention relates to the technical field of wireless communication, in particular to a wireless communication system signal sending and receiving method based on an AI model. The system comprises a delay coordinate embedding unit, a neural flow tracking unit, a continuous evolution unit, a Riemann decoding unit and a closed-loop control unit. The system maps the pilot frequency to a high-dimensional phase space by using a Takens principle, and reconstructs a channel dynamic topology; the core of the method is that a manifold derivative network is utilized to calculate a flow field vector, continuous time deduction is carried out through a Shenchang differential equation, evolution deviation is eliminated in combination with a geometric projection correction term, and thus the future channel state is accurately predicted. Calculating a CSI matrix based on the prediction result to optimize beam transmission; according to the method, the limitation of single-variable observation is broken through, and reconstruction and perception from discrete data to a full view of a high-dimensional nonlinear system are realized.

The invention provides a flexible connecting rod robot nonlinear system control method and system based on an observer, and belongs to the technical field of robot control, and the method comprises the steps: building a flexible connecting rod robot quasi unilateral Lipschitz nonlinear system dynamics model; creating a state observer based on the state vector of the nonlinear system; constructing an error system and an error expansion system containing predictable target signal information; designing a state feedback controller, and substituting the state feedback controller into the error expansion system to obtain a closed-loop system; analyzing stability and H-infinity performance conditions of the closed-loop system to obtain a state feedback controller gain matrix; and returning the gain matrix of the state feedback controller to the quasi unilateral Lipschitz nonlinear system to obtain a predictive controller based on the observer, and tracking and controlling the target signal. According to the method, the control performance of a closed-loop system is improved by combining a quasi single-side Lipschitz condition and utilizing predictable information of a target signal.

The invention provides an unmanned excavator track planning and control method, and relates to the field of artificial intelligence vehicle control. According to the system, aiming at engineering requirements of linear excavation and the like, an excavator working device is simplified into a four-degree-of-freedom mechanical arm, and a target excavation track is planned through an RRT-Connect algorithm and an S-type speed interpolation function; constructing the nonlinear system into a second-order linear system, and identifying model parameters on line by adopting a recursive least square method; and then an augmentation system containing error integration is constructed, model prediction control is combined, and high-precision trajectory tracking is realized through discretization processing, objective function optimization and a QP solver. The problem that a traditional control strategy is insufficient in precision is solved, the operation precision and adaptability of the unmanned excavator under complex working conditions are improved, the method is suitable for scenes such as groove excavation and slope leveling, and intelligent development of the excavator is promoted.

The invention discloses a dynamic load identification method and device based on a physical guidance convolution long-short-term memory network, and relates to the field of data processing, and the method comprises the steps: constructing a dynamic load identification model based on the convolution long-short-term memory network, and training the dynamic load identification model, and obtaining a trained dynamic load identification model; loss functions used in the training process of the dynamic load recognition model comprise a data driving loss function and a physical guidance loss function, the physical guidance loss function is constructed based on a kinetic equation converted from a motion equation of a linear system under the action of power, and an overall transfer matrix is used; acquiring the acceleration and / or strain response time domain signal of each test point acquired in each time window when the to-be-identified dynamic load is applied to one or more action points on the structure, and inputting the acceleration and / or strain response time domain signal into the trained dynamic load identification model to obtain the predicted dynamic load corresponding to the one or more action points. The problem that current load identification is high in dependence on data is solved.

The invention discloses a sparse triangular linear system solving accelerator based on an FPGA (Field Programmable Gate Array), and belongs to the technical field of calculation, reckoning or counting. The accelerator comprises an HBM, an instruction prefetching and decoding module, an input cache module, an FIFO module, a processing unit array, a partial sum register file module and a data decoding register file module. A super-long instruction word architecture instruction calculation scheduling and data information generation are adopted, FIFO and a register file are used as cache modules for node conversion and node multiplexing, periodic automatic alignment is realized without synchronization cost, a full interconnection structure realizes temporary storage of multiplexing data and intermediate results in the register file, and non-reused calculation results are directly written back. According to the method, a double-floating-point calculation operation granularity capable of fully reusing nodes and parallelism is adopted, a multi-PE parallel high-reusability operation mode is fully exerted, calculation control is simplified through scheduling of software and hardware, and an implementation scheme for efficient parallelism of SpTRSV on an FPGA is provided.

The invention discloses a ship air-sea cooperative task guidance and gain adaptive control method for surround alert. The method comprises the following steps: constructing a mixed-order ship-unmanned aerial vehicle nonlinear system model; setting a waypoint path planning reference path, and generating a ship reference signal; acquiring the real-time position of the ship and the surrounding radius of the unmanned aerial vehicle, and generating an unmanned aerial vehicle reference signal by combining the virtual unmanned aerial vehicle; defining a ship-unmanned aerial vehicle kinematics error according to the reference signal, and designing a virtual control law; a dynamic surface technology is introduced, a dynamic surface signal of the virtual control law is obtained, and a dynamic error is defined; a radial basis function neural network and a minimum learning parameter technology are used to carry out approximation on a nonlinear term of a ship-unmanned aerial vehicle system, an MLP technology is introduced to simplify external interference, a preset performance control law and an adaptive law of an actuator gain are designed, and path tracking control under an unmanned aerial vehicle surrounding warning task is realized; the method can guarantee the control precision, reduces the design complexity of the controller, gives full play to the maneuverability of the unmanned aerial vehicle, and achieves the purpose that a ship and the unmanned aerial vehicle execute a surrounding warning task.

The invention discloses a distributed finite time formation tracking control method with preset performance, which relates to the technical field of multi-agent cooperative control, and comprises the following steps: establishing a high-order nonlinear multi-agent system model, and determining multiple control targets; the multiple control targets comprise a formation tracking control target, a performance constraint guarantee target, a collision avoidance constraint target, a communication connection maintenance target and a robustness and finite time convergence target; constructing a virtual multi-agent system, and generating a reference trajectory satisfying collision avoidance and connection maintenance through error transformation and a performance function; designing an observer for each agent, and estimating system disturbance and a high-order state in real time; a feedback controller is constructed based on a sliding mode surface, tracking errors are limited in a performance funnel, and finite time convergence is ensured. The method provided by the invention breaks through the limitation that a traditional method mostly focuses on a low-order linear system, and has higher engineering applicability and universality.

The invention discloses a switching system dynamic quantization control method and device based on event-triggered communication, and the method comprises the steps: building a continuous time switching linear system model for a switching system, and giving a system stability guarantee mechanism; designing a dynamic quantizer for the continuous time switching linear system model, giving a dynamic quantization parameter and a dynamic quantization updating strategy, and cooperatively designing an event triggering mechanism according to a state variable of the system and the dynamic quantization parameter; and designing a switching law according to an event triggering mechanism, and adjusting dynamic quantization parameters of the system to realize stable control of the system. On the premise of ensuring the system performance, the communication frequency and calculation burden of the system can be reduced, the resource utilization efficiency of the system can be improved, the method can be widely applied to the fields of network control systems, industrial automation systems and the like, and an effective solution is provided for solving the control problem of a complex system.

The invention discloses a multi-constraint nonlinear self-adaptive method and system for a control valve positioner, relates to the technical field of automatic control, and solves the problems that the existing PID algorithm depends on fixed parameters, so that the control precision of a complex nonlinear system is insufficient, the change rate of proportional parameters is too large during rapid adjustment, overshoot is easily caused, and the control precision is poor. And the system stability is influenced. A current signal of a signal generator is obtained; the microprocessor analyzes the current signal to obtain a target position value of the valve; the position of the valve is monitored in real time through a valve position sensor, and the opening degree deviation of the valve is obtained through analysis according to the target position value and the position signal of the valve; the control current of the magnet coil is calculated according to the opening degree deviation; the magnet controls the valve to move to a target position according to the control current; overlarge overshoot caused by too fast increase of a proportional link can be prevented; the system is more stable in a small deviation range; and the reasonability of proportional control parameters and the stability of the system are ensured.

The invention discloses a transfer learning-based aero-engine full envelope transition state optimization method, which comprises the following steps of: training a deep reinforcement learning agent in a source task environment to obtain an optimal transition state control strategy under the working condition, and applying the strategy of the source task agent to a target task environment in a parameter transfer manner, and further training and optimizing the strategy in the target task environment until the optimal control strategy of the target working condition is obtained. According to the method, autonomous optimization and expansion of the control strategy can be realized according to different operation conditions of a complex nonlinear system, and the method is of great significance to intelligent control of the propulsion aero-engine and improvement of the operation performance and reliability of the engine.