460 results about "Predictive controller" patented technology

The invention discloses a biped robot reinforcement learning control method which comprises the following steps: after a model prediction controller receives a walking instruction, outputting expected angle data of each joint of a robot to a reinforcement learning neural network, and meanwhile, returning joint angle data of an actual strategy of the reinforcement learning neural network to the neural network by a sensing system at a bottom layer; a joint angle taking time as a sequence and planned by model prediction is compared with a joint angle actually generated by a neural network, and model prediction control is fused into a reinforcement learning training process by setting a reward function for punishment, so that the reinforcement learning training efficiency is improved, and a stable gait is more quickly achieved. Excellent gaits planned by the MPC are transplanted into reinforcement learning control, and control robustness can be improved under the condition that the excellent gaits of the MPC are reserved; and meanwhile, the joint angle data which is obtained by taking time as a sequence and is obtained by taking MPC as a planner can accelerate the reinforcement learning training process, so that the training speed and the control effect of reinforcement learning are greatly improved.

The invention relates to the crossing field of mechanical engineering and automatic control, in particular to a global path planning and anti-swing control method for a ship unloader, and aims to solve the problems of rigid path planning and poor synergism of out-of-control swing of a lifting appliance in traditional ship unloading operation. The method comprises the following steps: constructing a dynamic three-dimensional operation space model with fusion of a laser radar and binocular vision, and updating obstacle information in real time; an improved fast extended random tree algorithm is adopted to generate a high-smoothness initial path; establishing a six-degree-of-freedom lifting appliance swinging dynamic model and identifying parameters on line; path tracking and anti-swing torque are synchronously optimized through a model prediction controller, and the control period is smaller than or equal to 20 milliseconds; and closed-loop feedback correction is implemented by combining an encoder and an inertial measurement unit. According to the scheme, environment dynamic sensing, path-anti-swing depth cooperation and multi-disturbance self-adaptive compensation are achieved, the operation rhythm is improved by 30% or above, the system still operates stably under the 8-level wind condition, and high precision, high robustness and engineering implementability are achieved.

The invention discloses a new energy commercial vehicle fast charging working condition thermal management control method and system, and relates to the technical field of new energy vehicle thermal management and fast charging control, and the method comprises the following steps: collecting the temperature, voltage and current data of each subarea of a battery in a fast charging process, forming a time synchronization sequence, and based on the sequence, obtaining a new energy commercial vehicle fast charging condition; calculating internal thermal resistance and thermal capacity parameters of the battery in real time by using an online identification algorithm, updating a basic thermal model to obtain a corrected thermal dynamic model reflecting actual thermal characteristics of the current battery, importing the corrected model into a model prediction controller, constructing a multi-objective optimization function, and performing rolling solution in a prediction time domain to obtain a prediction model; and outputting an optimal target charging current instruction and a cooling total demand, adjusting the charging power according to the target current, and combining the temperature difference distribution of each partition. Accurate prediction and partition cooperative control of the thermal state of the battery in the fast charging process are achieved, the temperature rise and the temperature difference are effectively restrained while the charging efficiency is guaranteed, the service life of the battery is prolonged, and the system safety is improved.

The invention provides a high-speed magnetic levitation suspension system control method and system based on edge calculation and Transform prediction, and the method comprises the steps: constructing a Transform prediction model with a space-time attention mechanism and an autoregression mechanism based on obtained local low-delay calculation resources and train real-time sensing data, and deploying the Transform prediction model in a vehicle-mounted edge calculation unit; performing short-term high-precision prediction on the gap, the acceleration and the disturbance trend at a plurality of sampling moments in the future through a Transform prediction model to obtain a prediction result; processing actuator current saturation and gap safety threshold hard constraints in a limited prediction domain by using a model prediction controller, and solving an optimization control sequence in real time in combination with a prediction result; and overlapping a control barrier function as a safety filter of the model prediction controller, correcting the optimized control sequence to obtain an optimal control sequence, and controlling the high-speed magnetic suspension system. According to the method, the cloud communication delay and jitter are reduced, and the robustness and security of the system under uncertain disturbance are improved.

The invention provides an overhead and portal crane lifting appliance control method based on multi-stage model predictive control, and relates to the field of data processing. The method comprises the following steps: firstly, acquiring a control parameter and an initial state variable so as to define an operation boundary and an initial state, and establishing a dynamic model containing a coupling relationship among a trolley acceleration, a sling rope length acceleration and a sling swing angle; acquiring obstacle distribution by using space sensing equipment, and calculating the dynamic safety height of the lifting appliance by combining obstacle parameters and control parameters; judging whether the lifting appliance is in an obstacle avoidance stage or a target tracking stage according to the initial state variable and the dynamic safety height; constructing a model prediction controller and dynamically adjusting a state weight matrix and a control input weight matrix; finally, a control input sequence is generated through an optimization algorithm, and track safety and attitude stability control of the lifting appliance is achieved. According to the technical scheme, the swing angle of the lifting appliance is restrained, meanwhile, the obstacles are effectively avoided, and the safety of the lifting appliance in the whole operation process is guaranteed.

The invention belongs to the technical field of robot control, and particularly relates to a self-adaptive whole-body control method suitable for a quadruped robot in an uncertain dynamic environment, and the method integrates an extended state observer (ESO), a model prediction controller (MPC) and a whole-body controller (WBC) based on hierarchical optimization. And a closed-loop control architecture is constructed to improve the robustness and motion coordination ability of the quadruped robot in a complex environment. Firstly, external disturbance is estimated and compensated in real time through ESO; then, the MPC optimizes future system behaviors in a rolling manner under the condition of considering interference terms, and an expected foot end counter-acting force is output; and finally, the WBC is combined with the priorities of the multiple tasks to generate all joint control instructions in a constraint optimization form, and task collaboration and dynamic adaptation are achieved. The method has the advantages of being high in disturbance self-adaptive capacity, high in control precision, suitable for a multi-task environment and the like, and is particularly suitable for quadruped robot control tasks in complex dynamic scenes such as transportation and search and rescue.

The invention discloses a response control method for a charging station participating in a low-voltage treatment scene, and the method comprises the following steps: S1, collecting the voltage data of a charging pile, calculating a deviation, and judging a low-voltage grade; s2, when the deviation is in a light interval, outputting reactive power support voltage in proportion; s3, when the deviation exceeds a heavy threshold value, reducing active power and starting V2G feedback; s4, constructing a graph structure model, and extracting inter-node power coupling and user behavior factors; s5, inputting the model into an improved prediction controller, predicting a future voltage state, and optimizing and outputting a current period power control value; s6, power adjustment is executed, and feedback power is slowly output in the V2G stage; and S7, comparing the control deviation with the behavior factor change, updating the node control priority, and feeding back for rolling optimization of the next period. According to the invention, while the charging regulation and control precision is improved, the user experience and the voltage stability are effectively considered, and the method is suitable for various low-voltage treatment scenes.

The invention relates to an automatic guided vehicle (AGV) adaptive path tracking method based on MPC. The method comprises the following steps: S1, establishing a kinematic discretization error model based on the kinematic characteristics of the two-wheel differential AGV, processing a continuous kinematic equation by adopting an Euler discretization method, expressing a dynamic change relationship between a transverse deviation distance and an angle deviation in a state-space equation form, and generating a kinematic discrete state-space model; the method has the advantages that the continuous equation is processed by establishing the kinematics discretization error model and adopting the Euler discretization method, the deviation dynamic relation is expressed through the state space, the calculation process is simplified, the precision is kept, sensor data are fused, the wheel type odometer, IMU and laser data are integrated through the extended Kalman filtering algorithm, and the precision is improved. The real-time position and angle deviation are calculated, the positioning accuracy is improved, a model prediction controller objective function is designed, a weight matrix and boundary constraint are introduced according to constraint conditions, and the effect of obstacle avoidance constraint is combined.

The invention discloses a commercial vehicle team cruise control method and system, computer equipment and a storage medium, and relates to the technical field of automatic driving and vehicle infrastructure cooperative control, and the method comprises the steps: carrying out the vehicle role interaction of a team vehicle according to a cooperative relation and a vehicle role interaction logic; establishing a surrounding environment potential field model, and describing an interaction relationship between vehicles inside and outside the motorcade; calculating the longitudinal and transverse potential fields of the vehicles of the fleet, and controlling the distance between the vehicles and the safe distance; a model prediction controller for team cruise is constructed by considering the target speed and the environmental influence; and the safety, speed and control constraints of vehicle movement are set, and the driving performance is optimized. The stability of formation control is enhanced, the formation requirements of complex scenes are met, the real-time dynamic control capability is improved, and the formation energy efficiency is optimized.

The invention relates to a coaxial multi-rotor unmanned aerial vehicle control method based on a Koopman operator, and the method comprises the steps: constructing a deep neural network based on the Koopman operator, and mapping a state variable to a high-dimensional observable space through an encoder; in a high-dimensional observable space, state variables are predicted through a linear connection layer based on dimension rising state variables and rotor rotating speeds; the decoder restores the prediction result to an original state space; training a deep neural network by using historical flight data to obtain codec parameters and a weight of a linear connection layer, and constructing a linear dynamic model of the observation function and the unmanned aerial vehicle; and the prediction controller predicts state variables of future multiple steps of the unmanned aerial vehicle by using a linear dynamics model, and enables the unmanned aerial vehicle to track a given trajectory by minimizing a cost function to obtain optimal control input. Compared with the prior art, the method has the advantages that complete data-driven modeling is realized, and the method can adapt to unmanned aerial vehicles with different sizes, loads and flight conditions.

The invention belongs to the technical field of temperature control, and discloses a temperature control method and device of a hot runner system for an inverted mold. The method comprises the following steps: defining a critical melt area in a physical sprue which directly influences the product quality in a sprue of a hot runner system as a virtual sprue; dynamically generating a melt viscosity target track of the virtual gate region according to the type of an injection molding material and an injection molding process stage; based on measurable injection molding process parameters and sprue area temperature, estimating a current melt viscosity value of a virtual sprue area in real time through a state observer; calculating to obtain an optimal power control sequence by adopting a multivariable model prediction controller; and driving a sprue area heater according to the optimal power control sequence, so that the actual change of the melt viscosity of the virtual sprue area tracks a melt viscosity target track. According to the invention, the defects such as salivation and wire drawing can be effectively eliminated, so that the sprue quality stability and the production efficiency are improved.

The invention discloses a ground wire adaptive visual trajectory tracking control method for unmanned aerial vehicle inspection, relates to the technical field of unmanned aerial vehicle inspection, and solves the problem that it is difficult to effectively fuse geometric, texture and multispectral features to construct a ground wire lightweight model. And a three-dimensional coupling constraint system is difficult to be combined to adapt to a dynamic scene of ground wire inspection. Comprising the following steps: collecting an initial visual image and multispectral data of a ground wire, extracting and splicing geometric, texture and state features, and constructing a ground wire lightweight model based on knowledge distillation to output a state evaluation result; the flight controller combines the model and geographic information to construct a three-dimensional coupling constraint system, calls a dynamic programming algorithm to generate an initial trajectory and sets a constraint deviation real-time monitoring mechanism; multi-dimensional deviation is calculated, and comprehensive deviation is obtained through weighting of the incidence matrix; and if the deviation exceeds a threshold value, starting a lightweight prediction controller to solve an optimal control problem and adjust flight parameters to generate a new trajectory, otherwise, flying along an initial trajectory.

The invention relates to the technical field of industrial process control, and discloses a digital twinning-based fermentation process temperature adaptive control system, which comprises a data acquisition and state representation module, a probability generation type digital twinning module, an adaptive risk management module, an opportunity constraint model prediction control module and a model iteration trigger module, according to the method, probability distribution of future states is predicted by constructing probability generation type digital twinning, and the uncertainty of the model is quantified in real time; the system can dynamically adjust the risk tolerance, drives the chance constraint model prediction controller, seeks an optimal control solution on the premise of ensuring the process safety probability, triggers the model adaptive update by means of an online evaluation mechanism, and realizes the optimal control solution on the basis of effectively managing the process uncertainty. The fermentation temperature is subjected to high-performance self-adaptive control considering safety and economy, and the problem that a traditional deterministic model is insufficient in control robustness is solved.

The invention discloses a visual servo method for a transformer substation drainage wire disconnecting and connecting robot, and the method comprises the following steps: building a mapping relation between a mechanical arm tail end camera and a mechanical arm kinematic model, and building an image-based visual servo system IBVS; acquiring a drainage wire clamp image in real time, and extracting image feature points of a drainage wire clamp bolt by using the recognition model; the model prediction controller carries out rolling optimization based on the deviation between the extracted current image features and the expected image features, estimates and compensates external disturbance and unmodeled dynamics borne by the system in real time, and calculates an optimal, smooth and safe mechanical arm motion instruction; and the mechanical arm movement instruction is sent to a mechanical arm movement control unit to drive the mechanical arm to move. According to the method, the pose control of the drainage wire disconnecting robot can be realized, the error convergence in the visual servo process is rapid, the steady-state error is small, the dynamic response is timely, and the requirements of the drainage wire disconnecting operation on the precision, the stability and the real-time performance are fully met.

The invention relates to the field of metal plastic forming control, and discloses a self-adaptive control system and method for forging and pressing aviation precision forgings, and the system comprises an online dynamic model identification module which identifies a process fingerprint representing the characteristics of a current blank at the initial stage of machining; the target curve self-adaptive regulator is used for regulating a reference energy dissipation rate curve according to the fingerprint and generating a personalized reference curve; the model prediction controller performs rolling optimization by using continuously updated model parameters and taking the reference curve as a tracking target, and outputs an optimal speed instruction; and the event triggering and constraint dynamic modulation module is used for actively tightening the operation constraint applied to the controller before a forging pressure sudden increase event is pre-judged through a parallel monitoring model prediction error. According to the method, through combination of target self-adaption and constraint dynamic modulation, control over the forging and pressing process is achieved, forging pressure overshoot can be effectively restrained, and the forming precision and batch-to-batch quality consistency of forge pieces are remarkably improved.

The invention discloses an operation control method for a wind power generation system, and relates to the technical field of operation control, and the method comprises the steps: obtaining the historical operation data of a wind power generation system in a target sea area, taking an offshore environment factor as an interference factor, and coupling the time-space parameters of ocean turbulence intensity, wave load and salt spray corrosion rate; establishing a fan-marine environment digital twinborn body; operation data is acquired in real time, synchronous mapping and dynamic updating of the digital twin are realized, and a state prediction model is established in combination with historical operation characteristics; taking the maximum power generation efficiency and the minimum mechanical load as a multi-objective optimization function, and introducing a model prediction controller to obtain an optimal control sequence of the wind power generation system in a future time domain of each control period; and selecting a first control instruction in the optimal control sequence, issuing the first control instruction to a physical fan torque controller and a variable pitch system in real time, realizing rolling optimization of the wind power generation system, and obtaining a self-adaptive operation control scheme of the wind power generation system. The power generation benefit of the whole life cycle is improved.

The invention discloses a low-altitude large-speed small-radius maneuvering control method for an unmanned aerial vehicle. The method comprises the steps of data acquisition and preprocessing, establishment of an accurate unmanned aerial vehicle model, design of a model prediction controller, sensor fusion, real-time control and the like. Flight state data is collected and preprocessed through various sensors, dynamics and kinematics models considering aerodynamic nonlinearity are established, a model prediction controller is designed by using a recurrent neural network and a particle swarm optimization algorithm, sensor fusion is performed by using an extended Kalman filtering algorithm, and a model prediction model is established. Accurate control of the attitude and track of the unmanned aerial vehicle is realized. Meanwhile, the functions of environment perception and obstacle avoidance, fault diagnosis and fault-tolerant control, real-time controller parameter adjustment, target optimization and the like are added, the maneuvering performance, adaptability and safety of the unmanned aerial vehicle are improved, and the unmanned aerial vehicle can be widely applied to the fields of military reconnaissance, logistics distribution, film and television shooting and the like.

The invention discloses a wheel-foot humanoid robot operation control method and system based on maneuverability optimization, and relates to the technical field of robot intelligent control. According to a mechanical arm tail end trajectory tracking task and mechanical arm joint motion constraints, a weight matrix is calculated in a self-adaptive mode through state vectors of a base and a mechanical arm joint; a robot dynamic model is constructed, and the tail end contact force of the mechanical arm is estimated based on a disturbance observer; the direction of the control force is determined according to an estimation result, and then force maneuverability enhancement is carried out; a speed instruction of an end effector is obtained, the expected base speed and the expected mechanical arm joint speed are obtained through a weight matrix, a hierarchical control frame of a model prediction controller and a whole-body controller is constructed based on an integrated dynamic model, the optimal wheel-leg interaction force spinor and the optimal joint torque are obtained through solving, and the optimal wheel-leg interaction force spinor and the optimal joint torque are obtained. Therefore, the whole-body motion control of the robot is driven. Through organic combination of disturbance compensation and force maneuverability optimization, the motion stability and operation efficiency of the robot are enhanced.

The invention relates to the technical field of unmanned tracked vehicle trajectory tracking, in particular to a learning type unmanned tracked vehicle trajectory tracking prediction control method, which comprises the following steps of: establishing an interactive training virtual environment oriented to tracked vehicle trajectory tracking controller learning; receiving vehicle global expected trajectory point information output by a tracked vehicle trajectory planning module; acquiring the motion states of the crawler and the obstacle at the current moment; a controller expected parameter instruction and a crawler longitudinal acceleration and yaw angle acceleration expected instruction are determined; a tracked vehicle longitudinal lateral motion tracking controller is constructed, and a vehicle longitudinal lateral motion bottom layer control instruction is determined; motion states of the crawler and the obstacle at the next moment are acquired; data are collected while interaction between the crawler and the environment is carried out, and a data experience pool for controller parameter learning is constructed; and constructing a predictive controller parameter reinforcement learning algorithm. According to the invention, through an autonomous exploration learning technology, the trajectory tracking precision of the unmanned tracked vehicle in a dynamic complex environment is improved.

The invention relates to a gas turbine system predictive control method, device, equipment and medium, and relates to the technical field of gas turbine control, and the method comprises the steps: building a transfer function model of a gas turbine system at a plurality of preset load points through a step response experiment, a prediction controller is designed based on the transfer function models corresponding to the different load points, so that a control increment output by the prediction controller is obtained, and the prediction controller comprises a plurality of sub-prediction controllers corresponding to the different load point models; correcting the control increment which does not accord with a preset constraint condition based on an improved He-Make algorithm; and based on the deviation between the control increment corresponding to each sub-prediction controller and the actual output value, performing weighting processing on the control increment sequence corresponding to each sub-controller by using an improved recursive Bayesian weighting algorithm to obtain a final control increment. According to the method, the operation stability and the response speed of the heavy duty gas turbine system can be remarkably improved, and the strong performance advantage is shown in the aspect of set value tracking.

The invention relates to the technical field of vehicle control, and discloses a VCU torque control system based on multi-sensor fusion, and the VCU torque control system comprises a system monitoring and fault diagnosis module which is used for generating a sensor failure mark when a yaw velocity sensor is diagnosed to be failed; and the data acquisition and preprocessing module is used for receiving the sensor failure mark generated by the system monitoring and fault diagnosis module and acquiring real-time data of the health sensor so as to generate a real-time feature vector. A Gaussian process regression state observer and random model predictive controller fusion scheme is adopted, state perception uncertainty information is transmitted to a control decision-making layer, and the problem that in the prior art, when a deterministic state observer is cascaded with a conventional controller, the controller cannot perceive the upstream state estimation quality, and the control accuracy is poor is solved. And the system is unstable or the performance is reduced due to over-excitation control when the estimation is inaccurate.

The invention discloses a self-adaptive model optimization control method and system for an offshore wind turbine group. The method comprises the following steps: establishing a quasi-steady-state wake flow model, calculating wake flow propagation time delay based on a relative distance between units and a theoretical average wind speed, and correcting an incoming flow wind speed of a downstream unit by the time delay; constructing a linear parameter variation (LPV) model of a wind turbine generator based on the corrected incoming flow wind speed, and further assembling the model into a wind power plant distributed LPV control model considering wake flow time delay; a model prediction controller is constructed on the basis, a multi-objective optimization objective function and constraints are adopted, and a distributed LPV model serves as a prediction model; and solving and outputting an optimal control sequence aligned according to the time sequence of the unit in a prediction time domain by adopting rolling optimization, and realizing full-field collaborative optimization control so as to improve the power generation efficiency and reduce the fatigue load of the structure.

The invention relates to the technical field of fuel gas mixing, and discloses a biological natural gas mixing control method and system.The method comprises the steps that a natural gas branch, a synthesis gas branch and a mixed gas outlet are each provided with a multi-mode sensor unit; carrying out data fusion on the detection data and the detection data of an on-line chromatographic instrument and a mixed gas rapid calorific value instrument, and estimating the low calorific value, the bloom index and the gas component percentage of the mixed gas in real time based on a constraint model and Kalman filtering; establishing a prediction controller, setting input to predict gas characteristics required by a future gas turbine, and outputting a synthesis gas valve opening degree and a natural gas valve fine tuning signal; calculating an allowable mixing proportion upper limit to form a dynamic mixing window, and adjusting the mixing proportion of the natural gas and the synthesis gas based on the dynamic mixing window when a hard boundary condition is met; and when the instability state occurs, the safety interlocking is triggered. According to the invention, rapid detection is realized, active adjustment of rapid working condition fluctuation is realized, and safety interlocking is arranged, so that the overall operation safety is improved.

The invention discloses an intelligent yarn low-tension control system, and relates to the technical field of textile control systems. A tension estimation module takes output of a physical tension sensor and torque and speed signals of a servo driver as inputs; after being processed by a filter, the tension data signals are provided for the model prediction controller module and the self-adaptive PID module; the visual detection unit is coupled with the expansion reed driving mechanism through a control signal and time sequence synchronization interface, and the visual detection unit outputs segment position information corresponding to the position of the expansion reed to the edge real-time controller according to a breadth segment. According to the invention, through a fused sensing architecture of multi-channel physical sensing and virtual tension estimation, stable and redundant tension estimation can still be provided and confidence information can be output when measuring points are insufficient or local interference exists, and the problems that traditional single-point sensing is easily interfered by local liquid drops and dirt, the point supplementing cost is high and the installation space is limited are solved.

The invention discloses a welding wire production control system and method based on visual feedback, and belongs to the technical field of precision machining. The system comprises a multi-mode intelligent sensing subsystem, a self-adaptive model prediction controller and a safety and exception handling subsystem, and a two-stage control architecture of a quality closed loop and an execution closed loop is constructed. According to the method, the microcosmic roughness, macroscopic geometry, defects and other multi-dimensional quality characteristics of the surface of the welding wire are obtained in real time through multi-modal sensing and fused into a comprehensive quality index; carrying out rolling optimization by adopting a model prediction control algorithm for updating parameters on line, and generating a control instruction; meanwhile, trend early warning based on statistical process control and sudden fault diagnosis based on model residual analysis are operated in parallel, and active safety protection is achieved. According to the method, the problems of unstable quality, control lag and passive safety caused by supplied material fluctuation and tool time variation in the welding wire flaking machining process are solved, and self-adaptive accurate control and intelligent safety protection in the machining process are achieved.

The invention discloses a flight path tracking method and device based on a dynamic prediction step length, a medium and a product, and the method comprises the steps: obtaining the real-time operation state information of a current moment through a sensor borne by a platform in the navigation process of a water surface unmanned platform; according to the real-time operation state information and a pre-constructed interference observer, estimating ocean unknown time-varying interference at the current moment; calculating a curvature time function according to a real-time state and a reference path, obtaining a path curvature through filtering, and dynamically adjusting a prediction step length according to the path curvature; on the basis of a model prediction controller, the motion state of multiple moments in the future is predicted by combining the real-time state, the interference estimation and the dynamic prediction step length; solving the current optimal command rudder angle by using the optimization function, and implementing control; and in each control period, the real-time state of the platform is updated, the execution is cyclically performed until the flight path tracking is completed, and the technical scheme of the embodiment of the invention effectively improves the accuracy and the adaptive control capability of the flight path tracking of the water surface unmanned platform under the complex sea condition.

According to the clearance robot indoor and outdoor fusion navigation method and system, closed-loop detection and error state Kalman filtering are introduced, a feedback mechanism is established, accumulative errors of long-term operation are corrected in a bidirectional mode, and the global navigation precision is ensured. By constructing a multi-level semantic map and fusing laser, visual and inertial data in a tight coupling mode, high-precision and robust positioning and navigation of the cleaning robot in a complex community environment are realized. And on the basis of the closed-loop constraint in the step A5, the system can automatically adjust the prediction time domain and the control time domain of the model prediction controller, so that a smoother, more energy-saving, more stable and safer walking path can be planned. And after real-time pose correction of the filter, a robot pose sequence with higher global consistency is obtained and serves as input of the closed-loop detection module, so that subsequent global pose optimization is more effective and accurate.

The invention belongs to the technical field of hypersonic flight vehicle control, and particularly relates to a hypersonic flight vehicle protection control method considering non-starting of an air inlet channel. The method specifically comprises the steps of establishing a quasi-one-dimensional nominal mechanism model to describe flow field changes of an isolation section and a combustion chamber; adopting a physical information neural network to construct a reduced-order model as a real-time agent of the quasi-one-dimensional model; designing a dual extended Kalman filtering algorithm to realize joint online estimation of model parameters and blind area states, and introducing shock wave position pseudo measurement to form multi-loop feedback; a dual-channel fusion early warning system of a model channel and an intelligent sensor channel is constructed, and robust early warning is realized through adaptive weight; and designing a continuous adaptive model prediction controller, and dynamically adjusting a control strategy according to risk indexes and parameter uncertainty to realize active protection control.

The invention provides a smart building environment adaptive regulation and control method based on digital twinning and AI, and relates to the technical field of artificial intelligence, and the method comprises the following steps: extracting dynamic features based on multi-source system data after time alignment, so as to construct a dynamic feature set; inputting multi-source system data into the digital twin, performing iterative simulation on key environment parameters of a plurality of time steps in the future by taking a current building equipment state as a boundary condition, and outputting a multi-step prediction sequence; inputting into a model prediction controller, and solving to obtain an equipment regulation and control instruction sequence in a future first preset duration by taking the lowest total energy consumption in a prediction period as an optimization target and taking the condition that the key environment parameters do not exceed a comfort interval as a constraint condition; and the first equipment regulation and control instruction in the equipment regulation and control instruction sequence is issued to the field execution mechanism, so that self-adaptive regulation and control of the building environment are realized, the defect that passive response is performed after environmental parameters exceed the standard is overcome, and the quick response capability of the system to sudden environmental changes is remarkably improved.

The invention belongs to the technical field of control, and discloses a water surface robot high-precision trajectory tracking control method and related equipment, and the method comprises the steps: constructing a dynamic multi-modal environment map containing water surface three-dimensional geometric topology information and water flow field vector information; according to the dynamic multi-modal environment map, an improved quantum particle swarm optimization algorithm embedded into a water flow kinetic equation constraint is adopted to carry out global path planning, smooth parameterization processing is carried out on a global path obtained through planning, and a reference trajectory is generated; according to the vector information of the water flow field, flow field disturbance is predicted based on a fluid-structure interaction dynamics model, system residual disturbance is estimated by using an extended state observer, and feedforward control quantity is generated in combination; according to the real-time flow velocity of the water flow field and the trajectory tracking error, a nonlinear model prediction controller and an adaptive sliding mode controller are adaptively switched, and a control instruction is generated in combination with a feedforward control quantity to drive the water surface robot to track a reference trajectory; therefore, high-precision trajectory tracking control is realized.