1363 results about "Model predictive control" patented technology

The invention relates to the technical field of equalization control of a battery management system, and discloses a lithium battery hierarchical equalization control method based on a hierarchical model predictive control algorithm, comprising the following steps: constructing a hierarchical control architecture which comprises a state monitoring layer, an equalization decision layer and an execution control layer, each layer realizes cooperative control through closed-loop data interaction; the state monitoring layer collects multi-dimensional state parameters of the lithium battery system, pre-processes the collected data and then transmits the data to the equalization decision-making layer, the equalization decision-making layer constructs a multi-target optimization model based on a hierarchical MPC algorithm, and the model takes SOC consistency, equalization energy consumption minimization and cycle life maximization of the lithium battery system as optimization targets. The abnormal state of the sensor or the balancing module can be identified in time through a fault diagnosis mechanism, and when a fault occurs, a standby model is automatically switched or a balancing task is shared through an adjacent module, so that the system is ensured not to generate abrupt reduction of balancing performance due to the fault of a single component.

The invention relates to the technical field of robot control, particularly discloses a path planning and dynamic obstacle avoidance control method for multi-task collaborative operation of an industrial robot, and aims to solve the problems of task scheduling conflict, dynamic obstacle response lag and low collaborative efficiency in a multi-robot system. The method comprises the following steps: constructing a task-resource joint scheduling model and generating initial task allocation; planning a conflict-free collaborative path based on an improved space-time A star algorithm; predicting a dynamic obstacle trajectory by using an LSTM network and generating a space-time envelope; constructing a second-order safety barrier function fusing task priorities; local obstacle avoidance re-planning is realized through rolling horizon model predictive control; and the global rescheduling is triggered when the task delay exceeds the limit or the deadlock risk occurs. According to the technical scheme, closed-loop linkage of global task collaboration and local dynamic obstacle avoidance is realized, and the system collaboration efficiency, the obstacle avoidance success rate and the operation robustness are remarkably improved.

The invention discloses an intelligent energy storage system multi-target hierarchical scheduling method and system oriented to source network load storage cooperation, and belongs to the technical field of energy storage system optimization control. The method comprises three levels of day-ahead layer multi-objective game optimization, intra-day layer rolling correction optimization and real-time layer adaptive droop control. The day-ahead layer establishes three objective functions of economy, environmental protection and smoothness, and solves and outputs a day-ahead charging and discharging power plan by using a Nash negotiation algorithm. And the intra-day layer obtains ultra-short-term prediction data of the source load, performs rolling correction on the day-ahead plan by adopting a model prediction control method, and outputs a corrected real-time power instruction. The real-time layer collects power grid frequency deviation and a battery health state value, calculates an adaptive droop coefficient according to the health state value, and superposes and outputs primary frequency modulation response power and a real-time power instruction. According to the invention, source network load storage collaborative optimization is realized through multi-time scale hierarchical scheduling, and the service life of an energy storage system is prolonged through adaptive droop control based on health state perception.

The invention relates to the technical field of unmanned aerial vehicle control, in particular to an unmanned aerial vehicle dynamic obstacle avoidance method based on multi-sensor fusion. Comprising the steps of receiving an image sequence, a depth point cloud set, a pose state parameter and a flight speed parameter; calculating an illumination distortion gradient value and a speckle noise entropy value based on the image sequence and the depth point cloud set; performing coordinate registration and feature extraction on the image sequence, the depth point cloud set and the pose state parameter, and outputting a visual feature set and a radar feature set; generating a weighted visual feature set and a weighted radar feature set through a weight adjustment function, and generating a joint heterogeneous feature tensor through alignment splicing; and generating a body attitude and thrust control instruction by using the combined heterogeneous feature tensor through a probability prediction model and a model prediction control algorithm device. According to the method, through cross-domain multiplexing and deep coupling of the body physical parameters in the data stream, error accumulation and decision delay caused by multi-stage series calculation are avoided, and global performability of an obstacle avoidance task is facilitated.

The invention relates to the field of heating ventilation air conditioner automatic control, and discloses an efficient central air conditioner cold station optimization control system and method based on physical AI. The system comprises a data acquisition module, an energy efficiency modeling module, a load prediction module, a rolling optimization module, an execution control module and a feedback correction module. The data acquisition module forms a time sequence data set; the energy efficiency modeling module adopts transfer learning to obtain a system energy efficiency model of a target domain cold station; the load prediction module outputs a predicted cold load sequence; the rolling optimization module is used for solving an optimal control sequence under the constraints of cooling capacity balance, an equipment operation boundary and a temperature difference threshold by taking a predicted cooling load sequence, a system energy efficiency model and a current equipment operation state as input under a model prediction control framework; the execution control module issues a first control action to control the water supply temperature, the water pump and fan frequency and unit start and stop; and the feedback correction module calculates a residual error and is used for closed-loop correction of the next period.

The invention discloses a modeling and optimization control method for a gas supply system of a proton exchange membrane fuel cell, and belongs to the technical field of hydrogen energy power. The method comprises the following steps: establishing a nonlinear state space model of a proton exchange membrane fuel cell gas supply system; determining the optimal oxygen excess ratio of the system under different load currents through experiments, and fitting the optimal oxygen excess ratio into a reference function about the load currents; based on the nonlinear state space model, a model prediction control problem with tracking of the optimal oxygen excess ratio and minimization of the cathode and anode pressure difference as control targets is constructed and expressed as a constrained quadratic programming problem; and decomposing and iteratively solving the quadratic programming problem by adopting an alternating direction multiplier method to obtain the optimal control input of the current control period and act on the system. The method effectively solves the problem that traditional model predictive control is difficult to deploy in real time in a vehicle-mounted controller due to large calculated amount, so that efficient and accurate cooperative control of the proton exchange membrane fuel cell gas supply system is realized.

The invention provides a ship unloader grab bucket system and method based on multi-modal perception and artificial intelligence semantic segmentation. According to the system, point cloud data and image data are synchronously collected through a laser radar and an RGB camera, feature level alignment and fusion are conducted through an image fusion module, an artificial intelligence semantic segmentation network is combined with attention gating to restrain dust interference, grab bucket boundary information is output, and a position and posture estimation module solves the grab bucket position and posture based on the boundary information and geometric constraints. The path planning module combines reinforcement learning and model prediction control to generate a trajectory instruction, and the compensation module implements hierarchical correction according to the pose deviation and drives an execution device to realize high-precision positioning and stable control under severe working conditions.

Methods for training a series of neural networks to output driving behavior control parameters is disclosed. The training dataset for the neural networks includes sensor-based vehicle driving recordings that may be categorized by geographical area, by qualitative driving behaviors, or by some combination, such that various training data subsets are used to train the series of neural networks. By learning either city-specific driving behavior control parameters, qualitative driving behavior specific driving behavior control parameters, or both, the resulting parameters may then be provided to a motion planning model for use in modeling predictive control for an autonomous vehicle. Rather than relying on XYZ trajectories of agent vehicles when planning future trajectories of the ego vehicle, the motion planning model is adaptive, due to the use of the learned driving behavior control parameters.

A motion control method for an adaptive self-reconfigurable pipeline robot based on environmental perception includes: acquiring internal images of the pipeline for scene recognition, segmenting planar surfaces and curved surfaces in the images according to recognition results, and extracting boundary lines of the pipeline; calculating a straight-pipe width, a bent-pipe curvature, a slope angle, and a step height to analyze passability of the robot; designing a path planner and a swing-arm planner to generate a reference trajectory and a swing-arm angle sequence of the robot, performing smoothing, and inputting the reference trajectory and the swing-arm angle sequence into a model predictive control (MPC) motion controller; estimating a position and state of the robot through an Error State Kalman Filter (ESKF) algorithm, and inputting estimation results and collision warning signals into the MPC motion controller; and finally outputting a signal for control of a motor and a swing-arm motor.

The invention relates to a multi-time-scale toughness scheduling strategy of a multi-energy complementary system under an extreme high temperature condition in optimal scheduling of a power system. In order to solve the problems of load rising caused by high temperature, derating of a source network and difficulty in guaranteeing power supply safety by traditional economic dispatching, a source-network-load-storage temperature effect model of photovoltaic, thermal power, a power transmission transformer and a load is constructed, and a day-ahead, day-intraday and real-time three-layer collaborative optimization framework is embedded; weighted unsupplied electric quantity is used as a toughness index, node vulnerability and load grade weight are combined, dictionary order optimization is adopted before the day, prediction deviation is corrected in a rolling mode within the day, toughness-oriented model prediction control and rolling supply stop window constraint are adopted in real time, and conventional unit, energy storage and layered demand response are cooperatively scheduled. Therefore, load loss is reduced and new energy is abandoned in an extreme high-temperature scene, and the power supply guarantee capability of key nodes and important loads and the overall toughness and economical efficiency of the system are improved.

The invention relates to the technical field of intelligent control, and discloses a magneto-rheological damper regulation and control method and system based on machine learning, and the method comprises the following steps: S1, collecting the multi-dimensional state parameters of a system where a magneto-rheological damper is located in real time, the multi-dimensional state parameters comprising a vibration excitation parameter, a damper output parameter and an environment influence parameter; s2, a magneto-rheological damper dynamic characteristic mapping model based on deep learning is constructed, the mapping model takes multi-dimensional state parameters collected historically and corresponding control currents as training samples, and key characteristic weights are strengthened through an attention mechanism; and S3, based on the currently collected multi-dimensional state parameters. The time-varying hysteretic characteristics of the magnetorheological fluid are accurately modeled through an improved LSTM network fused with an attention mechanism, and a collaborative decision-making mechanism of reinforcement learning and model prediction control is combined, so that the problems of nonlinearity and time-varying characteristics which are difficult to deal with by a traditional control method are effectively solved.

The invention relates to an anti-interference speed control method for a permanent magnet synchronous motor, in particular to the technical field of electrical engineering, and effectively solves the problem that the control performance of the permanent magnet synchronous motor is degraded due to model parameter drift and external load sudden change under complex working conditions. According to the method, the high robustness of sliding mode control and the rolling optimization characteristic of model prediction control are creatively fused, and an adaptive observer is introduced to estimate the system state and lumped disturbance online, so that the real-time feedforward compensation and active suppression of parameter uncertainty and disturbance are realized; according to the method, the dynamic response speed and the steady-state precision of the system are remarkably improved, the rotating speed fluctuation and the torque ripple are effectively inhibited, meanwhile, controller parameters are adaptively adjusted through an intelligent learning mechanism, the stability and the adaptability in long-term operation are ensured, and the method is suitable for large-scale popularization and application. The limitation that a traditional control strategy depends on an accurate model and the disturbance boundary is unknown is overcome fundamentally, and high-performance and high-robustness speed control is achieved.

The invention relates to an unmanned aerial vehicle trajectory tracking control method based on model prediction and preset performance constraint, and the method proposes to introduce Lyapunov stability constraint into a model prediction control framework and integrate a preset performance control mechanism, thereby achieving the unification of performance constraint and system stability analysis. Comprising the following steps: establishing a nonlinear system model based on unmanned aerial vehicle dynamics; position errors and attitude errors are defined, a preset performance function is constructed, and errors with performance constraints are converted into unconstrained errors through error normalization and nonlinear transformation; establishing a model prediction optimization problem on the premise of considering input saturation and stability constraints; designing an auxiliary control law based on the transformation error to construct a stability constraint; it is proved that the control strategy can ensure that errors meet preset performance constraints and system local asymptotic stability. According to the invention, stable and reliable trajectory tracking control of the unmanned aerial vehicle system can be realized, and the method has high tracking precision and good dynamic performance.

The invention belongs to the technical field of electric power energy storage systems, and discloses a multi-element energy storage cooperative adjustment method, system, device and medium, and the method comprises the steps: constructing a discrete time dynamic equation based on the power system frequency response characteristics of a multi-element energy storage system; constructing a cost function of model prediction control according to a state matrix output by the discrete time dynamic equation, and solving the cost function to obtain a model prediction controller; outputting a target value through a deep learning model, substituting the target value into the model prediction controller, and generating a learnable model prediction controller; and calculating a prediction trajectory by using the learnable model prediction controller, comparing the prediction trajectory with a reference prediction trajectory obtained by pre-calculation, and updating deep learning model parameters according to a prediction trajectory comparison result. According to the learnable model prediction controller provided by the invention, the reference target of the model prediction controller is adaptively adjusted based on the deep learning model, so that the control effect of the model prediction controller is improved.

The invention relates to the technical field of motor control, discloses a direct current brushless motor control method and system based on current prediction, and aims to solve the problems of large torque ripple, low efficiency and poor stability caused by current loop lag in the prior art. The method comprises the following steps: acquiring a motor operation state signal in real time; determining a sector and an electrical angular velocity based on the rotor position and the rotational speed; inputting related parameters into the mixed current prediction model to obtain a three-phase current prediction value of the next period; a prediction error is calculated in combination with a current instruction, and an optimal voltage vector enabling a cost function to be minimum is solved through a model prediction control algorithm; and finally, a space vector pulse width modulation signal is generated to drive an inverter. According to the method, advanced control is realized by fusing a physical model and a data-driven prediction mechanism, the torque ripple is remarkably reduced, and the energy efficiency and robustness are improved.

The invention relates to the technical field of environmental protection, in particular to an intercepting well model prediction control method and system. Collecting multi-source information data, and performing weighting after data alignment to obtain a multi-source information set; based on the multi-source information set, constructing a hybrid model comprising a hydraulic model and a water quality model; automatically updating the hybrid model based on the real-time multi-source information set, and outputting state data; establishing a multi-objective optimization function for the water quality model, and solving to obtain a control parameter optimal solution set by taking the sewage overflow pollution load, the waterlogging risk data, the inflow water quality fluctuation range of the sewage treatment plant and the weighted minimum value of the system energy consumption as objective functions; and on the basis of the state data and the control parameter optimal solution set, rolling optimization control is implemented. Through fusion of multi-source prediction, dynamic adaptive modeling, multi-target collaborative optimization and closed-loop rolling control, the overall efficiency of the urban drainage system is significantly improved, and the operation level of the system is comprehensively improved.

The invention discloses an aspheric surface processing intelligent feedback control system based on digital twinning, and the system comprises a digital twinning modeling and baseline calibration module which is used for building an aspheric surface processing digital twinning body and generating a baseline; the twinborn update and virtual-real residual calculation module is used for calculating virtual-real residual update digital twinborn bodies; the reinforcement learning candidate strategy generation module is used for generating reinforcement learning candidate strategies through the reinforcement learning strategy network; the model predictive control optimization module is used for establishing a model predictive control optimization problem and performing rolling prediction; the double-strategy fusion control module is used for executing virtual processing simulation and generating a control vector; and the virtual-real closed-loop adaptive convergence execution module is used for executing aspheric surface processing to realize closed-loop adaptive convergence control. According to the method, digital twinning is combined with reinforcement learning and model prediction control, intelligent optimization of aspheric surface machining is achieved, and the method has the advantages of being high in precision and stability and rapid in convergence.

The invention belongs to the technical field of energy management, and particularly relates to a light storage direct current flexible load self-evolution cooperative scheduling method, system and equipment, and the method comprises the steps: constructing a parameterized energy utility curve, quantifying the comprehensive utility of flexible load response in energy efficiency, comfort and equipment loss, and calculating the unit power marginal utility as the flexibility; establishing a multi-target collaborative scheduling model considering the time-varying carbon intensity, the electricity price and the utility curve, and solving by adopting a model predictive control and reinforcement learning mixed strategy; static and dynamic data are fused to construct a knowledge graph, and flexibility is predicted and cross-scene migration is realized through a sequence diagram neural network; and cooperatively optimizing a knowledge graph prediction result and a scheduling instruction through a Lagrangian relaxation method to form a self-evolution closed-loop control system. According to the method, flexible load refined modeling, carbon perception economic optimization scheduling and system adaptive learning are realized.

The invention discloses a multi-parameter self-adaptive optimization intelligent vehicle trajectory tracking control method in the technical field of intelligent vehicle control. The method comprises the following steps: estimating a vehicle motion state in real time according to a three-degree-of-freedom dynamic model and a sensor measurement value by adopting a self-adaptive extended Kalman filtering algorithm; based on the estimated vehicle motion state, designing and implementing a model prediction controller to perform trajectory tracking; calculating to obtain an optimal control increment sequence in a future control time domain; taking a first element of the optimal control increment sequence as an actual control instruction increment at the current moment to act on a vehicle actuator, and entering a next control period, so as to adaptively balance closed-loop trajectory tracking control of tracking precision and driving stability; according to the method, adaptive state estimation and fuzzy dynamic predictive control are fused, deep coupling of high-precision perception and intelligent decision making is achieved, and the trajectory tracking precision, the driving stability and the system robustness are remarkably improved under the complex working condition.

The invention relates to the technical field of power system control, in particular to a source network load storage collaborative management and control method and system. According to the technical scheme, the source network load storage collaborative management and control system comprises a panoramic perception and digital twinning module, a collaborative optimization decision module and a closed-loop control and execution management module; according to the method, a closed-loop self-adaptive correction mechanism based on digital twinning and model prediction control is introduced, the execution effect of an instruction, the actual response of a controlled object and latest ultra-short-term prediction data are fed back to a digital twinning model in real time, the model serves as a system synchronously evolved and continued with a physical power grid, and the real-time performance of the model is improved. The method does not depend on a preset strategy any more, instant response can be made to various disturbances inside and outside, and the effects of coping with uncertainty and maintaining safe and stable operation of the system are remarkably improved.

The invention discloses a layered intelligent trajectory tracking control method and system for an under-actuated vehicle, and belongs to the technical field of intelligent control. In order to solve the problems that in the prior art, dependency on a model is high, a reward mechanism is rigid and perspective lacks, a double-loop framework combining outer-loop model predictive control (MPC) and inner-loop near-end strategy optimization (PPO) is adopted. The outer ring MPC generates a feasible speed reference instruction and a future prediction sequence based on a kinematic model; the inner ring PPO learns a non-linear inverse mapping of speed to thrust to compensate for uncertainty. The core innovation lies in that a look-ahead-response adaptive reward (PRAR) mechanism is designed, and the mechanism comprehensively utilizes real-time pose errors and a future prediction sequence of MPC to dynamically adjust the weight of a reward function, so that the controller has both the real-time error response capability and the future task complexity prediction capability. According to the invention, the trajectory tracking precision, robustness, learning efficiency and generalization ability of the under-actuated vehicle under complex disturbance are significantly improved.

The invention provides a bottom dead center position self-adjustment control method and system for servo stamping equipment, and the method employs a double-speed cooperation architecture of a field programmable gate array (FPGA) and a micro control unit (MCU): the FPGA carries out the high-frequency collection and preprocessing of position, direction, current, temperature, vibration and acceleration signals in a bottom dead center core region, and transmits the signals to the MCU at a low time delay; the MCU executes bottom dead center reference calibration and transmission chain back clearance recognition, constructs a comprehensive error in combination with Kalman filtering state estimation, solves the compensation amount in a rolling mode based on model predictive control (MPC), and writes the compensation amount into a servo driver fine adjustment motion curve through a bus in cooperation with dynamic dead zone control, so that the position of a bottom dead center is stably converged for a long time, and the stamping precision and consistency are improved.

The invention discloses a truss robot rehearsal control method based on digital twinning, and the method comprises the following steps: S1, constructing a truss robot digital twinning system, including constructing a truss robot virtual scene and constraint, performing data synchronization and bidirectional communication, and configuring a safety rule base and a data recording / playback interface at a twinning end; s2, rehearsing a task to be executed, generating a reference trajectory and a constraint set, and automatically checking the rehearsing process according to the safety rule base to obtain the reference trajectory and the constraint set which pass the rehearsing; and S3, performing parameterized predictive control and real-time tracking on the rehearsed reference trajectory and the constraint set, and controlling a trajectory tracking error to be within a tolerance range. According to the method, a digital twin system corresponding to the physical world is constructed, Laguerre function parameterized model predictive control is introduced to realize low-dimensional rapid solution, high-precision, reproducible and high-reliability rehearsal control of the truss robot is realized, and the field debugging and operation and maintenance cost is remarkably reduced.

The invention provides a ramp energy-saving control method based on off-line speed planning and dual-mode model prediction tracking, and aims to solve the problems of insufficient precision of ramp driving energy consumption and safety cooperative control and frequent mode switching of an automatic driving vehicle. The method comprises the following steps: firstly, identifying a key road section based on high-precision road gradient data, and generating an optimal energy-saving reference speed matched with gradient characteristics in an off-line manner by adopting a dynamic planning and sequential quadratic planning hybrid optimization strategy; secondly, when the vehicle runs, relevant information is loaded after confirmation of a driver, the system takes over the longitudinal control right, two control modes are dynamically switched based on the front vehicle distance, and frequent mode switching is avoided through a hysteresis threshold value; and finally, taking the slope-fused vehicle longitudinal dynamics model as a prediction model, solving an optimal control instruction online by adopting a model prediction control algorithm, performing closed-loop execution, monitoring intervention operation of a driver, and immediately returning the driving right after the intervention operation is detected. According to the method, offline planning and online dual-mode tracking technologies are integrated, the method has the advantages of high energy consumption optimization precision, stable mode switching and good safety adaptability, and energy-saving and safe driving of the automatic driving vehicle in a ramp scene is realized.

The invention provides a generator and battery power distribution method and device based on model prediction control, and belongs to the technical field of power distribution. The method provided by the invention comprises the following steps: loading a preset dynamic model library; generating and calibrating a total load power prediction sequence based on the flight plan and the rotor aerodynamic power model; calling the dynamic model library to predict and control the rolling optimization to output the optimal power instruction sequence of the generator; in the rolling optimization execution process, bus voltage dynamic characteristics are monitored in real time, a graded response mechanism is started based on a turboshaft engine dynamic model when load sudden change occurs, and the power of a generator and the power of a battery are adjusted; in the load abrupt change response process, rolling optimization is executed again based on the adjusted power and the corresponding system state, meanwhile, feed-forward compensation is carried out on the bus voltage deviation, and the voltage is controlled to be within a stable interval set by rolling optimization by adjusting the power of the generator; and circularly executing until the flight task is finished, and determining the generator power and the battery power.

The invention provides an agricultural machine four-wheel-drive control method and system for optimizing riding comfort, and relates to the technical field of agricultural machine control, and the method comprises the steps: building a dynamic model of a distributed four-wheel-drive agricultural machine based on basic parameters; an optimization model predictive control algorithm containing constraint conditions is constructed by taking the vehicle body acceleration and the driving stability as optimization targets; solving the dynamic model to obtain the optimal tire force distribution of each wheel of the distributed four-wheel-drive agricultural machine; on the basis of a tire magic formula model, through a reverse lookup table, converting the wheel longitudinal force in each optimal tire force distribution into a target wheel slip rate; designing a slip rate tracking controller to enable the actual wheel slip rate to track the target wheel slip rate; based on a tracking result of the slip rate tracking controller, calculating an independent driving torque instruction of each wheel of the distributed four-wheel-drive agricultural machine; independent drive torque commands are executed to control each wheel drive torque to track an optimal tire force distribution.

According to the diffusion type six-degree-of-freedom pose estimation-based steel column bottom plate prizing-free downward insertion method, the performability problem of one-time prizing-free downward insertion of a steel column bottom plate under the condition that a porous array is in a limited space and disturbed is solved, a task window is established under a unified construction coordinate system, and bolt axes and hole centers are collected and registered according to array topology; predictive interference is eliminated through diffusion type six-degree-of-freedom pose estimation with insertion constraint preposed, an allowable insertion pose range tightened along with the height is generated according to clearance and safety margin, and a downward insertion channel and an insertion constraint set are constructed in a communicating mode; tubular model predictive control is established in a feasible region, bounded disturbance of wind disturbance and swing is considered, a nominal trajectory and a segmented speed limit value of a channel center are formed, input shaping swing suppression and online monitoring are implemented, and withdrawing and rapid regeneration control are performed along a channel when necessary; the method is used for installation of simultaneous sleeving of multiple holes in the steel column bottom plate, and has the beneficial effects that the minimum clearance is kept not lower than the safety margin, lateral contact and prying are avoided, and the forbidden area is not touched under the limited space and disturbance.

The invention relates to a tunnel partition illumination dynamic optimal control method and system based on traffic flow space-time distribution prediction, and belongs to the technical field of tunnel illumination energy-saving operation. The method aims to solve the problems of black hole effect caused by response lag, trailing illumination caused by rough partition and lack of pre-judgment ability in the existing control technology. According to the technical scheme, data are collected through a multi-source traffic perception layer, and advanced prediction is carried out by fusing a macroscopic and microscopic model and deep learning through a traffic flow space-time trajectory prediction layer; the dynamic partition optimization decision-making layer maps a prediction result into a virtual light packet and solves an optimal dimming instruction meeting illuminance, uniformity and vehicle speed correlation type brightness change rate constraints through model prediction control, and finally the optimal dimming instruction is output through the smooth execution and closed-loop correction layer. According to the system, the black hole effect can be fundamentally eliminated, the safety is improved, fine energy-saving control over the lamp moving along with a vehicle is achieved, the visual comfort is guaranteed, and the system has high adaptability and robustness for multiple traffic scenes.

The invention discloses an industrial park comprehensive energy management method and system based on a hierarchical system, and belongs to the technical field of energy management and automatic control. The method comprises the following steps: integrating external data, and predicting load and renewable energy power generation power by using a machine learning algorithm; making a start-stop and output plan of each energy device in the park through an MILP model; and based on short-term prediction and an intra-day scheduling plan, establishing an MPC model, solving a real-time control instruction of each energy device, and controlling operation of various energy production, conversion and storage devices. According to the method, an algorithm combining reinforcement learning and model prediction control is creatively applied, the prediction model and the cost function of MPC are adaptively adjusted on line through reinforcement learning, the equipment power is dynamically adjusted in combination with short-term rolling prediction, uncertainty is effectively dealt with, more accurate second-level power balance is achieved, and the reliability of the system is improved. And the adaptability and the operation economy of the system to high-proportion renewable energy sources are effectively improved through hierarchical collaborative optimization.

The invention provides a motor vibration noise control method and system based on modal resonance frequency prediction, and belongs to the field of motor control. The method comprises the following steps: acquiring each order of intrinsic mode frequency of the permanent magnet motor; a cost function parameter, a current constraint condition and a control target are set, and a model prediction control method is adopted to drive an inverter to operate, specifically, the current operation state quantity of the permanent magnet motor is collected; predicting a state response in a future finite time domain based on the operation state quantity; constructing a value function, and evaluating and optimizing a state change result; and selecting an optimal voltage vector, generating a pulse signal to drive an inverter to execute, obtaining a motor high-frequency electromagnetic force wave distribution condition, comparing the motor high-frequency electromagnetic force wave distribution condition with the intrinsic mode frequency of the permanent magnet motor, and optimizing an optimal voltage vector selection logic. The problems that harmonic waves are concentrated and resonance is easily caused by a fixed switching frequency modulation method in the prior art, and a passive suppression method is high in cost and poor in flexibility are solved.