Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

33results about How to "Realize online optimization" patented technology

Aero-engine online optimization and multivariable control design method based on model predictive control

An aero-engine online optimization and multivariable control design method based on model predictive control achieves the control and online optimization of multiple variables of an aero-engine undera constraint and according to requirements of thrust and speed. A control system consists of two parts. The first part is a prediction model acquisition layer. Based on the actual working state of each control cycle and the external environmental parameters of the aero-engine, an engine small deviation linear model near different steady-state points is continuously established, and model parameters are provided for a model predictive controller. The second part is a control law decision layer. A closed-loop structure is formed by the model predictive controller and an external output feedback.The model predictive controller, based on an engine model in the current state, a control command and relevant constraint limits, determines the output of the controller at the next moment by solvinga linear optimization problem. The external output feedback introduces the aero-engine actual output into the decision on future controlled quantity of the controller to compensate for the influenceof model mismatch and external disturbances.
Owner:DALIAN UNIV OF TECH

Adaptive cruise control method based on approximate policy iteration

The invention discloses an adaptive cruise control method based on approximate policy iteration. The adaptive cruise control method comprises the steps of (1), collecting samples; (2), learning on the samples by using an approximate policy iteration algorithm to obtain an approximately optimal policy; (3), optimizing PI controller parameters online in the cruise control, namely, optimizing the PI controller parameters online in a data driving mode by using the approximately optimal policy, so that the cruise control can achieve expected performances. The adaptive cruise control method has the advantages that the principle is simple, online optimization can be achieved, control performances can be improved, and the like.
Owner:NAT UNIV OF DEFENSE TECH

Time series prediction and intelligent control combined online parameter adjustment method and system

The invention discloses a time series prediction-based wavelet neural network online PID adjustment method and a system using the same. The method specifically comprises the steps of initiating the parameters, computing the control parameters and rectifying the online adjustment parameters, computing the control amount, computing or acquiring the system output and computing the prediction result; the system specifically comprises a control decision device, an online adjuster, a control executer, a controlled object, an online predictor, a control perturbation source and a prediction perturbation source; the control decision device is used for realizing the parameter initiation; the online adjuster is used for computing the control parameters and rectifying the online adjustment algorithm parameters; the control executer is used for computing the control amount; the online predictor is used for computing the prediction result; and the control decision device is also used for judging whether the algorithm is finished. According to the method, the wavelet neural network and the classic control method are combined to solve the problem of dependence on the parameter configuration work before the system operates in the control field, so that the control system has the effects of prediction, learning, online parameter optimization and self-adaptation.
Owner:BEIJING UNIV OF TECH

Cooperative robot compliance force control method and system

The invention discloses a cooperative robot compliance force control method and system. The method comprises the steps that a state variable of a robot is obtained and initialized; a current rotationmatrix is obtained based on the initialized state variable; current state feedback information of the robot is read based on the current rotation matrix; equality constraints of compliance force control and inequality constraints of joint angle, joint angular velocity and joint moment in a robot system are established based on the current state feedback information; a joint torque function is rewritten, and a final constraint optimization model is obtained; the state variable and control torque in the final constraint optimization model are updated based on a dynamic neural network model; andwhether current time is longer than task time or not is judged, if yes, compliance force control is ended, and otherwise, the current rotation matrix is returned. In the method, high-precision force control in the contact force direction and motion control in the free movement direction can be realized at the same time.
Owner:INST OF INTELLIGENT MFG GUANGDONG ACAD OF SCI

Self-adaption steering system of double-crawler traveler unit and realization method of system

The invention discloses a self-adaption steering system of a double-crawler traveler unit and a realization method of the system. The self-adaption steering system comprises a GPS (global position system) receiver, an optical-electricity encoder set, a data acquisition card, an industrial personal computer, a D / A (digital / analogue) conversion unit, a drive motor control unit and a power supply, wherein the optical-electricity encoder set is connected with the data acquisition card; the output ends of the GPS receiver and the data acquisition card are connected with the input end of the industrial personal computer, and the outer put end of the industrial personal computer is connected with the input end of the D / A conversion unit; the output end of the D / A conversion unit is connected with a drive motor control unit; the power supply supplies power for the whole system. According to the self-adaption steering system of the double-crawler traveler unit and the realization method of the system, the situations of slippage and trackslip generated when the double crawler unit steers are solved, and the safety and the working efficiency of open-cast mining machines are improved; by utilizing fuzzy neural network technologies, the actual steering radius of the double-crawler traveler unit is matched with the steering radius required by the theory by controlling a drive motor of the double-crawler traveler unit, so as to realize the intelligent steering.
Owner:JILIN UNIV

Hydraulic support electro-hydraulic adaptive control system based on BP neural network model

The invention provides a hydraulic support electro-hydraulic adaptive control system based on a BP neural network model. A sensor detects working state parameters of a hydraulic support and environmental state parameters of the working face; the BP neural network model receives the working state parameters of the hydraulic support, the environmental state parameters of the working face, operationparameters of a coal mining machine and liquid supply parameters of a pump station, and determines ideal control target parameters and outputs the ideal control target parameters; an adaptive regulator obtains the error value between the ideal control target parameters and the working state parameters of the hydraulic support; and a support controller obtains the error value, the operation parameters of the coal mining machine and the liquid supply parameters of the pump station to determine action parameters of the hydraulic support, and thus the action of the hydraulic support is controlled.According to the hydraulic support electro-hydraulic adaptive control system, by analyzing the main factors affecting control over the hydraulic support in the working face, the BP neural network model of the hydraulic support system is constructed, by combining with the adaptive regulator, on-line optimization of the hydraulic support electro-hydraulic control system is achieved, and the adaptability of the hydraulic support electro-hydraulic control system is improved to the uttermost extent.
Owner:BEIJING TIANMA INTELLIGENT CONTROL TECH CO LTD +1

Multi-robot cooperative path planning method

The invention relates to the field of robot path planning and particularly relates to a multi-robot cooperative path planning method. A workpiece is provided, a main robot and a slave robot are defined, and the main information of the main robot and the slave information of the slave robot are acquired; the main robot adopts an active vision mode to acquire the information of the workpiece; according to the main information and the slave information, a robot model is built, and an environment model is built according to the workpiece information; according to the robot model and the environment model, the main robot determines the working tasks and the working paths of the main robot and the slave robot; and the main robot and the slave robot execute the working tasks according to the working paths. A three-dimensional object is intelligently identified through a binocular active vision system, which is not limited to features of the color and the shape and the like of the object. A sectional path planning technology is adopted, the path optimization efficiency is improved, a handshake collision avoidance problem in multi-robot superimposed motion can be solved, and dynamic adjustment of each joint and online optimization of the path during the multi-robot processing process can be realized.
Owner:SHANGHAI ELECTRICGROUP CORP

SLAM back-end track optimizing method based on pose chain model

InactiveCN107272673ASolve the problem of slow optimization speedMeet online optimization needsPosition/course control in two dimensionsNODALTrajectory optimization
The invention relates to the technical field of a full automatic movement robot, and particularly to an SLAM back-end track optimizing method based on a pose chain model. An SLAM is thought as a key for realizing the full automatic movement robot and is mainly composed of a frontend preprocessing part and a backend optimizing part. The frontend preprocessing part supplies an initial estimated map and position information through analyzing and integrating various kinds of sensor data. The backend optimizing part utilizes a picture model for describing initial estimation and probability restriction and utilizes a most optimized method for optimizing the initial estimation for realizing higher-precision mapping and positioning. According to the method, the pose chain model with a restrict time sequence relation between nodes is introduced; a sparse characteristic of the pose chain model is utilized for settling a problem of online real-time optimization which cannot be realized by common SLAM backend optimization technology; furthermore a requirement for high application precision can be satisfied; and a quick and effective settling method is supplied for settling an SLAM backend optimizing problem.
Owner:SUN YAT SEN UNIV

Asteroid detection low thrust transfer trajectory optimization method based on successive convex programming

The invention discloses an asteroid detection low thrust transfer trajectory optimization method based on successive convex programming, and belongs to the technical field of aerospace. The implementation method comprises the following steps of: establishing an improved spring equinox kinetic model for low thrust transfer of an asteroid probe; according to the dynamic characteristics of low thrusttransfer, giving constraints and optimization performance indexes of a low thrust trajectory optimization problem; giving a specific form of a low thrust interstellar transfer trajectory optimizationproblem; performing convexification of the problem of non-linear low thrust transfer through dynamic linearization and non-linear equality constraint relaxation; converting the continuous optimal control problem after the convexity into a convex optimization problem through numerical integration; and taking a convex sub-problem as an inner link of each step of iteration, and quickly performing solving to obtain an optimal asteroid detection low thrust transfer trajectory in a limited step number by using a successive approximation strategy, so that the online optimization of the low thrust trajectory can be achieved on the premise of ensuring the optimality and precision of the low thrust trajectory. The asteroid detection low thrust transfer trajectory optimization method is strong in robustness, high in repeatability and high in flexibility.
Owner:BEIJING INSTITUTE OF TECHNOLOGYGY

Real-time benchmarking optimization method for multi-level power plant

PendingCN111027744AExpanding the scope of online historical optimizationExpand the scope of optimizationForecastingSystems intergating technologiesPower stationAlgorithm
The embodiment of the invention discloses a real-time benchmarking optimization method for a multi-level power plant, and particularly relates to the field of benchmarking optimization algorithms, andthe method comprises the steps: building an index system template; establishing a benchmark library, and establishing transverse and longitudinal benchmark libraries according to historical data andsimilar objects; obtaining a marker post; finding a deviation according to the benchmark, guiding optimization of the deviation, finding associated factors through mechanism analysis, locking main deviation factors through main factor analysis, displaying adjustable parameters through reinforced analysis, and providing degradation reminding; analyzing a benchmarking result, and perfecting a benchmarking optimization knowledge base, so that benchmarking is more accurate and effective; carrying out feedback and optimization, checking whether optimization guidance is effective or not, further optimizing the benchmark, and enriching knowledge and factor analysis of the optimization guidance. According to the embodiment of the invention, the method can solve the problem that there is no lateralcomparison and optimization guidance because a conventional power plant benchmarking method employs static benchmarking, and can achieve the real-time benchmarking, benchmarking and optimization combination, mathematics and mechanism combination, and lateral and longitudinal benchmarking combination.
Owner:上海长庚信息技术股份有限公司

Online optimization method for secondary side water outlet temperature of central air-conditioning chilled water heat exchanger

The invention discloses an online optimization method for the secondary side water outlet temperature of a central air-conditioning chilled water heat exchanger. The online optimization method comprises the steps of (1) acquiring the temperature data and cooling load data measured in a central air-conditioning chilled water distribution system at the current moment online; (2) setting the search range and the search step size of the secondary side water outlet temperature set value of the heat exchanger and generating all possible alternative temperature set values at the next moment; (3) establishing a prediction model, calculating the operation energy consumption of a primary side water pump of the heat exchanger and the operation energy consumption of a secondary side water pump of theheat exchanger respectively and adding the operation energy consumption of the primary side water pump of the heat exchanger and the operation energy consumption of the secondary side water pump of the heat exchanger together to obtain the total energy consumption of the water pumps; and (4) determining the optimal secondary side temperature set value of the heat exchanger at the next moment, andminimizing the total energy consumption of the primary side water pump and the secondary side water pump of the heat exchanger. By establishing the prediction model, online optimizing the set value of the secondary side chilled water outlet temperature of the heat exchanger under the current cooling load working condition and minimizing the operation energy consumption of the chilled water pumpson the two sides of the heat exchanger, energy-saving operation of a central air-conditioning system is realized.
Owner:SUN YAT SEN UNIV

Current synchronous control method for doubly salient brushless DC motor

The invention discloses a current synchronous control method for a doubly salient brushless DC motor, and relates to the field of reluctance motor control. The invention comprises the following steps:an electrical angle corresponding to the current zero-crossing point is detected as the observation value of the current phase, the angle of the zero-crossing point is used as a controlled variable,and the advance commutation angle is used as the controlled variable, the feedback closed-loop control is performed, thereby realizing the automatic adjustment of the advance commutation angle and theautomatic control of the current phase, so that the current phase and the counter EMF phase keep synchronous under different excitation currents, rotational speeds and loads. The invention avoids theproblems of output torque reduction and torque ripple increase caused by current phase lag, improves the torque output performance of the motor at high rotation speed, and has important application value in multi-electric aircraft, new energy vehicle and other systems.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

Aperiodic condition-based maintenance method under condition of considering equipment detection uncertainty

The invention discloses a non-periodic condition-based maintenance method under the condition of considering equipment detection uncertainty; the method specifically comprises the steps: firstly obtaining corresponding degradation distribution according to an existing equipment degradation data set, and solving a distribution type; then assuming distribution obeyed by each parameter of degradation distribution, and obtaining prior information of the parameter by using a hypothesis testing method; assuming that a maintenance process threshold value and an adopted detection planning equation parameter are decision variables, considering that each time of detection obeys the random impact of Gaussian distribution, and establishing a non-periodic maintenance optimization model by using a semi-regeneration process; and finally, adopting a particle swarm algorithm based on a catastrophe strategy to obtain a related optimal value solution of a decision variable, and updating posterior parameters of the model through a Bayesian theory. According to the method, the influence of the cost of manpower, material resources and the like required by continuous monitoring and periodic detection of a traditional maintenance strategy is reduced; meanwhile, the influence of uncertainty brought by detection is considered, and technical reference is provided for condition-based maintenance detection, corresponding prediction, health management and the like.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

Power system information physical double-layer strategy optimization method considering network attack influence

The invention discloses a power system information physical double-layer strategy optimization method considering network attack influence, and belongs to the technical field of power generation, power transformation or power distribution. The method comprises the following steps: modeling an electric power information physical system based on an incidence matrix method; forming a mathematical vector by using a known network attack mechanism, and analyzing attack influence based on a power information physical system association model; on the basis of the influence of attacks on the physical side and the information side of a power system, an existing control strategy is judged firstly for the safety and stability control service of the power system, and if the judgment result is feasible,execution is performed; if the method is not feasible, optimizing a load reduction optimization strategy of a physical side according to the attack influence; and optimizing the strategy transmissionpath on the basis of upper-layer optimization, and finally obtaining an information physical coordination optimal control strategy of the network attack scene. According to the invention, an information physical cooperative control strategy under a network attack can be formed, and a better control effect is realized.
Owner:SOUTHEAST UNIV +1

System and method for bar flying shearing optimization control based on machine vision

The present invention discloses a system for bar flying shearing optimization control based on machine vision. The system comprises an image collection subsystem, a fuzzy controller and a flying shear regulation subsystem. The image collection subsystem comprises a plurality of cameras arranged at the rear portions of flying shears and light sources respectively matching each camera, and each camera is in communication connection with the image processing module; the fuzzy controller is in communication connection with the image processing module and is configured to receive image information completely processed by the image processing module, generate a flying shear regulation decision and transmit the flying shear regulation decision to the flying shear regulation subsystem; and the flying shear regulation subsystem comprises a control mechanism configured to control a flying shear driving mechanism or transmission mechanism and regulate the movement locus and the moment of the flying shearing. The work of the flying shears changes an open loop mode to a closed-loop work mode to realize the online optimization of the bar shearing work.
Owner:HUATIAN ENG & TECH CORP MCC +1

Laser output power optimization method based on variable-transmittance endoscope

InactiveCN105375255ARealize online optimizationAvoid increased development costsLaser detailsPhysicsResonator
The invention relates to a laser output power optimization method based on a variable-transmittance endoscope, and belongs to the technical field of laser. The method comprises the following specific steps: (1) calculating the output power of a needed pump source according to the requirement of the design index on the laser output characteristic; (2) calculating the optimal transmittance values under different pump power according to the range of pump power and the optimal transmittance formula; (3) determining the coating requirement of the variable-transmittance endoscope according to the tuning characteristics of the oscillation wavelength of a laser; (4) making the variable-transmittance endoscope according to the coating requirement; (5) adopting the selected pump source and the variable-transmittance endoscope to build a laser system; (6) setting the pump power, and adjusting a laser resonator to obtain laser output; (7) tuning the laser wavelength; and (8) making the laser work stably at the optimal transmittance to obtain the maximum output power, thus completing online optimization of the output power of the laser. According to the invention, there is no need to insert elements into the cavity, and the loss is low. The optimization method is simple, reliable in work, convenient in operation, and wide in adaptability.
Owner:BEIJING INSTITUTE OF TECHNOLOGYGY

Adaptive Steering System and Implementation Method of Dual-crawler Traveling Device

The invention discloses a self-adaption steering system of a double-crawler traveler unit and a realization method of the system. The self-adaption steering system comprises a GPS (global position system) receiver, an optical-electricity encoder set, a data acquisition card, an industrial personal computer, a D / A (digital / analogue) conversion unit, a drive motor control unit and a power supply, wherein the optical-electricity encoder set is connected with the data acquisition card; the output ends of the GPS receiver and the data acquisition card are connected with the input end of the industrial personal computer, and the outer put end of the industrial personal computer is connected with the input end of the D / A conversion unit; the output end of the D / A conversion unit is connected with a drive motor control unit; the power supply supplies power for the whole system. According to the self-adaption steering system of the double-crawler traveler unit and the realization method of the system, the situations of slippage and trackslip generated when the double crawler unit steers are solved, and the safety and the working efficiency of open-cast mining machines are improved; by utilizing fuzzy neural network technologies, the actual steering radius of the double-crawler traveler unit is matched with the steering radius required by the theory by controlling a drive motor of the double-crawler traveler unit, so as to realize the intelligent steering.
Owner:JILIN UNIV

Distributed coordination control optimization method for an urban rail transit ground super-capacitor energy storage system

The invention provides a distributed coordination control optimization method for an urban rail transit ground super-capacitor energy storage system, and belongs to the technical field of urban rail transit super-capacitor energy storage system control. The method comprises the steps of obtaining an SOC state of a super-capacitor, the state of a substation and the operation state of a train, and constructing a state set; taking the super-capacitor of each substation as an energy storage agent, and determining a revenue function of each energy storage agent according to the energy flow theory analysis of a traction power supply system and a multi-objective coordination optimization function; constructing a multi-agent dynamic game model, and solving and optimizing the distributed coordination control of the ground super-capacitor energy storage system by combining a distributed Q learning algorithm based on the model. According to the invention, the distributed independent control is carried out on each energy storage system, so that the calculation complexity is effectively reduced and the reliability of a control strategy is improved. The dynamic cooperative game theory and the reinforcement learning theory are combined. The game equilibrium point efficiency is effectively improved. Therefore, the online optimization of the overall energy saving effect of the whole line energystorage system can be achieved.
Owner:BEIJING JIAOTONG UNIV +1

Medical oxygen producing equipment and its control method

The medical oxygen production equipment includes air compressor, air storage tank, freeze drying machine, oxygen producing machine, oxygen storage tank, solenoid valves, etc. connected successively. The oxygen producing machine includes absorbing tower, multi-way rotary distributing valve, control solenoid valve, oxygen producing valve, exhaust valve, oxygen determining valve, cylinder and oxygen buffer tank. There are separator and water-separating air filter in the air path between the freeze drying machine and the oxygen producing machine. There is also a controller connected electrically to the constituent parts. The medical oxygen producing equipment of the present invention is small, intelligently controlled and high in efficiency and may be used widely in hospital and in field.
Owner:SANITARY EQUIP INST ACAD OF MILITARY MEDICAL SCI PLA

Distributed subgradient algorithm-based optimal control method for reactive power of power system

The invention provides a distributed subgradient algorithm-based optimal control method for a reactive power of a power system. Reactive power distribution of the power system is optimized and determined by a distributed subgradient algorithm; and distribution control on the reactive power is executed according to an optimal solution. By the distributed subgradient algorithm-based optimal control method for the reactive power of the power system, the probability of a single-point failure under centralized control and distributed control can be reduced; the loss of the power system is reduced when the running state of the power system is improved; and the optimal control method can be flexibly applied to the power systems with different scales and topological structures and is not disturbed by certain specific errors.
Owner:NANJING UNIV OF POSTS & TELECOMM

Optimization method of small thrust transfer trajectory for asteroid detection based on successive convex programming

The invention discloses a small-thrust transfer trajectory optimization method for asteroid detection based on successive convex programming, which belongs to the field of aerospace technology. The realization method of the invention is as follows: establishing an improved vernal equinox dynamics model for the small thrust transfer of the asteroid probe. According to the dynamic characteristics of low-thrust transfer, the constraints and optimization performance indexes of the low-thrust trajectory optimization problem are given. The specific form of the low-thrust interstellar transfer trajectory optimization problem is given. The nonlinear small thrust transfer problem is convexized by dynamic linearization and nonlinear equality constraint relaxation. The continuous optimal control problem after convexization is transformed into a convex optimization problem by numerical integration. Taking the sub-problem after convexization as the inner link of each iteration step, the optimal small-thrust transfer trajectory for asteroid detection can be obtained quickly by using the successive approximation strategy in a limited number of steps, that is, the optimality and accuracy of the low-thrust trajectory can be guaranteed. Under this condition, the online optimization of the low-thrust trajectory is realized. The invention has strong robustness, high repeatability and high flexibility.
Owner:BEIJING INSTITUTE OF TECHNOLOGYGY

Distributed coordinated control optimization method for urban rail transit ground supercapacitor energy storage system

The invention provides a distributed coordinated control optimization method for an urban rail transit ground supercapacitor energy storage system, and belongs to the technical field of urban rail transit supercapacitor energy storage system control. This method obtains the SOC state of the supercapacitor, the state of the substation and the running state of the train, and constructs a state set; takes the supercapacitor of each substation as an energy storage agent, and analyzes the energy flow theory and multi-objective coordination optimization of the traction power supply system The function determines the income function of each energy storage agent; constructs a multi-agent dynamic game model, based on this model, combines the distributed Q-learning algorithm to solve and optimize the distributed coordinated control of the ground supercapacitor energy storage system. The invention performs distributed and independent control on each energy storage system, effectively reduces the computational complexity, and improves the reliability of the control strategy; combines the dynamic cooperative game theory and the reinforcement learning theory, and the efficiency of the game equilibrium point is effectively improved. Therefore, it can Realize the online optimization of the overall energy-saving effect of the full-line energy storage system.
Owner:BEIJING JIAOTONG UNIV +1

Electro-hydraulic adaptive control system of hydraulic support based on bp neural network model

The invention provides a hydraulic support electro-hydraulic adaptive control system based on a BP neural network model. A sensor detects working state parameters of a hydraulic support and environmental state parameters of the working face; the BP neural network model receives the working state parameters of the hydraulic support, the environmental state parameters of the working face, operationparameters of a coal mining machine and liquid supply parameters of a pump station, and determines ideal control target parameters and outputs the ideal control target parameters; an adaptive regulator obtains the error value between the ideal control target parameters and the working state parameters of the hydraulic support; and a support controller obtains the error value, the operation parameters of the coal mining machine and the liquid supply parameters of the pump station to determine action parameters of the hydraulic support, and thus the action of the hydraulic support is controlled.According to the hydraulic support electro-hydraulic adaptive control system, by analyzing the main factors affecting control over the hydraulic support in the working face, the BP neural network model of the hydraulic support system is constructed, by combining with the adaptive regulator, on-line optimization of the hydraulic support electro-hydraulic control system is achieved, and the adaptability of the hydraulic support electro-hydraulic control system is improved to the uttermost extent.
Owner:BEIJING TIANMA INTELLIGENT CONTROL TECH CO LTD +1

Intelligent PID controller online optimization method and system thereof

InactiveCN113467225AAccelerate the speed of parameter convergenceImprove algorithm accuracyControllers with particular characteristicsTotal factory controlEngineering optimizationFitness function
The invention provides an intelligent PID controller online optimization method and system thereof. The method comprises the steps that a time-varying high-order linear discrete parameter model is initialized, model parameters are obtained in real time through a reliable recursion online identification algorithm, and modeling work suitable for the flow industrial process is completed. A real-time high-order model is used as a controlled object, and a PID controller is designed in a closed loop. The specific design method comprises the following steps: based on a given fitness function, carrying out PID controller parameter optimization by adopting an improved particle swarm algorithm, and finally obtaining a global optimal solution of PID controller parameters. When the working condition is changed (model parameters are changed) or the slow rate updating moment is reached, the PID controller parameters are optimized again so as to cope with the condition of working condition change, and control engineering optimization is achieved at the same time. The intelligent PID controller online optimization method and system provided by the invention are wide in application range, high in adaptability, long in life cycle and excellent in control effect.
Owner:王珠 +1

An online optimization and multivariable control design method for aeroengine based on model prediction

An aero-engine online optimization and multi-variable control design method based on model predictive control, which realizes the control and online optimization of multiple aero-engine variables according to requirements such as thrust and rotational speed under satisfying constraints. The control system consists of two parts: the first part is the prediction model acquisition layer, based on the actual working state of each control cycle of the aeroengine and the external environmental parameters, the engine small deviation linear model near different steady-state points is continuously established, and the model parameters Provided to the controller; the second part is the control law decision-making layer, which is a closed-loop structure composed of a model predictive controller and external output feedback. The model predictive controller is based on the engine model in the current state, control instructions and related constraints, by solving The linear optimization problem determines the output of the controller at the next moment, and the external output feedback introduces the actual output of the aeroengine into the decision of the controller for the future control quantity to compensate for the influence of model mismatch and external disturbance.
Owner:DALIAN UNIV OF TECH

Expert control system and control method based on batch coating machine

The invention discloses an expert control system based on a batch type coating machine. The system comprises a coating machine, an image detection system and an expert system. The expert system consists of a control cabinet and a display screen; a human-computer interaction interface, a knowledge base module, an inference engine module, a feedback self-learning module and a control center are arranged in the control cabinet; the control center is an industrial personal computer electrically and bidirectionally connected with the human-computer interaction interface, the feedback self-learningmodule and a PLC control module of the coating machine respectively; the human-computer interaction interface is in electrical output connection with the knowledge base module; the feedback self-learning module is in electrical output connection with the inference engine module; and a signal input terminal of the feedback self-learning module is further in signal connection with a signal output terminal of an image detection system and is used for receiving the coating qualification rate fed back by the image detection system. According to the invention, the processing parameters are automatically optimized and combined for different seeds; the efficiency is improved, the dosage of a coating agent is saved, and the effect is remarkable on the premise of meeting the coating quality and qualification rate.
Owner:NANJING AGRI MECHANIZATION INST MIN OF AGRI

A Machining Deformation Control Method Based on Meta Reinforcement Learning

A processing deformation control method based on meta-reinforcement learning, which is characterized in that the processing deformation control process optimization of each part in different groups of source data is regarded as a task, a reinforcement learning model is established for each task, and the workpiece processing is divided into For several processing steps, the processing state of the workpiece is taken as the state, the process selection of the next processing step is used as the action, and the next processing state and the subsequent processing state are used as the basis for designing the reward function; based on the meta-learning method, each reinforcement learning model is used as The base model, through the collaborative training of the base model and the meta-model through the source data; when faced with a new processing task, fine-tuning the meta-model through a small amount of sample data of the new task to obtain a reinforcement learning model adapted to the optimization of the machining deformation control process for the new task. The invention improves the effect of deformation control, can realize online optimization of processing technology, and reduces the demand for actual processing technology data.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products