206 results about "Optimum control" patented technology

The invention discloses a cable inspection robot attitude control method based on MPC and ADRC fusion, and the method comprises the steps: firstly, building a model prediction control (MPC) model, carrying out the prediction of the future state of a robot, solving an optimal control problem, and obtaining initial control input for achieving the internal dynamic compensation; secondly, an extended state observer (ESO) in an auto-disturbance rejection control (ADRC) model is adopted, and external disturbance is estimated in real time and used for compensating control input; thirdly, a fuzzy self-adaptive module based on fuzzy PID is introduced, the attitude error, the attitude error change rate and regeneration disturbance intensity generated based on estimation disturbance are collected in real time, the MPC weight and the ESO gain are dynamically adjusted, and the response speed and robustness of the system under variable working conditions are improved. According to the hierarchical control scheme, the defect that an existing single control method is difficult to keep the optimal control effect under variable working conditions is effectively overcome, and technical guarantee is provided for stable operation of the cable inspection robot in a high-risk and high-complexity environment.

A system for controlling motion of an articulated vehicle with one or multiple trailers is described. The system is configured to infer the state of a vehicle, determine a motion path with forward motions and backward motions for the vehicle based on the state, and formulate an optimal control problem for optimizing the motion path. The optimal control problem comprises an integral tracking error function indicating integral tracking error based on motion cusps relating to the motion path. The motion cusps indicate switching between forward motion and backward motion. The motion path is optimized over a prediction horizon based on solving the optimal control problem. A control command is generated for the vehicle based on the optimized motion path and a vehicle model, and the motion of the articulated vehicle is controlled based on the control command thereby changing its state.

The invention discloses a heat-pump water heater temperature control method based on artificial intelligence, relates to the technical field of heat-pump water heater temperature control, and aims to solve the problem that the COP (coefficient of performance) is reduced due to a low-temperature environment, the exhaust temperature of a compressor and the opening degree of an expansion valve are optimized in real time through a GA (genetic algorithm), and operating parameters of a heat-pump water heater are dynamically adjusted by taking COP maximization as a target; the operation frequency of a compressor and the flow of a water pump are dynamically adjusted through fuzzy control logic in combination with a GA optimization result, the current water temperature and the temperature set by a user, the stability of the water supply temperature is guaranteed, an optimal control strategy is calculated through defuzzification, and the adaptability under different environment conditions is improved; an ANN is adopted to learn and predict a user behavior pattern, an LSTM network is utilized to analyze time sequences of historical water consumption data, target temperature and environment temperature, future water consumption peak and temperature requirements are predicted, a preheating function is started in advance, and insufficient hot water supply in the water consumption peak is avoided.

The invention discloses a multi-parameter cooperative temperature control system of an energy-saving industrial oven, and relates to the technical field of temperature control of industrial ovens, load data in the oven are collected in real time through a high-precision sensor, and a Kalman filter is used for cleaning, calibrating and filtering environmental noise and drift to obtain smooth and stable data; analyzing a real-time load based on a support vector regression model, capturing a nonlinear relation in combination with a radial basis function kernel, and predicting temperature recovery time and expected energy consumption; a reinforcement learning algorithm is adopted, a high-dimensional state space is analyzed through a deep Q network, the heating power and the airflow speed are dynamically optimized, and optimal control parameters are output; and the control module executes the adjusted setting, monitors the temperature and the energy consumption in real time, feeds back data to a prediction model and a learning strategy, and periodically updates parameters to adapt to load and environment changes. The adaptive capacity and long-term stability are remarkably improved, and the method is suitable for industrial scenes with load change, equipment aging or environment fluctuation.

The invention discloses a model prediction variable-pitch control method, device and equipment for a floating type wind turbine generator, and relates to the technical field of wind turbine generator control, the whole model prediction variable-pitch control fully considers the characteristics of the floating type wind turbine generator, stabilizes the attitude of the generator while stabilizing the power, and improves the control accuracy of the floating type wind turbine generator. And the adaptability and the stability of the whole control process are improved. The method comprises the following steps: reading unit state data of a floating wind turbine generator under multiple working conditions, and constructing a nonlinear model under the working conditions by adopting the unit state data; constructing a linear variable parameter model corresponding to each nonlinear model by adopting the plurality of unit state data, calculating a plurality of gap values of the plurality of linear variable parameter models, and establishing a model library based on the plurality of gap values and a gap standard; determining a state-space equation according to the current wind speed and the model library, and constructing a model prediction controller based on the state-space equation; and calculating an optimal control sequence by adopting a model prediction controller, and controlling the floating wind turbine generator based on the optimal control sequence.

The invention discloses a wind power plant unit load reduction optimization method and system based on cabin type laser radar real-time wind measurement, and relates to the technical field of wind power generation. Constructing a load estimation model; performing real-time detection on a blade root bending moment predicted value sequence and a tower bottom vibration acceleration predicted value sequence, constructing a multi-objective optimization function including blade root bending moment, tower bottom vibration acceleration and power generation power, and setting a dynamic weight coefficient of the multi-objective optimization function according to three-dimensional wind field prediction sequence data; obtaining an optimal control variable through a multi-objective genetic algorithm based on the multi-objective optimization function; and according to the optimal control variable and vertical wind shearing in the three-dimensional area, differential adjustment is conducted on the pitch angle of each blade, and a personalized variable pitch angle sequence of each blade is obtained. According to the method, by establishing the optimization objective function fusing the load and the power, multi-variable collaborative optimization is achieved, and the safety and the economical efficiency of wind power plant unit operation are remarkably improved.

The invention discloses an intelligent control method and system for a deep water cooling system of a reservoir in a data center, and relates to the technical field of cooling control, and the method comprises the steps: analyzing the cooling demand distribution of the data center, constructing a demand database, constructing a water source monitoring database in combination with the temperature, the water layer depth and the water quality monitoring data of the reservoir, and storing the water source monitoring database; the method comprises the following steps: decomposing a water taking treatment process and a cooling treatment process, extracting and fitting a relationship between control parameters and a treatment effect and energy consumption, searching optimal control parameters according to cooling demand data and a process flow, and generating cooling system control information. The technical problems that an existing data center cooling system cannot be dynamically adjusted according to real-time environment changes and water source conditions, so that the cooling effect is unbalanced, and energy is wasted are solved, the control parameters are dynamically optimized through an intelligent control method in combination with the real-time cooling requirement and water source monitoring data, and the cooling efficiency is improved. The technical effects of precise cooling and energy consumption reduction are achieved.

The invention discloses a gelatin solution temperature control optimization method for donkey-hide gelatin processing, and belongs to the technical field of swarm intelligence optimization. Comprising the steps that a gelatin solution temperature closed-loop PID control system in the donkey-hide gelatin decocting process is constructed, an improved side hand spider turning optimization algorithm is configured to serve as a parameter setting core, the self-adaptive setting process of PID control parameters is executed, and a global optimal control parameter vector obtained through optimization is mapped to a donkey-hide gelatin solution temperature PID controller module. The method focuses on the PID parameter setting problem of donkey-hide gelatin liquid temperature control, introduces the improved side hand turning spider optimization algorithm as a swarm intelligence algorithm to set the donkey-hide gelatin liquid temperature PID control parameters, and can effectively overcome the defect that the side hand turning spider optimization algorithm is easy to fall into local optimum. And the temperature of the donkey-hide gelatin liquid can be controlled more excellently.

The invention relates to the technical field of tunnel lighting, and is a method for estimating the energy consumption of on-board lighting in a tunnel and the length of an optimal control section. The energy consumption estimation method comprises: obtaining geometric parameters of the tunnel, positions of lamps in the tunnel and historical traffic volume data; obtaining vehicle trajectory data based on the historical traffic volume data; establishing a one-dimensional coordinate system of the tunnel; and calculating the energy consumption of the tunnel within one day based on the one-dimensional coordinate system of the tunnel and the vehicle trajectory data. The energy consumption estimation method of the invention takes into account the distribution of historical traffic flow over time, so that the simulation scene is closer to reality and the energy consumption estimation result is more accurate. The energy consumption estimation method proposed by the invention can also evaluate the energy-saving effect under different control section lengths, thereby determining the optimal control section length, providing a more scientific basis for the intelligent lighting construction of the tunnel and maximizing the energy utilization.

The invention relates to the technical field of automobile suspension control, in particular to a control compensation method, medium and equipment based on the high-frequency hysteresis characteristic of an active suspension, and the method comprises the steps: collecting the dynamic state data of a vehicle in real time, carrying out the working condition recognition of the dynamic state data, and determining the control demand of the active suspension of the vehicle under the current working condition; establishing an active suspension model, and determining an execution boundary of an active suspension; based on the control requirement, a control strategy of the active suspension is obtained in combination with the active suspension model and hysteresis characteristics thereof, and it is ensured that the active suspension meets the execution boundary; based on the control strategy, performing multiple experiments on the active suspension model to obtain corresponding performance indexes; and based on the performance indexes, optimizing the control strategy until the active suspension reaches the optimal control performance, and obtaining the optimal control strategy. According to the method, the response hysteresis and the amplitude-frequency attenuation of the active suspension are considered in the control requirement, the active suspension is compensated, and the execution potential of an actuator of the active suspension is fully exerted.

The invention discloses a vehicle queue control method based on an improved gap strategy and a depth deterministic strategy gradient algorithm, and the method comprises the following steps: building a vehicle-to-vehicle gap strategy considering the difference between the speed of a front vehicle and the speed of a vehicle, constructing an MPC frame through the strategy, and adding the minimum safety distance between vehicles into a constraint condition of the MPC frame; adjusting parameters in the MPC framework in real time by using a trained depth deterministic strategy gradient algorithm model to obtain an optimal parameter combination in each state, and then substituting the optimal parameter combination into the MPC framework to calculate and obtain an optimal control sequence at each moment; and finally, longitudinally controlling the vehicles in the vehicle queue according to the specified control quantity in the optimal control sequence of each control period. Compared with a traditional fixed parameter MPC method, the method has the advantages that the motorcade gap error can be remarkably reduced, the stability and safety of motorcade longitudinal control are improved, and efficient and safe automatic driving motorcade management is achieved.

The invention discloses an intelligent deep peak regulation system for a coal-fired power generation unit, and particularly relates to the technical field of power generation control, and the system comprises a multi-source data collection module which carries out the real-time parallel collection of all-dimensional operation parameters through a sensing network and unit decentralized control system interface disposed at a key node, and builds a multi-modal time sequence data flow; according to the method, a foresight control strategy is formed by constructing a fusion prediction model, sensing the running state of a unit in real time and predicting the change trend of key parameters, the defect of response lag of a traditional system is effectively overcome, and the purposes of accurate load tracking and advanced regulation and control under the working condition of deep peak regulation are achieved; a global optimization decision-making mechanism is established by adopting a deep reinforcement learning algorithm, optimal control parameters are calculated in real time through the intelligent peak regulation module, a boiler, a steam turbine and an environmental protection system are dynamically coordinated, the problem of insufficient stability caused by subsystem independent control is solved, and the optimal balance of safety, stability and economic benefits is achieved.

Optimal control of multiple heating, ventilation, and air-conditioning units in an open-plan space demands fast and accurate thermodynamic modeling. Prior methods lack scalability required for effective control in large open-plan offices primarily due to air-mixing interactions. The present disclosure describes a physics-informed graph neural network (PI-GNN) to overcome these challenges. Specifically, thermodynamic interactions are modeled as edges between nodes that represent cells. Further, a modeling approach is used that allows explicit modeling of wall and window surface temperatures which are commonly ignored. The method of present disclosure utilizes PI-GNN as a state-estimator that employs a receding-horizon approach for optimal HVAC control. PI-GNNs are adapted for building HVAC control by incorporating a time-resetting strategy to handle time-dependent ambient conditions and therefore set-points. The method of the present disclosure outperforms a regular PINN model and other baseline control strategies on thermal model accuracy, computation time, energy consumption, and user comfort.

The invention relates to the technical field of power generation system control, and discloses an Agent-driven big data analysis and thermal power generation system operation control method and system, and the method comprises the steps: obtaining the operation data of a thermal power generation system; inputting the operation data into a power system intelligent agent, analyzing the operation state of the thermal power generation system, and calculating optimal control parameters for adjusting the thermal power generation system to the optimal operation state; controlling the operation of the thermal power generation system according to the optimal control parameter so as to adjust the operation state of the thermal power generation system in real time; based on a large amount of thermal power generation system operation data, the high-quality sample is rapidly extracted from the mass data through the power system intelligent agent, deep analysis of the operation state of the thermal power generation system and accurate calculation of the optimal control parameters are achieved, the control efficiency and the adjustment precision of the thermal power generation system are improved, and the practicability is high. The system is always adjusted towards the optimal operation state, and the stability and reliability of system operation are improved.

The invention relates to the technical field of car tipplers, in particular to a remote control method of an intelligent cleaning robot for a cargo compartment. Comprising the steps of generating various cleaning scenes according to historical cargo compartment parameters, and sequentially generating control models of the cleaning scenes; generating an initial cleaning plan according to the equipment parameters of the cargo compartment to be cleaned, and generating a plurality of feedback time nodes according to the initial cleaning plan; monitoring data of the cargo compartment to be cleaned are obtained according to the preset feedback time node, and whether a correction instruction is generated or not is judged according to the monitoring data; a plurality of cleaning scenes are set according to cargo compartment parameters and parameters for carrying coal, optimal control strategies under various cleaning scenes are set according to historical parameters, in the cleaning process of a to-be-cleaned cargo compartment, the to-be-cleaned cargo compartment is monitored by setting a plurality of feedback time nodes, and an initial cleaning plan is dynamically corrected according to a correction evaluation value, so that the cleaning efficiency of the to-be-cleaned cargo compartment is improved. Therefore, the cleaning quality of the to-be-cleaned carriage is ensured.

A vehicle thermal management system includes: a fluid transfer device that consumes power to perform a thermal management function, and a control unit that determines an operation mode of the fluid transfer device. In particular, the fluid transfer device operates in the determined operation mode based on an optimal control value derived using a control model for a predicted state value.

A thermal management system for a vehicle includes a fluid transfer device including a power consumption unit configured to consume power for performing the heat pump function and includes a control unit configured to control the fluid transfer device based on an optimal control value.

The invention discloses a power generation quality intelligent control method of a tidal current energy power generation system. Constructing a depth deterministic strategy gradient algorithm based on optimized learning parameters, processing a state space of the tidal current energy power generation system through the algorithm, updating network parameters of the algorithm, and obtaining system actions after processing; and judging the termination state of the current state space, and performing power generation quality intelligent control on system actions by optimizing learning parameters in real time. According to the method, real-time optimization control over the power generation voltage and frequency of the tidal current energy power generation system is achieved through deep reinforcement learning, the learning process can be effectively guided, the optimal control strategy is adjusted and converged in real time, and the method is applied to the actual tidal current energy power generation system so as to adapt to changes of the tidal current flow speed and complex ocean environments and tidal current changes; the robustness of the system is enhanced, it is ensured that the output power generation voltage and frequency meet the requirements of a power grid, the stability of power generation quality in a dynamic environment is ensured, and the overall performance is improved.

The invention provides a dimethyl sulfoxide production parameter control method and system based on reinforcement learning, and relates to the technical field of production parameter control, and the method comprises the steps: obtaining historical process operation data in a dimethyl sulfoxide production process; performing correlation analysis on the historical process operation data, and screening key control variables influencing the yield and the energy consumption; based on the historical process operation data and the key control variables, constructing a digital twinborn simulation model for providing an interaction environment for reinforcement learning; defining a state space, an action space and a reward function, and constructing a dimethyl sulfoxide production parameter control model based on reinforcement learning; based on the reward function and the digital twinborn simulation model, training and optimizing the dimethyl sulfoxide production parameter control model through a PPO algorithm, and outputting an optimal control strategy; and controlling the production parameters of dimethyl sulfoxide according to the optimal control strategy.

The present disclosure relates to an integrated control system for heat pump to optimize energy of solar power generation building, Including a computer comprising a processor and a memory within which a code for execution by the processor is stored, and the computer is configured to collect real-time data measured from at least any one of the heat pump of the solar power generation building, an external environment, a room and a photovoltaic power generation system, where interactions occur in a dynamic behavior of the heat pump; input the real-time data of before pre-set time into multiple dynamic behavior prediction models to derive an indoor air temperature prediction value, heat pump electricity consumption prediction value, and photovoltaic power generation prediction value, of after pre-set time; and search for an optimal control variable of the heat pump using the derived indoor air temperature prediction value, heat pump electricity consumption prediction value, and photovoltaic power generation prediction value.

The invention discloses an energy-saving operation control method for a desulfurization system, and relates to the field of wet flue gas desulfurization of a power plant. The method comprises the following steps: (1) establishing a clean flue gas SO2 concentration prediction model; (2) optimization control of energy-saving operation of the desulfurization system: selecting an optimal feature subset from the selected feature subset, and searching an optimal control value of the optimal feature subset under each working condition; and establishing an energy-saving operation optimization target and constraint conditions of the desulfurization system, and then adjusting operation parameters according to outlet data to ensure energy-saving operation. The method comprises the following steps: carrying out feature selection on desulfurization online operation parameters, and selecting an optimal feature subset to establish a clean flue gas SO2 concentration prediction model; by expanding the data acquisition range, introducing the deep learning algorithm and dynamically updating the data, the SO2 concentration of the purified flue gas can be predicted more accurately, and a reliable basis is provided for optimization control.

The invention discloses a closed-loop automobile crosswind stability dynamic evaluation system based on an MPC control algorithm, and belongs to the technical field of intelligent driving. According to the system, a CFD model unit obtains pneumatic six-component parameters according to a first motion state parameter and a lateral wind environment parameter of a tested automobile at a first moment; the MPC active control unit predicts the state quantity and the control quantity of the tested automobile in a plurality of time steps according to the first motion state parameter on the basis of an MPC algorithm by taking the minimum control cost as a target so as to determine a front wheel steering angle parameter corresponding to the optimal control quantity; and the MBD model unit updates the dynamic parameters of the tested automobile according to the pneumatic six-component parameters and the front wheel steering angle parameters to obtain the dynamic response parameters of the tested automobile at the second moment, and evaluates the crosswind stability of the tested automobile according to the dynamic response parameters. The system is high in reduction degree of actual conditions, and the reliability of test results and the success rate of calculation are improved.

Method for adapting the lateral acceleration of a remotely operated land vehicle to a curved trajectory. One aspect of the invention relates to a computer-implemented method (2) for adapting the lateral acceleration of a land vehicle (V) to a curved trajectory (C) on a surface, the vehicle being remotely controlled. Method (2) comprises a set of iterations for which, in each iteration, optimal longitudinal speed and optimal steering angle setpoints are obtained by solving a constrained finite-horizon optimal control problem. Figure to be published with the abstract: Figure 4.

The invention relates to the technical field of cable production, in particular to a safety early warning method and system for cable production, and the method comprises the steps: responding to the change of environmental parameters at any moment in a cable production process, taking control parameters as particles, taking the sum of production quality and production efficiency as a fitness function, and obtaining a fitness function; obtaining a globally optimal solution by using a particle swarm algorithm; and generating an early warning signal in response to the situation that the variation between the globally optimal solution and the moment control parameter is greater than an allowable variation or the stability of the globally optimal solution is less than a stability threshold. Through the technical scheme of the invention, the optimal control parameter can be quickly found, early warning is realized from two aspects of the variable quantity of the control parameter and the anti-interference capability of the optimal control parameter, and the safety and controllability of the cable production process are ensured.

A hydrogen-powered refrigeration system 900 and related intelligent and predictive control methods, comprises various subsystems integrated to create synergies and interdependencies providing high efficiency, mission anticipation and recommendations to minimize fuel consumption and increase the durability of the system while refrigerating a cargo volume during transportation at low or no carbon emissions; wherein the intelligent and predictive controls are achieved by the use of a control system based on deep neural networks that optimizes operation by anticipating the future state of the system and adjusting its configuration based on models to operate under an optimal control policy that considers external information obtained from calls to APIs linked to external information providers while ensuring cargo is maintained under conditions required or regulated as a part of the cold chain. The invention has particular application to the vehicular and multi-modal transportation of items requiring refrigeration.

The invention discloses an oil temperature monitoring and regulating method for an oil-immersed transformer, which belongs to the technical field of control optimization, and comprises the following steps: constructing an oil temperature PID control system of the oil-immersed transformer, introducing an improved candle flame optimization algorithm, and setting oil temperature PID control parameters by using the improved candle flame optimization algorithm. And setting three optimal control parameters obtained through optimization by using an improved candle flame optimization algorithm as parameters of an oil temperature PID controller in the PID control system of the oil-immersed transformer, and optimizing the oil temperature control effect of the oil-immersed transformer. According to the method, the oil temperature PID control system of the oil-immersed transformer is constructed, and the improved candle flame optimization algorithm is introduced, so that the oil temperature of the oil-immersed transformer can be recovered to be stable more quickly when working condition disturbance such as load sudden change or environment temperature change occurs, the insulation aging risk caused by long-time high-temperature operation can be reduced, and the service life of the oil-immersed transformer is prolonged. And the operation safety and reliability of the oil-immersed transformer are enhanced.

The invention discloses an intelligent vehicle switch control method and system with a self-defined function, and aims to improve the driving experience of a vehicle owner through an intelligent means, a user interacts with the system through a touch screen, voice control, gesture recognition, physical buttons and other modes, and precise control over vehicle windows, seat heating, air conditioners and other equipment is achieved. Through sensor data of temperature, humidity, vehicle speed and the like, in combination with an automatic control rule and a machine learning algorithm, automatic adjustment and optimization of equipment are realized, and it is ensured that an optimal control strategy is provided under different driving modes and environment conditions. A multi-verification mechanism, data encryption, identity verification and other security measures are designed, and misoperation and data leakage are avoided. Through efficient hardware integration, intelligent control logic and safety guarantee measures, intelligent, personalized and reliable vehicle-mounted equipment control experience is provided for a vehicle owner.

The invention relates to the technical field of electronic expansion valve control, and particularly discloses an electronic expansion valve control method based on a deep dynamic fuzzy neural network, and the method comprises the steps: obtaining the operation data of a heat pump unit; normalizing the operation data of the heat pump unit to obtain normalized operation data of the heat pump unit, and dividing the normalized operation data of the heat pump unit into a training set and a test set; constructing a deep dynamic fuzzy neural network model, and optimizing various parameters of the deep dynamic fuzzy neural network model by using a genetic algorithm and the data in the training set to obtain a trained deep dynamic fuzzy neural network model; and inputting data in the test set into the trained deep dynamic fuzzy neural network model for prediction so as to output an optimal control strategy of the electronic expansion valve. The deep dynamic fuzzy neural network model is used for effectively controlling the electronic expansion valve, so that the overshoot of the heat pump system is small, the response speed is high, and the operation performance of the system is improved.

The invention relates to the technical field of steel production equipment, in particular to a vanadium-titanium pellet oxygen-enriched roasting consolidation device which comprises a gas-coal mixed spraying burner, a high-pressure oxygen supply system and an automatic control system, and the high-pressure oxygen supply system is communicated with the gas-coal mixed spraying burner through a pipeline and used for supplying oxygen to the gas-coal mixed spraying burner; the automatic control system is electrically connected with the high-pressure oxygen supply system and used for monitoring and adjusting oxygen pressure, oxygen of two working conditions is provided, and therefore the device can prevent incomplete combustion caused by insufficient oxygen supply, the combustion efficiency of fuel is improved, and even under the condition that the oxygen consumption changes, the combustion efficiency of the fuel is improved. The roasting effect can be optimally controlled, fuel consumption is reduced through stable oxygen supply, and the quality consistency of pellets and the optimal utilization rate of high-pressure oxygen can be guaranteed.

The invention discloses a permanent magnet synchronous motor multi-objective optimization method fusing an equivalent magnetic network method and a Taguchi method, and relates to the technical field of permanent magnet synchronous motor optimization. The method comprises the following steps: step 1, establishing an equivalent magnetic network model of the permanent magnet synchronous motor; 2, determining an optimization target of optimization design under the fusion of the equivalent magnetic network method and the Taguchi method; 3, determining an optimization factor according to the influence factors of the optimization target; step 4, determining an optimization level according to the selected optimization factor and arranging an orthogonal test; step 5, calculating each scheme by using an equivalent magnetic network method according to an orthogonal test to obtain calculation results of different schemes; 6, analyzing data after calculation results of different schemes are obtained; and 7, determining an optimal control factor combination and an optimal control solution according to data analysis results of different schemes. According to the method, the requirements of multi-target simultaneous optimization and rapid calculation can be met, and the optimization design level and the calculation efficiency of the permanent magnet synchronous motor are effectively improved.