32 results about "Stochastic control" patented technology

The invention relates to the field of business management, and discloses a business management method based on a station inspection platform, which comprises the following steps: collecting order demands and external environment data, establishing a dynamic system model of the order demands, carrying out Kalman filtering prediction, constructing an optimization model based on an optimal control theory and a variational method, and finally realizing optimization of a resource scheduling strategy. Demand fluctuation and uncertainty are processed, and resource configuration is dynamically adjusted by adopting a multi-level feedback mechanism; the invention further provides a service management system based on the station inspection platform. The service management system comprises a data acquisition module, a nonlinear dynamic model module, a demand prediction module, a resource scheduling optimization module, a random control module and a feedback control module. According to the method, a nonlinear dynamic system model and a Kalman filtering technology are combined, so that accurate order demand prediction and dynamic adjustment are realized; resource scheduling is optimized based on an optimal control theory, a random control model is introduced to cope with uncertainty, and a multilevel feedback mechanism ensures quick response and adjustment.

The invention discloses a digital twinning-based multistage water-saving ship lock navigation safety guarantee method and system, and the method comprises the steps: collecting multi-source sensing data, generating an alignment data flow and a quality evaluation report, and updating a digital twinning state; by means of the aligned data flow and the quality evaluation report, through non-contact observation and probability fusion, mooring force probability distribution is obtained; based on the digital twinning state and the alignment data flow, identifying a hydraulic impulse response and adopting hydraulic phase lock tracking to generate a vibration suppression opening template; and in the digital twin system, integrating the mooring force probability distribution and the vibration suppression opening template, executing distribution robust random control barrier optimization, and outputting an executable valve track. According to the method, water hammer oscillation can be actively inhibited, robust safety guarantee is provided for uncertain mooring force, and the navigation safety of the large water-saving ship lock is effectively improved.

The invention discloses an urban drainage system randomness control method and system based on an LSTM proxy model. According to the method, a control period node overflow evaluation index sample set is generated by using a random generation control strategy based on an SWMM urban drainage pipe network model and a historical and designed rainstorm sequence; then, an LSTM model is adopted, through rainstorm input, a control strategy learns node overflow evaluation indexes, and an evaluation index agent model of an SWMM model based on machine learning is trained; furthermore, according to the uncertainty of forecast rainfall, a random rainstorm history is generated, and the forecast rainfall probability is reduced according to a back substitution reduction method to serve as a rainfall random input scene of random prediction control. A proxy model is used to quickly optimize rainfall input scenes and control strategy generation evaluation indexes, and real-time optimization decision control considering rainstorm inflow uncertainty is realized based on a rolling optimization framework.

The invention discloses a flexible mechanical arm vibration control method based on T-S fuzzy modeling, and belongs to the technical field of intelligent manufacturing and distributed parameter system control. The flexible mechanical arm vibration control method comprises the steps that a flexible mechanical arm T-S fuzzy distributed parameter model considering nonlinear disturbance and time-varying and time-lag is constructed; designing a fuzzy boundary observer under a limited boundary measurement condition to realize state estimation; introducing a controller random failure modeling mechanism based on a Markov process, and designing a fault-tolerant boundary controller; dynamic boundary sampling is realized in combination with AETM, and the consumption of communication resources is reduced; and stability and performance criteria are constructed by using LKFs and LMI methods. According to the method, the robust stability and performance guarantee of vibration suppression of the flexible mechanical arm are realized under the conditions of limited measurement and failure of the random controller.

The invention discloses a random control method of a three-stable-state piezoelectric cantilever beam structure energy harvester, and belongs to the field of energy harvesters. The implementation method comprises the following steps: introducing white noise by considering random excitation in an environment, establishing an electromechanical coupled strong nonlinear three-stable state energy harvester model, and carrying out dimensionless processing on the energy harvester model to obtain an electromechanical coupled strong nonlinear three-stable state energy harvester dimensionless model; based on the acquired displacement data and voltage of the three-stable-state energy harvester, establishing a model equation of the three-stable-state energy harvester by using dimensionless coefficients zeta, theta, km (m = 1, 2, 3) and D in an electromechanical coupling equation of the strong nonlinear three-stable-state energy harvester by using a sparse identification method of a nonlinear power system; based on a strong nonlinear three-stable-state energy harvester electromechanical coupling equation established by using an SINDy method and system response, an optimal control law alpha is calculated by using a model prediction control method, a control signal is applied through a Buck-boost circuit according to the optimal control law alpha, random control of the three-stable-state piezoelectric cantilever beam structure energy harvester is realized, and the output power of the energy harvester is increased.

This invention discloses an elevator bearing safety early warning method, device, and medium based on the Internet of Things (IoT), relating to the field of control testing and monitoring technology. The method includes: acquiring raw analog signals and preprocessing them to generate synchronous data frames; decomposing fault impact sequences from the synchronous data frames and obtaining a bearing safety status index through weighted D-S evidence, while simultaneously matching a pre-diagnostic control logic library to generate a pre-diagnostic confidence identifier; based on the pre-diagnostic confidence identifier and the bearing safety status index, obtaining a dynamic health baseline through sliding retrieval and elastic tracking compensation, and dynamically extrapolating the control envelope through a stochastic control boundary evolution algorithm to generate a dynamic safety threshold; comparing the bearing safety status index with the dynamic safety threshold, evaluating link quality, and selecting a candidate route set; and obtaining the optimal route through a shortest delay tree to form an encrypted alarm stream. This invention achieves accurate generation of the dynamic safety threshold.

The predictive controller determines, using the deep generative decoder model, a conditional probabilistic distribution of the latent representations of the disturbance conditioned on the partial observations of the disturbance, and samples the conditional probabilistic distribution of the latent representations to produce a latent sample of the time-series values of the disturbance affecting the mechanical system over the time horizon. The predictive controller decodes the latent sample with the deep generative decoder model to produce predicted values of the disturbance acting on the system within the time horizon with a probability of the latent sample on the conditional probabilistic distribution of the latent representations and controls the mechanical system using a predictive controller that determines control commands changing a state of the operation of the mechanical system using the probability of at least some of the predicted values of the disturbance.

The present application relates to the field of intelligent medical treatment, in particular to a tumor treatment dosing regimen Pareto optimization method based on forward-backward stochastic differential equation. The present application unifies the terminal tumor load, dosing cost and treatment risk into the same stochastic control framework, can establish the Pareto optimality condition corresponding to the nonlinear model, and further converts into the implementable closed-loop state feedback control law in the LQ case. Through the combination with the numerical example and the Pareto frontier analysis, an implementable, interpretable and scalable technical path is provided for the multi-objective individualized treatment regimen design, which can solve the problem that the existing technology is difficult to uniformly process the terminal therapeutic effect, dosing consumption and cumulative risk, and difficult to obtain the implementable closed-loop feedback strategy under the forward-backward stochastic control framework.

The embodiment of the invention provides an intelligent device control method, medium and system, and the method comprises the steps: obtaining historical operation records of all intelligent devices, and determining a circulation type corresponding to each intelligent device based on the historical operation records, the circulation type comprising a regular control type and a random control type; reasoning the historical operation record based on double models of a classification tree and a regression tree to obtain a first control signal corresponding to a rule control type intelligent device and a second control signal corresponding to a random control type intelligent device; performing rule control on the rule control type intelligent equipment based on the first control signal; the second control signal is sent to a user, feedback information of the user is obtained, and the random control type intelligent equipment is controlled according to the feedback information; the intelligent device can be automatically controlled according to the historical operation record of the intelligent device, and the control convenience of the intelligent device is improved.

This invention discloses a method and system for ensuring navigation safety in a multi-level water-saving ship lock based on digital twins. The method includes: collecting multi-source sensor data, generating an aligned data stream and quality assessment report, and updating the digital twin state; using the aligned data stream and quality assessment report, obtaining the mooring force probability distribution through non-contact observation and probabilistic fusion; identifying the hydraulic shock response based on the digital twin state and the aligned data stream, and generating a vibration-suppressing opening template using hydraulic phase-locked tracking; within the digital twin system, integrating the mooring force probability distribution and the vibration-suppressing opening template, performing sub-Bruker stochastic control barrier optimization, and outputting an executable valve trajectory. This invention can actively suppress water hammer oscillations and provide robust safety guarantees for uncertain mooring forces, effectively improving the navigation safety of large water-saving ship locks.

Systems and methods are disclosed herein for syntonizing machines in a network. A coordinator accesses probe records for probes transmitted at different times between pairs of machines in the mesh network. For different pairs of machines, the coordinator estimates the drift between the pair of machines based on the transit times of probes transmitted between the pair of machines as indicated by the probe records. For different loops of at least three machines in the mesh network, the coordinator calculates a loop drift error based on a sum of the estimated drifts between pairs of machines around the loop and adjusts the estimated absolute drifts of the machines based on the loop drift errors. Here, the absolute drift is defined relative to a drift of a reference machine.

The present invention discloses a control method and device for a steam turbine power generation system based on a random screening optimization algorithm. The control method includes: obtaining the setting range, number of iterations, random step size, and required number of control parameter groups for each control parameter used in performing active disturbance rejection control on the steam turbine power generation system; randomly selecting multiple random control parameter groups within the setting range of each control parameter based on the number of iterations and random step size; obtaining the transfer function of the steam turbine power generation system and analyzing the system stability margin corresponding to each random control parameter group based on the transfer function; determining the required number of excellent control parameter groups based on the system stability margin, and performing active disturbance rejection control on the steam turbine power generation system based on the excellent control parameter groups. By adopting the technical solution of the present invention, excellent control parameters can be quickly screened based on the system stability margin, thereby achieving rapid control of the stable operation of the power generation system.

The invention discloses an intelligent analysis system for public health decision and trend prediction. The intelligent analysis system comprises the following steps: establishing a random optimal control system state equation containing a drift term, a diffusion term and a control function, and an objective function; a disturbance term is introduced into the state equation, and an original optimal control problem is converted into a random differential game problem; constructing a smooth trajectory estimation function based on the observation data, and defining a joint objective function; solving a random differential game problem to obtain an optimal control function and a system parameter estimator; the method is applied to a random control SIRD infectious disease model, and dynamic estimation of time-varying parameters is achieved; and on the basis of an estimation result, predicting a future disease transmission trend, and providing decision support for prospective planning and accurate configuration of public health resources. According to the method, a system with high noise and time-varying parameters can be effectively processed, the prediction precision and robustness are improved, and a quantitative basis is provided for prevention and control of infectious diseases.

This invention relates to the field of new energy microgrid technology, specifically providing a method for calculating the probabilistic energy flow of an electricity-heat-gas-hydrogen multi-energy microgrid. The method includes: generating a set of correlated random control variables based on uncertainties on both the source and load sides of the multi-energy microgrid; establishing a linearized energy flow model of the multi-energy microgrid based on the physical characteristics of hydrogen-blended natural gas systems; generating a set of operating variables using the random control variable set and the linearized energy flow model, and obtaining a set of basic operating points for the power grid, heating network, and gas network subsystems; and performing multi-point linearized Monte Carlo probabilistic energy flow calculations on the basic operating point sets of multiple subsystems to obtain the probabilistic energy flow calculation results for the electricity-heat-gas-hydrogen multi-energy microgrid. This invention combines computational accuracy and efficiency, effectively reflecting the operating characteristics of multi-energy microgrids under hydrogen blending, and is suitable for calculating the probabilistic energy flow of electricity-heat-gas-hydrogen multi-energy microgrids in scenarios with a high proportion of new energy access.

The method of the present application provides an online control method of unknown switching system based on noise data, collects historical operation data at each time, divides the operation process of the system into four stages according to the operation track of the system, and controls in different stages by using different control rules. In the excitation stage, a set of designed random control sequence is used for the controller side to control the system. In the update stage, a low complexity data-based SDP problem is solved, and the optimal solution is used to construct a state feedback controller to control the system. In the convergence stage and the stable stage, the system does not solve the SDP, but uses the state feedback matrix solved recently to control the system in advance. As can be seen, the present application does not need prior system identification, only needs data sampling and calculation from the self-triggering time, and can perform state closed-loop control on the unknown switching system.

The application discloses a symbolic music generation method with emotional conditions, comprising the following steps: S1, preparing a data set, the data set comprising a midi data set and a piano roll data set, the piano roll data set being obtained by preprocessing the midi data set, the midi data set and the piano roll data set both containing symbolic music data covering classical music and popular music; S2, training a VAE network for encoding the piano roll data into a hidden space; S3, pre-training a diffusion model; the diffusion model adopts a DiT architecture, and the diffusion model is trained on the piano roll data with a split time sequence length of 10.24s; S4, using a stochastic control guide SCG to perform forward evaluation on a non-differentiable rule function, so as to work with the diffusion model in a plug-and-play manner, and to realize non-differentiable rule guidance on the diffusion model; S5, setting a music emotion evaluation index MAV; and S6, setting a non-differentiable rule function with emotional conditions to guide the diffusion model to generate music segments meeting the emotional conditions in a reverse diffusion process.

The present disclosure discloses a system and a method for controlling a vehicle in an environment. The method uses a processor coupled to a memory storing a probabilistic map of the environment relating measurements of a magnetic field and time of the measurements of the magnetic field to a probability of locations within the environment. The processor is coupled with stored instructions when executed by the processor carry out steps of the method comprising estimating a probability of the current location in the environment based on a current measurement of a magnetometer at a current timestamp by submitting the current measurement and the current timestamp to the probabilistic map, and controlling an actuator of the vehicle based on a stochastic control employing the probability of the current location.

This application relates to the field of business management and discloses a business management method based on a one-stop inspection platform: by collecting order demand and external environment data, establishing a dynamic system model of order demand, performing Kalman filter prediction, and constructing an optimization model based on optimal control theory and variational methods, ultimately achieving optimization of resource scheduling strategies, handling demand fluctuations and uncertainties, and dynamically adjusting resource allocation using a multi-level feedback mechanism; the present invention also provides a business management system based on the one-stop inspection platform: a data acquisition module, a nonlinear dynamic model module, a demand forecasting module, a resource scheduling optimization module, a stochastic control module, and a feedback control module. The present invention combines a nonlinear dynamic system model with Kalman filtering technology to achieve accurate order demand prediction and dynamic adjustment; optimizes resource scheduling based on optimal control theory, introduces a stochastic control model to deal with uncertainty, and uses a multi-level feedback mechanism to ensure rapid response and adjustment.

The application discloses a flexible mechanical arm vibration control method based on T-S fuzzy modeling, belongs to the technical field of intelligent manufacturing and distributed parameter system control, and comprises the following steps: a T-S fuzzy distributed parameter model of a flexible mechanical arm considering nonlinear disturbance and time-varying time delay is constructed; a fuzzy boundary observer is designed under the condition of limited boundary measurement, and state estimation is realized; a controller random failure modeling mechanism based on a Markov process is introduced, and a fault-tolerant boundary controller is designed; dynamic boundary sampling is realized in combination with AETM, and communication resource consumption is reduced; and LKFs and LMI methods are used to construct stability and performance criteria. The application realizes robust stability and performance guarantee of flexible mechanical arm vibration suppression under the condition of limited measurement and random controller failure.

The application discloses a micro-grid power tracking method based on cooperation of electric vehicles and temperature control loads, and comprises the following steps: precise and efficient tracking is realized by constructing a hierarchical coordination control framework. Firstly, a price-power dynamic response model of electric vehicle clusters and a temperature-energy dynamic mathematical model of temperature control loads are established, and a geometric calculation method is adopted to aggregate the feasible operation domain of temperature control load clusters; taking the minimization of total control cost as an objective, an optimal incentive price sequence and an auxiliary control reference power sequence are solved through a main control model; aiming at the main control response error, a decentralized stochastic control algorithm is used to calculate the control signal and the equipment state switching probability, and temperature control loads are guided to compensate quickly. The method combines the advantages of the two types of resources, avoids the limitation of single control, does not need to collect private data of users, guarantees the comfort of users, takes into account the regulation capacity, response speed and economy, and effectively improves the power tracking accuracy and operation reliability of a micro-grid tie line.

The invention provides a random MPC control method driven by reinforcement learning and inspired by terminal strategy optimization, and relates to the field of on-orbit avoidance control, and the method comprises the steps: constructing a discrete relative dynamics model; generating expert demonstration data through stochastic model predictive control (SMPC); defining the state and action of reinforcement learning and designing an instant reward function; training a terminal strategy by adopting an offline reinforcement learning algorithm, determining a reinforcement learning state in a prediction time domain and generating corresponding reference control input to obtain an initial reference control sequence; and a random model prediction control SMPC framework is adopted, an initial reference control sequence is introduced into a target function, solving optimization is performed to obtain a current control quantity, and prediction and optimization at the next moment are propelled in a rolling manner. According to the method, through fusion of reinforcement learning and random model prediction control, the spacecraft control has better adaptability and robustness when dealing with orbit perturbation and environment uncertainty, and the overall control performance of spacecraft space debris avoidance is remarkably improved.

A controller for optimizing a local control policy of a system for trajectory-centric reinforcement learning is provided. The controller includes performing the following steps: learning a stochastic predictive model of the system using a set of data collected during trial-and-error experiments performed using an initial random control policy; estimating associated mean predictions and uncertainty; determining a local set of deviations of the system from a nominal system state using the learned stochastic system model at a current time step using a control input; determining a system state with a worst-case deviation; determining a gradient of a robustness constraint; using a nonlinear programming to provide and solve a robust policy optimization problem to obtain a system trajectory and simultaneously stabilize the local policy; updating control data according to the solved optimization problem; and outputting the updated control data via an interface.

The predictive controller determines, using the deep generative decoder model, a conditional probabilistic distribution of the latent representations of the disturbance conditioned on the partial observations of the disturbance, and samples the conditional probabilistic distribution of the latent representations to produce a latent sample of the time-series values of the disturbance affecting the mechanical system over the time horizon. The predictive controller decodes the latent sample with the deep generative decoder model to produce predicted values of the disturbance acting on the system within the time horizon with a probability of the latent sample on the conditional probabilistic distribution of the latent representations and controls the mechanical system using a predictive controller that determines control commands changing a state of the operation of the mechanical system using the probability of at least some of the predicted values of the disturbance.

The present application relates to the field of new energy microgrid technology, and specifically provides a kind of electricity-heat-gas-hydrogen multi-energy microgrid probability energy flow calculation method, comprising: based on the uncertainty source of the double side of multi-energy microgrid source and load, generate random control variable sample set with correlation;According to the physical characteristics of hydrogen blending operation of natural gas system, the linearization energy flow model of multi-energy microgrid is established;Using random control variable sample set and linearization energy flow model, generate operating variable sample set, and obtain the basic operating point set of power grid, heat network and gas network subsystem;Multiple subsystem basic operating point set is executed respectively Multi-point linearization Monte Carlo probability energy flow calculation, obtain electricity-heat-gas-hydrogen multi-energy microgrid probability energy flow calculation result.The present application method has both calculation precision and operation efficiency, can effectively reflect the operating characteristics of hydrogen blending multi-energy microgrid, suitable for high proportion new energy access scene under electricity-heat-gas-hydrogen multi-energy microgrid probability energy flow calculation.

The invention discloses a method for controlling and suppressing high-frequency noise of a DCDC converter through a double random algorithm. The method comprises the following steps that the application range of the random switching frequency of an IGBT is obtained; the method comprises the following steps of: controlling the switching frequency of an IGBT (Insulated Gate Bipolar Translator) to realize random change in a controllable application range in each PWM switching period through a double random algorithm, and carrying out random pulse output weight distribution according to a calculated and output PWM duty ratio in each PWM switching period, and randomly cutting a complete PWM wave into a plurality of PWM waveforms with different weight ratios under different time sequences; and forming an output random pulse according to a pulse sending mechanism so as to suppress the high-frequency noise of the DCDC converter. According to the method, through random IGBT switching frequency and random monopulse distribution and weight ratio, fixed noise distribution under traditional control is broken, noise spectrum characteristics are changed, peak clipping and valley filling are carried out especially for a high-frequency part, and high-frequency noise generated by the DCDC converter is effectively suppressed on the premise that the control effect is ensured to be consistent.

The present application relates to a robust fault-tolerant tracking and anti-interference dynamic output feedback control method for the pressure maintaining system of an injection molding machine, belonging to the field of advanced control of industrial processes, comprising the following steps: Step one: design a dynamic output feedback switching controller with probability; Step two: establish a closed-loop discrete system actuator random failure model containing controller state deviation; Step three: sufficient condition for system asymptotic stability when the system is not affected by external disturbance and variable output set value; Step four: sufficient condition for system asymptotic stability when the system is affected by external disturbance and variable output set value; This method proposes a new scheme for the control of the pressure maintaining stage of injection molding with parameter uncertainty, unknown external disturbance and time-varying set value under the condition that the state variables are not completely measurable; This scheme combines the theories of stochastic control, robust predictive control and dynamic output feedback, which not only guarantees the tracking performance of the system, but also reduces the energy consumption of the equipment.

The predictive controller determines, using the deep generative decoder model, a conditional probability distribution of latent representations of the perturbation conditioned on the portion of the observations of the perturbation, and samples the conditional probability distribution of latent representations to produce a latent sample of time series values of the perturbation that affects the mechanical system over a time horizon. The predictive controller decodes the latent sample using the deep generative decoder model to produce predicted values of the perturbation that act on the system over the time horizon using probabilities of the latent sample under the conditional probability distribution of latent representations, and controls the mechanical system using the predictive controller that determines control commands that change operating states of the mechanical system using probabilities of at least some of the predicted values of the perturbation.

Techniques for facilitating the use of quantum computing circuits in conjunction with stochastic control problems are provided. In one embodiment, a system is provided that includes a quantum computing circuit for preparing a quantum state representing a stochastic control problem. The system may further include a classical computing device for determining a plurality of parameters for the quantum computing circuit.