72 results about "Control disorders" patented technology

The invention relates to the technical field of medical informatics, in particular to a construction method of an osteoporotic fracture risk prediction model. The method comprises the following steps: acquiring an included angle between a foot and the ground, a step speed and a CT image of a target person in a monitoring process; dividing pixel points in the CT image into a plurality of bone tissue areas; according to the shape distribution characteristics of the edge lines in the bone tissue area, bone characteristic values of the bone structure are obtained; obtaining a posture control factor of each gait according to the included angles between the left and right feet of the target person in each gait and the ground; determining an abnormal posture index of each gait in combination with the posture control factor and the corresponding step speed; obtaining a control disorder coefficient of each time period according to the numerical distribution characteristics and the change characteristics of all the posture control factors in each time period; and determining an osteoporosis evaluation value by integrating the bone characteristic value and the disorder control coefficient of the skeleton structure. The accuracy of the bone comprehensive evaluation result of the target person is improved.

Systems and methods are provided for operation of a vehicle to prevent the vehicle from entering unsafe driving states. In examples, a current operational state of a vehicle is determined based on sensor data collected by sensors on the vehicle. Based on the current operational state, a safety-critical threshold value for a vehicle dynamic parameter at which the vehicle is predicted to breach a limit-of-handling is determined. A command to operate the vehicle in a requested operational state is received, which includes driving inputs for operating the vehicle in the requested operational state. The command is filtered by constraining the requested operational state according to a control barrier function based on the safety-critical threshold value and a requested value of the vehicle dynamic parameter determined from the requested operational state. A control signal is generated that controls the vehicle by modifying the driving inputs based on the filtered command.

The invention discloses an acupuncture intervention method after a pancreatic cancer operation, and aims to solve the problem that autonomic nerve regulation based on heart rate variability in an acupuncture stimulation closed loop is difficult to objectize and safely optimize. Heart rate variability time-frequency and time-domain features and respiratory coherence are extracted based on synchronous compression wavelets, a reliability score is generated, short-time heart rate variability and uncertainty are predicted through a neural state space model, a hierarchical control barrier function is generated through a context gating network, a safe MPC is constructed, and real-time quadratic programming solution is carried out. The heart rate variability enters the target domain and the stimulation parameter change rate and the energy consumption are reduced under the condition that safety constraints such as current, pulse width, charge quantity and impedance are met by combining safety verification and self-adaptive updating, and the reliability and the robustness of closed-loop control are improved.

The invention belongs to the technical field related to mechanical arm movement, and discloses a mechanical arm safety critical control method and system fused with tail end posture locking. The method comprises the following steps: establishing a controller which takes the minimum deviation between the actual joint speed and the target joint speed at different moments as a target function and takes the condition that the tail end of the mechanical arm does not collide with an obstacle in the movement process and the movement is stable as a constraint condition; and the optimal joint speeds of the controller at different moments are solved, and the joints of the mechanical arm move according to the optimal speeds, so that the mechanical arm is controlled. By means of the method, the problem that the posture of the tail end of the mechanical arm cannot be abstracted into mathematical constraints and cannot be embedded into quadratic programming of the control obstacle function is solved.

The invention belongs to the technical field of active driving safety, and provides a safe driving judgment method and system based on an in-vehicle microwave signal and a fatigue signal, and the method comprises the steps: obtaining the microwave signal, the fatigue signal, the driving duration and the in-vehicle temperature of a driver; and performing safe driving judgment by using the abnormal driving prediction result and the fatigue prediction result. On the basis that abnormal driving prediction and fatigue prediction are carried out by means of a generalized linear regression analysis model and a deep neural network, microwave signals, fatigue signals, driving duration and in-vehicle temperature are comprehensively considered, the problem existing when alarm information is considered to be single is solved, prediction precision is improved, and meanwhile, in the fatigue prediction process, the fatigue prediction accuracy is improved. The corresponding abnormal fatigue signals when the abnormal driving prediction result goes wrong at the same moment are eliminated, the problem of control disorder caused by prediction according to the abnormal driving prediction result and the fatigue driving prediction result at the same time is avoided, and meanwhile the overall data processing amount of the model is reduced.

The invention discloses an aircraft performance constraint compliance control method for contact type nondestructive testing, and belongs to the field of aircraft control. The implementation method comprises the following steps: introducing a saturated contact force controller into a position ring, and dynamically adjusting a confidence factor based on a position error to adaptively adjust normal rigidity and tangential flexibility; a zero-order control barrier function ZOCBF restrains the force controller, a three-dimensional dynamic safety boundary is established by using a sampling data mechanism, and the position, speed and contact force of the unmanned aerial vehicle are optimized and limited through quadratic programming; designing a hybrid torque controller in the attitude ring, and dynamically selecting a balance point through a binary logic switching strategy; the controller performs safety limitation on the attitude and angular velocity of the unmanned aerial vehicle in combination with zero-order control obstacle function constraint; monitoring a quaternion scalar component symbol in real time by defining a manifold switching set and a jump set; by fusing position loop and attitude loop control logic, compliance control during contact-type nondestructive testing of the unmanned aerial vehicle is realized.

The invention provides an agent security control network training method, a control method, electronic equipment and a medium, and relates to the technical field of agents. The training method comprises the steps of obtaining a training sample set; inputting the training sample set into a pre-constructed heterogeneous graph control barrier function network, outputting barrier function values corresponding to the intelligent agents, and updating parameters of the heterogeneous graph control barrier function network based on a preset first loss function; inputting the training sample set into a task controller, and outputting an action sequence; correcting the action sequence through quadratic programming under the forward security constraint model to obtain a central security action sequence of each agent; taking the central security action sequence as a supervision label, and training the distributed control network together with the training sample set; and repeating the steps until a preset iteration termination condition is met. According to the invention, the intelligent agents can still output high-reliability safety control actions under the condition of only depending on local observation.

The invention discloses a man-machine interaction control method and device based on a high-order data driving control obstacle function, and the method comprises the steps: considering a mechanical arm dynamic model containing unknown parameters, and building an admittance model to generate a robot expected track conforming to interaction force feedback; constructing a robot nonlinear tracking controller based on a neural network; the method comprises the following steps: collecting input and output information of a robot system, establishing an equivalent dynamic data model, and designing a data-driven sliding mode adaptive controller; and a high-order control barrier function based on data driving is constructed, and a final control input is obtained by solving a quadratic programming problem under a unified framework of a control function and a data-driven sliding mode controller. According to the method, a more complex interaction control problem can be solved while robot dynamic model information is not needed, and reliable transient response and steady-state tracking precision are ensured under the condition that a robot dynamic model is unknown.

The present invention discloses a control method and control system for cooling balance in a pipe network, which adopts a method to meet the needs of the first unfavorable cooling user. First, the normal return water temperature range value of the user is preset; then, the return water temperature value and valve opening of each user are monitored; then, the first unfavorable cooling user is obtained, and when the user is monitored to have a maximum valve opening and a return water temperature value not within the preset normal return water temperature range value, it is determined to be the first unfavorable cooling user; the working frequency of the cooling water pump can be adjusted, and the cooling water pump can adjust the water supply again, or only the valve opening can be adjusted to adjust the water supply amount for different users; finally, it is ensured that the return water temperature value of each user is within the preset normal return water temperature value, and the pipe network enters a cooling balance state; this solves the problem in the prior art that a centralized cooling system generally uses a balancing valve for cooling balance control, resulting in poor cooling balance control effect caused by control disorder.

The invention discloses a vertical farm integrated control system and method and a computer readable storage medium, and the system comprises a sensor group which is used for collecting environment and crop growth data; the quality prediction module is used for predicting future quality indexes of crops; the joint optimization module is used for constructing a multi-objective function containing quality indexes and energy cost and calculating first control input; the security shielding module defines a security set based on the control barrier function, and projects the first control input into the security set to generate a second control input when the first control input violates a security constraint. And the actuator group is used for adjusting the farm environment according to the second control input. According to the invention, through establishing the quality prediction model and performing joint optimization with the real-time energy cost, the system can actively use the electricity price valley period to adjust the environment on the premise of ensuring the target quality, the energy cost is significantly reduced, and the economic benefit is maximized.

The present application relates to the technical field of robot tracking control, and discloses a kind of man-machine shared tracking control method based on differential game, comprising: establishing man-machine differential game model;Estimate human control strategy and objective function parameter;Design robot shared control strategy;To the shared control strategy determined by robot, realize man-machine shared tracking control;The present application uses differential dynamic game to model the dynamic negotiation relationship between human participants and robot, so that the robot adjusts its own willingness under the game framework by estimating the willingness of human to eliminate tracking error, and designs robot tracking control strategy on this basis;Further, the present application considers the safety of man-machine cooperation, designs robot safety control strategy based on control barrier function, so that it can realize safe shared control together with robot tracking control strategy.

The application discloses a vehicle control method and device based on a composite control barrier function, relates to the technical field of safety-critical control, and comprises the following steps: performing smoothing operation on an original control barrier function of a mixed relative degree to obtain a smoothed modified control barrier function; acquiring road geometry information and traffic rule information corresponding to a current driving scene of a vehicle to determine a candidate drivable area of the target vehicle; determining a road boundary constraint set participating in combination according to the boundary of the candidate drivable area, and determining a smoothed modified control barrier function set participating in combination and corresponding Top-r combination parameters; performing overall smoothing combination on the smoothed modified control barrier function set based on an implicit smoothing Top-r combination strategy to obtain an overall road composite safety function, so as to construct a safety constraint and generate a safety control instruction of the vehicle, thereby helping to reduce the constraint scale in complex intersection scenes and taking into account safety and control flexibility.

The present disclosure proposes an actuator failure compensation and safety control method based on a double-layer evaluation architecture, a storage medium and a system. The bottom layer uses an adaptive model predictive control to output a nominal instruction, a reinforcement learning model is built thereon to output a high-frequency residual compensation instruction to eliminate model mismatch, and a second evaluation network is independently built to evaluate the future global loss-of-control risk of the vehicle. The Lagrange dual optimization is introduced to convert the macro risk evaluation into a mathematical constraint to guide the first strategy network correction; the global risk index is used to feed forward the target cost weight of the predictive control to realize continuous flexible degradation, and the control barrier function is triggered at the limit boundary to realize discrete quadratic programming instruction projection. The present application overcomes the conservative strategy degradation defect caused by the traditional mixed reward, establishes an absolute safety line, and improves the control accuracy and safety robustness of the vehicle in complex nonlinear working conditions.

The present invention relates to methods and devices for providing a treatment recommendation based on a prediction of at least one Impulse Control Disorder occurrence for a patient undergoing a treatment with Dopamine Agonists.

The application discloses a heavy vehicle anti-rollover safety control law design method based on a control barrier function, utilizes Newton's second law of motion and the law of conservation of angular momentum to analyze a vehicle lateral-yaw subsystem and a roll subsystem respectively, and constructs a three-degree-of-freedom state space model; the traditional lateral load transfer rate LTR for measuring vehicle rollover is re-stated by using state variables in the three-degree-of-freedom state space model, and a vehicle anti-rollover safety certificate and a barrier function are constructed; a control Lyapunov function and a control barrier function are constructed for the three-degree-of-freedom state space model, and a quadratic optimization framework is used to solve the anti-rollover control law which meets the requirements of heavy vehicle driving control tasks and the non-rollover safety constraint condition. The application does not depend on a large number of sensors and complex calculation algorithms, strives to achieve a more efficient control effect with fewer resources, and reduces the dependence on expensive hardware, so that a balance between cost and performance is found.

The present disclosure provides'vehicle operation around an obstacle '. A computer includes a processor and a memory, and the memory stores instructions executable by the processor to: determine a threat number based on sensor data indicative of an obstacle, the threat number representing a risk of an impact between a vehicle and the obstacle; formulating a control obstacle function based on sensor data indicative of the obstacle; determining a control input based on an expression including the control barrier function and the threat number; and actuating a component of the vehicle in accordance with the control input.

The invention provides a robot manipulator control method, device and equipment and a medium, and relates to the technical field of manipulator control, the method comprises the steps that according to obtained stress data of two hands of a robot, a trained neural network model is adopted, and the mass center position of a carried object is determined; on the basis of the double-hand force-moment balance condition, according to the mass center position, the grabbing point position of the carried object grabbed by the double hands of the robot is determined, and the double hands of the robot are controlled to grab the carried object; on the basis of a model prediction control technology and a control obstacle function technology, according to the obtained obstacle information, a collision-free translational motion track of the carried object and collision-free translational motion tracks of the two hands of the robot are generated; and according to the obtained translation acceleration when the two hands of the robot carry the carried object, the expected posture when the two hands of the robot carry the carried object is determined. According to the method, through logic connection among the steps, the defects of object grabbing, two-hand posture adjustment and obstacle avoidance links in the prior art are comprehensively overcome.

The invention provides a control method of a motor system and electronic equipment, the motor system comprises a target motor and a plurality of sensors, the plurality of sensors comprise a target sensor and an associated sensor, the target sensor is used for detecting a target parameter to obtain a detection value of the target parameter, and the associated sensor is used for predicting the target parameter to obtain a detection value of the target parameter; the method comprises the following steps: determining a weight coefficient according to the working state of a target sensor; the weight coefficient represents the credibility of the detection value of the target parameter; determining a final control parameter corresponding to the current moment of the target motor according to the weight coefficient, the detection value and the predicted value; and controlling the target motor based on the final control parameter. Therefore, the working state of the sensor, such as a fault, can be quantified into the weight coefficient, and the final control parameter is determined based on the predicted value corresponding to the associated sensor in combination with the weight coefficient, so that control disorder or shutdown of the motor can be avoided when the sensor fails, and the system stability is improved.

The application discloses a decorative plate production line stacking process automation industrial control system, and belongs to the technical field of automation control, and comprises the following steps: collecting and standardizing processing multi-dimensional data representing system operation state in real time through a system state monitoring module, at least including production efficiency indexes representing unit time output, dimensionless end effector performance drift, normalized environmental humidity, and execution certainty indexes quantifying single task completion quality; a dynamic risk assessment module receives multi-dimensional operation data, calculates based on a preset correction entropy model and a dynamic safety baseline model, quantifies control disorder caused by execution certainty decrease and environmental humidity interference, and generates correction entropy representing current control disorder degree, so that the application provides more accurate and timely early warning before failure occurs.

The present invention discloses a method for collaborative target encirclement control of multiple unmanned boats based on a control obstacle function. The method comprises: establishing a collaborative target encirclement control model of a multi-unmanned boat-target system model; when a multi-unmanned boat network encircles a moving target in real time, the position of the moving target acquired and estimated by the multiple unmanned boats is input into the model, the model outputs the forward and steering power of the unmanned boat to control the unmanned boat in real time, and the unmanned boat outputs the lateral velocity and angular velocity to the model to realize closed-loop control, thereby realizing collaborative target encirclement control of multiple unmanned boats. The method of the present invention can estimate the global position and velocity information of the target by the unmanned boat, realize collaborative target encirclement control when the position and velocity of the target are unknown, and when the unmanned boat is in the presence of model uncertainty and external interference, the unmanned boat can also accurately track the expected speed in real time, while considering safety design to ensure that the unmanned boats do not collide with each other and obstacles, and ultimately improve the overall control performance.

The present invention provides a method for coordinated control of an elastic dynamic robust formation based on a control obstacle function, and belongs to the technical field of unmanned system control. The method comprises the following steps: Step S1, establishing a motion dynamics model for each unmanned system, and determining the position information and motion speed of each unmanned system; Step S2, using a control obstacle function to ensure a collision-free safety set between the unmanned system and static obstacles and dynamic unmanned systems, and solving the input safety set of the control system based on forward invariance; Step S3, maintaining the formation based on the control obstacle function; Step S4, performing coordinated control of the formation based on the control obstacle function. The present invention adopts the above-mentioned method for coordinated control of an elastic dynamic robust formation based on a control obstacle function, which can effectively deal with uncertainties and random obstacles in unknown dynamic environments, and improve the coordinated control performance of multiple unmanned systems.

The invention belongs to the technical field of robot control, and particularly relates to a robot robust safety control method based on a control barrier function, which comprises the following steps of: S1, establishing a robot system model containing a state variable, control input and a disturbance term; S2, designing a disturbance observer, and estimating and compensating disturbance of a system in real time; s3, based on an interference estimation result, defining a system security target, constructing a control barrier function to convert security constraints of the system into inequality conditions which need to be met by control input, performing system security analysis, and proving forward invariance of a system security set; s4, designing a safety controller by controlling a barrier function in combination with an expected tracking controller; and carrying out system security analysis to prove the forward invariance of the system security set. According to the method, the control target of considering the safety and the tracking performance of the system in an uncertain environment is achieved.

The invention provides a continuum robot safety critical control method which comprises the following steps: establishing a dynamical model of a continuum robot, and designing a control barrier function; designing an extended state observer; designing a nominal control law; a safety critical control law is designed, and the safety critical control law is obtained by integrating Lyapunov-like constraints into a quadratic programming problem of a control barrier function; obtaining a nominal control signal after the initial control input and the state observation result pass through a nominal control law; the nominal control signal passes through a safety critical control law to obtain control input after safety critical control; the control input after safety critical control and external interference input are input to the continuum robot, and control output is obtained; and after the control output and the control input after the safety critical control are input to the extended state observer, a state observation result is output. According to the method, the safety of the system state can be always kept without violation even under a complex safety boundary condition.

The invention discloses an interface rolling control method and device, electronic equipment and a storage medium, and relates to the technical field of interface interaction.The method comprises the steps that when the wrist of a target user rotates, accumulated rotation angle information is calculated according to angular velocity information of wrist rotation, interface rolling parameter information is mapped according to the accumulated rotation angle information, and the interface rolling parameter information is obtained; and controlling the interface rolling of the target equipment according to the interface rolling parameter information. Screen rolling is controlled based on the accumulated rotation angle corresponding to the angular velocity, so that screen rolling control does not depend on the gravity direction, the problem of rolling control disorder caused by horizontal and vertical posture changes of a wrist is solved, and the stability of interface rolling control is improved.

The invention relates to an automatic driving control method based on elastic safety critical control. The method comprises the steps that the vehicle state, the reference path and the environment information of automatic driving are obtained in real time; establishing a control-oriented automatic driving vehicle dynamics controlled model, and establishing an optimization problem considering time-varying safety constraints; designing an elastic safety critical control model: estimating time-varying disturbance, converting safety and stability into constraints through an elastic control barrier function of a self-adaptive penalty parameter, establishing a unified constrained optimization framework, and integrating safety constraints, stability constraints and control input constraints into a quadratic optimization problem; and solving a secondary optimization problem of the elastic safety critical control model in real time to obtain safety control input of the automatic driving vehicle. Compared with the prior art, the method has the advantages that the vehicle can accurately track the reference path under the time-varying disturbance, and the system safety and stability are ensured.

The invention discloses a feasibility-enhanced robust safety critical control method. The method fully considers the influence of the non-matching disturbance on the system safety when the relative orders of the input and the disturbance are inconsistent. Unknown disturbance is estimated through a robust integral type nonlinear disturbance observer based on error symbol integration, and an estimation result is applied to a high-order control barrier function, so that the high-order safety of the system is ensured. Furthermore, according to the method, unknown terms in high-order control barrier function constraints are replaced by estimating disturbance and the lower bound of errors of the disturbance, and the unknown terms are embedded into a quadratic programming controller. For the feasibility problem possibly caused by multi-input and multi-obstacle function constraints, the method introduces a volume control obstacle function to quantify the feasible region volume, and further combines a disturbance observer with the volume obstacle function to ensure that the feasible region volume is always positive, thereby improving the feasibility of a controller when disturbance exists. By integrating the method, the unification of the system security and the multi-constraint compatibility is realized.

The present invention provides, inter alia, methods, apparatus, and systems useful for ameliorating impulse control disorders known to be extremely disabling and common to many neurological and psychiatric conditions using closed-loop (responsive) neuro stimulation.

Aiming at the problem of missile terminal guidance with no-fly zone and impact angle constraints, a model predictive static programming guidance law based on control barrier function is proposed. The proposed algorithm inherits the high efficiency of the traditional model predictive static programming while ensuring the no-fly zone constraints. The main reasons are as follows: first, the projection operator under the linear inequality constraints has an explicit expression, avoiding additional optimization solving; second, due to the forward invariance of the control barrier function, the no-fly zone constraints do not need to be imposed at all discrete nodes, but only at one or a few discrete nodes, reducing the scale of solving. The simulation results show that the proposed algorithm can meet the no-fly zone and impact angle constraints while ensuring high computational efficiency. Subsequent research will focus on trajectory optimization and guidance problems with multiple no-fly zone constraints, even dynamic no-fly zone constraints.

The present invention discloses a method for optimizing the motion planning and control of an unmanned vehicle by using CLF-CBF, and the specific steps include establishing a two-wheel differential chassis model of the driverless vehicle; establishing a two-wheel differential kinematic model of the driverless vehicle; designing a Lyapunov function to improve the stability of the vehicle control path tracking; providing input constraints and safety-critical constraints for the control system by controlling the obstacle function to improve the system safety; establishing a CBF-NMPC model predictive control system; adding CLF constraints to establish a CBF-CLF-NMPC model predictive control system. This method can solve the problem of poor path planning results caused by the characteristics of various planning algorithms, fully improve the vehicle control performance on the premise that the safety of the driverless vehicle is sufficiently guaranteed, and achieve the optimal path planning and efficient control of the driverless vehicle.

The invention provides a reinforcement learning-based hybrid vehicle queue safety control method and system, and the method comprises the steps: constructing a communication framework of a hybrid vehicle queue, and obtaining the state data of the hybrid vehicle queue in real time; dividing the mixed vehicle queue into a plurality of sub-queues; constructing a dynamic model of each sub-queue; a trained parameter sharing SAC reinforcement learning algorithm is used to generate a preliminary control action for the networked autonomous vehicle in each sub-queue; and constructing a safety control layer fusing a control obstacle function and quadratic programming, performing safety correction on the preliminary control action based on the safety control layer, generating a control output instruction meeting a collision avoidance constraint, and issuing the control output instruction to each networked autonomous vehicle. And then a safety control layer formed by a control barrier function and quadratic programming is adopted to provide safety guarantee, and the safety of automatic driving control is improved.