Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

177results about How to "Stable tracking" patented technology

Flight control method and system of unmanned aerial vehicle tracking technology

The invention discloses a flight control method and system of an unmanned aerial vehicle tracking technology, and relates to the technical field of unmanned aerial vehicle control, and the method comprises the following steps: before an unmanned aerial vehicle takes off, starting an airborne sensor in advance, executing parameter initialization and calibration operation, and installing a magnetic marker on a tracking target; acquiring the body position of the unmanned aerial vehicle in the flight process, and sensing the target position of the tracking target in real time by adopting a multi-sensor data fusion algorithm; obstacles existing in the flight path are detected in real time, a three-dimensional environment model is integrated, and the motion state of a tracking target is captured in combination with a follow-up visual tracking algorithm; target tracking data are stored and fed back in real time, and the battery state and the energy consumption speed of the unmanned aerial vehicle are monitored. By combining the magnetic guidance technology, multi-sensor data fusion and a follow-up visual tracking algorithm, high-precision target tracking can be realized in a dynamic complex environment, meanwhile, obstacles are effectively avoided, and the flight stability and tracking precision of the unmanned aerial vehicle are ensured.
Owner:HEFEI HEZHIXIN MICROELECTRONICS CO LTD

Distributed driving steering intelligent vehicle hierarchical trajectory planning method and system

The invention discloses a layered trajectory planning method and system for a distributed driving steering intelligent vehicle, and belongs to the technical field of intelligent vehicles. The method comprises the steps that firstly, a kinematic model of the distributed driving steering vehicle is analyzed, and relevant parameters of an unstructured scene are obtained; redesigning a cost function and a node expansion mode of a mixed A * algorithm, searching out a rough path segmented according to mode switching points, and constructing a corresponding initial track; and finally, optimizing the initial trajectory by adopting a numerical optimization method based on a driving corridor, designing an objective function and constraint conditions considering trajectory smoothness, comfort, safety and high efficiency, constructing a trajectory optimization optimal control problem, and then solving the trajectory optimization optimal control problem to obtain an optimal trajectory. According to the invention, the distributed driving steering intelligent vehicle can generate a continuous, smooth, comfortable, safe and efficient track in a complex unstructured scene with narrow congestion and dense obstacles.
Owner:HUNAN UNIV

Target identification tracking system based on unmanned aerial vehicle

The invention discloses a target identification tracking system based on an unmanned aerial vehicle, and relates to the technical field of deep learning. The target identification tracking system based on the unmanned aerial vehicle comprises a data processing and expansion module, a target detection and tracking algorithm module, a visual positioning and control module, an information sampling and image processing module and an intelligent analysis and data management module. According to the invention, the position information of the tracked object is obtained by using the target tracking technology to generate the control information so as to autonomously control the flight of the unmanned aerial vehicle, and the camera is autonomously controlled through the real-time position information of the tracked object obtained through target tracking, thereby realizing the automatic zooming function of the unmanned aerial vehicle, and ensuring that the target is always in the center of the picture. Therefore, the whole automatic process from target finding to tracking of the unmanned aerial vehicle is realized.
Owner:LANZHOU JIAOTONG UNIV

Multi-modal target identification and tracking prediction method based on laser radar and binocular camera

The invention relates to a multi-modal target identification and tracking prediction method based on a laser radar and a binocular camera, and belongs to the field of robot / unmanned system perception identification. Comprising the following steps: preprocessing a target two-dimensional image acquired by a binocular camera and target point cloud data acquired by a laser radar to obtain a preprocessed two-dimensional image and point cloud data; s2, performing two-dimensional target detection and tracking detection based on the preprocessed two-dimensional image to obtain a two-dimensional target detection and tracking result; s3, performing three-dimensional target detection based on the preprocessed point cloud data and the two-dimensional target detection and tracking result to obtain a three-dimensional detection result; and S4, based on the pixel coordinates in the two-dimensional target detection and tracking result and the pixel coordinates of the vertexes of the target point cloud boundary in the three-dimensional detection result, target fusion tracking prediction is carried out, and the target ID, the position, the category and the target point cloud boundary are obtained. And accurate identification and tracking of the target are realized.
Owner:ZHONGBING INTELLIGENT INNOVATION RES INST CO LTD +1

Unmanned aerial vehicle image high-efficiency identification system

The invention relates to an unmanned aerial vehicle image high-efficiency identification system. The system comprises an unmanned aerial vehicle, an image acquisition unit, an image preprocessing unit, a target detection unit, a target tracking unit and a control unit. The unmanned aerial vehicle has a high-speed stable flight capability, and the image acquisition unit consists of a high-resolution camera and is used for capturing image data in real time in a flight process; the image preprocessing unit carries out denoising and deblurring processing on the captured image data to generate preprocessed image data; the target detection unit adopts a pre-trained deep learning model to realize efficient recognition of a target object in the preprocessed image; the target tracking unit is combined with a Kalman filter and an optical flow method to lock and track a target object; the control unit adjusts the flight path of the unmanned aerial vehicle according to the target object position and motion information provided by the target tracking unit to ensure continuous tracking of the target object; according to the system, efficient and accurate identification and tracking of a target object are realized through cooperative work of all the units.
Owner:CADDX US (SHENZHEN) LTD CO LTD

High-robustness target loss detection and rapid tracking method

The invention discloses a high-robustness target loss detection and rapid tracking method, and belongs to the technical field of calculation, reckoning or counting. By combining the YOLO algorithm and the MOSSE algorithm, the method can actively search the target and realize re-detection and rapid recovery tracking of the target after the space target is lost for a long time. And when the target moves out of the visual field, the MOSSE algorithm cannot continue tracking, and at the moment, the YOLO algorithm is automatically started to carry out target detection so as to confirm that the target appears again. Once a target is detected, the features of the target are immediately transmitted to the MOSSE algorithm so as to quickly switch back to the tracking mode, thereby ensuring the continuity and stability of tracking. The key point of the method is that a switching mechanism can quickly respond between target loss and reoccurrence, and time delay in the detection and tracking process is remarkably reduced.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS +1

Spacecraft attitude tracking sliding mode control method based on all-drive system method

The invention discloses a spacecraft attitude tracking sliding mode control method based on an all-drive system method, and belongs to the technical field of spacecraft control. The method is based on an all-drive system method, and a second-order all-drive system model of the system is established for a spacecraft attitude tracking system with external disturbance and actuator saturation. And an anti-saturation auxiliary system is designed to reduce the influence of saturation of the actuator. Meanwhile, a disturbance observer based on a fixed-time multivariable superhelix system is designed and used for estimating external disturbance. Based on an all-drive system method, a linear steady closed-loop system is obtained through a state feedback controller, and a sliding mode controller based on the all-drive system method is designed, so that the system can stably track a target attitude under the influence of external interference, and effective control of a spacecraft attitude tracking system is realized.
Owner:HANGZHOU DIANZI UNIV

Fault-tolerant control method for rotating speed of driving motor of deep-sea robot

The invention discloses a fault-tolerant control method for the rotating speed of a driving motor of a deep-sea robot. The fault-tolerant control method comprises the following steps: S1, establishing a discrete state space model based on electrical and mechanical equations of the motor; s2, determining a fault characteristic parameter to describe the loss probability of the control signal when the control signal is attacked and interfered; s3, calculating a feedback control matrix according to the fault characteristic parameters; s4, calculating a feedforward control matrix according to the fault characteristic parameters; s5, constructing a controller based on the feedback control matrix and the feedforward control matrix, calculating a control signal online and transmitting the control signal to an execution mechanism; and S6, the execution mechanism receives the control signal, and if the signal is lost, the stored control signal is adopted to replace the control signal, and control is executed in real time. According to the invention, fault-tolerant control of the motor rotating speed can be realized under the condition that the control signal is randomly lost, and the motor rotating speed can stably track a predetermined trajectory.
Owner:SHAOXING UNIVERSITY

Tracking method for massive moving particles based on image recognition

The invention belongs to the technical field of particle motion track recognition, and particularly relates to a method for tracking a large number of moving particles based on image recognition, the moving particles suitable for the method are particles undergoing active Brownian motion, the same color mark is made on each moving particle, and image acquisition is performed through a microscope or a video recorder; identifying a pixel point cluster corresponding to the color mark on each moving particle by setting an RGB value; determining moving particles corresponding to the color marks by setting a threshold value in the pixel point cluster; taking a pixel point corresponding to the average value position of all the position data as the position of the moving particle; and recording the motion trail of the moving particles in a period of time. According to the method, the marks are introduced to the particles, the algorithm is developed to identify the marks, calculate and record the average positions of the pixel points corresponding to the marks, the particles are tracked, the colored marks can exist stably and do not interfere with one another, and it can be ensured that a large number of particles can be tracked for a long time.
Owner:SHENZHEN MSU-BIT UNIVERSITY

Advanced power control method suitable for marine photovoltaic power generation system

The invention discloses an advanced power control method suitable for a marine photovoltaic power generation system, and relates to the technical field of photovoltaic power control, and the method comprises the following steps: collecting multi-dimensional data in a ship navigation process, and taking the multi-dimensional data as input information; and on the basis of the collected multi-dimensional data, an ultra-short-term photovoltaic power prediction model of CNN-LSTM-AM is constructed. According to the method, the CNN-LSTM-AM ultra-short-term marine photovoltaic power prediction model is introduced, the photovoltaic power generation power in the next second can be accurately predicted, power distribution is carried out according to the photovoltaic power generation power, accurate prediction and dynamic adjustment of the photovoltaic power are achieved, and the photovoltaic power generation power can be accurately predicted and dynamically adjusted by monitoring the photovoltaic power generation power, the SOC of the storage battery and the direct-current bus voltage key parameters in real time. The system can dynamically adjust the power control strategy, ensures the stable tracking of the output current of the inverter, effectively avoids the problems of power deviation and energy accumulation or insufficiency, and remarkably improves the stability and reliability of the system.
Owner:OCEAN UNIV OF CHINA

Human-machine action mapping control system and method based on hybrid LM-GA algorithm

The invention discloses a human-machine motion mapping control system and method based on a hybrid LM-GA algorithm, and relates to the field of human-machine motion mapping control. According to arm joint position information obtained by an optical motion capture system, a corresponding arm joint rotation angle is obtained by using a geometric solution in inverse kinematics; secondly, joint angle data of the mechanical arm are obtained through an inverse kinematics iterative algorithm, and the joint angle data are verified in the virtual environment; then track data of the tail end of the mechanical arm is obtained through an optical motion capture system, the motion reproduction precision of the mechanical arm can be evaluated by comparing the track data of the tail end of the human arm and the track data of the tail end of the mechanical arm, and the accuracy and reliability of a human-machine motion mapping system are ensured; by continuously approaching the optimal solution, the iterative algorithm can gradually adjust the angle of the robotic arm joint until a predetermined end effector position is reached.
Owner:ANHUI POLYTECHNIC UNIV

Composite loop tracking method and system of anti-interference navigation signal receiver, computer equipment and storage medium

The invention discloses a composite loop tracking method of an anti-interference navigation signal receiver. The method comprises the following steps: copying a pseudo code and a carrier corresponding to a satellite signal based on a roughly captured signal; performing coherent operation to obtain a coherent integral value; performing FLL frequency discrimination, PLL phase discrimination and FFT frequency discrimination on the coherent integral value, and performing weighting processing to obtain a frequency error; carrying out carrier loop filtering on the frequency error to output a carrier loop tracking result; performing incoherent accumulation to obtain an incoherent integration result, and performing DLL phase discrimination to obtain an epoch code loop phase difference; performing code loop filtering on the epoch code loop phase difference to output a code loop tracking result; calculating a first frequency control word corresponding to the code loop according to the wave loop tracking result; and controlling code loop updating based on the first frequency control word and the code loop tracking result. According to the invention, stable tracking of navigation signals in different dynamic and different interference scenes can be realized.
Owner:CHANGSHA HAIGE BEIDOU INFORMATION TECH CO LTD

Phased array radar for unmanned aerial vehicle detection based on multi-target tracking

The invention discloses a phased array radar for unmanned aerial vehicle detection based on multi-target tracking, which comprises a radar antenna array, a signal processing unit, a control unit and a display unit, and is characterized in that the control unit comprises a motion state judgment module; a filtering switching module; a Kalman filtering module; a particle filtering module; and a data association module. The method can achieve the high-precision detection and positioning of an unmanned plane target, has a multi-target tracking capability, and improves the detection efficiency and accuracy of the unmanned plane.
Owner:BEIJING RUIDAEN TECH CO LTD

Smoking detection method and system based on deep learning

The invention provides a smoking detection method and system based on deep learning. The method comprises the following steps: acquiring image acquisition data of a to-be-identified no-smoking area; based on the image acquisition data, whether a suspected smoking area exists in the image acquisition data is obtained by using a pre-constructed smoking area detection model; when a suspected smoking area exists in the image acquisition data, generating a smoking action trajectory by using a ByteTrack target tracking algorithm; according to the smoking action track, determining whether a smoking behavior exists in the to-be-identified smoking-forbidden area or not; according to the method, the visual features are determined by combining the neural network and the ByteTrack target, so that the accuracy of identifying the suspected smoking area can be effectively improved, false alarms and missing alarms are reduced, and the human cost is reduced.
Owner:BEIJING SHANGHAI WENTIAN TECH DEV CO LTD

Automobile stamping part dynamic grabbing and boxing method and system based on flexible manipulator

The invention discloses an automobile stamping part dynamic grabbing and boxing method and system based on a flexible manipulator, and the method comprises the steps: obtaining the three-dimensional point cloud data of a target stamping part on a conveyor belt in real time, extracting the key geometric features of the target stamping part, and determining the type, position and posture of the target stamping part; the type, the key geometric features and the posture of the target stamping part are input into a pre-trained contact point prediction model, and the contact point of the flexible manipulator is predicted; according to the position and posture of the target stamping part and the predicted contact point of the flexible manipulator, trajectory planning of the flexible manipulator is conducted, and a planned trajectory is obtained; and target stamping parts are grabbed and boxed according to the planned track of the flexible manipulator. The stamping part grabbing device can flexibly meet the grabbing requirements of stamping parts of different shapes, sizes and positions and has good adaptability to special-shaped stamping parts of complex shapes, and the grabbing precision and the boxing efficiency are improved.
Owner:WUHAN UNIV OF TECH

Multi-source fusion positioning processing method, device and equipment for vehicle terminal

The invention provides a multi-source fusion positioning processing method, device and equipment for a vehicle terminal, and relates to an automatic driving technology, and the method comprises the steps: obtaining inertia measurement data, wheel speed data, laser point cloud data and other source data of the vehicle terminal in a current frame in a driving process of the vehicle terminal; performing pre-integration on the inertia measurement data and the wheel speed data to generate a pre-integration result; and performing feature matching on the laser point cloud data of the current frame and the laser point cloud data of the previous frame of the current frame, and if the current frame is determined as the key frame, determining the point cloud of the key frame. Fusing the pre-integration result, the point cloud of the key frame and other source data to generate a current pose of the vehicle terminal in the key frame; and determining a target pose of the vehicle terminal according to the current pose of the key frame, the point cloud of the key frame, the historical point cloud of the key frame and a preset point cloud base map. According to the method provided by the invention, the technical problems of low positioning precision and poor robustness of the vehicle terminal are solved.
Owner:HANGZHOU FABU TECH CO LTD

Multivariable control method for urban sewage treatment process, storage medium and server

The invention discloses a multivariable control method for an urban sewage treatment process, and the method comprises the steps: constructing a sewage treatment process control environment, determining a state space function, an action space function and a reward function, constructing a DO intelligent agent and an NO intelligent agent based on a deep reinforcement learning algorithm, and carrying out the training, according to the trained DO intelligent agent and NO intelligent agent, a second controller is obtained and used for controlling the nitrate nitrogen concentration and the dissolved oxygen concentration, and stable tracking of the set values of the dissolved oxygen concentration and the nitrate nitrogen concentration is achieved; even if the expected values of the dissolved oxygen concentration and the nitrate nitrogen concentration are changed, the dissolved oxygen concentration and the nitrate nitrogen concentration can be quickly stabilized near new expected values, and the accuracy of controlling the dissolved oxygen concentration and the nitrate nitrogen concentration is improved.
Owner:BEIJING UNIV OF TECH

Unmanned aerial vehicle autonomous tracking trajectory planning method

The invention particularly relates to an unmanned aerial vehicle autonomous tracking trajectory planning method. The method comprises the steps that firstly, an unmanned aerial vehicle obtains the speed and position of a target at the current moment according to a target recognition result; then motion primitive expansion is carried out according to the position and speed information to predict the position of the target at a certain moment in the future, and meanwhile Markov chain state transition is carried out to predict the probability that the target appears at a certain position. And generating viewpoints beneficial to observation of the target near all potential points according to the potential points generated by the prediction result. Judging whether the target is in the field of view of the unmanned aerial vehicle, and if so, determining that the path planning end point of the unmanned aerial vehicle is a globally optimal observation point; and if so, sequentially traversing the viewpoints with the highest cost to try to recapture the target. And finally, according to a decision result, constructing a multi-constraint combined B-spline trajectory optimization model, and solving a final optimal tracking trajectory by taking the yaw angle as an independent optimization variable. According to the scheme, the unmanned aerial vehicle can complete robust and efficient autonomous tracking in a complex and dense environment.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

A decentralized fault-tolerant control method for flexible joint space robots without velocity feedback

ActiveCN118789557BIncrease equivalent stiffnessSolving Motion Control ProblemsProgramme-controlled manipulatorRobotic systemsRobotic arm
The invention discloses a decentralized fault-tolerant control method for a flexible joint space robot without speed feedback, comprising the following steps: S1: constructing a dynamic model of a flexible joint space robot system whose carrier posture is not controlled; S2: introducing a flexible compensator; based on a singular perturbation method, decomposing the model into a fast-changing subsystem representing joint flexible vibration and a slow-changing subsystem representing arm trajectory tracking; S3: for the fast-changing subsystem, designing a torque differential feedback controller; S4: for the slow-changing subsystem, using a speed observer to identify the joint angular velocity, and using a decentralized neural network to identify the uncertainty and fault terms of the model, and designing a decentralized fault-tolerant control method without speed feedback accordingly; the beneficial technical effects of the invention are: solving the problem that the singular perturbation method cannot be applied to a robot system with a small joint stiffness, using a decentralized neural network to reconstruct the model to improve the task execution efficiency of the space robot, and the robot arm can stably track the expected trajectory.
Owner:XIANGJIANG LAB

Comprehensive maneuvering motion planning method and system for sudden lane changing of autonomous vehicle

The invention discloses a comprehensive maneuvering motion planning method for sudden lane changing of an automatic driving vehicle, and relates to the technical field of automatic driving vehicles. The method comprises the following steps: receiving vehicle driving state information, wherein the driving state information comprises the positions, speeds, accelerations, course angles and yaw velocities of a vehicle and surrounding vehicles; constructing an MOBIL lane changing decision model, making a lane changing decision by using the model, judging whether a lane changing operation is carried out or not, and if so, carrying out calculation to obtain a lane changing movement track taking the minimum lane changing time and the minimum lane changing distance as optimization targets on the basis of a quintic polynomial form; and establishing a minimum safe collision-free circle based on a vehicle-vehicle geometrical relationship. According to the lane changing trajectory quintic polynomial optimization method based on the steady-state steering principle, the motion planning trajectory capable of achieving stable tracking of the vehicle under the emergency lane changing condition and avoiding the sideslip risk can be generated, and the method has good application prospects for autonomous collision avoidance and safe driving of the vehicle in the emergency scene of the dynamic environment.
Owner:SOUTHEAST UNIV

Bolt 6D pose detection and visual servo method based on 3D template matching

The invention discloses a 6D pose detection and visual servo method of a bolt based on 3D template matching. The method comprises the following steps: S1, establishing a CAD model of the bolt; s2, acquiring a bolt image, and performing image preprocessing; s3, performing bolt feature information detection to obtain feature points, feature lines and feature surfaces; s4, bolt initial point matching is carried out, and matched feature information is stored; s5, performing tracking and 6D pose estimation on the bolt, and performing subtraction on the estimated 6D pose and a set expected pose as input of a visual servo algorithm; s6, acquiring the movement speed of the depth camera; s7, the movement speed of the mechanical arm is obtained and sent to the mechanical arm, and the mechanical arm is made to move; s8, the steps S5-S8 are repeated until the pose error in the step S5 is smaller than the pose error threshold value; and S9, a move L instruction is used for enabling an end effector installed at the tail end of the mechanical arm to conduct bolt alignment. According to the invention, the bolt can be stably tracked and the 6D pose of the bolt can be detected in real time.
Owner:SOUTHWEST JIAOTONG UNIV

Dynamic target tracking system and method based on image detection and holder

The invention relates to a dynamic target tracking system and method based on image detection and a holder. The system comprises a data processing terminal, a holder, a camera, a single-chip microcomputer and a motion unit. When the system carries out target detection, model training is carried out by collecting and marking target images and corresponding negative sample data under diversified environmental conditions, and target detection is carried out through subgraph division processing, so that the robustness, speed and detection precision of target detection are improved. When the target is dynamically tracked, the deviation angle between the central point of the target marking frame and the central point of the image picture is converted into a PWM signal to carry out real-time accurate control on the holder steering engine, and the holder speed intelligent coefficient and the decision boundary are introduced, so that the movement of the holder is smoother and more stable, and the target is continuously kept at the center of the image picture. And the tracking distance between the holder and the target is monitored and maintained through the laser radar, so that the holder can stably track the moving target.
Owner:NAT UNIV OF DEFENSE TECH

A flight control method and system for unmanned aerial vehicle tracking technology

The present invention discloses a flight control method and system of unmanned aerial vehicle tracking technology, which relates to the field of unmanned aerial vehicle control technology. The method comprises the following steps: before the unmanned aerial vehicle takes off, the airborne sensor is pre-started, parameter initialization and calibration operations are performed, and magnetic markers are installed on the tracking target at the same time; the body position of the unmanned aerial vehicle during flight is obtained, and a multi-sensor data fusion algorithm is used to sense the target position of the tracking target in real time; obstacles existing in the flight path are detected in real time, integrated into a three-dimensional environmental model, and combined with a follow-up visual tracking algorithm to capture the motion state of the tracking target; target tracking data is saved and fed back in real time, and the battery status and energy consumption rate of the unmanned aerial vehicle are monitored. By combining magnetic guidance technology, multi-sensor data fusion and a follow-up visual tracking algorithm, the present invention can achieve high-precision target tracking in a dynamic and complex environment, while effectively avoiding obstacles and ensuring the flight stability and tracking accuracy of the unmanned aerial vehicle.
Owner:HEFEI HEZHIXIN MICROELECTRONICS CO LTD

Single-leg sliding mode control method for quadruped robot based on disturbance observer

The invention relates to a quadruped robot single-leg sliding mode control method based on a disturbance observer, and belongs to the technical field of robot control. Firstly, a foot end track of a single leg of the quadruped robot in a swinging stage is established; then, establishing a kinematics model of a single leg of the quadruped robot to realize conversion between a foot end target position and a corresponding joint angle; on the basis, a nonsingular terminal sliding mode controller is designed to cope with dynamic control under the non-interference condition; finally, a final composite control strategy is designed in combination with a sliding mode controller and interference estimation, stable tracking of the joint angle of the robot is achieved, and therefore the anti-interference performance of the single-leg system is improved. According to the method, a composite controller is designed by combining a finite time disturbance observer and a nonsingular terminal sliding mode controller, so that the foot end trajectory tracking precision and the system robustness of the quadruped robot are improved, and the uncertainty caused by external disturbance and modeling errors of the robot is eliminated.
Owner:CHONGQING UNIV OF POSTS & TELECOMM

Structural multi-point dynamic displacement identification method based on improved KCF algorithm

The invention belongs to the technical field of displacement recognition, particularly relates to a structural multi-point displacement recognition method based on an improved KCF algorithm, and aims to solve the problems that an existing traditional passive target detection algorithm cannot perform generalized target tracking and a discriminant-based target tracking algorithm cannot meet the requirements of real-time performance and high precision. The method comprises the following steps: acquiring an image frame of a current moment in an input video in real time; obtaining a region of interest and extracting features; inputting the extracted features into a trained tracker based on an improved KCF algorithm to obtain a distribution diagram of peak response intensity, and further determining the position of the displacement recognition target at the current moment; calculating the pixel displacement of the displacement identification target by combining the position at the current moment and the initial position; determining a calibration factor through a conversion relation between a physical coordinate system and a pixel coordinate system; and calculating the real displacement of the displacement identification target in combination with the calibration factor and the pixel position. According to the invention, the precision and real-time performance of displacement identification are improved.
Owner:SHIJIAZHUANG TIEDAO UNIV

Photovoltaic maximum power point tracking method based on two-dimensional convolution and multi-agent deep reinforcement learning

PendingCN119002621Afast trackingUniform trackingElectric variable regulationSimulationPoint tracking
The invention provides a photovoltaic maximum power point tracking method based on two-dimensional convolution and multi-agent deep reinforcement learning. The main steps of the photovoltaic maximum power point tracking method based on two-dimensional convolution and multi-agent deep reinforcement learning are as follows: (1) measuring the maximum power points of a photovoltaic array under different irradiances and temperatures; (2) obtaining an area where a photovoltaic maximum power point is located through a two-dimensional convolutional network; (3) the multi-agent deep reinforcement learning model obtains an optimal control hyper-parameter in exploration and training; and (4) outputting the optimal control quantity. The method based on two-dimensional convolution and multi-agent deep reinforcement learning can solve the problems of complex environment change and stable control during photovoltaic maximum power point tracking, realizes a dynamic photovoltaic maximum power real-time tracking control function, optimizes the power generation stability of a photovoltaic system, and improves the performance and efficiency of the photovoltaic system.
Owner:GUANGXI UNIV

Power balance adjusting method and system of new energy hydrogen production system

PendingCN119029830AImprove real-time response rateReduce scheduling deviationLoad balancing in dc networkForecastingNew energyPower balancing
The invention relates to the technical field of hydrogen production process optimization, and discloses a power balance adjustment method and system for a new energy hydrogen production system, and the method carries out the optimization through minimizing the deviation between the hydrogen production load scheduling variable quantity of the new energy hydrogen production system and the current hydrogen production load scheduling plan quantity, thereby reducing the scheduling deviation, adapting to the load fluctuation, and improving the power balance of the new energy hydrogen production system. Stable tracking of day-ahead scheduling optimization is realized, and the optimal scheme of hydrogen production load scheduling of the new energy hydrogen production system is determined and executed by determining power operation balance of the new energy hydrogen production system as a constraint condition and optimizing and solving a target optimization function. The real-time response rate of the new energy hydrogen production system adapting to the fluctuating load is improved, and the power balance of the new energy generation power and the real-time load power is continuously maintained.
Owner:GUANGZHOU POWER SUPPLY BUREAU GUANGDONG POWER GRID CO LTD

Low-altitude unmanned aerial vehicle countering monitoring system based on state feature decoding

PendingCN121953740AImplement hierarchical trackingImplement directional countermeasuresDefence devicesWave based measurement systemsRadio frequencyThreat level
The invention discloses a low-altitude unmanned aerial vehicle countering monitoring system based on state feature decoding, relates to the technical field of unmanned aerial vehicle prevention and control, and is used for solving the problem of poor low-altitude target detection and countering. According to the invention, through closed-loop management and control of heterogeneous radar networking detection, signal level fusion processing, threat assessment and resource scheduling and intelligent countering decision, accurate identification and directional countering of the low-altitude unmanned aerial vehicle are realized; according to the method, the detection precision and the micro-Doppler feature extraction capability of a low-speed small target are improved by combining a virtual aperture synthesis technology, then unbalanced resource allocation is implemented based on a threat level, the system efficiency is optimized, and finally seamless migration of an interfered node task is realized by constructing a signal interference situation map. And continuous tracking and effect evaluation on the target are maintained in the active radio frequency countering process, so that the overall efficiency and reliability of low-altitude security and protection in a complex environment are effectively improved.
Owner:SHANGHAI YUNZHE INFORMATION TECHNOLOGY CO LTD

Pulse signal source tracking method based on robust Kalman filter

The invention discloses a pulse signal source tracking method based on a robust Kalman filter. The method comprises the following steps: reading a target state vector and error covariance matrix at a previous moment, and observing a noise covariance matrix; a variational Bayesian parameter before iteration, a target state vector and an error covariance matrix are initialized; starting iteration, and calculating the quadratic form sufficient statistics of the observation error and the forecast error; updating variational Bayesian parameters; updating the forecast error covariance matrix and the observation noise covariance matrix; calculating a target state vector and an error covariance matrix of the iteration; when the variation of the target state vector of the current iteration and the target state vector of the last iteration is smaller than the tolerance, ending the iteration, and outputting the target state vector at the current moment, the error covariance matrix and the observation noise covariance matrix; compared with a deterministic integral sampling method, the method provided by the invention adopts adaptive volume sampling to realize higher tracking precision under lower calculation cost.
Owner:SOUTHEAST UNIV

A method, device and equipment for adaptive coordinated control of powered thigh prosthesis

ActiveCN118830956Bimprove coordinationGuaranteed biomimicrySensorsDiagnostic recording/measuring
The present application belongs to the field of power prosthesis control, and specifically discloses a method, device and equipment for adaptive collaborative control of a power thigh prosthesis, including: obtaining examples of motion trajectories of healthy users crossing obstacles of different heights and / or different widths; when the prosthesis needs to cross an obstacle, the obstacle crossing process of the prosthesis is divided into the initial stage of obstacle crossing, the middle stage of obstacle crossing and the final stage of obstacle crossing according to the hip joint angle and angular acceleration of the residual limb; in the early stage of obstacle crossing, a knee joint trajectory example is selected and combined with the hip joint angle to determine the knee joint control angle of the prosthesis; in the middle stage of obstacle crossing and the final stage of obstacle crossing, two knee joint trajectory examples are selected for interpolation, and the knee joint control angle of the prosthesis is determined in combination with the hip joint angle, and the dynamic motion primitive algorithm is used to smoothly connect the knee joint trajectories of the latter part of the middle stage of obstacle crossing and the front part of the final stage of obstacle crossing, and the knee joint control angle of the final stage of obstacle crossing is updated. Through this application, adaptive collaborative control of a power thigh prosthesis is achieved to reduce the risk of falling.
Owner:SOUTHERN UNIVERSITY OF SCIENCE AND TECHNOLOGY