12results about How to "Guaranteed convergence speed" patented technology

The invention discloses a mechanical arm specified performance high-precision trajectory control method based on an improved super-torsion expansion state observer. The mechanical arm specified performance high-precision trajectory control method comprises the following steps that a dynamic model of an n-joint mechanical arm is established; the kinetic model of the n-joint mechanical arm is re-described as a mechanical arm kinetic model based on total disturbance; an improved super-torsion expansion state observer is designed to estimate the total disturbance in the mechanical arm dynamic model based on the total disturbance; and according to the equivalent control law, the switching control law and the total disturbance estimation value, a recursive integral sliding mode controller based on funnel error transformation is constructed, and trajectory tracking of the mechanical arm is achieved. According to the method, the convergence speed of the system can be effectively improved, the buffeting phenomenon in the system can be effectively inhibited, and meanwhile, the method has good anti-interference performance.

The application discloses a kind of based on space alignment and timing correction multi-intersection adaptive signal control method, belong to traffic signal control field, including: through the traffic detection sensor deployed in intersection, real-time traffic state data are collected and sent to signal lamp controller;According to road network topology, send cooperative data to downstream intersection;Traffic flow and candidate phase set are constructed;The traffic data associated with candidate phase is aggregated as demand value and executes ordering transformation to obtain combination state;To combination state, execute spatial feature alignment processing and map as state feature vector;State feature vector is input into near-end strategy optimization controller, and output target phase and basic phase duration;The traffic flow information of last phase period on upstream intersection is combined to carry out timing correction to basic phase duration;Drive signal lamp hardware to execute and generate reward feedback and update near-end strategy optimization controller parameter.The application realizes the cooperative optimization of multi-intersection traffic signal, improves the traffic efficiency and adaptive capacity.

The application provides a three-dimensional path fuzzy tracking control method for underactuated AUV based on improved integral observer line-of-sight guidance law, which comprises the following steps: step one, a dynamic model of underactuated AUV disturbed by sea current is given, and the model uncertainty part in the dynamic model is separated; step two, a three-dimensional path tracking error model of underactuated AUV disturbed by sea current is constructed; step three, an improved reduced-order observer is designed, and the path tracking uncertainty part caused by sea current disturbance is estimated based on the observer; step four, an improved integral observer guidance law is designed, and an adaptive part in the guidance law is designed; and step five, a controller is designed according to the underactuated AUV tracking error model and a fuzzy logic system. The three-dimensional path tracking control method designed in the application can make the underactuated AUV complete the task requirements of accurate path tracking and rapid convergence under the dynamic disturbance of sea current.

The invention provides a transformer bushing partial discharge mode identification method and system, and relates to the technical field of power system fault diagnosis. Comprising the steps of obtaining transformer bushing partial discharge signals and extracting original features; carrying out dimension reduction processing on the extracted original features to obtain features after dimension reduction; a radial basis function SVM model is constructed, and parameters of the radial basis function SVM model are optimized through a GTO algorithm optimized by the chimpanzee troops; and inputting the dimensionality-reduced features into a parameter-optimized radial basis function SVM model for classification to obtain a classification identification result. According to the method, the KPCA algorithm and the GTO-SVM algorithm are combined, KPCA dimension reduction processing is carried out on high-frequency signal features, data redundancy is reduced, SVM parameter selection is optimized through the GTO algorithm, the classification and recognition performance is remarkably improved, the high recognition rate is shown in partial discharge fault diagnosis, and particularly the method has remarkable advantages in the aspect of processing complex fault modes.

The invention discloses a multi-modal large model training method, and relates to the technical field of artificial intelligence, and the method comprises the steps: data collection, preprocessing, feature extraction, multi-modal fusion, and model training. During preprocessing, for temperature, humidity and pressure parameters, abnormal value analysis is carried out by calculating an average value and a standard deviation, and a model is obtained; calculating an intermediate value by using front and back normal values to replace an abnormal value; for coordinate position information, calculating a direction angle according to adjacent coordinates, comparing the direction angle with a threshold value to judge abnormity, and replacing abnormal coordinates with middle coordinates of front and back normal coordinates; a feature extraction link: calculating a temperature change rate mean value of adjacent nodes as a feature coefficient according to the temperature; calculating the mean value of the humidity and the absolute value of the mean value difference; the pressure adopts a maximum and minimum parameter difference value; calculating a speed mean value of adjacent nodes according to coordinates; calculating a fusion feature vector according to a preset weight during multi-modal fusion; according to the method, multi-modal data can be effectively processed, and the model performance and accuracy are improved.

The present invention relates to the field of multi-agent collaborative technology, and discloses a ship collaborative control method based on self-learning, step S10, using an input module to obtain the parameters of each ship in the multi-agent system, including the expected operation trajectory of the ship; step S20, using a parameter and network initialization module, a network weight assignment module and a global loop module to start the global loop; step S30, using a network training module and a local loop module to start the local loop based on the initialized related parameters; step S40, using the iterative control law and the local optimal performance index function to replace the current iterative control law and performance index function, and using the output module to obtain the ship collaborative control strategy. In the present invention, combined with the key technologies of self-learning optimization ADP algorithm and multi-agent system communication, with the support of these technologies, it can be realized that multiple ships can automatically obtain control strategies according to the status of themselves and adjacent ships during operation, thereby achieving the purpose.

The application discloses a polar code construction method based on genetic algorithm acceleration convergence, which comprises the following steps: step 1, setting parameters; step 2, initial genetic algorithm population; step 3, selecting two parents from the population by using a roulette algorithm; step 4, crossing the two parent information bits to generate offspring; step 5, mutating the unlocked information bits of the offspring by using the non-locked frozen bits; step 6, adding the mutated offspring to the population, selecting the optimal one according to the fitness, updating the population and recording the population information; step 7, repeating steps 3 to 6 until the number of genetic iterations reaches a number of spans, judging whether the optimal fitness decreases to a limit or not, if yes, reducing the number of locked bits, temporarily releasing the channel, repeating steps 3 to 6 until the number of genetic iterations reaches a minimum number of spans, if the optimal fitness decreases and the temporarily released channel changes, updating the channel locking condition according to the temporarily released channel, if no, directly repeating steps 3 to 6; and step 8, ending when the genetic iteration stopping condition is met. The application can solve the problem of slow convergence speed by dynamically locking the channel.

This invention discloses a sliding mode control method and system for tracking the trajectory of a robotic arm. Addressing external disturbances and model uncertainties in the robotic arm system, it proposes an improved non-singular fast terminal sliding mode surface, combined with an adaptive disturbance upper bound estimation strategy, to design a robust controller with finite-time convergence characteristics. Furthermore, it proposes an adaptive boundary layer thickness adjustment method based on the sliding mode surface norm to suppress chattering while ensuring tracking accuracy. Specifically, it includes: establishing a six-degree-of-freedom robotic arm dynamic model; designing a sliding mode surface integrating exponential and fractional power terms; constructing an equivalent control law; designing an adaptive law to estimate the upper bound of the lumped parameter uncertainty; replacing the traditional sign function with an adaptive boundary layer saturation function; and proving the finite-time stability of the closed-loop system using Lyapunov theory. This invention can significantly reduce control input chattering and energy consumption, and is suitable for high-precision motion control scenarios such as industrial manufacturing, medical surgery, and aerospace.

This invention belongs to the field of communication technology and discloses a federated learning method based on partial client participation and power constraints. The method includes: employing biased client selection, setting client addressability and continuously reporting to a central server, allowing the central server to understand the state of each client during iteration; and allocating power across communication time slots by adding a total power constraint, enabling devices to transmit their local updates to the server. This invention addresses the problems of existing technologies by reducing communication costs while maintaining model convergence performance. The proposed design can mitigate the negative impacts caused by imperfect channel conditions. Convergence of the learning process is slowed by power control, while biased client selection accelerates convergence, balancing model aggregation. This invention can guarantee fast convergence under harsh wireless conditions with low signal-to-noise ratios, and is cost-effective in terms of time and energy savings in wireless FL systems.

The invention discloses a student score online monitoring method and system for processing high-dimensional features based on an SVR model, and relates to the technical field of student score monitoring, and the method comprises the following steps: S1, data collection; s2, initial parameters are set; S3, a model is constructed and trained; step S4, feature selection and parameter optimization; and S5, carrying out online monitoring and feedback. According to the method, the improved breach algorithm is introduced to select and optimize the features and the model parameters, compared with a traditional method, the IDA algorithm continuously searches better solutions in a parameter space by simulating the breach process, and finally a parameter combination enabling the model prediction error to be minimum is found, so that the prediction accuracy and efficiency of the SVR model are improved, and the prediction efficiency of the SVR model is improved. The calculation complexity of the model is reduced, the parameters of the SVR model and the feature selection process are optimized, the adaptability of the model is improved, real-time monitoring and feedback of student scores are achieved, the real learning condition of students is accurately reflected, and the requirement for real-time monitoring is met.

The invention provides an optimization method for improving the stability and economy of a wind-light-fire-bundled power system by using an optimal dynamic convergence method, and the method comprises the steps: connecting various generators to a bus of a multi-machine power system through a transformer, and constructing the wind-light-fire-bundled power system; a power system stabilizer, a unified power flow controller and a static synchronous compensator of an additional power oscillation damper are connected into the wind-light-fire bundled power system; the method comprises the following steps: establishing a target function based on a damping ratio, voltage and active power according to the bus voltage of a controller and the active power of a generator in a wind-solar-thermal bundled power system; and performing coordinated optimization on the parameters of the wind, light and fire bundled power system controller by using an optimal dynamic convergence method based on an Euclidean distance weighting strategy, an inertia weight dynamic adjustment strategy, a gradient position updating strategy and an adaptive step length updating strategy to obtain optimized controller parameters. According to the method, low-frequency oscillation in the power system is effectively improved, active power loss generated by system operation is reduced, and the overall stability and economical efficiency of the power system are remarkably improved.

The invention discloses a sensing-free force position control method for a cable-driven robot. The sensing-free force position control method comprises the steps that (1) a cable-driven robot dynamic model containing unknown disturbing force is established; 2) establishing a control structure for seamless switching between cable force control and pose control; (3) a real-time cable force distribution algorithm meeting given control constraint conditions and any number of ropes is designed, pose estimation is obtained based on a forward kinematics model and a Newton iteration method, and motor torque is solved through a kinetic model and friction force compensation; 4) constructing a state observer for predicting unknown disturbing force and a rapid pose error tracking controller; and 5) designing a cable force compensation optimization algorithm to ensure that the output of the controller is always non-negative. According to the method, force control, position control and seamless switching of the force control and the position control of the cable-driven robot are achieved under the sensor-free condition, and the problem that the force control and the position control of the cable-driven robot depend on a force or torque sensor is effectively solved.