3results about How to "Realize high-precision tracking" patented technology

The present application relates to a kind of active hinged angle tracking control method based on sinusoidal trajectory of articulated vehicle, belong to vehicle intelligent control field.It aims to solve the problem of insufficient tracking accuracy caused by the step change of articulated angle when traditional articulated vehicle turns, the influence of nonlinear friction of hydraulic system and the risk of vehicle instability.The present application proposes: through path planning and cubic spline interpolation to generate smooth trajectory, the expected articulated angle is calculated through coordinate system conversion and kinematics model;Adopt Fourier series to decompose articulated angle into N order sine component, construct continuous and smooth bionic trajectory, eliminate step mutation;Based on articulated angle-hydraulic cylinder piston geometric constraint model, design adaptive tracking differentiator, robustly extract displacement high-order derivative through dynamic parameter adjustment mechanism, inhibit noise interference;Develop time-varying sliding mode controller, combine ATD output signal with asymmetric hydraulic cylinder model, use saturation function to suppress nonlinear friction buffeting, realize high-precision tracking of piston displacement.

This invention relates to the field of agricultural machinery testing technology, specifically to a dynamic loading test system and method for a hybrid tractor drive wheel test bench. The test system includes a physical test bench subsystem, a virtual simulation subsystem, and a model predictive controller as the central coordinating unit. The controller integrates a predictive model with the optimization objectives of minimizing equivalent fuel consumption, stabilizing battery state of charge, and minimizing tracking error. It synchronously solves and outputs torque distribution and loading torque commands in each control cycle, achieving real-time coordinated optimization of power output and dynamic load. By deeply integrating virtual working conditions, power distribution, and dynamic loading through model predictive control, complex field conditions such as plowing impact and hill driving can be reproduced with high fidelity, significantly improving the hardware-in-the-loop testing realism, verification efficiency, and safety of hybrid tractor energy management strategies.

The application discloses an unmanned ship formation control optimization method based on a double-channel reinforcement learning framework, aiming at solving the problems of existing adaptive dynamic programming control parameter setting difficulty, traditional genetic algorithm easy to fall into local optimum and multi-dimensional error physical quantity dimension not unified. The application constructs an unmanned ship formation mathematical model and a bottom online control channel, and constructs an upper offline optimization channel; a dimensionless fitness function based on state energy ratio is designed; the upper channel utilizes a reinforcement learning intelligent agent to dynamically decide a genetic operator selection strategy according to a population evolution state to generate a control parameter, the bottom channel utilizes the parameter to perform simulation and feeds back a performance index to the upper channel to update a decision model, and the optimal control parameter is output through double-channel closed-loop iteration. The application improves control parameter optimization efficiency and precision, eliminates the interference of order of magnitude difference on optimization, and significantly enhances the dynamic response speed, steady-state tracking precision and adaptive capacity of the unmanned ship formation system.