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

3results about How to "Realize automatic tuning" patented technology

Methods and devices for tuning control parameters of magnetic levitation bearings, storage media and electronic equipment

This invention relates to a method and apparatus for tuning control parameters of magnetic levitation bearings, a storage medium, and an electronic device, belonging to the technical field of magnetic levitation control parameters. The tuning method includes: S1, constructing a mathematical model of a PID parameter optimization problem; S2, generating a Bayesian optimization sample set, fitting a Gaussian process surrogate model, and globally exploring to generate a PID parameter subspace; S3, executing a dung beetle optimization algorithm within the subspace to obtain the optimal point (x) within the subspace. db y db S4, add the optimal point to the Bayesian optimization sample set and update the Gaussian process model; S5, repeat steps S2 to S4 until the condition is met, and output the optimal PID parameter x. db * By combining the global exploration capability of Bayesian algorithms with the local development capability of the dung beetle algorithm, the Bayesian optimization reduces the dependence on the initial sample size, while the dung beetle algorithm accelerates convergence within the subspace, thus balancing efficiency and accuracy.
Owner:SHANDONG ZHANGQIU HUADONG BLOWER

Optical cable line tuning method and system

ActiveCN119030617ARealize automatic tuningReduce tuning costsRadio-over-fibreEngineeringcomputer science
An optical cable line tuning method and system relates to the field of optical cable resource maintenance, and comprises the following steps: when a target landmark point with accurate information is received, determining two target adjacent points which are adjacent to the left and right of the target landmark point on a target optical cable section where the target landmark point is located; performing insertion processing on the target landmark point according to the position information of the two target adjacent points and the position information of the target landmark point, and updating the serial number of the landmark point behind the target landmark point on the target optical cable section; for each target inaccurate landmark point, calculating the optical cable optimization length of the target inaccurate landmark point according to the optical cable theoretical length and the optical cable actual length corresponding to the target landmark point, the optical cable theoretical length of the target inaccurate landmark point and the optical cable theoretical length of the target accurate landmark point closest to the target landmark point; and performing landmark point data adjustment on the target optical cable section based on the optical cable optimization length. According to the invention, automatic tuning of inaccurate landmark point data in an optical cable line can be realized, so that the tuning cost is effectively reduced.
Owner:FIBERHOME TELECOMMUNICATION TECHNOLOGIES CO LTD

Trajectory generation method based on deep reinforcement learning training game coefficient

PendingCN122281953ARealize automatic tuningReduce development costsAlgorithmSimulation
A trajectory generation method based on deep reinforcement learning for training game coefficients. The advantages of this invention are as follows: By organically combining deep reinforcement learning and game theory trajectory planning, this invention achieves automated and intelligent optimization of game coefficients. It automatically learns the sensitivity coefficient α in the game objective function using algorithms such as DQN, completely replacing traditional manual parameter tuning methods and significantly reducing development costs and time. A reward function centered on the vehicle's forward distance guides the vehicle to pass quickly, while introducing penalty terms such as collision and acceleration to enhance safety and comfort. The generated trajectory outperforms manually tuned results in terms of traffic efficiency, safety, and smoothness. Simultaneously, it preserves the interpretability of the game theory model; the optimized α value has a clear physical meaning and can dynamically adjust the driving style according to the real-time environment, improving the system's scene adaptability and generalization robustness.
Owner:FUJIAN POLYTECHNIC OF WATER CONSERVANCY & ELECTRIC POWER