6results about How to "Reduce model error" patented technology

The application relates to an optimal design method of a modular axial flux permanent magnet synchronous wind generator, and belongs to the field of wind power generation. The generator comprises a stator and a rotor; torque pulsation and torque density are used as optimization targets, and stator slot depth, rotor permanent magnet thickness and rotor permanent magnet pole arc coefficient are used as to-be-optimized design variables; constraint conditions of the design variables are determined, a Latin hypercube sampling experiment is carried out, a DNN proxy model of the optimization target and the to-be-optimized design variables is established; a Bayesian optimization algorithm is used to optimize hyperparameters of the proxy model, and optimal hyperparameters are obtained; the proxy model adopting the optimal hyperparameters is trained to obtain an optimal proxy model, and based on the optimal proxy model, an NSGA-II optimization algorithm is used to optimize the to-be-optimized design variables, and finally, an optimal combination of the to-be-optimized design variables is determined. The application can reduce modeling errors, improve calculation efficiency, robustly process multi-target trade-off under complex parameter coupling conditions, and effectively improve the performance of the modular generator.

The application provides a wind turbine generator control method and device and a wind turbine generator. The method comprises the following steps: obtaining an initial control rate of the wind turbine generator based on a constructed dynamic model of the wind turbine generator and a selected reference model of the wind turbine generator; obtaining time delay information in a system of the wind turbine generator, calculating a time delay observation value of the wind turbine generator based on the time delay information, and using the time delay observation value to describe a dynamic response characteristic of the wind turbine generator, to represent an interference received by the wind turbine generator in a running state and a model error of the wind turbine generator; and substituting the time delay observation value into the initial control rate to obtain a target control rate, and using the target control rate to control the wind turbine generator. The method can reduce the influence of the working condition interference of the wind turbine generator on the control effect, compensate for the system modeling error, and improve the effectiveness and stability of the wind turbine generator control.

This invention discloses a furnace temperature control method, relating to the field of intelligent control of electronic packaging welding processes. The method includes: collecting real-time temperature data and welding process parameters of the substrate to be welded, and acquiring post-weld deformation data; aligning and fusing the real-time temperature data, process parameters, and deformation data to extract key features of the furnace temperature curve, and constructing a data record set by associating them with the deformation of corresponding measuring points; based on the data record set, establishing a quantitative prediction model using regression analysis or machine learning algorithms; under preset process constraints, optimizing the furnace temperature curve setpoint with the predicted warpage as the optimization objective, calculating the corresponding predicted warpage using the quantitative prediction model, generating the optimal furnace temperature curve setpoint, and sending it to the welding equipment for execution. By constructing a quantitative prediction model using temperature data from sensitive points and post-weld deformation, the optimal furnace temperature curve is generated through reverse optimization to suppress welding warpage.

This invention relates to the field of unmanned aerial vehicle (UAV) swarm control technology, and more particularly to a method, system, medium, and software product for simulating and modeling phase trajectory of a UAV network system. The method includes system and task analysis, construction of interaction rule matrices, state analysis and phase vector space construction, approximate calibration of the stability domain, determination of the ultimate impulse, simulation of disturbance impulse injection, and data segmentation and transition zone marking, realizing a closed-loop process from modeling to disturbance assessment. Trajectory prediction is performed using a NARX neural network, combined with Gaussian white noise augmentation and multi-round simulation to achieve approximate calibration of the stability domain and determination of the ultimate impulse, and automatically outputs a structured trajectory dataset. This invention improves modeling accuracy, simulation efficiency, and system security.

This invention discloses a method for identifying damage to aircraft smart skin based on complex modal expansion and Kalman filtering. The steps include: acquiring strain values ​​at the location of fiber optic strain sensors; constructing a finite element model of the aircraft smart skin and extracting modal features; constructing a complex modal expansion equation; solving for the full-field strain value of the aircraft smart skin based on the complex modal expansion equation; and obtaining the damage identification result of the aircraft smart skin. This invention uses a finite element model obtained by discretizing a proportional 3D model of the aircraft smart skin to solve for the full-field strain value. It employs a finite fiber optic strain sensor to expand the full-field strain in real time and performs damage identification based on the full-field strain. The finite element model has a simple structure and does not require iterative optimization, effectively improving identification efficiency and robustness while ensuring identification accuracy.

The invention discloses a robot friction compensation and external force estimation method based on an ANFIS, and the method comprises the steps: enabling a joint to walk through a static friction-Stribeck-viscous friction full speed range in a controlled environment, collecting the angular speed and motor torque, carrying out the preprocessing, training an ANFIS model, and obtaining a friction torque estimation value which can be output in real time; introducing the estimated value as feed-forward compensation into a generalized momentum observer, and calculating an external torque initial value; denoising is carried out through median filtering and Butterworth low-pass filtering, and a clean external torque signal is obtained; and finally, establishing an AR (1) noise model under the working condition of no external force, setting a dynamic collision threshold value by using the variance and the safety margin, and judging the collision if the signal exceeds the threshold value. Only a joint encoder and motor current are used in the whole process, an additional force sensor is not needed, and accurate and real-time external force sensing and collision protection can be provided for dragging teaching and man-machine cooperation.