Six-dimensional force / torque sensor calibration data enhancement method and system

By using a weight-based loading method and an error-adaptive interpolation method, the training dataset of the six-dimensional force/torque sensor is expanded, which solves the overfitting problem caused by the sparsity of calibration data, improves the measurement accuracy and stability of the sensor, and is applicable to multiple application fields.

CN120760930BActive Publication Date: 2026-09-04SOUTHEAST UNIV
2 Cites 0 Cited by

Patent Information

Application Number
CN202510907107.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-07-02
Publication Date
2026-09-04
Estimated Expiration
2045-07-02

AI Technical Summary

Technical Problem

The existing calibration data for six-dimensional force/torque sensors is sparse, which makes the decoupling model prone to overfitting. This makes it difficult to meet the requirements of nonlinear decoupling algorithms for data density and diversity, thus affecting the accuracy and stability of the sensor.

Method used

The calibration experiment was conducted using a weight-based loading method to acquire sensor output data in real time. By using high-density and low-density calibration experimental data, combined with error adaptive interpolation and weighted training, the training dataset was expanded, the data spatial distribution was optimized, and the model's generalization ability was improved.

Benefits of technology

It significantly improves the richness and effectiveness of the training dataset, alleviates the overfitting problem of the nonlinear decoupled model, and enhances the measurement accuracy and stability of the sensor. It is applicable to fields such as robot end-effector force control, intelligent manufacturing, aerospace assembly, and biomedical equipment.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application discloses a kind of six-dimensional force / torque sensor calibration data enhancement methods, first using weight hammer type loading method is carried out calibration experiment to six-dimensional force / torque sensor, the output data of sensor is acquired in real time, the data vector of the output data of each loading point sensor and actual loading force value constitutes training data and test data;Again, according to the local linear error of each loading point, adaptive interpolation is carried out, and data is expanded;Finally, training data and the expanded data obtained by interpolation are merged, input into six-dimensional force / torque decoupling model for weighted training, the model parameters are fixed, and the final decoupling model is obtained, the test data is used to test the decoupling effect of the model, so as to realize data enhancement.The method of the present application enhances the spatial density and feature expression ability of the training data set without increasing the complexity of the experiment, improves the generalization ability of the nonlinear decoupling model under unknown loading conditions, and improves the measurement accuracy and stability of the six-dimensional force / torque sensor.
Need to check novelty before this filing date? Find Prior Art