Decoupling Method for Six-Axis Force Sensors Based on WOA-ELM

The coupling problem between the six dimensions of force sensors seriously affects the improvement of measurement accuracy. To address this issue, this study focuses on the strain-based six-axis force sensor with a six-beam structure. The whale optimization algorithm (WOA) is used to optimize the input weights and hidden layer thresholds of the extreme learning machine (ELM) model, and a decoupling algorithm is proposed. The research results show that after decoupling, both Type I and Type II errors are controlled within 0.3%, effectively improving the measurement accuracy of the six-axis force sensor. Compared with other prediction models (Least Squares, BP neural network, and ELM), the WOA-ELM model proposed in this paper has significant improvements in prediction accuracy, decoupling time, and generalization ability.