Identification and modeling of 3-DoF mechanism with nonlinear friction effects by combination of LuGre and neural network modeling

Here we present two types of data connected with our paper "Identification and modeling of 3-DoF mechanism with nonlinear friction effects by combination of LuGre and neural network modeling": 1) Comparison of measured outputs with outputs generated by pure LuGre model and model combining LuGre and Neural Network. These data are present in "data_results" subdirectory and correspond to all figures in article's appendix. These data are extended to all absorber legs' motion (for sake of brevity, only second leg's data have been graphically presented in the article). A CSV file is used per leg per experiment. 2) In addition to the resulting data, an executable Python notebook "train_neural_network.ipynb" is available in subdirectory "nn_training_software" for final optimization of Neural Network model weights. This subdirectory contains two more datafiles with training and testing data used by the Python notebook: "AI_in_uy_var_B_train.csv" and "AI_in_uy_var_B_test.csv".