FEA-ANFIS Dataset for Fault-Tolerance Analysis of a Twelve-Legged Jansen Walking Robot

This dataset accompanies the manuscript "Symmetry-Breaking and Fault-Tolerance Analysis of a Twelve-Legged Jansen Robot Using a Hybrid FEA-ANFIS Framework" submitted to Symmetry (MDPI) Special Issue on "Finite Element Analysis, Structural Dynamics, and Symmetry/Asymmetry". The dataset comprises: (1) 210 finite element analysis (FEA) results covering 21 failure scenarios (single-leg, diagonal, same-side, group, and multi-leg failures) under 10 load levels (20-200 N) on a PLA-based 3D-printed twelve-legged Jansen walking robot, computed using ANSYS Workbench 2024 R2 (Static Structural, SOLID186 elements, ~211k nodes / 408k elements per case). (2) Two novel dimensionless symmetry-breaking metrics: Resilience Index (RI) and Asymmetry Index (AI), computed for all 21 scenarios. (3) MATLAB ANFIS (Adaptive Neuro-Fuzzy Inference System) training/evaluation code and two trained .fis models for maximum von Mises stress (R² = 0.817) and safety factor (R² = 0.936) prediction. (4) Comparison data with three baseline machine-learning methods: Linear Regression, Polynomial Regression (degree 2), and Multilayer Perceptron neural network. Software requirements: MATLAB R2023b or later with the Fuzzy Logic Toolbox. The dataset enables full reproduction of all tables and figures in the accompanying manuscript. This dataset is released under the Creative Commons Attribution 4.0 International (CC BY 4.0) license.