• Proposes a data-driven iterative learning fault estimation method that requires no model parameters, eliminating the need for system modeling.
• Utilizes orthogonal triangular decomposition and singular value decomposition to construct a residual generator from input-output data.
• Achieves superior transient and steady-state performance with enhanced real-time capability compared to existing methods.
• Validates effectiveness on a mobile robot, demonstrating reduced manual intervention and operational complexity.