Adaptive Arc-Voltage Control for Narrow-Gap Pulsed TIG Welding Based on Feedback Reconstruction and Effective-Error Identification

Reliable arc-length regulation is essential in narrow-gap pulsed tungsten inert gas (TIG) welding because restricted groove clearance makes small torch-height errors capable of destabilizing the arc and reducing process repeatability. However, pulse switching, wire–pool interaction, and acquisition noise generate voltage transients that conventional arc-voltage control (AVC) may misinterpret as geometric deviations, whereas strong filtering delays genuine drift correction. This study proposes a reconstruction–decision–adaptation architecture. An experimentally calibrated actuator–arc model supports adaptive Kalman filter (AKF)-based feedback reconstruction; an amplitude–duration–area criterion fixed from open-loop statistics rejects brief disturbances; and only identified effective errors drive online fuzzy-PID gain adaptation. Using fixed decision thresholds, NSGA-II jointly tunes estimator and controller parameters based on voltage RMSE and cumulative actuator travel. Across 20 simulation seeds, the tuned configuration reduced voltage RMSE and ramp-disturbance error by 15.8% and 51.0%, respectively, while travel decreased by 1.9%. Physical welding tests demonstrated improved voltage regulation while maintaining actuator activity: the 13.0 V comparison reduced RMSE by 19.7% and adjustment events by 8.3%, while six additional records at three prescribed voltages showed consistent mean voltage regulation within the tested conditions.