Welding robots play a crucial role in manufacturing industries, where minimizing energy consumption (EC) is increasingly important for enhancing efficiency and reducing operational costs. This study presents a data-driven approach to model and optimize EC in welding robot systems, utilizing a dataset generated from real-world measurements of robot EC during various motions and integrated with trajectory data. A predictive model was developed using an extreme gradient boosting (XGBoost) regression technique focused on joint torque data, which achieved a mean absolute percentage error (MAPE) of 1.86%. Furthermore, trajectory optimization was achieved by adjusting the spatial position of the workpiece, effectively reducing EC. To solve the optimization problem, an improved whale optimization algorithm (IWOA) was employed. Experimental validations with a welding robot demonstrate that the proposed method not only accurately predicted EC with a MAPE of 2.66% but also reduced the robot system’s EC by 6.72%, outperforming the traditional method focused solely on joint motor EC, which achieved a 4.08% reduction. These results confirm the efficacy of the proposed approach, underscoring its potential for broad application in robotic systems to achieve significant energy savings.

Robotic tack welding poses challenges in path optimization due to local optimum entrapment, limited adaptability, and high-dimensional complexity. To overcome these challenges, a Lévy flight-enhanced improved whale optimization algorithm (LF-IWOA) was developed. The algorithm combines elite opposition-based learning (EOBL), differential evolution (DE), and Lévy flight (LF) to improve global exploration capability, increase population diversity, and improve convergence. Additionally, a dynamic trajectory optimization model is designed to consider joint-level constraints, including velocity, acceleration, and jerk. The performance of LF-IWOA was evaluated using two industrial workpieces with varying welding point distributions. Comparative experiments with metaheuristic algorithms, such as the genetic algorithm (GA), WOA and other recent nature-inspired methods, show that LF-IWOA consistently achieves shorter paths and faster convergence. For Workpiece 1, the algorithm reduces the welding path by up to 25.53% compared to the genetic algorithm, with an average reduction of 14.82% across benchmarks. For Workpiece 2, the optimized path is 18.41% shorter than the baseline. Moreover, the dynamic trajectory optimization strategy decreases execution time by 26.83% and reduces mechanical energy consumption by 15.40% while maintaining smooth and stable joint motion. Experimental results demonstrated the effectiveness and practical applicability of the LF-IWOA in robotic welding tasks.

Human gait exhibits stable contralateral coupling, making healthy-side motion a viable predictor for affected-limb kinematics. Leveraging this property, this study develops FusionTCN–Attention, a causality-preserving temporal model designed to forecast contralateral hip and knee trajectories from unilateral IMU measurements. The model integrates dilated temporal convolutions with a lightweight attention mechanism to enhance feature representation while maintaining strict real-time causality. Evaluated on twenty-one subjects, the method achieves hip and knee RMSEs of 5.71° and 7.43°, correlation coefficients over 0.9, and a deterministic phase lag of 14.56 ms, consistently outperforming conventional sequence models including Seq2Seq and causal Transformers. These results demonstrate that unilateral IMU sensing supports low-latency, stable prediction, thereby establishing a control-oriented methodological basis for unilateral prediction as a necessary engineering prerequisite for future hemiparetic exoskeleton applications.

To address the challenge of autonomous process adaptation in non-standard components with continuously varying groove angles, this study proposes an intelligent decision-making framework based on Response Surface Methodology (RSM) for oscillation welding. Instead of solely identifying a single optimal parameter set, RSM is employed as a knowledge-modeling tool to reveal adaptive relationships between groove geometry and key welding parameters. A Central Composite Design (CCD) is utilized to establish predictive models for weld geometry under varying conditions: wire feed rate (8–12 m/min), travel speed (5–9 mm/s), travel angle (70–110°), oscillation amplitude (2–6 mm), dwell time (0.2–0.6 s), and groove angle (80–100°). The significance and adequacy of the models are validated through analysis of variance (ANOVA), demonstrating high predictive accuracy with all coefficients of determination (R²) exceeding 0.82. Furthermore, defect-aware physical constraints derived from the formation mechanism of bottom humping are incorporated into the optimization process, specifically restricting the travel angle to a push angle of 70–85° to ensure feasible and reliable decision outputs. Based on the established response surfaces, geometry-dependent parameter selection rules are derived to simultaneously optimize root penetration (target 8.5–10.5 mm) and sidewall fusion (>2.5 mm) for groove angles ranging from 80° to 100°. Experimental validation confirms that the proposed decision-making strategy achieves stable bead formation and defect-free fusion, demonstrating high quantitative reliability with root penetration prediction errors below 7% and bead width errors below 13%. This work bridges the gap between geometric perception and process control, providing a practical pathway toward intelligent and adaptive robotic welding of non-standard components.

Arc stability is a critical factor determining the quality and reliability of welded joints in robotic welding, yet its quantitative, real-time assessment remains a significant challenge. This paper proposes a novel physics-informed approach that overcomes the limitations of single-feature methods. A six-dimensional feature space is constructed to characterize the arc’s state from geometric, energetic, and periodic perspectives. On an experimental robotic GMAW platform, a unique physics-informed labeling strategy was employed: welding experts established quantitative stability thresholds for each feature by correlating their time-series values with direct physical observations from synchronized high-speed imaging. The resulting feature space demonstrated excellent separability, which was validated by training a Support Vector Machine (SVM) model that achieved a classification accuracy of 96.7%. Furthermore, t-SNE visualization confirmed a distinct clustering of stable and unstable states. This robust and interpretable method provides a powerful tool for real-time monitoring and lays a solid foundation for developing adaptive intelligent control systems for robotic welders.