A multi-task spatiotemporal deep neural network for predicting penetration depth and morphology in laser welding

2026-06-24

AI Summary

This study addresses the challenge of real-time, accurate assessment of weld penetration status and bead morphology in laser keyhole welding, a critical bottleneck in welding quality control. To overcome this limitation, the authors propose a multitask deep learning architecture that integrates convolutional neural networks with a state-space model, jointly leveraging spatiotemporal features extracted from molten pool images captured by a CMOS camera and process parameters to simultaneously predict penetration status, penetration depth, and cross-sectional weld bead morphology. By constructing a high-quality dataset and incorporating a multitask learning mechanism, the model achieves significantly enhanced robustness and generalization capability. Experimental results demonstrate a penetration status prediction accuracy of 99.35%, a penetration depth prediction error as low as 1.79 mm, and a 95.65% accuracy in reconstructing cross-sectional weld bead profiles.

Abstract

In laser penetration welding, the assessment of penetration state and weld seam morphology plays a crucial role in determining the weld quality. This paper presents a comprehensive introduction of the innovative muti-task deep learning model that has the capability to predict penetration state, depth, and weld seam morphology with high accuracy. The monitoring platform relies on weld pool images captured during the laser welding process using a complementary metal-oxide-semiconductor camera. The proposed model integrates spatiotemporal features extracted from top weld pool images along with welding parameters, establishing a deep learning framework based on convolutional neural networks and state space models for more efficient extraction and processing of spatial-temporal information. Furthermore, a reliable method for constructing the dataset is proposed to enhance both robustness and generalization capability of the developed model. Validation results on the test set demonstrate that prediction accuracy for penetration state can reach 99.35%, while prediction error for penetration depth is 1.79 millimeter, and accuracy of reconstructing the weld cross-section is 95.65%. This study provides new insights and methodologies for in-situ quality control strategies in laser penetration welding systems.

Problem

• laser welding
• penetration depth
• weld morphology
• weld quality
• spatiotemporal prediction

Innovation

• multi-task learning
• spatiotemporal deep neural network
• laser penetration welding
• weld pool imaging
• state space model