Abstract
In modern production environments, advanced and intelligent process monitoring strategies are required to enable an unambiguous diagnosis of the process situation and thus of the final component quality. In addition, the ability to recognize the current state of product quality in real-time is an important prerequisite for autonomous and self-improving manufacturing systems. To address these needs, this study investigates a novel ensemble deep learning architecture based on convolutional neural networks (CNN), gated recurrent units (GRU) combined with high-performance classification algorithms such as k-nearest neighbors (kNN) and support vector machines (SVM). The architecture uses spatio-temporal features extracted from infrared image sequences to locate critical welding defects including lack of fusion (false friends), sagging, lack of penetration, and geometric deviations of the weld seam. In order to evaluate the proposed architecture, this study investigates a comprehensive scheme based on classical machine learning methods using manual feature extraction and state-of-the-art deep learning algorithms. Optimal hyperparameters for each algorithm are determined by an extensive grid search. Additional work is conducted to investigate the significance of various geometrical, statistical and spatio-temporal features extracted from the keyhole and weld pool regions. The proposed method is finally validated on previously unknown welding trials, achieving the highest detection rates and the most robust weld defect recognition among all classification methods investigated in this work. Ultimately, the ensemble deep neural network is implemented and optimized to operate on low-power embedded computing devices with low latency (1.1 ms), demonstrating sufficient performance for real-time applications.
Highlights
Process monitoring and fault detection are an essential requirement for a multitude of manufacturing processes and are relevant and necessary when human safety is at stake
Weld quality is affected by several factors, such as thermal conditions during laser–material interaction, variations in material properties, impurities on the workpiece surface, and changes in the properties of the laser beam, all of which may result in an unacceptable product [2,3]
During laser welding the complex interaction between laser beam and the weld material can lead to weld imperfections such as cavities, solid inclusion, lack of fusion as well as lack of penetration, weld seam deformations, cracks, and other deviations from the desired weld quality
Summary
Process monitoring and fault detection are an essential requirement for a multitude of manufacturing processes and are relevant and necessary when human safety is at stake (e.g., safety-critical automotive parts, battery parts, aerospace parts). Recent advances in sensing technology and an increasing number of sensors applied on laser machines and processes enable online weld quality monitoring with higher precision by combining multiple data sources. Deep learning models are capable of extracting more refined and complex image characteristics and are expected to provide higher classification accuracies than conventional approaches based on feature engineering and traditional classifiers. CNNs and GRUs with high performance classification algorithms (i.e., SVM, kNN) for real time detection of six different welding quality classes; Comparison of the proposed architecture with available deep learning architectures as well as classical machine learning methods based on manual feature extraction; Assessment of the significance of geometric and statistical features extracted from the keyhole and weld pool region of two different image data sources (i.e., MWIR and NIR).
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
