A convolutional neural network-based multi-sensor fusion approach for in-situ quality monitoring of selective laser melting. (July 2022)

• Record Type: Journal Article
• Authors: Li, Jingchang; Zhou, Qi; Cao, Longchao; Wang, Yanzhi; Hu, Jiexiang
• Is Part Of: Journal of manufacturing systems. Volume 64(2022)
• Page Start: 429
• Page End: 442
• Publication Date: 2022-07
• Subjects: Additive manufacturing -- Selective laser melting -- Multi-sensor fusion -- In-situ quality monitoring -- Convolutional neural network; Manufacturing processes -- Periodicals; Production engineering -- Data processing -- Periodicals; Robots, Industrial -- Periodicals; Production, Technique de la -- Informatique -- Périodiques; Robots industriels -- Périodiques; Electronic journals; 670.42
• DOI: 10.1016/j.jmsy.2022.07.007
• Languages: English
• ISSNs: 0278-6125

Abstract

Abstract: Selective laser melting (SLM) is an emerging and popular metal additive manufacturing (AM) technique to fabricate advanced metal components with complex geometries. However, its broad adoption in industry is still hampered by poor process repeatability and low part consistency. To overcome this limitation, there are growing efforts towards in-situ monitoring and control technologies for quality assessment of parts. In this paper, a convolutional neural network (CNN)-based multi-sensor fusion approach is proposed to integrate layer-wise images, acoustic emission signals, and photodiode signals for in-situ quality monitoring of SLM. An off-axial in-situ monitoring system equipped with three types of sensors, namely, a digital camera, a microphone, and a photodiode is first developed for signatures acquisition. Porosity and density measurements are then carried out to label the layer-based sensing data and measure the quality. Thereafter, an image processing method and a signal-to-image strategy are proposed to merge the multi-source heterogeneous sensor data. Finally, three CNN-based multi-sensor fusion models are developed from data-level fusion, feature-level fusion, and decision-level fusion respectively and compared in quality identification. Data-level fusion model is established through channel fusion, features are extracted and fused in the feature-level fusion model, and the decision-level fusion model is developed by fusing the classification results from individual models. Results showed that the proposed CNN-based multi-sensor fusion approach can significantly improve the classification accuracy compared to the three individual sensor-based models. Furthermore, the feature-level data fusion model exhibits the best classification performance among the three data fusion models. Highlights: Layer-wise images, acoustic emission signals, and photodiode signals are combined to achieve in-situ quality monitoring. An image processing method and a signal-to-image strategy are developed to process the multi-source sensor data. A CNN-based multi-sensor fusion approach is proposed to identify the part quality. The proposed multi-sensor fusion approach significantly outperforms the single sensor-based methods.