In-situ monitoring additive manufacturing process with AI edge computing

TL;DR

This paper presents an AI edge computing-based in-situ monitoring system for additive manufacturing that uses a visual transformer network for super resolution and a convolutional network for geometric feature extraction, enabling real-time quality control.

Contribution

It introduces a novel AI edge computing system with a ViTSR network for super resolution and FCN for feature extraction, achieving high accuracy and real-time performance in AM monitoring.

Findings

ViTSR outperforms 6 state-of-the-art super resolution methods in PSNR.

System inference time is optimized to under 120 ms for real-time monitoring.

Achieved 96.34% accuracy in multi-object detection during AM.

Abstract

In-situ monitoring system can be used to monitor the quality of additive manufacturing (AM) processes. In the case of digital image correlation (DIC) based in-situ monitoring systems, high-speed cameras were used to capture images of high resolutions. This paper proposed a novel in-situ monitoring system to accelerate the process of digital images using artificial intelligence (AI) edge computing board. It built a visual transformer based video super resolution (ViTSR) network to reconstruct high resolution (HR) videos frames. Fully convolutional network (FCN) was used to simultaneously extract the geometric characteristics of molten pool and plasma arc during the AM processes. Compared with 6 state-of-the-art super resolution methods, ViTSR ranks first in terms of peak signal to noise ratio (PSNR). The PSNR of ViTSR for 4x super resolution reached 38.16 dB on test data with input size of 75 pixels x 75 pixels. Inference time of ViTSR and FCN was optimized to 50.97 ms and 67.86 ms on AI edge board after operator fusion and model pruning. The total inference time of the proposed system was 118.83 ms, which meets the requirement of real-time quality monitoring with low cost in-situ monitoring equipment during AM processes. The proposed system achieved an accuracy of 96.34% on the multi-objects extraction task and can be applied to different AM processes.