Inkjet printing is a powerful direct material writing process. It can be used to deposit microfluidic droplets in designated patterns at submicrometer resolution, which reduces materials usage. Nonetheless, predicting jetting characterizations is not easy because of the intrinsic complexity of the ink-nozzle-air interactions. Thus, inkjet processes are monitored by skilled engineers to ensure process reliability. This is a bottleneck in industry, resulting in high labor costs for multiple nozzles. To address this, we present a deep learning-based method for jetting characterizations. Inkjet printing is recorded by an in situ CCD camera and each droplet is detected by YOLOv5, a 1-stage detector using a convolutional neural network (CNN). The precision, recall, and mean average precision (mAP) at a 0.5 intersection over the union (IoU) threshold of the trained model were 0.86, 0.89, and 0.90, respectively. Each regression result for a detected droplet is accumulated in chronological order for each class of droplet and nozzle. The quantified information includes velocity, diameter, length, and translation, which can be used to synchronize multinozzle jetting and, eventually, the printed patterns. This demonstrates the feasibility of autonomous real-time process testing for large-scale electronics manufacturing, such as the high-resolution patterning of biosensor electrodes and QD display pixels while exploiting big data obtained from jetting characterizations.
Keywords: convolutional neural network (CNN); inkjet printing; jetting characteristics; microfluidics; multijet synchronization; object detection; quantum dot (QD).