Towards Accurate Fused Deposition Modeling 3D Printer Fault Detection using Improved YOLOv8 with Hyperparameter Optimization

This research article presents an enhanced YOLOv8 model with additional feature extraction layer integrated into the traditional architecture to improve fault detection performance in smart additive manufacturing, specifically for FDM 3D printers. Hyperparameter optimization techniques are employed ensure is trained optimal input and batch size configurations. The findings demonstrate that module successfully enhances model’s detecting faults during printing process. best results achieved using YOLOv8s image of 640 a 16, achieving mAP val (50-95) 89.7%. Despite increased complexity from layers, there favorable trade-off between complexity. Furthermore, testbed implementation conducted validate real-world setting, showing latency remains insignificant even multiple Raspberry Pi clients. Overall, this provides insights improving manufacturing highlights effectiveness proposed layers.