An intelligent online parameter adjustment method based on an improved YOLOv11 model was proposed to address poor print quality and the heavy reliance on manual expertise for parameter tuning in 3D printers. On the basis of a conventional 3D printing platform, a nozzle-targeted image acquisition system was incorporated, and a quantitative mapping model between printing parameters (such as speed and temperature) and print quality metrics (such as tensile strength and surface roughness) was established. The improved YOLOv11 model was employed to identify early visual signatures of various defects (such as stringing and under-extrusion) during the printing process, enabling real-time adjustment of key compensatory parameters. Experimental results demonstrate that, under preset defect parameters, activating the online adjustment method increases the tensile strength of printed parts by four times compared to the unadjusted state, while significantly reducing surface roughness from Ra100 to Ra50. The proposed method can automatically adjust parameters during use to improve print quality.