Existing　methods　for　detecting　anomalies　in　digital　light　processing　(DLP)　3D　printing　and　performing　in-situ　repairs　can　reduce　most　defects　and　improve　success　rates.　However,　since　printing　control　parameters　cannot　adapt　to　real-time　printing　conditions,　anomalies　may　persist　across　successive　layers,　and　continuous　repairs　could　ultimately　lead　to　printing　failure.　Therefore,　achieving　stable　printing　quality　requires　integrating　anomaly　detection　with　the　dynamic　adjustment　of　control　parameters.　In　this　paper,　we　propose　a　hybrid　approach　that　combines　physical　models　with　real-time　status　data　to　achieve　quality-reliable　DLP　3D　printing.　We　developed　a　status　data　acquisition　scheme　to　monitor　printing　status,　including　the　downward　force　exerted　on　the　printing　platform,　curing　temperatures,　resin　levels,　and　surface　morphology.　Analyzing　the　collected　data　provides　both　status　and　anomaly　information,　enabling　in-situ　repair　strategies　to　address　abnormalities　with　minimal　disruption　to　the　printing　process.　Additionally,　an　Extended　Kalman　Filter　integrates　status　data　with　physical　models　to　dynamically　optimise　printing　parameters.　Experimental　results　show　that　the　proposed　scheme　effectively　addresses　typical　anomalies,　optimises　printing　times,　and　significantly　improves　success　rates　while　preserving　the　mechanical　performance　of　printed　models.　Furthermore,　the　approach　adapts　to　varying　printing　status,　resin　materials,　and　models.