The　ball　screw　is　a　vital　component　in　the　feed　drive　systems　of　machine　tools.　It　is　susceptible　to　thermal　errors　that　significantly　impact　its　accuracy.　Current　thermal　error　modeling　methods　for　ball　screws　face　significant　challenges　in　achieving　full-time　series　prediction.　Furthermore,　these　methods　impose　stringent　requirements　for　a　complex　temperature　data　collection　process,　further　constrained　by　the　compact　structure　of　machine　tools.　Additionally,　valuable　working　condition　data　in　thermal　error　prediction　remains　underutilized.　This　paper　proposes　a　new　hybrid-driven　model　that　combines　mechanism　and　data-driven　approaches　to　achieve　full-time　series　thermal　error　prediction　of　ball　screws.　The　proposed　model　utilizes　the　operating　rotational　speed　as　a　key　input　parameter,　eliminating　the　need　for　temperature　collection　during　the　modeling　stage　and　the　compensation　process.　The　temperature　model　is　proposed　as　a　mechanism-driven　model　based　on　heat　transfer　theory　to　calculate　the　temperature　of　the　thermal　sensitive　points　by　utilizing　operating　rotational　speed.　The　accuracy　of　the　model　is　validated　through　thermal　characteristic　experiments　of　ball　screws　under　four　different　working　conditions.　The　data-driven　models　based　on　different　traditional　neural　networks　are　established　to　predict　thermal　errors　according　to　the　time　series　temperature　data　from　the　temperature　model.　Moreover,　hyperparameters　of　different　neural　networks　are　optimized　by　the　Beetle　Antennae　Search　(BAS).　Comparative　analysis　among　different　neural　network-based　hybrid-driven　models　reveals　that　the　convolutional　neural　network　(CNN)　model　optimized　by　BAS　consistently　exhibits　lower　absolute　errors　predominantly　below　10　mu　m,　as　well　as　lower　root　mean　squared　error　(RMSE)　and　mean　absolute　error　(MAE)　values　in　each　working　condition.　The　BAS-CNN　model,　within　the　hybrid-driven　model　framework,　is　better　suited　for　the　full-time　series　prediction　of　thermal　errors　in　ball　screws.　The　BAS-CNN　model　is　a　foundation　for　thermal　error　compensation　by　utilizing　working　condition　data.