Continuous　monitoring　of　blood　pressure　(BP)　plays　a　crucial　role　in　the　early　prevention　of　cardiovascular　diseases.　However,　continuous　BP　estimation　is　only　possible　with　an　invasive　catheter　measurement　method　as　the　gold　standard.　Meanwhile,　ordinary　cuff　type　blood　pressure　measuring　devices　have　the　drawbacks　of　cumbersome　operation　and　inability　to　monitor　continuously.　Thus,　continuous　BP　estimation　only　based　on　photoplethysmography　(PPG)　signals　has　important　clinical　value　in　early　prevention　of　cardiovascular　diseases.　In　this　study,　we　proposed　an　Attention-U-Net　neural　network　for　noninvasive　continuous　BP　estimation　using　PPG　signals.　Jumping　connections　in　U-Net　retains　the　local　context　information　of　the　input　signal　improving　the　receptive　field.　Our　model　was　evaluated　on　Physionet＇s　Cuff-Less　Blood　Pressure　Estimation　Dataset.　The　experimental　results　validate　the　feasibility　of　the　proposed　method　for　continuous　BP　estimation　based　on　PPG　signals.　The　systolic　blood　pressure　(SBP)　and　diastolic　blood　pressure　(DBP)　predicted　by　the　proposed　Attention-U-Net　both　reach　level　A　under　the　British　Hypertension　Society　(BHS)　standard.　Moreover,　the　results　also　showed　that　Attention-U-Net　has　better　performance　than　Res-Net,　Dense-Net,　GRU　based　Seq2Seq　and　etc.　Therefore,　the　proposed　method　is　a　promising　alternative　for　noninvasive　continuous　BP　estimation　and　early　diagnosis　of　cardiovascular　diseases.