The　safety　of　spacecraft　and　satellite　in　orbit　is　very　important,　and　structural　health　monitoring　is　needed.　At　present,　the　existing　technology　is　limited　by　load　and　difficult　to　realize.　In　this　paper,　we　propose　a　feasible　method　to　detect　and　locate　the　damage　of　satellite　by　combining　ultrashort　femtosecond　grating　array　inscribed　on　oxide-doped　fiber　with　multilayer　artificial　neural　network.　An　oxide-doped　fiber　with　high　robustness　is　designed,　and　ultrashort　grating　arrays　are　fabricated　on　the　fiber　by　femtosecond　laser　point-by-point　writing　technology.　The　effects　of　impactor　velocity　and　angle　on　impact　response　was　investigated　by　numerical　simulations　and　physical　experiments.　Subsequently,　repeated　impact　experiments　were　conducted　on　the　satellite　to　obtain　the　training　dataset　and　testing　dataset　for　two-dimensional　convolutional　neural　network.　The　network　with　symmetric　convention　kernels　has　an　88.12%　localization　accuracy　and　a　better　performance　in　boundary　region,　and　the　network　architecture　with　asymmetric　convention　kernels　has　a　90.31%　accuracy　and　a　better　performance　in　middle　region.