In　this　study,　a　high-temperature　fretting　wear　prediction　model　was　established　for　metal　rubber,　which　was　then　validated　through　experiments.　Initially,　a　three-dimensional　numerical　model　of　metal　rubber　was　reconstructed,　and　statistical　distribution　of　contact　points　and　types　of　curved　wires　inside　the　virtual　component　was　achieved.　Meanwhile,　a　high-temperature　fretting　wear　evolution　model　for　curved　wires　was　constructed　by　introducing　a　temperature　function　f(T),　considering　material　thermal　expansion,　softening,　and　oxidation.　Subsequently,　the　model　was　incorporated　into　the　macro　model,　establishing　a　cross-scale　predictive　model　for　wear　from　micro-coil　elements　to　component　wear.　Experimental　validation　demonstrated　good　prediction　performance　of　the　model,　with　a　maximum　wear　mass　prediction　error　of　14.81%　and　prediction　errors　below　10%　for　80,000　cycles.