The　25　specimens　of　automotive　friction　material　with　different　relative　amounts　of　the　ingredients　of　aluminosilicate　fiber,　steel　fiber,　phenolic　resin　and　Cu　powder　mostly　effecting　on　the　tribological　properties　of　designed　brake　material　were　manufactured　by　compression　molding.　Dry　sliding　friction　characteristics　of　composites　were　tested　on　a　model　JF150D-II　pad-on-disk　type　friction　tester.　A　model　of　feed-forward　artificial　neural　networks　(ANN)　consisting　of　four　input　neurons,　six　output　neurons　and　one　hidden　layer,　was　used　for　the　analysis　and　prediction　of　the　correlation　between　material　components　and　friction　performance.　The　input　parameters　of　ANN　were　the　contents　of　four　main　components　as　aluminosilicate　fiber,　steel　fiber,　phenolic　resin　and　Cu　powder.　The　outputs　were　the　friction　coefficients　of　brake　material　against　cast　iron　at　six　different　operating　tempetures　from　100　degrees　C　to　350　degrees　C　with　50　degrees　C　step.　Based　on　ANN　model　trained　successfully　by　the　above　25　samples,　genetic　algorithm(GA)　was　used　to　optimize　the　input　parameters　of　compositions　of　brake　material　with　the　goal　of　minimizing　fluctuation　of　friction　coefficients　at　100　degrees　C　to　350　degrees　C.　The　optimum　composition(wt%)　of　brake　material　optimized　by　GA　in　this　paper　was　aluminosilicate　fiber　17.2%,　steel　fiber　22.8%,　phenolic　resin　22.1%　and　Cu　powder　12.9%.　The　friction　experiments　of　specimens　of　designed　material　were　carried　out　by　same　tribometer.　As　test　temperatures　increased　from　100　degrees　C　to　350　degrees　C,　the　maximum　fluctuation　of　friction　coefficient　was　0.04　with　the　average　of　0.383.　The　impressive　results　show　excellent　friction　stability　for　automotive　friction　material　at　elevated　temperatures.　The　neural　network　has　considerable　potential　for　solving　time-consuming　problems　for　the　design　of　automobile　brake　material.