This　paper　proposes　an　adaptive　fuzzy　neural　algorithm.　In　fact,　this　algorithm　changes　the　parameters　by　using　Lyapunov　stability　theory　to　ensure　the　stability.　This　algorithm　didn＇t　need　to　seek　the　whole　minimum　value　when　it　modifies　the　parameters.　So　the　algorithm　can　reach　the　stability　result　more　quickly　than　the　conventional　fuzzy　neural　algorithm.　The　analyses　of　theory　prove　the　stability　of　the　algorithm.　Then　we　use　this　algorithm　to　control　the　activated　sludge　in　wastewater　treatment　process,　and　compares　with　the　conventional　fuzzy　neural　algorithm.　The　results　of　simulations　show　the　superiority　of　this　algorithm　and　nicer　robustness　in　the　process.　Besides,　the　structure　of　the　new　fuzzy　neural　network　is　simple　and　can　be　broadly　used.