The　traditional　indoor　wireless　location　algorithm　based　on　distance-loss　model　mostly　need　fit　the　parameters　A　and　n　of　the　wireless　signal　propagation　model　through　experience　or　large　amounts　of　experiment　data,　so　they　do　not　fully　reflect　the　real　volatile　environment,　also　result　in　low　accuracy.　After　lots　of　research　and　analysis　of　radio　signal　propagation　model　and　the　traditional　indoor　location　algorithm,　a　new　indoor　location　algorithm　using　BP　neural　network　to　fit　the　distance-loss　model　is　proposed.　From　a　number　of　distances　between　reference　nodes　and　blind　node,　a　more　accurate　six-point　centroid　algorithm　is　used　to　estimate　the　position　of　the　blind　node　instead　of　using　the　traditional　three-point　centroid　algorithm.　Finally,　the　experiment　result　shows　that　the　new　algorithm　improves　the　positioning　accuracy　and　universality,　compared　with　the　traditional　positioning　algorithms.　©　2012　Chinese　Assoc　of　Automati.