This　paper　presents　an　on-line　energy　management　strategy　(EMS)　based　on　trip　condition　prediction　for　commuter　plug-in　hybrid　electric　vehicles　(P-HEVs).　The　purpose　is　to　provide　an　on-line　predictive　control　approach　to　minimize　fuel　consumption.　Two　pivotal　contributions　are　provided　to　realize　the　purpose.　First　of　all,　we　establish　the　trip　condition　prediction　model　by　using　back　propagation　neural　network,　to　obtain　the　real-time　vehicle-speed　trajectory　on-line.　Particularly,　both　the　genetic　algorithm　and　particle　swarm　optimization　algorithm　are　applied　to　improve　the　prediction　accuracy　of　the　trip　condition　prediction　model.　Next,　to　obtain　an　applicable　EMS　in　real　time,　we　propose　a　dynamic　programming-based　predictive　control　strategy.　Finally,　a　simulation　study　is　conducted　for　applying　the　proposed　strategy　to　a　practical　trip　path　in　the　Beijing　road　network.　The　results　show　that　the　designed　trip　condition　prediction　model　can　effectively　realize　the　on-line　vehicle-speed　prediction,　and　the　prediction　accuracy　is　more　than　93%.　In　addition,　compared　to　the　offline　global　optimization　EMS,　although　the　proposed　strategy　makes　the　fuel　consumption　grow　less　than　5.2%,　it　can　be　implemented　in　real　time.　Moreover,　compared　with　the　existing　real-time　EMSs,　it　can　further　reduce　the　fuel　consumption　and　emissions.　It　shows　that　the　proposed　EMS　can　provide　an　effective　solution　for　commuter　P-HEVs　applying　it　on-line.