To　achieve　better　fuel　economy　for　plug-in　hybrid　electric　vehicles　(PHEVs),　this　paper　proposes　a　novel　improved　adaptive　equivalent　consumption　minimization　strategy　(A-ECMS)　integrated　driving　condition　prediction　using　artificial　neural　network　(ANN)　combined　the　least-squares　with　forgetting　factors.　Firstly,　the　ANN　method　and　the　least-square　with　forgetting　factors　are　used　to　predict　the　velocity　of　the　vehicle　and　the　slope　of　the　road.　Then　a　trip　adaptive　ECMS　is　proposed　which　the　equivalent　factor　(EF)　is　adjusted　in　real-time　according　to　the　remaining　distance.　Furthermore,　the　driving　condition　prediction　technology　is　integrated　into　A-ECMS　to　decrease　fuel　consumption　further.　Besides,　the　impact　of　different　preview　horizon　lengths　on　fuel　consumption　is　analyzed.　Finally,　a　simulation　study　is　conducted　for　applying　the　proposed　strategy　to　a　practical　trip　path　in　the　Fuzhou　road　network.　Simulation　results　show　that,　compared　with　CD-CS,　the　A-ECMS　combined　with　driving　condition　prediction　can　achieve　better　fuel　economy　with　a　fuel　consumption　reduction　by　12.1%,　which　effectively　improves　the　fuel　economy　of　the　PHEV.