The　state　of　charge　(SOC)　and　the　state　of　health　(SOH)　are　two　crucial　parameters　for　monitoring　the　battery　status　because　SOH　determines　whether　the　battery　can　continue　to　operate　safely　and　stably,　and　the　SOC　determines　the　battery＇s　endurance.　This　paper　proposes　an　online　synthesis　method　based　on　the　response　characteristics　of　load　surges　and　an　improved　fuzzy　cerebellar　model　neural　network　(IFCMNN)　to　co-estimate　SOH　and　SOC.　Firstly,　multiple　features　are　extracted　from　the　voltage　response　signals.　Then,　the　grey　relational　analysis　is　utilized　to　verify　the　rationality　of　the　extracted　features　and　to　fuse　key　features　for　SOH　and　SOC　estimation.　Secondly,　IFCMNN　models　aiming　at　estimating　SOH　and　SOC　are　proposed　to　estimate　the　SOH　and　SOC　simultaneously　and　quickly.　Finally,　experimental　results　on　ten　batteries　with　different　aging　levels　show　that　the　proposed　method　can　achieve　fast　estimation　of　SOH　and　SOC　at　1.64　%　and　2　%　resolution　accuracy　respectively,　regardless　of　the　temperature　and　in　rush　currents　variations.　In　addition,　the　proposed　model　has　higher　estimation　accuracy　compared　with　other　traditional　methods.　Thus,　the　proposed　method　has　a　high　generalization　ability.