The　cutting　force　coefficients　are　important　parameters　in　the　milling　process,　which　not　only　affects　the　milling　stability　but　also　directly　reflects　the　tool　wear　state.　This　paper　proposed　a　method　for　online　identification　of　cutting　force　coefficients　and　prediction　of　tool　wear　state　based　on　the　current　and　voltage　of　the　feed　drive.　The　method　is　based　on　the　instantaneous　electromagnetic　torque　theory　and　utilizes　a　neural　network　to　establish　a　complex　mapping　relationship　between　current,　voltage,　and　instantaneous　milling　force,　achieving　high-precision　online　prediction　of　the　milling　force　waveform　during　the　milling　process.　Then,　a　method　for　online　identification　of　cutting　force　coefficients　and　prediction　of　tool　wear　state　is　proposed　by　integrating　the　predicted　milling　force　with　machining　information.　Through　the　experiments　on　different　cutting　conditions　and　materials,　the　results　show　that　the　proposed　method　can　identify　the　cutting　force　coefficients　under　different　machining　conditions　by　fully　training　the　prediction　model　and　predicting　the　wear　state　of　milling　cutters　by　online　monitoring　the　variation　trend　of　cutting　force　coefficients　along　with　the　wear　process　developing,　and　accurately　determine　the　key　points　of　milling　cutters　replacement.