During　the　peripheral　milling　process　of　thin-walled　components,　a　workpiece　with　poor　rigidity　will　cause　workpiece　deformation　error　because　of　the　milling　force　and　result　in　the　degradation　of　machining　accuracy　and　related　machining　ability　of　machine　tools.　As　a　result,　how　to　obtain　the　workpiece　deformation　error　and　its　effect　on　the　surface　machining　quality　of　workpiece　is　the　focus　of　the　research.　Hence,　a　synthesis　approach　was　developed　in　this　study　to　analyze　the　machining　accuracy　reliability　during　the　peripheral　milling　process　of　thin-walled　components.　The　feedback　mechanism　between　the　milling　force　and　milling　deformation　error　was　studied,　and　then　a　workpiece　deformation　error　model　based　on　an　advanced　neural　fuzzy　network　was　developed.　By　applying　the　D-H　method,　a　machining　accuracy　model　of　the　machine　tool　was　established　for　the　machine　tool　considering　the　workpiece　deformation.　Based　on　the　reliability　analysis　method　combined　with　RF　and　Edge　worth,　a　machining　accuracy　reliability　model　was　developed,　and　then　the　reliability　of　machining　accuracy　during　the　peripheral　milling　process　of　thin-walled　components　was　obtained.　To　verify　this　approach,　a　machining　experiment　was　conducted　on　a　three-axis　machine　tool;　the　experimental　results　indicate　that　better　predictive　ability　was　achieved　using　the　approach　presented　in　the　paper.