Parallel　manipulators　have　the　potentials　of　high　efficiency　and　high　precision　in　the　field　of　machining　and　manufacturing.　However,　accuracy　improvement　of　the　parallel　manipulator　is　still　an　essential　and　challenging　issue,　encountering　two　important　problems.　Firstly,　the　ignorance　of　elastic　deformation　caused　by　gravity　or　deviations　of　static　stiffness　model　restricts　further　improvement　of　accuracy.　To　solve　this　problem,　an　elasto-geometrical　error　modeling　method　is　proposed.　The　comprehensive　effects　of　structural　errors,　elastic　deformation　under　gravity　and　compliance　parameter　errors　on　pose　deviations　are　disclosed.　On　this　basis,　the　identification　equation　of　actual　structural　errors　and　compliance　parameter　errors　can　be　established.　Secondly,　the　ill-conditioned　identification　matrix　and　the　identification　equation　with　anisotropic　residual　error　can　lead　to　inaccurate　identification　results.　To　solve　this　problem,　a　weighted　regularization　method　is　proposed.　The　identification　equation　with　isotropic　residual　error　is　built,　and　accurate　identification　can　be　realized　with　the　regularization　method.　Based　on　the　proposed　methods,　the　error　compensation　experiment　is　conducted　on　the　prototype　of　a　five-axis　parallel　machining　robot　using　a　laser　tracker.　Experiment　results　show　that　the　accuracy　of　the　machining　robot　is　significantly　improved　after　compensation.　An　M1_160　test　piece　and　an　S-shaped　test　piece　are　machined　and　measured　to　further　validate　the　effectiveness　of　the　proposed　methods.　The　elasto-geometrical　error　modeling　method　and　the　weighted　regularization　method　can　be　applied　to　other　parallel　manipulators＇　accuracy　improvement.