This　study　proposes　a　multi-objective　optimization　method　based　on　a　hybrid　of　computational　fluid　dynamics　(CFD)　and　experimental　techniques,　which　integrates　a　weighted　average　surrogate　model　and　the　NSGA-II　intelligent　algorithm.　To　validate　the　feasibility　of　this　method,　structural　optimization　for　the　self-excited　oscillation　mixer　(SEOM)　was　conducted.　The　optimization　objectives　aimed　to　reduce　potential　abrasives　accumulation　in　the　mixed-flow　cavity　and　minimize　erosion　on　the　elbow　of　the　slurry　outlet　caused　by　mixed　slurry,　thereby　enhancing　the　service　life　and　rust　removal　efficiency　of　the　mixed　flow　rotary　jet　descaling　(MFD).　A　comparison　between　the　optimized　model　and　original　model　revealed　a　2.51%　increase　in　negative　pressure　within　the　cavity　of　the　optimized　model,　as　well　as　a　10.36%　decrease　in　velocity　at　the　outlet　of　mixed　slurry　based　on　simulation　results.　Experimental　methods　measured　both　mass　flow　rate　of　inhaled　abrasive　particles　and　impact　force　of　mixed　slurry　outlet.　The　experimental　results　demonstrated　that　compared　to　its　original　counterpart,　the　optimized　model　exhibited　superior　performance　with　a　22.81%　increase　in　abrasive　particle　flow　rate　and　an　11.34%　reduction　in　mixed　slurry　impact　force　indirectly,　verifying　better　simulation　effectiveness　for　SEOM　with　optimized　structure.　This　approach　also　enhanced　efficiency　and　surface　quality　of　MFD　processing　strip　steel,　providing　guidance　for　structural　optimization　of　similar　SEOMs　used　in　mixed　flow　descaling.