At　present,　how　to　establish　a　mathematical　model　of　deoxygenation　alloying　link　through　historical　data,　predict　and　optimize　the　type　and　quantity　of　alloy　input　online,　and　minimize　the　production　cost　of　alloy　steel　while　ensuring　the　quality　of　steel　and　water.　It　is　an　important　issue　for　major　steel　companies　to　improve　their　competitiveness.　Based　on　the　main　component　and　neural　network　and　multivariate　nonlinear　regression　theory,　based　on　the　existing　alloy　historical　data,　this　paper　optimizes　the　ingredients　scheme　of　＇deoxygenation　and　alloying＇of　steel　and　water,　establishes　the　mathematical　model,　calculates　the　historical　harvest　rate　of　the　main　elements,　and　predicts　the　historical　harvest　rate　of　the　main　elements.　Combined　with　the　price　of　the　alloy,　the　automatic　ingredient　scheme　of　the　steel　water　deoxygenated　alloy　is　given,　and　the　cost　of　the　steel　water　deoxygenated　alloy　is　optimized.　©　Published　under　licence　by　IOP　Publishing　Ltd.