The　effective　control　of　converter　inlet　temperature　in　the　process　of　acid　production　with　flue　gas　is　an　effective　means　to　improve　the　conversion　rate　of　sulfur　dioxide　and　reduce　environmental　pollution.　According　to　the　characteristics　of　the　process　of　acid　production　with　flue　gas,　the　control　process　of　converter　inlet　temperature　is　studied　in　this　paper.　Firstly,　the　CARIMA　(Controlled　auto-regressive　integrated　moving　average,　CARIMA)　model　of　converter　inlet　temperature　is　established.　Then,　a　generalized　predictive　controller　based　on　CARIMA　model　is　designed.　Finally,　the　proposed　method　is　verified　by　experiment　and　compared　with　PID　controller.　Experimental　results　show　that　the　proposed　method　has　a　better　tracking　effect　and　smaller　error.　The　effectiveness　of　the　proposed　method　is　verified.