The　slag　powder　is　a　kind　of　powder　formed　by　grinding　iron　and　steel　waste　slag,　and　it　is　an　efficient　and　environmentally　additive　for　building　materials.　There　is　a　positive　correlation　between　the　inlet　and　outlet　temperatures　of　the　mill　during　the　production　of　the　slag　powder,　but　the　increase　in　the　inlet　temperature　under　normal　conditions　will　help　to　increase　the　yield,　while　the　decrease　in　the　outlet　temperature　will　help　to　ensure　the　safety　of　the　production.　Therefore,　the　solution　of　the　temperature　set　value　will　be　a　multi-objective　optimization　problem,　and　it　is　difficult　to　obtain　the　optimal　value.　Starting　from　the　actual　production　conditions,　multi-objective　optimization　algorithms　based　on　non-dominated　sorting　genetic　algorithm　II,　multi-objective　particle　swarm　optimization　algorithm　and　multi-objective　grey　wolf　optimization　algorithm　are　used　to　solve　this　problem,　and　the　optimal　feasible　solution　set　is　obtained　by　comparative　analysis.　The　optimized　solution　set　can　provide　a　better　reference　for　temperature　setting,　thereby　improving　yield　and　production　safety.　©　2020,　Editorial　Department　of　Control　Theory　&　Applications.　All　right　reserved.