The　traditional　circulating　cooling　water　system　regulates　the　flow　rate　through　parallel　pumps　and　valves.　Due　to　fluctuations　in　operation,　there　will　be　lots　of　energy　waste,　resulting　in　inefficient　operation　of　the　circulating　cooling　water　system.　This　research　proposed　a　mixed-integer　nonlinear　programming　(MINLP)　method.　By　installing　variable　frequency　drives　(VFDs)　on　the　pumps,　changing　constant-speed　pumps　(CSPs)　into　variable　speed　pumps　(VSPs),　we　can　regulate　flow　rate　with　valves　and　VSPs　simultaneously.　Optimizing　the　system　using　Genetical　algorithm　(GA)　to　obtain　precise　operating　parameters,　including　the　configuration　of　VFDs,　the　number　of　CSPs　and　VSPs　and　the　resistance　coefficients　of　valve　in　the　branch　and　main　pipe.　Sensitivity　analysis　of　the　model　is　carried　out,　and　the　energy-saving　effect　of　VFD　under　different　temperature　differences,　pump　types　and　electricity　prices,　the　operating　status　of　the　pump　and　the　status　of　the　pipeline　are　compared.　The　results　indicate　that　the　MINLP　genetic　algorithm　optimization　model　for　industrial　circulating　water　considering　variable　frequency　drive　proposed　in　this　paper　has　a　wide　range　of　applicability.　It　can　save　an　average　of　23　%　of　the　total　cost　under　different　conditions,　and　has　a　promising　energy　saving　effect.　©　2022　Institution　of　Chemical　Engineers