With　the　development　of　industrial　Internet　of　Things,　manual　production　in　the　factory　has　gradually　changed　to　automated　production,　and　the　temperature　requirements　in　many　aspects　of　the　production　process　are　very　strict.　In　order　to　control　temperature　more　intelligently,　reduce　errors　and　improve　production　efficiency,　through　the　study　of　BP　neural　network,　this　paper　designs　and　implements　an　intelligent　temperature　prediction　system　based　on　BP　neural　network　for　wireless　industrial　Internet　of　Things.　Through　the　selection　of　intelligent　algorithms,　the　establishment　of　the　model　and　the　realization　of　the　system,　a　temperature　prediction　system　suitable　for　the　actual　production　environment　of　the　industrial　Internet　of　Things　and　improving　the　accuracy　according　to　the　intelligent　algorithm　is　finally　realized.　The　system　is　relatively　complete　in　function.　Temperature　prediction　and　error　correction　can　accurately　predict　the　change　of　temperature.　It　can　meet　the　requirements　of　industrial　production　control　and　make　the　temperature　control　more　stable.　©　2019　IEEE.