Municipal　solid　waste　incineration　(municipal　solid　wastes　incineration,　MSWI)　is　a　common　method　to　reduce　waste　and　produce　energy.　In　the　process　of　municipal　solid　waste　incineration,　furnace　temperature　is　an　important　index　to　control　and　optimize　the　process　of　municipal　solid　waste　incineration.　However,　due　to　the　limitation　of　environment　and　instruments,　it　is　difficult　to　accurately　measure　the　furnace　temperature　online.　This　paper　proposes　a　neural　network　based　on　Sparrow　Search　Algorithm　(SSA)　to　optimize　Elman,　and　designs　a　furnace　temperature　prediction　model　for　urban　solid　waste　incineration　process,　trying　to　obtain　real-time　and　accurate　measurement　of　furnace　temperature.　The　structure　and　training　method　of　the　prediction　model　based　on　SSA-ELMAN　network　are　introduced　in　detail,　and　the　nonlinear　relationship　between　furnace　temperature　and　other　process　variables　is　established.　Finally,　a　comparative　experiment　was　carried　out　using　the　historical　data　of　a　waste　incineration　plant.　The　results　show　that　the　furnace　temperature　model　established　in　this　paper　has　the　advantages　of　accuracy,　generalization　ability,　stability　and　training　efficiency.　©　2023　IEEE.