The　municipal　solid　waste　incineration　has　great　advantages　for　resource　recovery　and　utilization,　and　the　stability　of　its　combustion　state　is　of　great　significance　to　the　control　process.　However,　the　problem　of　low　accuracy　still　exists　in　the　classification　of　the　images　of　municipal　solid　waste　incineration　(MSWI).　For　this　reason,　this　paper　proposes　an　image　classification　algorithm　for　MSWI　based　on　attention　module.　The　framework　of　ResNet　is　employed　to　improve　the　depth　and　accuracy　of　the　network,　which　solves　the　problem　of　insufficient　depth　of　the　traditional　network　while　suffering　from　the　deficiency　of　slow　convergence　speed.　Consequently,　the　attention　module　is　embedded　to　solve　the　problem　of　different　importance　of　different　parts　in　the　incineration　flame　image.　The　results　show　that　the　algorithm　improves　the　recognition　accuracy　of　municipal　solid　waste　incineration　flame　images　to　96.7%,　and　the　convergence　speed　is　significantly　improved　compared　to　other　basic　neural　network　models.　©　2024　IEEE.