With　the　development　and　widespread　use　of　blockchain　in　recent　years,　many　projects　have　introduced　blockchain　technology　to　solve　the　growing　security　issues　of　the　Industrial　Internet　of　Things(IIoT).　However,　due　to　the　conflict　be-tween　the　operational　performance　and　security　of　the　blockchain　system　and　the　compatibility　issues　with　a　large　number　of　IIoT　devices　running　together,　the　mainstream　blockchain　system　cannot　be　applied　to　IIoT　scenarios.　In　order　to　solve　these　problems,　this　paper　proposes　SBFT　(Speculative　Byzantine　Con-sensus　Protocol),　a　flexible　and　scalable　blockchain　consensus　mechanism　for　the　Industrial　Internet　of　Things.　SBFT　has　a　consensus　process　based　on　speculation,　improving　the　throughput　and　consensus　speed　of　blockchain　systems　and　reducing　communi-cation　overhead.　In　order　to　improve　the　compatibil-ity　and　scalability　of　the　blockchain　system,　we　select　some　nodes　to　participate　in　the　consensus,　and　these　nodes　have　better　performance　in　the　network.　Since　multiple　properties　determine　node　performance,　we　abstract　the　node　selection　problem　as　a　joint　opti-mization　problem　and　use　Dueling　Deep　Q　Learning　(DQL)　to　solve　it.　Finally,　we　evaluate　the　performance　of　the　scheme　through　simulation,　and　the　sim-ulation　results　prove　the　superiority　of　our　scheme.