The　wastewater　treatment　system　is　a　complex　unknown　system　with　nonlinear　and　uncertain　characteristics.　It　is　necessary　to　control　the　concentration　of　the　dissolved　oxygen　and　the　nitrate　nitrogen　at　the　set　value　in　the　wastewater　treatment　process.　However,　traditional　control　methods　are　difficult　to　meet　the　accuracy　requirements　for　the　required　concentration　value.　At　the　same　time,　the　digital　twin　(DT)　technology　has　been　widely　applied　to　practical　industrial　systems　like　the　wastewater　treatment　system　in　recent　years.　Based　on　the　above　backgrounds,　an　online　DT　adaptive　critic　design　(DTACD)　is　developed　by　combining　the　long　short-term　memory　(LSTM)　neural　network　with　the　action-critic　structure.　First,　a　set　of　historical　data　is　collected,　which　is　used　to　build　a　digital　model　using　LSTM.　Then,　the　digital　model　is　used　to　guide　the　real　wastewater　treatment　system　to　control　the　nitrate　nitrogen　concentration　and　the　dissolved　oxygen　concentration　at　set　values.　Finally,　we　select　the　Benchmark　Simulation　Model　No.1　as　the　model　for　the　simulation　experiment.　Compared　with　other　methods,　DTACD　shows　a　better　performance.　Note　to　Practitioners-Since　the　concentration　control　of　the　dissolved　oxygen　and　the　nitrate　nitrogen　is　involved　in　the　process　of　the　wastewater　treatment,　this　problem　can　be　regarded　as　the　tracking　control　problem　of　nonlinear　systems,　which　is　an　important　research　direction　in　the　field　of　the　optimal　control.　Adaptive　dynamic　programming　has　shown　good　performance　in　this　field,　which　is　adopted　to　the　tracking　control.　In　the　actual　wastewater　treatment　process,　the　control　variables　that　do　not　meet　the　input　requirements　may　affect　the　control　performance.　The　DT　technology　can　test　whether　the　control　strategy　satisfies　the　requirements　in　advance　by　constructing　a　digital　model.　Therefore,　we　are　committed　to　combining　adaptive　dynamic　programming　and　DT　to　realize　optimal　tracking　control　for　industrial　systems　such　as　the　wastewater　treatment　system,　integrating　neural　networks　to　improve　the　tracking　control　accuracy　and　ensure　the　rationality　of　control　variables.　Finally,　simulation　experiments　are　carried　out　on　the　internationally　recognized　Benchmark　Simulation　Model　No.1　to　verify　the　effectiveness　of　the　control　design.