A　fuzzy　super-twisting　algorithm　sliding　mode　controller　is　developed　for　the　dissolved　oxygen　concentration　in　municipal　wastewater　nitrification　process.　First,　a　fuzzy　neural　network　(FNN)　model　is　designed　to　approach　the　oxygen　dynamics　with　unmeasurable　disturbances,　then　the　established　model　consists　of　the　nominal　system　model　and　the　modelling　error.　Second,　based　on　the　FNN　model,　a　super-twisting　sliding　mode　controller　is　employed　to　stabilize　the　nominal　system　and　to　suppress　the　modelling　error.　Moreover,　the　stability　of　the　system　is　investigated　and　an　adaption　law　is　applied　to　ensure　the　robustness　of　the　closed-loop　system.　Finally,　the　comparison　experiments　on　benchmark　simulation　model　no.　2　(BSM2)　of　wastewater　treatment　show　the　advantages　of　the　proposed　method　in　multiple-units　oxygen　concentration　control.