Because　of　highly　complexity　and　large-scale　operation,　wastewater　treatment　process　(WWTP)　is　considered　as　a　robust　adaptive　control　problem.　This　paper　proposes　a　data-driven　robust　adaptive　control　with　deep　learning　(DRAC-DL)　for　WWTP　to　improve　the　operational　performance.　In　ths　DRACDL　framework,　a　robust　controller　is　firstly　designed　to　construct　the　closed-loop　control　scheme.　Meanwhile,　an　adaptive　deep　belief　network　(ADBN)　is　developed　based　on　the　self-incremental　learning　strategy　to　approximate　the　ideal　control　law.　The　main　advantage　of　DRAC-DL　lies　in　its　improved　robustness　and　low　computational　burden,　which　benefit　from　Lyapunov-based　closed-loop　controller　and　efficient　ADBN　approximator.　Finally,　the　effectiveness　of　DRAC-DL　is　demonstrated　on　the　benchmark　simulation　model　No.1　(BSMI)　of　WWTP.　　©　2022　IEEE.