Aiming　at　the　characteristics　of　high　coupling　degree,　strong　nonlinearity,　and　serious　time　delay　in　the　measurement　of　ammonia　nitrogen　concentration　in　wastewater　treatment　process　(WWTP),　a　prediction　model　of　ammonia　nitrogen　concentration　based　on　gray　relational　analysis　(GRA)　and　time　convolution　network　(TCN)　was　proposed.　Firstly,　based　on　the　relevant　water　quality　parameters　collected　in　WWTP,　the　grey　correlation　analysis　method　was　used　to　find　out　other　characteristic　variables　highly　related　to　the　ammonia　nitrogen　concentration.　Then,　a　new　group　of　multivariate　time　series　data　was　constructed　by　using　the　sliding　window　method.　Finally,　based　on　the　advantages　of　the　time　convolution　network　in　processing　time　series　data,　such　as　simple,　flexible,　and　easy　to　parallel,　the　constructed　time　series　data　were　modeled　to　predict　the　concentration　of　effluent　ammonia-nitrogen.　To　verify　the　validity　of　the　model,　the　predicted　results　were　compared　with　the　other　four　models.　The　experimental　results　show　that　the　ammonia-nitrogen　concentration　prediction　model　based　on　GRA　and　TCN　has　good　prediction　performance,　which　is　helpful　to　realize　the　accurate　prediction　of　effluent　ammonia-nitrogen　concentration.　At　the　same　time,　it　can　also　provide　timely　and　effective　guidance　for　the　control　and　optimization　of　the　wastewater　treatment　process.　©　2021　IEEE.