In　wastewater　treatment　process　(WWTP),　data-based　implement　techniques　ensure　the　stable　operation　and　reduce　energy　consumption.　Different　missing　patterns　of　missing　values　often　occur　due　to　some　harsh　environments　and　sensor　failures.　However,　existing　imputation　methods　are　difficult　to　obtain　satisfactory　data　for　implementation　techniques　as　they　only　consider　a　single　missing　pattern.　To　solve　this　problem,　a　missing-pattern-aware-based　multi-model　imputation　method　(MPAMI)　is　proposed.　First,　a　missing　pattern　aware　network　combining　the　advantages　of　the　encoder　and　the　axial　attention　mechanism　is　designed　to　identify　different　missing　patterns.　The　network　employs　the　encoder　to　extract　nonlinear　feature　representations　and　utilizes　the　axial　attention　mechanism　to　focus　on　the　most　informative　differential　features.　Second,　a　hybrid　multi-model　imputation　method　based　on　the　long　short-term　memory　network　and　the　denoising　autoencoder　is　developed　to　recover　missing　values.　The　imputation　method　utilizes　the　spatiotemporal　information　of　missing　patterns　to　improve　imputation　performance.　Finally,　experiments　are　conducted　on　a　real　WWTP　dataset　to　validate　the　imputation　performance　of　the　proposed　MPAMI.　©　2023　IEEE.