Neutron　detector　is　an　important　equipment　of　nuclear　measurement　system,　providing　accurate　measurement　data　is　of　great　significance　to　ensure　the　safe　and　stable　operation　of　nuclear　power　plants.　In　this　study,　an　unknown　fault　identification　method　based　on　Support　Vector　Data　Description　(SVDD)　is　proposed　for　the　neutron　detector　of　γ　-compensation　ionization　chamber,　and　the　model　parameters　are　optimized　by　particle　swarm　optimization　(PSO)　algorithm.　The　normal　sample　data　are　used　to　train　the　model,　and　then　the　model　is　used　to　identify　the　unknown　faults　that　may　occur　in　the　future　of　the　neutron　detector.　The　unknown　fault　identification　method　proposed　in　this　study　reduces　the　dependence　on　the　fault　sample　data　of　neutron　detectors　to　a　certain　extent,　and　solves　the　problem　of　lack　of　fault　data.　The　experimental　results　show　that　the　proposed　method　can　be　applied　to　the　unknown　fault　identification　of　neutron　detectors.　©　2022,　The　Author(s),　under　exclusive　license　to　Springer　Nature　Singapore　Pte　Ltd.