During　the　operation　and　maintenance　of　power　equipment,　a　large　amount　of　text　data　is　accumulated,　and　it　is　of　great　importance　to　mine　valuable　information　and　evaluate　the　operation　status　of　the　equipment.　Among　them,　named　entity　recognition　technology　is　a　key　prerequisite　for　downstream　tasks.　However,　with　the　development　of　natural　language　processing　technology,　while　improving　the　accuracy　of　entity　recognition,　the　existing　models　are　gradually　unable　to　meet　the　requirements　of　time　and　equipment　cost　for　model　training　in　practice.　In　this　paper,　we　propose　a　low-cost　ALBERT-BiLSTM-CRF-based　named　entity　recognition　model　applicable　to　power　equipment　defective　text.　The　model　achieves　an　F1　score　of　92.47%　in　entity　recognition　in　the　power　domain,　outperforming　the　benchmark　BERT　model　performance　in　terms　of　time　cost　and　effect.　©　2022　IEEE.