In Accurate assessment of transformer life and operating conditions has important guiding significance for the formulation of its maintenance strategy. In order to achieve objective and scientific assessment of transformer life estimation and condition assessment, this paper constructs a transformer life prediction and condition assessment method based on multi-feature diagnostic parameters of adaptive fuzzy neural network (ANFIS). First extract the characteristic parameters that affect the life of the transformer, learn these characteristic parameters through an adaptive fuzzy neural network, use the back-propagation algorithm to solve the adaptive dynamic adjustment of the weights, build a life prediction model of the transformer, and then build a A comprehensive health assessment model for transformers. Through experimental data research and demonstration, this model can accurately and effectively diagnose the life and state of transformers, and at the same time has higher prediction accuracy and assessment accuracy than traditional methods. It is a new and effective method for transformer state assessment.