In view of the drawbacks of the existing insulator state recognition models, and open-loop cognitive mode and insufficient generalization ability of loss function for detailed recognition deep network, imitated imitating human inspection mode, i.e., real-time evaluation of reliability of cognitive results and self-optimizing and regulation of the multi-scale image knowledge space, this paper explores a feedback cognition method of insulator state based on attention mechanism. Firstly, for the pre-processed insulator image, a stacked convolutional neural network with adaptive scale architecture is designconstructed, which renders the network input is scaled from the overall image to the detailed area. Each scale network shares the same architecture with different parameters to ensure the discriminative ability of different resolution inputs and generate a detailed attention area for the next scale. Secondly, for multiple scale features, stochastic configuration network (SCN) establish builds the classification criterion of the insulator states with universal approximation ability. Thirdly, an inter-class classification loss function and an intra-class ranking loss function are constructed to optimize the attention network, which generates a higher confidence score ranking than the previous prediction. Finally, learned from closed-loop control idea, the generalized error entropy performance index is definestablished to evaluate the reliability of the uncertain cognition results of insulator states in real time. Then, the network scale level is dynamically regulated to realize the self-optimizing regulation of the feature space and the reconstruction of the classification criteria based on the constraint of the uncertain detection results, which renders insulator states is re-recognized with feedback mechanism. Experimental results show that, compared with other network architectures, the proposed method enhances the generalization ability and improves the cognition accuracy of the model.