In order to solve the problems of high subjectivity, frequent error occurrence and easy damage of traditional corn seed identification methods, this paper combines deep learning with machine vision and the utilization of the basis of the Swin Transformer to improve maize seed recognition. The study was focused on feature attention and multi-scale feature fusion learning. Firstly, input the seed image into the network to obtain shallow features and deep features; secondly, a feature attention layer was introduced to give weights to different stages of features to strengthen and suppress; and finally, the shallow features and deep features were fused to construct multi-scale fusion features of corn seed images, and the seed images are divided into 19 varieties through a classifier. The experimental results showed that the average precision, recall and F1 values of the MFSwin Transformer model on the test set were 96.53%, 96.46%, and 96.47%, respectively, and the parameter memory is 12.83 M. Compared to other models, the MFSwin Transformer model achieved the highest classification accuracy results. Therefore, the neural network proposed in this paper can classify corn seeds accurately and efficiently, could meet the high-precision classification requirements of corn seed images, and provide a reference tool for seed identification.

As artificial intelligence technology continues to advance in the smart grid domain, it shows significant potential for optimizing online monitoring and intelligent diagnosis of high-voltage switchgear. Online monitoring and intelligent diagnosis involve the real-time collection of characteristic parameters to assess equipment health, enabling fault diagnosis, condition evaluation, and lifespan prediction through algorithmic integration. However, challenges such as limited data samples, insufficient data validity and correlation, reliance on single diagnosis algorithms, and suboptimal performance in practical applications restrict the accuracy and usability of fault diagnosis. In this work, we employ the GANs model to mitigate the issue of limited valid data samples. Additionally, we analyze the correlations among multi-feature variables affecting equipment health, develop a multi-factor fusion diagnosis algorithm, and propose a novel DualLSTM-DropNet model by improving the traditional LSTM model. The model's validity is experimentally verified, achieving data and algorithm optimization for intelligent diagnosis of high-voltage switchgear through artificial intelligence. This work offers valuable insights for implementing condition-based maintenance, predictive maintenance, and lifecycle management of high-voltage switchgear.