Jing Zhang

Tea is one of the most popular drinks in the world. The rapid and accurate recognition of tea diseases is of great significance for taking targeted preventive measures. In this paper, an information entropy masked vision transformation (IEM-ViT) model was proposed for the rapid and accurate recognition of tea diseases. The information entropy weighting (IEW) method was used to calculate the IE of each segment of the image, so that the model could learn the maximum amount of knowledge and information more quickly and accurately. An asymmetric encoder–decoder architecture was used in the masked autoencoder (MAE), where the encoder operated on only a subset of visible patches and the decoder recovered the labeled masked patches, reconstructing the missing pixels for parameter sharing and data augmentation. The experimental results showed that the proposed IEM-ViT had an accuracy of 93.78% for recognizing the seven types of tea diseases. In comparison to the currently common image recognition algorithms including the ResNet18, VGG16, and VGG19, the recognition accuracy was improved by nearly 20%. Additionally, in comparison to the other six published tea disease recognition methods, the proposed IEM-ViT model could recognize more types of tea diseases and the accuracy was improved simultaneously.

To obtain a more comprehensive knowledge of the surface electric field distribution of composite insulators, a three-dimensional (3D) simulation model of a 10 kV FXBW4-10/70 composite insulator was established, and the distribution of the axial and radial electric fields on the surface of the insulator under normal, damaged, internal defect, and fouling fault conditions were calculated and analyzed based on the finite element method. The results showed that the axial and radial electric field distributions on the surfaces of the normal composite insulators were “U” shaped, the radial electric field at the damaged location had a greater change than the axial electric field, and both the axial and radial electric fields at the internal defect location increased significantly. For the insulator covered with NaCl conductive fouling, the axial electric fields at the high-voltage (HV) and low-voltage (LV) ends showed a greater change. The results can provide a basis for the fault identification of composite insulators and the optimal design of insulation structures.

A LiNbO₃ integrated optics sensor fusing with an optical waveguide Mache–Zehnder interferometer (MZI), a loop-antenna, and a segmented electrode has been proposed, designed, and fabricated for the measurement of pulsed current. The experiment results have demonstrated that, for measurement of the standard 8/20 μs lightning pulsed current, the average of the front time and duration time of the sensor detected pulsed current waveform are 7.00 μs and 19.78 μs, respectively, while those detected by the Person CT are 7.30 μs and 20.35 μs, respectively. From 100 A to 3300 A, the sensor shows good linear characteristics, and the correlation coefficient is 0.9989. Moreover, the minimum detectable pulsed current is about 66 A in the time domain. All these results reveal the sensor can provide a new and potential technology for the measurement of pulsed current in the time domain.