Chinese Optics, Volume. 18, Issue 1, 160(2025)
Non-destruction detection of jelly orange granulation disease using laser Doppler vibrometry
Fig. 3. Flow chart of vibration multi-domain image generation. (a) Vibration spectrum curves of jelly orange obtained by fast Fourier transform; (b) vibration response signal of jelly orange; (c) vibration multi-domain image generation module which contains the convolution block for downscaling the time-frequency signal, the Stockwell transform (ST) block for generating the time-frequency image, the Gramian Angle Field (GAF) block for generating from the time-frequency signal into the time-domain or frequency-domain images, and the normalization block; (d) the result of visualizing the vibration ST time-frequency domain image; (e) the visualizing vibration GAF frequency domain image; (f) the visualizing vibration GAF time-domain image
Fig. 4. Schematic diagram of ResT model structure. ResT mainly consists of multiple CNN-based Bottleneck blocks and Transformer-based Swin Transformer blocks, respectively, which extract local and global deep information from vibration multi-domain images
Fig. 5. Vibration spectra of jelly orange at different placement positions
Fig. 7. Selection of effective frequencies from the vibration spectrum using the CARS algorithm
Fig. 9. Comparison of the jelly orange granulation disease identification performances obtained by ResT, Resnet50, ViT, VMIT-SVM, VST-SVM, VMIT-PLS-DA, and VST-PLS-DA models
Table 1. Classification results of jelly orange granulation disease by PLS-DA and SVM models based on vibrational multi-domain image texture features
View tableView in ArticleTable 1. Classification results of jelly orange granulation disease by PLS-DA and SVM models based on vibrational multi-domain image texture features
模型 实际类别 预测类别 类别 准确率 (%) 总体 准确率(%) 正常 粒化 SVM 正常 96 5 95.04% 95.13% 粒化 2 41 95.35% PLS-DA 正常 93 8 92.08% 86.81% 粒化 11 32 74.42%
Table 2. Classification results of jelly orange granulation disease by PLS-DA and SVM models based on vibration spectral features
View tableView in ArticleTable 2. Classification results of jelly orange granulation disease by PLS-DA and SVM models based on vibration spectral features
模型 实际类别 预测类别 类别 准确率 总体 准确率 正常 粒化 SVM 正常 96 5 95.04% 89.58% 粒化 10 33 76.74% PLS-DA 正常 97 4 92.08% 90.97% 粒化 9 34 74.42%
Table 3. Training and prediction set results by ResT, Resnet50 and ViT models
(%) View tableView in ArticleTable 3. Training and prediction set results by ResT, Resnet50 and ViT models
(%) 模型 训练集准确率 预测集准确率 正常 粒化 总体 正常 粒化 总体 ResT 100.00 100.00 100.00 99.01 97.67 98.61 Resnet50 100.00 100.00 100.00 98.02 97.67 97.92 ViT 100.00 98.61 99.53 98.02 95.35 97.22
Get Citation
Copy Citation Text
Zhi LIU, Qing-rong LAI, Tian-yu ZHANG, Bin LI, Yun-feng SONG, Nan CHEN. Non-destruction detection of jelly orange granulation disease using laser Doppler vibrometry[J]. Chinese Optics, 2025, 18(1): 160
Category:
Received: Jun. 21, 2024
Accepted: Sep. 12, 2024
Published Online: Mar. 14, 2025
The Author Email:
