Rapid spectral identification of hairy foot calluses based on visible/near infrared spectroscopy

March 8, 2024
Latest company news about Rapid spectral identification of hairy foot calluses based on visible/near infrared spectroscopy

In this study, a 400-1000nm hyperspectral camera was applied, and FS13, a product of Hangzhou Color Spectrum Technology Co., LTD., could be used for related research. The spectral range is 400-1000nm, the wavelength resolution is better than 2.5nm, and up to 1200 spectral channels can be reached. The acquisition speed can reach 128FPS in the full spectrum, and the maximum after band selection is 3300Hz (support multi-region band selection).

latest company news about Rapid spectral identification of hairy foot calluses based on visible/near infrared spectroscopy  0latest company news about Rapid spectral identification of hairy foot calluses based on visible/near infrared spectroscopy  1

mounting time is one of the important factors affecting cocoon quality. In the actual acquisition, usually the cocoon that is spinning silk and the hairy foot cocoon that has not pupated are collectively referred to as hairy foot cocoon. Generally, mature silkworms are cocooned from the first day of cocooning at 25℃ to the third or fourth day of cocooning, and then moult and pupate after 2~3 days. With the increasing of mounting time (3-7d), the number of cocoon layers and cocoon-layer ratio were increased by 2. According to the study, no cocoon was pupaed on the same day when the cocoons collected 48h after cocooning were cocooned. Cocoons collected 72h after cocooning were cocooned had a chrysalis rate of 26%. The pupaation rate of silkworm cocoons collected 96h after cocooning was 78%. The pupaation rate of cocoons collected 120h after cocooning was 100%. In the process of cocoon circulation and processing, the main harm of hairy foot cocoon is that the drying and folding is larger than normal cocoon, which affects the quality of cocoon and raw silk. Especially the cocoon which has not finished spinning will directly affect the filament length, cocoon layer ratio and silk yield. The pupa, tender pupa and normal pupa of hairy foot cocoon were easily suffocated after steaming, and the pupa shell of the tender pupa was easily broken in the dry, and the dirty juice or oil of the pupa polluted the cocoon layer and formed the next cocoon. According to statistics, the boarding rate of hairy foot cocoons in the same batch is 2~4% lower than that of normal cocoons, the relaxation rate is reduced by 4~6%, and the relaxation rate of severe steam heat is reduced by 10% or more. According to the experience data of the silk factory, the relaxation rate decreased by 1% or the boarding rate decreased by 1%, the corresponding nest fold increased by 3 to 4kg, the cost of raw silk will increase, and the quality of raw silk and the price of silk will be reduced. In this study, visible/near infrared spectroscopy was used to identify the hairy foot cocoon. The feature wavelength was extracted by continuous projection algorithm (SPA) and the model was established by PLS method, which provided the basis for rapid identification of hairy foot cocoon.

latest company news about Rapid spectral identification of hairy foot calluses based on visible/near infrared spectroscopy  2

latest company news about Rapid spectral identification of hairy foot calluses based on visible/near infrared spectroscopy  3

latest company news about Rapid spectral identification of hairy foot calluses based on visible/near infrared spectroscopy  4

latest company news about Rapid spectral identification of hairy foot calluses based on visible/near infrared spectroscopy  5

In this study, visible/near infrared spectroscopy was used to identify hairy foot calluses. First, the baseline correction pretreatment method was used to eliminate the difference in the baseline of sample spectral data caused by different acquisition times, and then the principal component analysis (PCA) method was used to qualitatively analyze the hairy foot cocoon and mature cocoon. Then, a method for identifying hairy foot cocoon based on least square support vector machine (LS-SVM) algorithm was proposed. The continuous projection algorithm (SPA) was used to reduce the 601 spectral variables to 12, reducing the model variables by 98.00%. The identification accuracy of hairy foot cocoon by this model reaches 100%. The results show that the hairy foot cocoon can be detected by visible/near infrared spectroscopy.