Quantitative Study On Impact Damage Of Yellow Peach Based On Hyperspectral Imaging Technology And Mechanical Parameters

Yellow peaches have become an important part of the human dietary structure due to their delicious taste and rich nutrition.With the continuous improvement of agricultural mechanization,the mechanical damage of yellow peaches usually occurs in the process of picking,transporting and packing.Damaged yellow peaches are not only more susceptible to rot,but also affect other intact yellow peaches,resulting in economic losses.Mechanical damage mainly includes static pressure damage,vibration damage,puncture damage and impact damage,among which impact damage is the most serious and prone to occur.If the damage degree of fruit can be quantitatively evaluated,the economic losses will be reduced by grading fruit based on the damage degree of them.In this paper,yellow peaches are used as the research object,and hyperspectral imaging technology is used to make accurate predictions of mechanical parameters,so as to achieve quantitative prediction of the degree of impact damage of yellow peaches and provide theoretical guidance for the classification of yellow peaches.The main study and conclusion of the thesis are as follows:(1)Quantitative study on impact damage of yellow peach based on reflectance spectroscopy data.The combined hyperspectral technology and mechanical parameters method was used to quantitatively investigate the impact damage of yellow peaches.Firstly,the impact device was used to obtain values for the mechanical parameters of the yellow peach in terms of its damage area,absorbed energy,maximum contact force and maximum stress during the collision.The mechanical parameters were correlated with the damage area which showed that two of the parameters(absorbed energy and maximum contact force)correlated well with the damage area,and its were able to accurately characterize the degree of damage of the yellow peaches.Then,preprocessing methods such as SNV,MSC and SG smoothing were used to improve the predictive performance of the model and CARS was employed to select the characteristic wavelengths in all wavelengths.The results showed that there is a strong linear correlation between the spectral data and the mechanical parameters,and the prediction performance of SNV-CARS-PLSR model is best,and the R_P and RMSEP of the damaged area,absorbed energy,maximum contact force,and maximum stress of it were 0.920 and 86.452mm~2,0.845 and 1.303 J,0.943 and 49.666 N,0.660 and 0.146 MPa,respectively.(2)Quantitative study on impact damage of yellow peach based on hyperspectral image information combined with spectral information.In this paper,the combined hyperspectral image features and spectral features method was proposed to predict the values of mechanical parameters of yellow peaches.A collision device based on the pendulum principle was built to acquire the mechanical parameters which were maximum force,absorbed energy and average pressure.A hyperspectral imaging system was used to acquire the images of the bruised yellow peaches and the spectral information and color characteristics of images were extracted,respectively.The PCA was used to reduce the dimensionality of the image of bruised yellow peaches,and a grey scale co-generation matrix(GLCM)algorithm was used to extract the texture features of the feature wavelength image.The PLSR models of mechanical parameters were built with extracted spectral and image information.The results show that the PLSR models based on spectral information combined with image information are best in prediction the values of damage area and maximum force.However,the PLSR models have not achieved satisfactory performance in prediction the values of absorbed energy and average pressure.To improve the predictive performance of the PLSR model for absorbed energy and mean pressure,the CARS algorithm was used to extract the characteristic wavelengths and to correlate the image data with the mechanical parameters.The results show that the accuracy of all mechanical parameters is significantly improved by the PLSR models based on the feature spectral information combined with the image feature information.The R_P and RMSEP of the damaged area,absorbed energy,maximum force and average pressure are 0.928 and 86.632mm~2,0.826 and 1.469 J,0.924 and 61.765 N,0.815 and 0.050 MPa,respectively.(3)Quantitative study of impact damage on yellow peaches based on reflectance,absorbance and Kubelka-Munk spectral data.In the present study,mechanical parameters such as damage area,absorbed energy and maximum force were obtained based on a single pendulum collision device and an intelligent data acquisition system.The reflection spectra(R)of damaged areas of yellow peaches were collected by hyperspectral imaging system and transformed into absorbance(A)spectra and Kubelka-Munk(K-M)spectra.The SNV,MA and GF were used to preprocess the R,A and K-M spectra,respectively,and to build the PLSR and SVR models.By analyzing the performance indicators of the model,the spectral data with better prediction performance(raw spectra or preprocessed spectra)are selected from all spectra,and the characteristic wavelengths with good predictive power were selected from these better spectral data using both CARS and UVE algorithms.The PLSR and SVR models were built based on the screened feature wavelengths.respectively.The results revealed that the prediction performance of K-M-GF-CARS-PLSR model is best.For the damage area,absorbed energy and maximum force,the R_P~2 and RMSEP of the K-M-GF-CARS-PLSR model were 0.870 and77.865 mm~2,0.772 and 1.065 J,0.895 and 47.996 N,respectively.And the values of their RPD were 2.700,1.768 and 3.050,respectively.The characteristic wavelengths of the model were18.8%,10.2%and 21.6%,respectively.The results of this study showed that there was a strong correlation between mechanical parameters and K-M spectrum,which demonstrates the feasibility of quantitatively predicting the damage degree of yellow peaches based on K-M spectrum.