Search

The moisture content of black tea is an important factor affecting its suitability for processing and forming the unique flavor. At present, the research on the moisture content of black tea mainly focuses on a single withering step, but the research on the rapid detection method of moisture content of black tea applicable to the entire processing stage is ignored. This study is based on a miniaturized near-infrared spectrometer(micro−NIRS) and establishes the prediction models for black tea moisture content through machine learning algorithms. We use micro−NIRS for spectroscopic data acquisition of samples. Linear partial least squares (PLS) and nonlinear support vector regression (SVR) were combined with four spectral pre−processing methods, and principal component analysis (PCA) was applied to establish the predictive models. In addition, we combine the gray wolf optimization algorithm (GWO) with SVR for the prediction of moisture content, aiming to establish the best prediction model of black tea moisture content by optimizing the selection of key parameters (c and g) of the kernel function in SVR. The results show that SNV, as a method to correct the error of the spectrum due to scattering, can effectively extract spectral features after combining with PCA and is better than other pre−processing methods. In contrast, the nonlinear SVR model outperforms the PLS model, and the established mixed model SNV−PCA−GWO−SVR achieves the best prediction effect. The correlation coefficient of the prediction set and the root mean square error of the prediction set are 0.9892 and 0.0362, respectively, and the relative deviation is 6.5001. Experimental data show that the moisture content of black tea can be accurately and effectively determined by micro-near-infrared spectroscopy. [ABSTRACT FROM AUTHOR]

To explore the drying characteristics of soybean dregs and a nondestructive moisture content test method, in this study, soybean dregs were dried with hot air (80 °C), the moisture content was measured using the drying method, water status was analyzed using low-field nuclear magnetic resonance (LF-NMR) and the moisture content prediction models were built and validated. The results revealed that the moisture contents of the soybean dregs were 0.57 and 0.01 g/g(w.b.), respectively, after drying for 5 and 7 h. The effective moisture diffusivity increased with the decrease in moisture content; it ranged from 5.27 × 10−9 to 6.96 × 10−8 m2·s−1. Soybean dregs contained bound water (T21), immobilized water (T22) and free water (T23 and T23'). With the proceeding of drying, all of the relaxation peaks shifted left until a new peak (T23') appeared; then, the structure of soybean dregs changed, and the relaxation peaks reformed, and the peak shifted left again. The peak area may predict the moisture content of soybean dregs, and the gray values of images predict the moisture contents mainly composed of free water or immobilized water. The results may provide a reference for drying of soybean dregs and a new moisture detection method. [ABSTRACT FROM AUTHOR]

In this study, moisture contents and product quality of Pu‐erh tea were predicted with deep learning‐based methods. Images were captured continuously in the sun‐drying process. Environmental parameters (EP) of air humidity, air temperature, global radiation, wind speed, and ultraviolet radiation were collected with a portable meteorological station. Sensory scores of aroma, flavor, liquor color, residue, and total scores were given by a trained panel. Convolutional neural network (CNN) and gated recurrent unit (GRU) models were constructed based on image information and EP, which were selected in advance using the neighborhood component analysis (NCA) algorithm. The evolved models based on deep‐learning methods achieved satisfactory results, with RMSE of 0.4332, 0.2669, 0.7508 (also with R2 of.9997,.9882,.9986, with RPD of 53.5894, 13.1646, 26.3513) for moisture contents prediction in each batch of tea, tea at different sampling periods, the overall samples, respectively; and with RMSE of 0.291, 0.2815, 0.162, 0.1574, 0.3931 (also with R2 of.9688,.9772,.9752,.9741,.8906, with RPD of 5.6073, 6.5912, 6.352, 6.1428, 4.0045) for final quality prediction of aroma, flavor, liquor color, residue, total score, respectively. By analyzing and comparing the RMSE values, the most significant environmental parameters (EP) were selected. The proposed combinations of different EP can also provide a valuable reference in the development of a new sun‐drying system. [ABSTRACT FROM AUTHOR]

• A novel soft sensor method has been developed and evaluated. • Evaporation of void space water cools vacuum filter cake and suction air. • Change in suction air temperature correlates with filter cake solids contents. • Temperature change information increases the accuracy of moisture content estimates. • Conditions for minimum specific energy consumption were identified. The moisture content of filter cakes is probably the most important characteristic that should be kept at a desired level in industrial cake filtration applications to maintain consistent product quality and minimize energy consumption. Most of the currently applied methods for contactless real-time monitoring of the moisture content are based for example on x-ray or microwave techniques, and therefore, the equipment for the purpose is highly specialized. This paper introduces a novel soft sensor for filter cake moisture estimation that uses machine learning algorithms and data collected with basic process instrumentation. The method is primarily based on the cooling effect observed in the cake and air, caused by evaporation of liquid from the cake during the dewatering period, and it can be supported by other process data. The specific energy consumption of vacuum filtration and the subsequent thermal drying to zero moisture is also analyzed. The results of pilot-scale experiments with calcite slurry and a horizontal belt vacuum filter show that in order to minimize the specific energy consumption of vacuum filtration, it is crucial to find the right combination of slurry concentration, vacuum level, and mass of filter cake per unit area. The proposed method for estimating the filter cake moisture content is especially suitable for real-time monitoring and control, enabling also considerable reduction in the energy consumption of the overall process. When applying the proposed soft sensor method in a pilot-scale process, the mean absolute error of the estimated moisture content of the filter cake is ∼0.4 percentage points when the temperature of air at the vacuum pump inlet and the vacuum pump air flow rate are included in the input variables. [ABSTRACT FROM AUTHOR]

• A hybrid 1D-CNN and attention-based Bi-GRU model is developed for moisture content prediction. • The proposed model can simultaneously extract spectral local abstract information and position information. • The proposed model shows superior performance on both LUCAS and sand gravel spectral datasets. • A moisture content characteristic wavelength (CW) screening process is established. • The top ten CW points are calculated to help realize low-cost discrete NIR spectrometer. A non-destructive and rapid moisture content detection method of sand gravel material is required in loose material dams. The near-infrared (NIR) spectrum of sand materials is closely related to its moisture content. Recently, there is a growing need for fully using spectral information when establishing calibration models for sand gravel moisture content detection. To address these issues, a hybrid one dimensional-convolutional neural network (1D-CNN) and attention-based bidirectional gated recurrent unit (Bi-GRU) neural network was proposed to detect sand gravel moisture content with NIR spectrum. Two learners, namely, 1D-CNN and Bi-GRU, were constructed to extract local abstract information and sequence position information from the spectrum, respectively. In the 1D-CNN learner, multiple kernels CNN layers and one dimensional-separable convolution layers were conjunct to improve model accuracy and reduce network parameters. In the Bi-GRU learner, a multi-head self-attention mechanism was appended to evaluate the weights of the output features extracted by Bi-GRU layers. The proposed model achieved the best prediction results in LUCAS dataset (R2 greater than 0.75, RPD greater than 2.0) and our sand gravel spectral dataset (R2 = 0.96, RPD = 5.06) compared to other deep learning and conventional spectroscopy analysis methods. In addition, the top ten characteristic wavelength points of sand gravel were identified. These can be used to choose a discrete spectrum measuring instrument, which has a relatively low cost. [ABSTRACT FROM AUTHOR]

Near infrared (NIR) hyperspectral imaging has been used as a rapid non-destructive technique to predict moisture content of tea. To improve the performance of predicting, we first find and validate the fact that the texture near the veins is continues and directional. And then we propose Three-Dimension Gabor Filter (TDGF) and its corresponding filterbank to describe the textures of tealeaf. After that we construct two types of models based on partial least squares (PLS) regression. Experiments are conducted to predict the moisture content of Longjing tea, and different regression models based on different types of features are built for comparison. The results show that the proposed filterbank is able to detect the optimal direction of water flow and the model combining the spectrum and TDGF textures outperform the other comparative models. [ABSTRACT FROM AUTHOR]