Monitoring the moisture content of withering leaves in black tea manufacturing remains a difficult task because the external and internal information of withering leaves cannot be simultaneously obtained. In this study, the spectral data and the color/texture information of withering leaves were obtained using near infrared spectroscopy (NIRS) and electronic eye (E-eye), respectively, and then fused to predict the moisture content. Subsequently, the low- and middle-level fusion strategy combined with support vector regression (SVR) was applied to detect the moisture level of withering leaves. In the middle-level fusion strategy, the principal component analysis (PCA) and random frog (RF) were employed to compress the variables and select effective information, respectively. The middle-level-RF (cutoff line = 0.8) displayed the best performance because this model used fewer variables and still achieved a satisfactory result, with 0.9883 and 5.5596 for the correlation coefficient of the prediction set (R_p) and relative percent deviation (RPD), respectively. Hence, our study demonstrated that the proposed data fusion strategy could accurately predict the moisture content during the withering process.

Catechin is a major reactive substance involved in black tea fermentation. It has a determinant effect on the final quality and taste of made teas. In this study, we applied hyperspectral technology with the chemometrics method and used different pretreatment and variable filtering algorithms to reduce noise interference. After reduction of the spectral data dimensions by principal component analysis (PCA), an optimal prediction model for catechin content was constructed, followed by visual analysis of catechin content when fermenting leaves for different periods of time. The results showed that zero mean normalization (Z-score), multiplicative scatter correction (MSC), and standard normal variate (SNV) can effectively improve model accuracy; while the shuffled frog leaping algorithm (SFLA), the variable combination population analysis genetic algorithm (VCPA-GA), and variable combination population analysis iteratively retaining informative variables (VCPA-IRIV) can significantly reduce spectral data and enhance the calculation speed of the model. We found that nonlinear models performed better than linear ones. The prediction accuracy for the total amount of catechins and for epicatechin gallate (ECG) of the extreme learning machine (ELM), based on optimal variables, reached 0.989 and 0.994, respectively, and the prediction accuracy for EGC, C, EC, and EGCG of the content support vector regression (SVR) models reached 0.972, 0.993, 0.990, and 0.994, respectively. The optimal model offers accurate prediction, and visual analysis can determine the distribution of the catechin content when fermenting leaves for different fermentation periods. The findings provide significant reference material for intelligent digital assessment of black tea during processing.

Fermentation is a key link in determining the quality and flavor formation of black tea. However, during the actual production, the judgment of black tea fermentation quality mainly relies on the sensory evaluation of the tea maker, which is more subjective and prone to cause inconsistency in tea quality. Traditional testing methods, such as physical and chemical analyses, are time-consuming, laborious, and costly and are unable to meet the needs of the actual production. In this study, a self-developed machine vision system was used to quickly and accurately identify the degree of black tea fermentation by acquiring color and texture information on the surface of fermented leaves. To accurately control the quality of black tea fermentation and to understand the dynamic changes in key endoplasmic components in the fermented leaves, a quantitative prediction model of the key endoplasmic components in the fermentation process of black tea was constructed. The experiments proved that the system achieved 100% accuracy in discriminating the degree of fermentation of black tea, and the prediction accuracy of catechin components and thearubigin content reached more than 0.895. This system overcomes the defects of accurate measurement of multiple sensors coupled together, reduces the detection cost, and optimizes the experimental process. It can meet the needs of online monitoring in actual production.

The rapid and intelligent evaluation of black tea taste quality during the fermentation process is an unsolved problem because of the complexity and hysteretic of the current taste evaluation method. Common infrared spectroscopy and machine vision technologies can rapidly evaluate the taste quality of black tea, but they can not obtain comprehensive sample information. To obtain comprehensive sample information and achieve the rapid evaluation of the taste quality of black tea, the fusion data from hyperspectral images of fermentation samples were applied to predict the taste quality. The successive projection algorithm (SPA) and ant colony optimization (ACO) were used to select effective bands for spectral data. Subsequently, the color images were synthesized using three carefully selected effective bands obtained through the SPA and ACO. The 18 image features were extracted from each synthesized color image and fused with spectral effective bands. The fusion data and three different algorithms, such as partial least squares regression (PLSR), support vector machine regression (SVR), and extreme learning machine (ELM), were employed to establish the regression model for taste quality. Specifically, the fusion-SPA-PLSR model exhibited the best performance. This study provides a novel method for the intelligent evaluation of taste quality during black tea fermentation and lays a theoretical foundation for the intelligent processing and control of black tea.

The intelligent perception of moisture content (MC) for tea leaves during the black tea withering process is an unsolved task because of the acquisition of limited sample characteristic information. In this study, both the external and internal features of withering samples were simultaneously acquired based on near-infrared spectroscopy (NIRS) and machine vision (MV) technology. Different data fusion strategies, including low-, middle- and high-level strategies, were employed to integrate two types of heterogeneous information. Subsequently, the different fused features were combined with a support vector regression (SVR) algorithm to establish the moisture perception models of withering leaves. The middle-level-variable iterative space shrinkage approach (VISSA) displayed the best performance with 5.7705 for the relative percent deviation (RPD). Therefore, the proposed multi-information fusion strategy could achieve an intelligent perception of tea leaves in the black tea withering process. The integration of NIRS and MV technology overcomes the limitations of single-technology approaches in black tea withering assessment, providing a robust methodology for precision processing and targeted quality control of black tea.

Rolling is a critical step in the processing of black tea, marking the beginning of fermentation. At this stage, the formation of tea pigments causes significant changes in the color of the processed leaves, laying the essential groundwork for the development of color and flavor quality components in subsequent fermentation processes. However, the rapid and non-destructive sensing of tea pigments during black tea rolling remains challenging. This study focused on black tea products undergoing rolling as its research subject, utilizing electrical characteristic detection technology to collect time-series electrical parameters of rolling leaves at various testing frequencies. The original electrical parameters were preprocessed using multiplicative scatter correction (MSC), min-max normalization (Min-Max), and smoothing (Smooth). Various selection methods, including the competitive adaptive reweighting algorithm (CARS), uninformative variable elimination (UVE), and the variable combination population analysis and iterative retained information variable algorithm (VCPA-IRIV), were employed to identify electrical parameters relevant to the targeted attributes. Quantitative prediction models for the content of tea pigments were established using partial least squares regression (PLSR) and support vector machine regression (SVR). The results demonstrated that the Smooth-VCPA-IRIV-SVR model exhibited superior performance in predicting the contents of theaflavins (TFs), thearubigins (TRs), and theabrownins (TBs). Correlation coefficients of prediction (R_p) all exceeded 0.99, and Relative prediction deviation (RPD) values were all above 6.5, indicating that the model enables rapid and non-destructive detection of tea pigment content during black tea rolling. These findings provide preliminary technical support and reference for the digital production of black tea.