Guiyu Zhang

Dr. Guiyu Zhang


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 May 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
GZGuiyu Zhang
Guiyu Zhang
XTXian-Guo Tuo
Xian-Guo Tuo
YPyingjie peng
yingjie peng
XLXiaoping Li
Xiaoping Li
TPTingting Pang
Tingting Pang
Liquor has a complex system with high dimensional components. The trace components in liquor are varied and have low content and complex coordination relationships. This study aimed to solve the problem of reliance on smell and taste. Based on the characteristics of near-infrared spectrum response to hydrogen-containing groups, qualitative analysis was carried out in combination with machine learning technology. Firstly, an iterative adaptive weighted penalized least squares algorithm with spectral peak discrimination was used for baseline correction to effectively retain useful information in the feature absorption peaks. Then, the convolution smoothing algorithm was used to filter the noise, and the spectral curve smoothness was adjusted using the convolution window width. The near-infrared spectrum has a high dimension. Monte Carlo random sampling combined with an improved competitive adaptive reweighting method was used to evaluate the importance of spectral sampling points. According to the importance coefficient, the dimension of the spectral data set was optimized by using an exponential attenuation function through an iterative operation, and the data set with the smallest root-mean-square error was taken as the characteristic spectrum. The nonlinear separability of characteristic spectra was further improved by kernel principal component analysis. Finally, a liquor quality recognition model based on principal component analysis was established by using the hierarchical multiclass support vector machine method. Our key findings revealed that the prediction accuracy of the model reached 96.87% when the number of principal components was 5–12, with more than 95% of the characteristic information retained. These results demonstrated that this rapid nondestructive testing method resolved the challenge posed by relying on subjective sensory evaluation for liquor analysis. The findings provide a reliable analytical approach for studying substances with high-dimensional component characteristics.

9 January 2026 in European Food Research and Technology
Verified
Journal Article
Closed access
PDF file
GZGuiyu Zhang
Guiyu Zhang
YTYaohong Tang
Yaohong Tang
LGLi Gao
Li Gao
XZXianglin Zeng
Xianglin Zeng
RHRutao He
Rutao He

17 October 2025 in Food Analytical Methods
Verified
Journal Article
Closed access
PDF file
GZGuiyu Zhang
Guiyu Zhang
YTYaohong Tang
Yaohong Tang
RHRutao He
Rutao He
XZXianglin Zeng
Xianglin Zeng
GLGao Li
Gao Li

4 June 2025 in Buildings
Verified
Journal Article
Open access
PDF file
LYLiu Yong
Liu Yong
CLCheng Liu
Cheng Liu
GZGuiyu Zhang
Guiyu Zhang
XHXiang He
Xiang He
Predicting pit deformation to prevent safety accidents is the primary objective of pit deformation forecasting. A reliable predictive model enhances the ability to accurately monitor future deformation trends in pits. To enhance the prediction of pit deformation and improve accuracy and precision, an Improved Crown Porcupine Optimization Algorithm (ICPO) based on a Bidirectional Time Convolution Network–Bidirectional Gated Recirculation Unit (BITCN-BIGRU) is developed. This model is utilized to forecast the future deformation trends of the pit. Utilizing site data from a metro station pit project in Chengdu, the accuracy of the predicted values from Historical Average (HA), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) models is evaluated against the six models developed in this study, including the ICPO-BITCN-BIGRU model. Comparison of the test results indicates that the ICPO-BITCN-BIGRU prediction model exhibits superior predictive performance. The predicted values from the ICPO-BITCN-BIGRU model demonstrate R2 values of 0.9768, 0.9238, and 0.9943, respectively, indicating strong concordance with the actual values. Consequently, the ICPO-BITCN-BIGRU prediction model developed in this study exhibits high prediction accuracy and robust stability, making it suitable for practical engineering applications.

29 October 2026 in Analytical Methods
Verified
Journal Article
Closed access
GZGuiyu Zhang
Guiyu Zhang
MQMaohan Qin
Maohan Qin
KCKerong Chen
Kerong Chen
SDShiliao Deng
Shiliao Deng
XZXianglin Zeng
Xianglin Zeng
LLLongxin Li
Longxin Li
Multi-level XAI reveals a shared discriminative anchor near 4663 cm −1 , Grade 2-related evidence at 5812–5836 cm −1 , and broader Grade 3-associated responses across 5800–6600 cm −1 , enabling interpretable NIR-based Baijiu grade classification.

27 December 2025 in Computational Particle Mechanics
Verified
Journal Article
Open access
PDF file
JZJunchao Zhou
Junchao Zhou
HYHang Yang
Hang Yang
XCXin Chen
Xin Chen
LDLin Du
Lin Du
JGJianjie Gao
Jianjie Gao
XTXianguo Tuo
Xianguo Tuo
In order to reduce the penetration resistance of equipment into the strong fragrance liquor cellar, accelerate the expansion of intelligent, information-based products applied to the field of strong fragrance liquor fermentation, improve brewing quality, and solve the current situation of lack of competitiveness of medium and high-end liquor products. Based on the discrete unit method (DEM), through preliminary experiments and simulation, the material parameters and contact parameters of sorghum in fermented grains were established. On this basis, a contact model of fermented grains pit was established based on Hertz-Mindlin with JKR (Johnson-Kendall-Roberts) Cohesion model, and the penetration characteristics of the cone bar inserted into the contact model of fermented grains pit were analyzed. The results showed that the material parameters and contact parameters of sorghum measured by the previous experiment and simulation were accurate, and the accuracy of the parameters was verified by the repose Angle experiment. The influence of conical rod structure (diameter, shape and Angle) on penetration resistance is as follows: the maximum difference of penetration resistance caused by diameter is about 450N, that caused by double cone is 10.3%, and that caused by cone Angle is about 4.3–9.6%. The influence of operation mode (depth and velocity) on the penetration resistance is: the depth is greater than the velocity, and the penetration resistance presents a trend of “slow before and slow after”. When the penetration depth is large, the difference of the penetration resistance caused by different penetration velocity is not significant. This study not only enriched the relative material parameters of grain and sorghum discrete elements, but also provided a basis for reducing penetration resistance and further optimizing the structure of monitoring equipment and the design of operation mode.