Early recognition of problematic wine fermentations through multivariate data analyses

Emparan, M.; Simpson, Ricardo; Almonacid, Sergio; Teixeira, Arthur A.; Urtubia, Alejandra

doi:10.1016/j.foodcont.2012.03.029

Cited by 11 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to the above-mentioned process data analysis, fault diagnosis and detection investigates variation in a process caused by special issues rather than common reasons. For example, Nway PLS was used in problematic wine fermentations (Emparán et al, 2012). A dynamic N -way PLS was employed for online monitoring of the batch process (Chen and Yen, 2003).…”

Section: Chemometricsmentioning

confidence: 99%

Tensor Regression

Liu

Zhu

Zhang

et al. 2021

FNT in Machine Learning

View full text Add to dashboard Cite

The presence of multidirectional correlations in emerging multidimensional data poses a challenge to traditional regression modeling methods. Traditional modeling methods based on matrix or vector, for example, not only overlook the data's multidimensional information and lower model performance, but also add additional computations and storage requirements. Driven by the recent advances in applied mathematics, tensor regression has been widely used and proven effective in many fields, such as sociology, climatology, geography, economics, computer vision, chemometrics, and neuroscience. Tensor regression can explore multidirectional relatedness, reduce the number of model parameters and improve model robustness and efficiency. It is timely and valuable to summarize the developments of tensor regression in recent years and discuss promising future directions, which will help accelerate the research process of tensor regression, broaden the research direction, and provide tutorials for researchers interested in high dimensional regression tasks.

show abstract

Section: Chemometricsmentioning

confidence: 99%

Tensor Regression

Liu

Zhu

Zhang

et al. 2021

FNT in Machine Learning

View full text Add to dashboard Cite

show abstract

“…MPCA will unfold = ( × × ) in such a way as to put each of its vertical slices ( × ) side by side to the right, which start with the one corresponding to the first time interval. The resulting two-dimensional matrix has dimensions ( × ) [21,22] (Figure 2).…”

Section: Multiway Principal Component Analysismentioning

confidence: 99%

Process Monitoring and Fault Diagnosis for Shell Rolling Production of Seamless Tube

Xiao

Gao

Wang

et al. 2015

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Continuous rolling production process of seamless tube has many characteristics, including multiperiod and strong nonlinearity, and quickly changing dynamic characteristics. It is difficult to build its mechanism model. In this paper we divide production data into several subperiods byK-means clustering algorithm combined with production process; then we establish a continuous rolling production monitoring and fault diagnosis model based on multistage MPCA method. Simulation experiments show that the rolling production process monitoring and fault diagnosis model based on multistage MPCA method is effective, and it has a good real-time performance, high reliability, and precision.

show abstract

“…6 The potential of NIR and MIR to monitor and model alcoholic fermentations was also investigated, demonstrating the usefulness of these techniques to monitor the evolution of the fermentation process. [7][8][9][10] Regmi et al used MIR in the transmission mode with PLSR to predict the concentration of several acids in wine. They obtained good calibration results for citric, malic, tartaric, acetic, succinic, and lactic acids.…”

Section: Introductionmentioning

confidence: 99%

Early detection of undesirable deviations in must fermentation using a portable FTIR‐ATR instrument and multivariate analysis

Cavaglia

Giussani

Mestres

et al. 2019

Journal of Chemometrics

View full text Add to dashboard Cite

A portable FTIR-ATR spectrometer was used to monitor small-scale must fermentations (microvinifications) with the aims to describe the process and to early detect problematic fermentations. Twenty fermentations at normal operation conditions (NOC) and three fermentations that were intentionally deviated from NOC (yeast assimilable nitrogen deficiency-YAN) were monitored. FTIR-ATR spectra were registered after a minimum sample pretreatment during the fermentation process. In addition, density, sugars (glucose and fructose), and acetic acid contents were determined by traditional methods. Different multivariate analysis strategies (global and local models) were applied to the spectroscopic data to describe the evolution of the NOC fermentation and to early detect the abnormal fermentations. Global models based on principal component analysis (PCA) and partial least squaresdiscriminant analysis (PLS-DA) allowed to describe the evolution of fermentations in time and to correctly classify NOC and YAN fermentations. Abnormal deviations were successfully detected by developing one model for each sampling time. YAN experiments could be identified 49 hours after the beginning of the fermentations by means of Hotelling T 2 and residual F statistics. In conclusion, ATR-FTIR coupled to multivariate analysis showed great potential as a fast and simple at-line analysis tool to monitor wine fermentation and to early detect fermentation problems.

show abstract

Early recognition of problematic wine fermentations through multivariate data analyses

Cited by 11 publications

References 16 publications

Tensor Regression

Tensor Regression

Process Monitoring and Fault Diagnosis for Shell Rolling Production of Seamless Tube

Early detection of undesirable deviations in must fermentation using a portable FTIR‐ATR instrument and multivariate analysis

Contact Info

Product

Resources

About