KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 7 of 7

Some of the metrics are blocked by your
consent settings
Systematic evaluation of spectral preprocessing and machine learning for near-infrared prediction of mechanical stability in complex colloidal systems
(2026-06-30)
Suttho, Pisit
;
Phetpan, Kittisak
;
Al Riza, Dimas Firmanda
;
Lim, Chin Hock
;
Kuson, Pramote
Natural rubber latex (NRL) is a critical industrial material, with concentrated rubber latex (CRL) serving as a major export product. Among its quality parameters, mechanical stability time (MST) is particularly important, reflecting colloidal stability and influencing downstream applications such as glove and balloon manufacturing. Conventional MST testing, however, relies on reagents, manual agitation, and visual assessment, making it labor-intensive, operator-dependent, and unsuitable for real-time quality monitoring. Since variations in proteins, lipids, and carbohydrates strongly govern MST, near-infrared (NIR) spectroscopy offers a promising non-destructive alternative by probing their molecular vibrations. This study developed a near-process NIR instrumentation system integrated with machine learning (ML) to predict MST in CRL. Spectral signals were preprocessed using eight techniques and modeled with five supervised regression algorithms. The best-performing configuration, Savitzky-Golay second derivative and orthogonal signal correction coupled with partial least squares regression, yielded high predictive accuracy, with coefficient of determination for prediction (R2<inf>p</inf>) of 0.94 and ratio of performance to deviation (RPD) of 4.2. This performance demonstrates the system's ability to extract chemically relevant information governing latex stability. The proposed NIR-ML framework provides a rapid, reagent-free, and scalable alternative to conventional MST testing, addressing the limitations of existing methods and supporting industrial quality monitoring. This approach is also transferable to the analysis of complex colloidal systems across diverse applications. Furthermore, the study provides mechanistic insight into how spectral preprocessing enhances the extraction of chemically meaningful information, establishing a physically interpretable framework for NIR-based analysis of such complex systems.
Some of the metrics are blocked by your
consent settings
Prediction of Cross-Link Density of Prevulcanized Latex Using InGaAs NIR Spectroscopy
(2026-02-17)
Dachapan, Suntaree
;
Saengprachatanarug, Khwantri
;
Phuphaphud, Arthit
;
Sirisomboon, Panmanas
;
Lim, Chin Hock
Cross-link density plays a critical role in determining the mechanical strength, elasticity, and long-term performance of prevulcanized (PV) latex products. This study aimed to evaluate the feasibility of near-infrared (NIR) spectroscopy for predicting cross-link density in PV latex using InGaAs-based instruments. Two spectrometers operating in the 960–1700 nm range were investigated: a noncontact MicroNIR and a contact AvaSpec system. Partial least-squares regression (PLSR) models were developed using two data sets. Data set I contained only NIR spectra, whereas Data set II combined spectra with industrial process variables, including holding time and latex grade. Cross-link density was referenced using the Prevulcanizate Relaxed Modulus (PRM, 100% and 300% elongation) and Toluene Swelling Index (TSI, 3 and 6 h) methods. Models based solely on Data set I showed limited predictive performance, while Data set II yielded markedly improved accuracy, highlighting the importance of integrating process information. The TSI-based models consistently surpassed PRM, with TSI-3 h identified as the most reliable reference. Using MicroNIR, the best TSI-3 h and TSI-6 h models achieved SEP values of 5.64 × 104 and 5.96 × 104 N·m– 2 and R2 values of 0.96 and 0.95, respectively. Comparable performance between contact and noncontact instruments further confirmed the practicality of noncontact NIR measurement. This work demonstrates, for the first time, that combining InGaAs NIR spectroscopy with process variables enables accurate, rapid, and nondestructive forecasting of TSI-based cross-link density for PV latex manufacturing.
Some of the metrics are blocked by your
consent settings
Classification of the Crosslink Density Level of Para Rubber Thick Film of Medical Glove by Using Near-Infrared Spectral Data
(2024-01-01)
Jongyingcharoen, Jiraporn Sripinyowanich
;
Howimanporn, Suppakit
;
Sitorus, Agustami
;
Phanomsophon, Thitima
;
Posom, Jetsada
Classification of the crosslink density level of para rubber medical gloves by using near-infrared spectral data combined with machine learning is the first time reported in this paper. The spectra of medical glove samples with different crosslink densities acquired by an ultra-compact portable MicroNIR spectrometer were correlated with their crosslink density levels, which were referencely evaluated by the toluene swell index (TSI). The machine learning protocols used to classify the 3 groups of TSI were specified as less than 80% TSI, 80–88% TSI, and more than 88% TSI. The 80–88% TSI group was the group in which the compounded latex was suitable for medical glove production, which made the glove specification comply with the requirements of customers as indicated by the tensile test. The results show that when comparing the algorithms used for modeling, the linear discriminant analysis (LDA) developed by 2nd derivative spectra with 15 k-best selected wavelengths fairly accurately predicted the class but was most reliable among other algorithms, i.e., artificial neural networks (ANN), support vector machines (SVM), and k-nearest neighbors (kNN), due to higher prediction accuracy, precision, recall, and F1-score of the same value of 0.76 and no overfitting or underfitting prediction. This developed model can be implemented in the glove factory for screening purposes in the production line. However, deep learning modeling should be explored with a larger sample number required for better model performance.
Some of the metrics are blocked by your
consent settings
Transflection Near-infrared Spectroscopy Combined with Machine Learning for Mechanical Stability Time Evaluation in Concentrated Rubber Latex
(2023-01-01)
Suttho, Pisit
;
Phetpan, Kittisak
;
Sirisomboon, Panmanas
;
Lim, Chin Hock
;
Ruttanadech, Nuttapong
This study aims to apply near-infrared spectroscopy (NIRS) in transflection mode combined with a machine learning approach to evaluate the mechanical stability time (MST) in Para concentrated rubber latex. Four supervised learning algorithms, including principal component regression (PCR), partial least squares regression (PLSR), support vector regression (SVR) and random forest regression (RFR), were employed to relate the NIR spectra with the MST degree of the latex samples. A comparison of predictive performance among these different algorithms was performed. The RFR model exhibited the best fitting performance with a coefficient of determination for calibration (R2) and root mean square error of calibration (RMSEC) of 0.95 and 37 seconds, respectively. In addition, the RFR-based model outperformed all others with its predictive performance, presenting coefficient of determination for prediction (r2) and root mean square error of prediction (RMSEP) of 0.64 and 91 seconds, respectively. Based on these results, this study could imply that the relationship between the NIR spectra and the change in the MST degree of the samples tends to be nonlinear.
Some of the metrics are blocked by your
consent settings
Measurement of cross link densities of prevulcanized natural rubber latex and latex products using low-cost near infrared spectrometer
(2021-01-01)
Lim, Chin Hock
;
Sirisomboon, Panmanas
The objective of this project is to use the four models to predict the crosslink densities based on reference method of PRM 300% using portable low-cost visible and shortwave near-infrared (Vis/SW-NIR) spectrometer across wavelengths of 350-1100 nm. The degrees of crosslink reflect on the properties of the prevulcanized (PV) latices and latex products produced and hence useful for quality control in the process of production. The four models were optimized using partial least squares regression (PLSR) that the spectra were collected from PV, PV<inf>50</inf>, thin and thick films. The use of thin and thick films was to emulate the latex products that used the PV latices. The results showed that there were almost no difference in the PV and PV<inf>50</inf> models by the coefficient of determination (R2) and root mean square error of calibration (RMSEC) of 0.70 and 9.04 × 104 N/m2 and 0.75 and 8.59 × 104 N/m2, respectively. Among the four models, thin and thick film models had poor results indicated by the coefficient of determination (R2) and root mean square error of calibration (RMSEC) of 0.02 and 17.31 × 104 N/m2 and 0.05 and 16.63 × 104 N/m2, respectively. Based on these results, only the models of prevulcanized (PV) latices could be used for quality assessment. Hence the Vis/SW-NIR spectrometer could be a cheap alternative for crosslink density determination of PV latices and would be a beneficial tool for monitoring the process of vulcanization in the rubber industry.
Some of the metrics are blocked by your
consent settings
Near infrared spectroscopy as an alternative method for rapid evaluation of toluene swell of natural rubber latex and its products
(2018-06-01)
Lim, Chin Hock
;
Sirisomboon, Panmanas
Toluene swell or equilibrium swelling is universally used by rubber factories to measure the degree of crosslink of their compounded or prevulcanized latices at different stages of production. To apply near infrared spectroscopy for rapid and accurate quality control, spectral acquisition of prevulcanized latex, thin film and thick film was performed using a Fourier transform near infrared spectrometer in diffuse reflection mode across the wavenumber range of 12,500–3600 cm1. For prevulcanized latex an effective model was developed using partial least squares regression with preprocessing (first derivative + straight line subtraction method). The coefficient of determination (r2), root mean square error of cross validation and bias of the validation set were 0.71, 3.93% and 0.005%, respectively. For the thin film model the r2, root mean square error of cross validation and bias were 0.65, 4.01% and 0.028%, respectively. Whereas for the thick film model the r2, root mean square error of cross validation and bias were 0.70, 4.00% and 0.006%, respectively. Three models including prevulcanized latex, thin film and thick film were validated by 23 unknown samples, providing standard error of prediction and bias of 5.357 and 2.494, 4.565 and 1.001 and 3.641 and 0.961%, respectively, for prevulcanized latex, thin film and thick film. The model developed for the thick film spectra gave the best results.
Some of the metrics are blocked by your
consent settings
Evaluation of prevulcanisate relaxed modulus of prevulcanised natural rubber latex using Fourier transform near infrared spectroscopy
(2017-01-01)
Lim, Chin Hock
;
Sirisomboon, Panmanas
The analysis of the cross-link density of prevulcanised natural rubber latex using near infrared spectroscopy was conducted using a Fourier transform near infrared spectrometer in diffuse reflection mode over the wavenumber range of 12500- 3600 cm-1. As the density of cross-link is an indication of the degree of cure, hence the properties of the latex products, the proposed method is useful for industrial purposes. For samples of prevulcanised latex of 50% total solids content (i.e. PV 50%) at 100% extension (prevulcanisate relaxed modulus 100%), the best model was developed using the partial least squares regression from the spectra, which were pre-treated using the first derivative method, where the coefficient of determination (r2), root mean square error of prediction and bias were 0.66, 6.06×104 Nm-2 and 1.63×104 Nm-2, respectively. The ratio of standard error of prediction to the standard deviation of the reference data in the prediction sample set was 1.8. This model could be used for screening. For samples at 300% extension (prevulcanisate relaxed modulus 300%) for PV 50%, the best model was developed using spectra pre-treated for scattering correction: r2, root mean square error of prediction and bias were 0.88, 6.74×104 Nm-2 and 1.35×104 Nm-2, respectively and the ratio of prediction to deviation was 3.0. Hence, the near infrared spectroscopy technique can be utilised as a rapid screening method for estimating the cross-link densities of prevulcanised natural rubber latex.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results