KMITL

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

Browse

Settings

Author: search.filters.author.Kuson, Pramote

Search Results

Now showing 1 - 4 of 4
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    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 (R<sup>2</sup><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.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    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.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Measuring the impact of tractor trailers on soil compaction for typical sugarcane-haulage operations in Thailand
    (2017-04-01)
    Thungsotanon, Dithaporn
    ;
    Usaborisut, Prathuang
    ;
    Kuson, Pramote
    ;
    Kulketwong, Chompoonud
    ;
    Abdullakasim, Wanrat
    Mechanization associated with operations in sugarcane production may lead to severe soil compaction. Soils may be particularly susceptible during harvesting and transport of sugarcane from the fields. A tractor towing a trailer can be a useful mean of sugarcane transport even in moist soil, but this can lead to soil compaction. In this study, the influence of tractor traffic when towing two types of trailers, i.e. a full-trailer (one on the front and two axles tandem on the rear) and a semitrailer (two axles tandem), were studied. The results showed that after the passage of a tractortowed trailer, soil bulk density in the test field was increased significantly. The passage of a tractor-towed trailer increased the penetration resistance to more than 3 MPa. The effect of a vehicle passage could reach to soil depths exceeding 45 cm, and increased as axle load increased. Analysis of the soil stresses indicated that the soil had been subjected not only to the compression stress but also the shear stress. The maximum principal stress (s1) generated by a tractor-towed semi-trailer was high. Further study should determine the thresholds for carried weight on different soil conditions in order to avoid excessive soil compaction.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    A young-coconut-fruit-opening machine
    (2007-10-01)
    Jarimopas, Bundit
    ;
    Kuson, Pramote
    The purpose of this research was to design, construct, and evaluate a prototype machine for opening young coconut fruit. The design concept was that a trimmed coconut could be opened by causing a small sharp knife to gradually move and shear off a circular section of the husk and shell at the top of the rotating fruit. The prototype consisted of a fruit holder, a height control mechanism, a knife and its feed controller, and a power transmission system. In operation, the small stainless-steel knife slowly penetrates through the husk and shell of the turning fruit in a direction approximately perpendicular to its surface. The rotation of the fruit causes the husk and shell to be cut by the sharp edge of the knife, which results in the formation of a circular opening at the top of the fruit. In this study, the key design parameters and their operation settings were determined as follows: the angle between the knife and the rotating plane (horizontal) was 50°; the angle between the knife cutting edge and the tangential line to the circular opening was 50°; the knife feeding speed was 50 mm/min; and the fruit rotation speed was 80 rpm. Based on these design parameters, a commercial prototype was manufactured and tested. The prototype had the capacity to open an item of fruit at an average time of 30 s. A 58-mm-diameter opening was cut and a mean 0.2% of the juice was spilled, while the juice that remained contained 0.2 g of fine pieces of shell and husk. The mechanically opened coconuts were well received by consumers. © 2007 IAgrE.