Murathathunyaluk, Siripan

Preferred name

Alternative Name

Murathathunyaluk, S.

Main Affiliation

School of Engineering

siripan.mu@kmitl.ac.th

Now showing 1 - 6 of 6

Some of the metrics are blocked by your
consent settings
A machine learning approach for predicting osmotic coefficients and deriving activity coefficients in alkyl ammonium salts
(2026-12-01)
Chawuthai, R.
;
Murathathunyaluk, S.
;
Saengsuradech, S.
;
Nukaew, A.
;
Simasatitkul, L.
Quaternary Ammonium Salts (Quats) have diverse applications across various domains. They are extensively used as phase-transfer catalysts (PTCs) in chemical reactions, facilitating the transfer of reactants between aqueous and organic phases. Their unique structure enables the formation of ion pairs, enhancing reaction rates at phase boundaries. This research develops a novel method for predicting Quats’ osmotic coefficients using Simplified Molecular Input Line Entry System (SMILES) notation and supervised machine learning. A comprehensive dataset of 1,654 data points from 52 distinct Quats was compiled. The structural characteristics were encoded using SMILES notation. The data was evaluated using random splitting and Leave-One-Group-Out (LOGO) validation to train seven machine learning algorithms. Gaussian Process (GP) emerged as the optimal algorithm. The GP model achieved a mean absolute percentage error (MAPE) of 5.29% and root mean square error (RMSE) of 0.034. Comparisons with Electrolyte-NRTL and Extended UNIQUAC models demonstrate that this data-driven approach offers competitive accuracy while enabling generalization to structurally similar compounds. This work marks a significant starting point for the machine learning-enhanced prediction of activity coefficients, with considerable potential for future refinement and application.
Some of the metrics are blocked by your
consent settings
Development of rotating tray dryer and study of the hot air flow pattern with computational fluid dynamics
(2015-01-01)
Murathathunyaluk, Siripan
;
Srisakwattana, Nitika
;
Saksawad, Treenuch
;
Bumrungthaichaichan, Eakarach
Rotating tray dryer has the advantages over Cabinet dryer when we compare them, which is the end product from drying procedure has more regularity of moistness after the procedure. A new tray dryer with three rotating trays was designed, constructed and evaluated to find the optimal pattern for inputting hot air into the chamber. Three experiments to supply hot air were investigated. First, hot air flows in lower inlet tube with and without tray rotation. The comparison on hot air ratio with tray rotation was made by varying the ratio of air flow rate though three wall-side tubes at 0:0:100, 20:20:60 and 30:30:40 (upper: middle: lower). The optimal ratio was found to be 30:30:40. Next, this optimal ratio was used to compare the drying efficiency between entering hot air through one-way inlet with tray rotation (rotating tray) and entering hot air through two-way inlets without tray rotation (stationary trays). The optimal pattern for entering hot air is two-way inlets of hot air with stationary trays at the ratio of 30:30:40. This setting was used for drying of mulberry and measuring total phenolic compound (TPC) in dried mulberry. After drying process, the quantities of TPC in each tray were not significantly different. Furthermore, the optimal condition is used to study the temperature profile with simulation program (Computational Fluid Dynamics, CFD) and the results from CFD are correlated with the experiments.
Some of the metrics are blocked by your
consent settings
Integration of Genetic Algorithm with Machine Learning for Properties Prediction
(2025-01-01)
Chawuthai, Rathachai
;
Murathathunyaluk, Siripan
;
Amornratthamrong, Nalin
;
Arunchaipong, Run
;
Anantpinijwatna, Amata
Numerous studies have demonstrated that machine learning (ML) provides more accurate estimations of properties for oxygenated organic derivatives compared to the conventional Quantitative Structure-Property Relationship (QSPR) method. Consequently, ML’s predictive capabilities have been extended to encompass a broader range of properties, including Partition Coefficient, Boiling Point, and Solubility, among others, for oxygenated hydrocarbon derivatives. Algorithms such as Linear Regression, Support Vector Machine, Random Forest, and Gaussian Process are selected through trial-and-error to identify the most suitable approach. The models are trained and validated using experimental data from published literature. Despite the accuracy of these property predictions, they have limited practical utility in industry, where specific property ranges are essential for processes. To address this, Genetic Algorithms (GA) are employed to design chemical compounds that meet industrial requirements. Integrating GA with ML could yield alternative chemical compounds, enhancing overall production processes by increasing economic potential, sustainability, and reducing environmental impact.
Some of the metrics are blocked by your
consent settings
Effect of regeneration conditions on dehumidification desiccant packed bed
(2019-01-01)
Murathathunyaluk, Siripan
;
Junjiewchai, Jarukit
;
Kitchaiya, Prakob
In the present study, dynamic performance of a dehumidification desiccant regeneration system has been investigated theoretically. The simulation of the combined heat and mass transfer that occur in a solid desiccant packed bed is carried out with MATLAB. The presented model takes into account only forced convection along the bed without heat conduction and heat loss across the wall. The simulated results are validated with the previous published studies. Using the explicit finite differential numerical method, the performances of dehumidification systems are presented by moisture removal capacity (MRC). The dynamic systems have been studied at the regeneration temperatures between 60 to 120 °C and air flow ratio between 0.2 to 2. Increasing the regeneration temperature and the regeneration air flow ratio are shown to have positive effect to MRC. However, excessively increase these values leads to the constant of MRC. Therefore, optimum values for these manipulated parameters has been examined. The result of this study help reducing heat consumption for regenerating heated air; as well as, reducing electric consumption used by the fan.
Some of the metrics are blocked by your
consent settings
Theoretical study on a novel temperature breakpoint cyclic operation to enhance desiccant packed bed performance
(2021-08-01)
Murathathunyaluk, Siripan
;
Kitchaiya, Prakob
In a conventional desiccant packed bed dehumidification, the adsorption and desorption operations switched at a constant cycle. However, this Conventional Steady Cyclic (CSC) operation was not performed well under disturbances. Therefore, a Temperature Breakpoint Cyclic (TBC) operation is proposed. A numerical model of the desiccant packed bed dehumidification system has been constructed and validated. The model was then used to assess the desiccant packed bed dehumidification performances in term of moisture removal capacity (MRC) and dehumidification coefficient of performance (DCOP) under various cycle times and temperature factors. The calculation results showed that under CSC, larger amounts of energy were required in the desorption operation, while the TBC exhibited higher performances in term of both MRC and DCOP. Notably, at a high regeneration temperature, the MRC of the TBC was 10% higher than the CSC's; moreover, the DCOP of the TBC was twice higher than the CSC's. In other words, at high recovery temperature, both operations exhibited comparable capacities while the energy cost was halved under TBC operation.
Some of the metrics are blocked by your
consent settings
Development of machine learning enhanced low-cost spectrophotometer for pesticide prediction
(2025-05-15)
Murathathunyaluk, S.
;
Jinorose, M.
;
Janpetch, K.
;
Chanthapanya, N.
;
Sombatsri, W.
Conventional analytical methods for measuring pesticide concentrations, such as chromatography, offer high accuracy but require expensive instrumentation, prompting the investigation of cost-effective alternatives like smartphone-based spectrophotometers. Despite their potential, these methods face challenges related to assembly and precision, often requiring human intervention to select appropriate images for analysis. This study presents a novel, affordable spectrophotometer designed for integration with machine learning algorithms. The device captures images of two spectral bands and employs a six-step image processing methodology to prepare images for analysis. A machine learning model trained on four algorithms with feature selection and cross-validation demonstrates high accuracy in predicting chemical concentrations of coloured solutions. The approach achieves 98.5 % accuracy for KMnO<inf>4</inf> and 96.7 % for Carbosulfan solutions, comparable to high-end spectrophotometry devices. The design eliminates the need for human intervention, reducing biased selection and result manipulation. However, concentration estimation of non-coloured compounds remains inaccurate, indicating areas for further refinement.

Murathathunyaluk, Siripan

Filters

Settings

Sort By

Results per page