KMITL

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

Browse

Search Results

Now showing 1 - 10 of 22

Some of the metrics are blocked by your
consent settings
Integration of discriminant analysis with Artificial neural networks to decision analytic framework for enhancing automated visual IC inspection accuracy
(2026-05-15)
Kiatcharoenpol, Tossapol
;
Klongboonjit, Sakon
This study aims to enhance the accuracy and reliability of automated visual inspection (AVI) in semiconductor manufacturing by integrating Linear Discriminant Analysis (LDA) and an Optimization Layer by Layer Neural Network (OLLNN). Unlike prior LDA-ANN hybrid approaches that primarily emphasize classification accuracy, this study formalizes a decision-analytic inspection loop that explicitly links discriminant centroids, feasible lighting regions, surrogate nonlinear modeling, and production level validation. A two-stage decision analytic framework is developed. In the first stage, LDA is applied to classify and identify discriminant boundaries and centroids between acceptable and defective image features under three lighting setups: coaxial ring, high ring, and low ring lights. In the second stage, OLLNN is trained using these features to capture nonlinear dependencies between greyscale intensity and lighting parameters, and then a surface response plot is used to ease the optimal parameter selection. The integrating model is validated using experimental IC marking inspection data to evaluate improvements in accuracy, especially false positive rates (Type I error). It was found that for the validation state, the false positive rates are reduced from 5.8% to below 4.6%, and classification accuracy improves significantly across variable illumination conditions. After implementation in mass production, the yield is increased to 99.6% with zero false positive found. This significant development of the integrating model enhances a foundation for adaptive, data-driven control of AVI parameters in smart factory environments that support real-time learning and improvement.
Some of the metrics are blocked by your
consent settings
Evaluation of Bio-Oil Quality from Hydrothermal Liquefaction of Chlorella vulgaris Using Entropy–TOPSIS Method
(2025-10-14)
Santikunaporn, Malee
;
Asavatesanupap, Channarong
;
Echaroj, Snunkhaem
;
Manjai, Kanokwan
;
Limcharoen, Wararat
Bio-oil production from microalgae presents a promising approach to address both energy crisis and environmental pollution. This study investigates the hydrothermal liquefaction (HTL) of Chlorella vulgaris for bio-oil production under varying solvents (methanol, ethanol, and propanol), catalyst types (zeolite, activate carbon, and graphene oxide) and catalyst loadings (0, 5, and 10 wt % of relative to dry algae). HTL reactions were conducted at temperatures ranging from 250 to 280 °C for 30 min, with biomass cake concentrations of 42.8–60.0 wt %. The objective was to determine optimal conditions for producing high-quality bio-oil using the Entropy–TOPSIS multicriteria decision-making method. Catalyst properties were characterized using SEM–EDS and nitrogen sorption analysis. Bio-oils were analyzed for higher heating value (HHV) and chemical composition via elemental analysis and gas chromatography-simulated distillation. Results showed bio-oil yields ranging from 43.65 to 71.51 wt %, with HHVs between 23.92 and 40.36 MJ/kg, indicating their suitability as transportation fuels. Among the solvents, propanol produced the highest amount of solid residue (biochar), while methanol promoted higher oil yields. The Entropy–TOPSIS analysis identified the most favorable conditions as HTL using methanol with 5 wt % graphene oxide catalyst, followed by methanol with 5 wt % activated carbon, and ethanol with 10 wt % zeolite. Energy recovery ranged from 63.69% to 96.18%, outperforming comparable biomass conversion processes. These findings support the potential for scalable, catalyst-enhanced HTL systems in commercial microalgae-based biofuel production.
Some of the metrics are blocked by your
consent settings
PREDICTION OF STOCK PRICE USING HYBRID NEURAL NETWORK: A CASE OF COAL PRODUCTION COMPANY
(2025-01-15)
Kiatcharoenpol, Tossapol
;
Klongboonjit, Sakon
Stock market prediction is a critical issue in the field of economics. As machine learning technologies advance, an increasing number of algorithms are being utilized to forecast stock price movements. Nonetheless, predicting stock market trends remains a challenging task due to the inherent noise and volatility in stock market data. This paper addresses this challenge by proposing a novel hybrid neural network model designed to predict stock market prices using parameters related to commodity prices and stock indices. A case study company is mainly in coal production business in Thailand, which produce coal, sale, distribute and operate coal-fired power plants as well. The Multiple Linear Regression (MLR) and Back propagation neural network (BPNN) as traditional prediction technique are employed to comparatively investigate the accuracy and performance of the proposed HNN. Experiment results show that the prediction accuracy of HNN is superior to MLR but similar to that of the BPNN model. However, HNN has a good performance both in accuracy, speed and practice. It can help investing analysts and investors make their wise decisions.
Some of the metrics are blocked by your
consent settings
Optimization of Gelatin Fibrous Scaffold Properties by PCL and CMC by Using Electrospinning Technique
(2025-01-01)
Meesa, Banpot
;
Klongboonjit, Sakon
This study aimed to utilize the electrospinning process to produce cell culture scaffolds from blends of gelatin-polycaprolactone and carboxymethyl cellulose. The experimental design involved determining the optimal voltage and feed rate for various ratios of the gelatin-polycaprolactone-carboxymethyl cellulose blends, including 100/0/0, 90/5/5, 80/15/5, 70/25/5, and 60/35/5. Gelatin served as the primary raw material at a 10% ratio, while polycaprolactone was added at 10%, and carboxymethyl cellulose acted as a strengthening agent at 0.8%. The solvent used for gelatin and polycaprolactone was 2,2,2 -trifluoroethanol, while water was used for carboxymethyl cellulose. The raw materials were thoroughly mixed to ensure homogeneity, and the resulting blend was processed by an electrospinning machine under various conditions to form nanofiber scaffolds. The workpieces were then dried and left to relax for 48 hours before being baked at 140°C for 72 hours, resulting in high-quality fiber material. The experiment revealed that the fiber sizes ranged from 1.5 μm to 5.2 μm, with the swelling ratio of the GPC60:35:5 mixture at 11.65%, confirming the feasibility of using electrospinning to create effective scaffolds for cell culture applications.
Some of the metrics are blocked by your
consent settings
Electrospinning of Nanofibers Effect of Gelatin by Polycaprolactone and Carboxymethyl Cellulose Degradation Characteristics
(2025-01-01)
Meesa, Banpot
;
Klongboonjit, Sakon
This study aims to investigate the degradation of gelatin-based polycaprolactone and carboxymethyl cellulose scaffolds produced through the electrospinning technique for nanofiber scaffolds. The experimental design varies the voltage and feed rate for different ratios of gelatin, polycaprolactone, cellulose, and carboxymethyl cellulose, which are 100/0/0, 90/5/5, 80/15/5, 70/25/5, and 60/35/5, respectively. An organic solvent, 2,2,2-trifluoroethanol, which is a suitable solvent for gelatin, polycaprolactone, and carboxymethyl cellulose, is used, though the materials are dissolved in water to prepare the raw material for electrospinning. To characterize the scaffolds, their physical properties are analyzed, including fiber morphology and size, using scanning electron microscopy. The results reveal that as the polycaprolactone content increases from 0%, 5%, 15%, 25%, to 35%, with carboxymethyl cellulose maintained at 0% or 5%, the fiber size decreases from 1.5 μm to 5.2 μm. This suggests that electrospinning is effective for fabricating scaffolds from all three materials. Furthermore, the decomposition rates are optimized for GPC90/5/5, GPC80/15/5, and GPC70/25/5, which completely decompose within 36 hours. Additionally, GPC80/15/5 shows a good degradation rate, while GPC100/0/0 and GPC60/35/5 exhibit rapid degradation.
Some of the metrics are blocked by your
consent settings
Application of Two-Step Entropy–TOPSIS Method and Complete Linkage Clustering for Water-Pumping Windmill Investment on Thailand Peninsula
(2024-12-01)
Klongboonjit, Sakon
;
Kiatcharoenpol, Tossapol
This study focuses on identifying suitable areas for the installation of water-pumping windmills in Thailand, which require wind speeds of at least 4 m/s to operate efficiently. A simple combined approach is introduced, integrating the Entropy–TOPSIS method complete linkage clustering to prioritize and categorize potential locations. Out of 271 initial areas, 28 have been selected based on their ability to meet the 4 m/s wind speed threshold. The Entropy–TOPSIS method first evaluates these areas based on monthly wind speed and agricultural area. The analysis reveals that regions with higher wind speeds generally score better for wind energy potential, while areas with larger agricultural spaces tend to score higher for farming suitability. The final integrated scores show that agricultural area is more significant, with a weight of 0.7788, compared to the wind speed weight of 0.2212. The areas are then ranked, and complete linkage clustering groups them into six categories, from the most to the least suitable for windmill installation. A sensitivity analysis confirms the robustness of the clustering method, as the group composition remains stable despite minor changes in weight adjustments. This approach simplifies decision-making for sustainable energy investments in Thailand agriculture sector.
Some of the metrics are blocked by your
consent settings
Study of Air in a Vehicle Brake System by TOPSIS and EDAS Combining with FAHP
(2024-01-01)
Khamwiangsa, Weerachai
;
Klongboonjit, Sakon
All vehicles are exported globally through sea freight, which involves extended storage periods and exposure to high temperatures. Consequently, issues with the brake system have been identified, arising from the presence of air and contaminants within the system. The aim is to minimize the number of Air in the Vehicle Brake System, targeting zero defects while eliminating repair and labor costs. Research integrating TOPSIS and EDAS with FAHP to address design and transportation issues in vehicles has not yet been identified. Through a systematic literature review, specialist questionnaires, and the Fuzzy Analytic Hierarchy Process (FAHP), the study identified the main contributing factors to the brake system issues and established their importance ranking. Based on this analysis, a multi-criteria framework for weights was determined using the FAHP comprehensive evaluation method. Subsequently, the Technique for Order of Preference by Similarity to the Ideal Solution (TOPSIS) method and The Evaluation based on Distance from Average Solution (EDAS) were employed to evaluate and classify the alternatives based on the obtained weights. By specifying a scoring guideline, the attributes of the brake system could be quantified, ensuring objectivity. Consequently, the brake system issue is implemented, verified, and analysed using TOPSIS and EDAS supported by FAHP. the priority ranking of 4 criteria levels and alternatives are calculated with Pi = 0.995, 0.690, and 0.574 respectively in the TOPSIS technique and ASi = 0.796, 0.500, and 0.478 respectively in the EDAS technique. The total Rejection per thousand of Air in a Vehicle Brake System is 0.99 for CA1, 0.12 for CA2, and 0.03 for CA3. The results highlight the effectiveness of integrating TOPSIS and EDAS with FAHP in reducing the presence of Air in the Vehicle Brake System and minimizing repair costs, with a primary focus on enhancing vehicle safety control as the most critical concern. Additionally, the research prioritizes assessing the risk associated with Air in the Vehicle Brake System.
Some of the metrics are blocked by your
consent settings
DEFECT REDUCTION OF AUTOMATIC FARE COLLECTION SYSTEM FOR A NEW MRT MONORAIL LINE USING DMAIC
(2024-01-01)
Kiatcharoenpol, Tossapol
;
Pratalab, Kewalin
;
Klongboonjit, Sakon
The objective of this research is to examine and address issues related to the quality of the automatic fare collection system for the new Mass Rapid Transit (MRT) line and to decrease maintenance time to meet the key performance indicator (KPI) set by the Mass Rapid Transit Authority (MRTA). A total of 1,497 work orders were collected from a survey conducted between June and August 2023. The study utilizes the DMAIC methodology and identifies the primary issue as “Note Module Faulty” commands on the Ticket Vending Machine (TVM), particularly for cash transactions where banknotes become stuck in the banknote acceptor (BNA) section, resulting in transaction failures. After conducting a root cause analysis, it was determined that the problem stemmed from the inadequate design of the banknote acceptor for the new polymer banknotes, Biaxially Oriented Polypropylene (BOPP) film. Following the resolution of the problem, it was noted that the daily influx of work orders follows an exponential decay trend, represented by the equation Yt = 3.525x(0.97803t), and the maintenance time has decreased from 62 minutes per work order to 9.27 minutes per work order.
Some of the metrics are blocked by your
consent settings
A lean manufacturing approach to waste minimization: a case of industrial rack plant
(2024-01-01)
Kiatcharoenpol, Tossapol
;
Chaosamthong, Kirati
;
Rawirangsun, Phuwit
;
Klongboonjit, Sakon
The concept of Lean Manufacturing is a methodology focused on eliminating waste in various activities through the application of five key principles: defining value, mapping the value stream, ensuring flow, establishing pull, and pursuing perfection. Starting with the identification of value based on product sales, it was determined that industrial rack product is the top-selling product. A Current Value Stream Map (Current VSM) was created to illustrate value-adding activities within the production process and highlight sources of waste. The analysis identified inefficiencies in the production processes of side frames, beams, and packaging, which hindered the ability to meet the target takt time of 60 seconds per unit. Once the processes requiring improvement were identified, strategies for optimization were developed, leading to the creation of an Improved Value Stream Map (Improve VSM). The implementation of waste reduction measures resulted in a significant decrease in production cycle time, from 104 seconds per unit to 60 seconds per unit—a reduction of 42.31%, enabling compliance with the target takt time. Ultimately, the complete elimination of waste led to the creation of an Ideal Value Stream Map (Ideal VSM). This was achieved by incorporating pull system and continuous u-shaped line principles and consolidating workstations to minimize non-value-adding activities. These improvements not only enhanced production efficiency but also maximized the ability to meet customer demands and contributed to building a competitive advantage.
Some of the metrics are blocked by your
consent settings
Assessment of Potential Area for Solar Energy Investment in Northeastern Thailand by Entropy-TOPSIS Method
(2024-01-01)
Phonphoon, Phichata
;
Kiatcharoenpol, Tossapol
;
Klongboonjit, Sakon
Agriculture is one of the important engines of Thailand's food industrial growth however the cost of fossil energy is quite high for Thai farmers. Since Thailand has great solar potential, especially northeastern region, renewable energy sources of sunlight in this region should be considered to be another energy source for Thai agriculture. To assess and classify the potential of the investment in agricultural solar power systems of 20 provinces in Thailand's northeastern region, this study applied the combining method of Entropy Weight Method and TOPSIS with secondary data of solar irradiance, farmer household density, and income of farmer households. With this combining method, the results showed that farmer household density and income of farmer household were more influence on assessing and classifying the potential of this investment than solar irradiance. Finally, all 20 provinces were classified into four groups of Group A (A<inf>12</inf>, A<inf>2</inf>, A<inf>4</inf>, A<inf>1</inf>, and A<inf>10</inf>), Group B (A<inf>8</inf>, A<inf>9</inf>, A<inf>19</inf>, A<inf>3</inf>, and A<inf>15</inf>)), Group C (A<inf>17</inf>, A<inf>13</inf>, A<inf>18</inf> A<inf>16</inf>, and A<inf>20</inf>) and Group D (A<inf>6</inf>, A<inf>11</inf>, A<inf>7</inf>, A<inf>14</inf>, and A<inf>5</inf>) from the most potential province group for investment in agriculture solar power system to the least potential province group for investment in agriculture solar power system.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results