Klongboonjit, Sakon

Preferred name

Klongboonjit, Sakon

Alternative Name

Klongboonjit, S.

Klongboonjit, Sakol

Main Affiliation

School of Engineering

sakon.kl@kmitl.ac.th

Now showing 1 - 10 of 13

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
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
Quality Evaluation of Wind Energy Data with Complete Linkage Clustering
(2022-12-01)
Klongboonjit, Sakon
;
Kiatcharoenpol, Tossapol
Although wind is an important free energy and most investors or farmers would like to invest in wind energy projects, they sometimes lack of the wind quality data in alternative areas for making decision. It should be definitely good to have some simple methods to classify the quality of wind energy for alternative areas. In this study, Complete Linkage method combining with the Euclidean distance calculation, which is really a simple method for users, is introduced to cluster wind energy quality of alternative areas. In a case of 13 alternative areas in the south of Thailand, the data of average wind velocity along 12 months from the secondary data source can be used to generate the initial distance matrix before continuously improving with Complete Linkage method. Finally, these 13 alternative areas are suitable clustered at C.D. = 5.11 into 3 groups of the low wind quality area with I.D. = 1.21, the medium wind quality area with I.D. = 1.41 and the high wind quality area with I.D. = 1.45
Some of the metrics are blocked by your
consent settings
Applying Shainin’s Tools to Process Improvement for Reducing Cracking Defect of Sanitary Product
(2023-01-01)
Kiatcharoenpol, Tossapol
;
Seeluang, Rachan
;
Klongboonjit, Sakon
s: The objective of this research attempt is to implement the DMAIC (Define, Measure, Analyze, Improve, Control) approach, a part of the Six Sigma methodology, in order to diminish the loss of sanitary ware during the production process. Specifically, this study focuses on addressing the issue of cracking defects that often occur in the production of sanitary wares after the firing process. Cracking defects manifest as gaps on the surface of sanitary wares, resulting in nonconforming and aesthetically inferior products. The AG27 Model, a highly demand toilet bowl, was selected as the case study due to its significant occurrence of cracking defects, accounting for 20% of the total defective units. The research utilizes the Six Sigma methodology in conjunction with Shainin's tools to identify the root causes and enhance production yield. The employed Shainin's tools include the Family of variation (FOV's), Concentration chart, Paired comparison, and Better and current (B vs C). The primary focus area of investigation involves the variation in the forming process and the design of the plaster mold. Through the use of the concentration chart, it was determined that the cracking defects predominantly appear along the border line between the rim and body of the toilet bowl. Subsequent experiments, based on paired comparison, confirmed that the design of the border line, which incorporates a hollow body shape, and the potential degradation of mold quality due to frequent use, were the two significant factors contributing to the cracking defects. In order to address these issues, a new design was implemented to enhance the connection between the rim and solid body of the AG27 toilet bowl. The practicality of this solution was validated through the utilization of the B vs C tool during the improvement phase. As a result, the occurrence of cracking defects decreased from approximately 4.0% to 1.92% during the control phase, representing a potential reduction of defects by over 50%.
Some of the metrics are blocked by your
consent settings
LEAN IMPROVEMENT FOR PANTOGRAPH JACK PRODUCTION PROCESS USING VALUE STREAM MAPPING
(2023-05-01)
Kiatcharoenpol, Tossapol
;
Wisayathaksin, Chayanan
;
Chumongkon, Nopphawat
;
Khuisangeum, Thapanon
;
Klongboonjit, Sakon
The objectives of this research are to study the current process and improve the production process of pantograph jack by using Lean manufacturing techniques. The Lean tool used is Value stream mapping (VSM). The study starts with collecting data from the upstream to downstream to create a Current-state VSM to identify wastes and problems. The first problem was the low efficiency of the production process due to the high lead time of 7 days 8 hours. The ratio of value-added time to the lead time was only 0.026%. The next problem was overproduction because the cycle time is 69.54 seconds/piece while the takt time is 140.15 seconds/piece, which is 46.62% of the takt time, resulting in the early stoppage of the production line to prevent over inventory of finished products. After identifying the problems, the next step is to define production process improvement approaches by creating a Future-state VSM. The tools for the improvement included the Kanban system, Supermarket, Line balancing, and Cellular manufacturing then a simulation model of both current and future states was created to compare the results before and after the process improvement. The result from the simulation shows that the total lead time was reduced to 4 hours 39 minutes or a decrease of 97.54% from the current state. The ratio of value-added time to the lead time was increased to 1.304%, which is 49.39 times more than before the improvements, and the cycle time was increased to 133.02 seconds/piece, which is 94.91% of the takt time.
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
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
A Hybrid Neural Network for Predictive Model in A Plastic Injection Molding Process
(2022-04-01)
Kiatcharoenpol, Tossapol
;
Klongboonjit, Sakon
A reliable and sensitive technique for predicting quality of a plastic work-piece produced in injection molding process is essential help for practicing engineers. A system based on the process parameters that can estimate both two prime characteristics, %volume shrinkage and warpage of work-piece before it produced is significantly beneficial. In this paper, a fast feed forward network, Hybrid Neural Network (HNN), is proposed to construct the predictive model for those two quality characteristics. The unique algorithm of HNN based on the optimization of the weights of each layer is changed to a linear problem by linearization of the sigmoid functions. As iteration procedure used in Backpropagation algorithm is eliminated, the network training time is significant reduced. With this fast convergence of using HNN, the intelligent predictive model for injection molding process that can learn online is possible for further study. To entitle the network to cater for various process parameter conditions, a knowledge base as training and testing data have to be generated on the experimental data in a comprehensive working range of a plastic injection molding process. Consequently, the experiments were performed in 256 conditions based on the combination of nine basic process parameters. The neural networks were trained and the architecture of networks was appropriately selected by benchmarking the Root Mean Square error (RMS). The results of the novel network, HNN, have shown the ability to accurately predict the percentage of volume shrinkage with the 1.02% and 4.87% error at training and testing stages, respectively and for warpage with the 3.76% and 2.47% error at training and testing stages, respectively. These accuracy results are similar to those of backpropagation neural network (BPNN), but HNN has shown the superior fast converging about 38.5% and 66.7% over than those of BPNN
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.
Some of the metrics are blocked by your
consent settings
Lean Production for Reducing Wastes in Convex Lens Production Process
(2023-06-21)
Kiatcharoenpol, Tossapol
;
Rattanapakdee, Wanchai
;
Klongboonjit, Sakon
This research aimed to investigate the waste generated during the production of traditional convex lens. The study proposed a method to eliminate such waste by utilizing value stream mapping (VSM) as a tool for data collection and waste identification throughout the entire production process. Through the analysis of data using VSM, three specific types of waste were identified. These included losses resulting from ineffective utilization of the oven machine during the polymerization process, inefficiencies in personnel performance, and inappropriate working procedures. To address these waste issues, the task employed the work study method to optimize machine utilization, develop efficient work processes for personnel, and improve inappropriate procedures to enhance overall efficiency. The ECRS method was utilized to improve the process of waste elimination. The research findings demonstrated substantial reductions in waste within the production process. Specifically, the total throughput time decreased from 661.07 minutes to 480.68 minutes, representing a reduction of 27.29%. Furthermore, the total production lead time decreased from 1.20 days to 0.94 days, indicating a reduction of 21.67%. In terms of personnel, the workforce decreased from 42 employees per shift to 29 employees, reflecting a decrease of 30.95%. Finally, the number of oven machinery units required for all three shifts decreased from 3 ovens to 2 ovens, resulting in a reduction of 33.33%.

Klongboonjit, Sakon

Filters

Settings

Sort By

Results per page