KMITL

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

Browse

Settings

Access type: UnknownAuthor: search.filters.author.Lekawat, Lertsak

Search Results

Now showing 1 - 6 of 6
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    PM 2.5 Prediction & Air Quality Classification UsinMachine Learning
    (2024-06-01)
    Soontornpipit, Pichitpong
    ;
    Lekawat, Lertsak
    ;
    Tritham, Chatchai
    ;
    Tritham, Chattabhorn
    ;
    Pongpaibool, Pornanong
    Forecasting plays a vital role in air pollution alerts and the management of air quality. Studies and observations conducted in Thailand indicate a concerning rise in pollution levels, particularly in the concentration of PM2.5. concentrations. Bangkok, in particular, has been flagged for its alarmingly high PM2.5 By projecting the future PM2.5 concentrations in these urban areas, we can obtain valuable short-term predictive information regarding air quality. After conducting experiments using four different machine learning algorithms, it was found that the LSTM (Long Short-Term Memory) model provides the most accurate forecasts based on various statistical evaluation indicators. These indicators include a Root Mean Square Error (RMSE) of 2.74, Mean Absolute Error (MAE) of 1.97, R-squared value of 0.94, and Mean Absolute Percentage Error (MAPE) of 10.53. Then the classified air quality based on PM2.5 from the LSTM model gives the best performance indicators including accuracy = 0.9072, precision = 0.8466, negative predict value = 0.9403, sensitivity = 0.8144, specificity = 0.9381, and F1-score = 0.8169. The results show that the machine learning model can predict PM2.5 concentration, which is suitable for early warning of pollution and information provision for air quality management systems in Bangkok.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    CFD—Assisted Expert System for N2-Controlled Atmosphere Process of Rice Storage Silos
    (2024-03-01)
    Angsrisuraporn, Phakkawat
    ;
    Samakkarn, Chawit
    ;
    Lekawat, Lertsak
    ;
    Singkhornart, Sasathorn
    ;
    Thongsri, Jatuporn
    Since organic rice storage silos were faced with an insect problem, an owner solved this problem using the expert system (ES) in the controlled atmosphere process (CAP) under the required standard, fumigating insects with an N<inf>2</inf>, reducing O<inf>2</inf> concentration to less than 2% for 21 days. This article presents the computational fluid dynamics (CFD) assisted ES successfully solved this problem. First, CFD was employed to determine the gas flow pattern, O<inf>2</inf> concentration, proper operating conditions, and a correction factor (K) of silos. As expected, CFD results were consistent with the experimental results and theory, assuring the CFD’s credibility. Significantly, CFD results revealed that the ES controlled N<inf>2</inf> distribution throughout the silos and effectively reduced O<inf>2</inf> concentration to meet the requirement. Next, the ES was developed based on the inference engine assisted by CFD results and the sweep-through purging principle, and it was implemented in the CAP. Last, the experiments evaluated CAP’s efficacy in controlling O<inf>2</inf> concentration and insect extermination in the actual silos. The experimental results and owner’s feedback confirmed the excellent efficacy of ES implementation; therefore, the CAP is effective and practical. The novel aspect of this research is a CFD methodology to create the inference engine and the ES.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Track width measurement in heat-assisted magnetic recording systems using the cross-track DC noise method
    (2022-07-01)
    Kampun, Prasit
    ;
    Lekawat, Lertsak
    ;
    Tongsomporn, Damrongsak
    This paper uses a cross-track DC noise measurement technique to determine the written track width in heat-assisted magnetic recording (HAMR). The method is approached as a simple, no-extra-hardware-required technique on a spin-stand to determine the written track width as well as the DC noise amplitude at the center track in a HAMR system. The track width data show the expected trends with changing laser operating current (Iop) and write current (Iw), and they are strongly correlated with track density capabilities and physical near-field transducer (NFT) peg width. The written track width is essentially defined by the Iop, which increases as Iop increases. The method is useful for comparing the magnetic responses of different writer pole or NFT peg geometries, as well as media design comparison to provide insight into the head/component necessary to improve HAMR system performance, which is useful HAMR recording parameters for head/media designers and test engineers.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Magnetic write field characterization in heat-Assisted magnetic recording systems
    (2020-01-01)
    Kampun, Prasit
    ;
    Lekawat, Lertsak
    ;
    Tongsomporn, Damrongsak
    Magnetic write field is a critical factor in determining the quality of the magnetic write transitions, which determine the linear density (LD) limit in heat-Assisted magnetic recording (HAMR). We introduce a reversed DC band approach as a simple, no extra-hardware-Required technique in a spin-stand to assess the magnetic write field contributions, independently in an HAMR system. Heads with different distances between near-field transducer and writer pole, and media with and without soft magnetic under layer were characterized. The estimated result strongly correlates with LD and signal-To-noise ratio, which agrees with previous modeling studies. These results give insight into the head/component required to optimize the HAMR's system performance. The technique provides qualitative ranking of magnetic write fields and recording temperature, as well as laser operating current at Curie temperature for head/component designs.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Manufacturing Performance and Yield Prediction with Continuous Process Variables
    (2018-12-24)
    Lekawat, Lertsak
    ;
    Kampun, Prasit
    This paper presents a manufacturing process performance and yield prediction method that has been applied with satisfactory results in a hard disk drive (HDD) and component assembly plant in Thailand. Distribution profiles of key process input parameters are developed. The response functions relating key process output parameters and the input parameters are also developed. Subsequently, manufacturing yields and/or performances of key output parameters can be analyzed and optimized if needed by altering design targets and tolerances of key input parameters.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Improvement of HF RFID reader performance under metallic environment using ferrite sheet
    (2017-12-19)
    Kankhunthod, Kittipon
    ;
    Lekawat, Lertsak
    ;
    Pakasiri, Charpol
    Conventional loop antennas for RFID reader usually perform worse with metallic environment. To improve reading range under this condition, a ferrite sheet is incorporated in the conventional loop antenna. The proposed antenna yields similar reading range with or without metallic environment.