Tantrapiwat, Akapot

Loading...
Thumbnail Image
Preferred name
Tantrapiwat, Akapot
Alternative Name
Tantrapiwat, A.
Main Affiliation
Email
akapot.ta@kmitl.ac.th

Settings

Now showing 1 - 3 of 3
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Fin Coil Dent Detection Using Deep Learning
    (2025-01-01)
    Tantrapiwat, Akapot
    ;
    Pinsopon, Unnat
    This work introduced the object detection using deep learning in order to detect and locate dents on fin coils. It was aimed at using the AI as a tool to detect fin coil dents and restore them in the fin coil manufacturing and assembly processes. Not only were the images of dents used to train object detection models, two different types of distinctive marks were added for the purpose of positioning calibration in the system. Three scalable models of the state-of-art EfficientDat D0, D1 and D2 were used and compared for their accuracies and performances. All models were trained successfully with the custom dataset. It took only 30 epochs to achieve a functionable performance. The dent detection accuracies which were considered from the True Positive, obtained from the D0, D1, and D2 models were 55%, 66% and 75 % respectively. The three models can identify additional marks with 100% accuracy. In all models, there was no False Negative detection in all object classes showing good potential of using the models in the real applications.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    A RUBBER TREE ORCHARD MAPPING METHOD VIA IMAGE PROCESSING
    (2022-08-01)
    Kunghun, Worawut
    ;
    Tantrapiwat, Akapot
    This research was carried out in order to evaluate the performance of a computer visual mapping method using permanent targets mounted on the tree trucks as the distinctive marks to the environment. Two targets per tree trunk were used to create sufficient target perception from a distance. The computer vision uses the known distance between these two targets to determine the location of the camera using pin-hole camera principle. The system was designed based on configurations of the rubber tree orchard which is one of the main industrial crops in South East Asia. A set of experiment was carried out on both laboratory and real plantation site. With different parameters and setup, the mapping system was able to achieve the RMS maximum error 43.06 mm in laboratory control environment and 114.57 mm in actual site. This magnitude of error was considered acceptable in low accuracy autonomous operation in automatic agricultural tasks such as watering, fertilization and harvest. Several aspects regarding parameters in the mapping method setup and the outcome were discussed and compared.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Multi-Objective Optimization of Lightweight Inboard Bearing Design for High-Speed Railway Axle
    (2024-06-03)
    Nwe, T.
    ;
    Tantrapiwat, A.
    ;
    Pimsarn, M.
    This research delves into the intricate balance between reducing axle weight and maintaining structural integrity in high-speed rail transportation. Focusing on the critical factor of weight reduction in high-speed axle design, the study employs finite element simulations and standard calculations to systematically explore inboard and outboard bearing wheelsets. Particularly noteworthy is the examination of inboard bearing axles, revealing advantages in mass reduction, deflection, and stress mitigation, with an 8% lower weight than outboard bearing axles. Utilizing multi-objective optimization, the research achieves a remarkable 4% reduction in mass and an associated 4% decrease in stress, resulting in a 12% mass reduction compared to traditional axles. The study also enhances fatigue resistance, demonstrated through radial fatigue reverse factor (FRF) analysis. With a detailed methodology involving ABAQUS modeling, Python scripting, and optimization using the Pointer algorithm in Isight, this research adeptly navigates the trade-off, significantly contributing to the advancement of railway transportation systems.