Smerpitak, Krit

Loading...
Thumbnail Image
Preferred name
Smerpitak, Krit
Main Affiliation
Email
krit.sm@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,
    Design of PLC-based system for linearity output voltage of AC–DC converter
    (2022-04-01)
    Pongswatd, Sawai
    ;
    Smerpitak, Krit
    ;
    Asadi, Farzin
    ;
    Thepmanee, Teerawat
    This paper presents the PLC-Based system for controlling the SCR power module which is AC–DC converter proposes to linearity output voltage with trigger signal. The technique converted the trigger signal by arccosine function and analog module in the PLC. Converted signal from PLC system is fed to SCR power module instant the traditional signal. Proposed of this paper describes the PLC hardware configuration, compute/math and trigonometric functions with Studio 5000 software. In addition, the interfacing, parameters configuration, and monitoring are considered for testing. The technique with PLC-based, devices configuration and experimental results have been presented will be useful for electric power supply in the industry with more and more demand to apply the PLC system to develop the traditional industry to semi or automatic control in the industry.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Improving Accuracy in Image-Recognition Systems with Techniques for Handling Similar-Looking Items in Inventory Management
    (2025-01-01)
    Smerpitak, Krit
    ;
    Kummool, Sart
    ;
    Asadi, Farzin
    ;
    Ar-Karachaiphong, Chitsanuwit
    ;
    Sopha, Watcharapon
    Inventory management is crucial for businesses dealing with many visually similar items. This paper presents the development of an automated board game detection system utilizing computer vision and deep learning to enhance the accuracy and efficiency of tracking visually similar inventory. The dataset used to train the model was collected using a Pi Camera Module 3 mounted on a Raspberry Pi 5, ensuring consistency in captured images. To improve the model's performance, images were annotated using CVAT, and dataset augmentation was applied using Augmentations, incorporating transformations such as flipping, brightness adjustment, blurring, and noise addition. These augmentations allowed the model to learn and differentiate board games under varying environmental conditions accurately. The selected model was YOLOv8m, chosen for its balance between accuracy and computational efficiency. The model was trained for 20 epochs using a learning rate of 0.0005, a batch size of 12, and augmentation techniques such as Mosaic and MixUp. Additionally, overfitting prevention techniques including early stopping, dropout, and weight decay were applied. After training, the model was converted into the ONNX format to optimize it for deployment on embedded devices and then uploaded to the Raspberry Pi 5 for realworld testing. The system was evaluated on 10 visually similar or small-sized board games, with 10 tests per game, totaling 100 trials. The results showed that the model successfully classified all board games without a single error. Moreover, these findings demonstrate that the proposed system effectively identify board games with high accuracy while maintaining real-Time processing capability. The use of data augmentation and model optimization significantly improved object classification performance, making it a promising approach for inventory management in board game cafes and similar environments.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    EXPERIMENTAL STUDY ON ENERGY CONSUMPTION OF TEMPERATURE CONTROL BY USING ON-OFF INTELLIGENT FUNCTION
    (2023-05-01)
    Pongswatd, Sawai
    ;
    Sopha, Watcharapon
    ;
    Asadi, Farzin
    ;
    Smerpitak, Krit
    ;
    Thepmanee, Teerawat
    In order to save electrical energy for on-off temperature control, a useful concept of on-off intelligent function to execute in a programmable logic controller (PLC) is presented. An implementation of PLC-based control system based on electric heating is also described as a case study to demonstrate the performance of the proposed function. IEC 61131-3-based ladder diagrams were created by using Studio 5000 software to run in the PLC modeled CompactLogix L30ER. Compared with the traditional on-off control action, the proposed on-off intelligent function can minimize energy consumption of a heater used in the implemented temperature control by 4.57%-6.65%.