KMITL

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

Browse

Settings

Author: search.filters.author.Huang, YuHas files: No

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Optimizing Product Quality Prediction in Smart Manufacturing Through Parameter Transfer Learning: A Case Study in Hard Disk Drive Manufacturing
    (2025-04-01)
    Kaitwanidvilai, Somyot
    ;
    Sittisombut, Chaiwat
    ;
    Huang, Yu
    ;
    Bom, Sthitie
    In recent years, the semiconductor industry has embraced advanced artificial intelligence (AI) techniques to facilitate intelligent manufacturing throughout their organizations, with particular emphasis on virtual metrology (VM) systems. Nonetheless, the practical application of data-driven virtual metrology for product quality inspection encounters notable hurdles, such as annotating inspections in highly dynamic industrial environments. This leads to complexities and significant expenses in data acquisition and VM model training. To address the challenges, we delved into transfer learning (TL). TL offers a valuable avenue for knowledge sharing and scaling AI models across various processes and factories. At the same time, research on transfer learning in VM systems remains limited. We propose a novel parameter transfer learning (PTL) architecture for VM systems and examine its application in industrial process automation. We implemented cross-factory and cross-recipe transfer learning to enhance VM performance and offer practical advice on adapting TL to meet individual needs and use cases. By leveraging extensive data from Seagate wafer factories, known for their large-scale and high-dimensional nature, we achieved significant PTL performance improvements across multiple performance metrics, with the true positive rate (TPR) increasing by 29% and false positive rate (FPR) decreasing by 43% in the cross-factory study. In contrast, in the cross-recipe study, TPR increased by 27.3% and FPR decreased by 6.5%. With our proposed PTL architecture and its performance achievements, insufficient data from the new manufacturing sites, new production lines and new products are addressed with shorter VM model training time and smaller computational power with strong final quality prediction confidence.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Improvement of pavement design and management for more frequent flooding caused by climate change
    (2015-04-01)
    Wang, Yuhong
    ;
    Huang, Yu
    ;
    Rattanachot, Wit
    ;
    Lau, K. K.
    ;
    Suwansawas, Suchatvee
    Climatological records show a trend of the increasing occurrence of extreme weathers caused by global climate change. One form of extreme weathers is heavy rainfall which, combined with rising sea levels, made highways in some subtropical regions susceptible to flooding. Flooding in these regions causes noticeable damages to flexible highway pavements. However, little research has been conducted to quantify such damages and develop possible mitigation measures. This study developed a method to incorporate flood risk into the structural analysis of flexible pavements, examined the effects of flooding on pavement materials and structures through laboratory tests and design simulations, and recommended better pavement design and management strategies. Flexible pavement is found to be significantly affected by flooding. Future climate change and the resultant increase of flooding frequency pose a serious challenge to the reliability of flexible highway pavements. To mitigate the detrimental effects of flooding, pavement thickness and drainage system need to be adequately designed and post-flood traffic control may need to be imposed.