본문 바로가기
  • Home

AI-based Prediction of Electrical Faults in Control Boards

  • Journal of Software Assessment and Valuation
  • Abbr : JSAV
  • 2025, 21(2), pp.71~77
  • Publisher : Korea Software Assessment and Valuation Society
  • Research Area : Engineering > Computer Science
  • Received : May 22, 2025
  • Accepted : June 20, 2025
  • Published : June 30, 2025

Lee Bong Kyu 1

1제주대학교

Accredited

ABSTRACT

Smart factories operate various self-moving smart equipment for efficient logistics. Electrical failures occurring in the control boards that control these smart equipment can cause malfunctions or fires. Carbonization is a useful indicator for identifying electrical failures occurring in the control boards. In this study, we propose an artificial intelligence-based carbonization inspection system that predicts whether electrical failures occur in internal control boards that control smart equipment. The proposed system is an ensemble model of MMLSTM type consisting of LSTM, CNN, and MLP. Using LSTM and CNN, different types of data are combined into a single feature vector. The combined feature vector is fed into the MLP to predict the carbonization degree of the control board. The usefulness of the proposed system is proven through experiments.

Citation status

* References for papers published after 2023 are currently being built.