Scholarlink

In this paper, the authors suggest and compare models for industrial oven Time-to-Failure (TTF) prediction within a critical 60-min timeframe using sensor data. They compare traditional methods such as LSTM, GRU + Attention, and XGBoost with a new hybrid approach: CNN-Autoencoder + XGBoost (CNN-AE + XGBoost). Experimental outcomes, in terms of RMSE, MAE, and R2, confirm the performance superiority of the proposed system. For the complete dataset, R2 for the hybrid model was 0.89, well ahead of LSTM (0.27), GRU + Attention (0.47), and XGBoost (0.83). Importantly, for the focused TTF ≤ 60 min frame, it also had a low Mean Absolute Error (MAE) of 6.57. These results present the CNN-AE + XGBoost model as an effective predictive maintenance tool for curbing production downtime within the food processing sector.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Time to Failure Prediction for Industrial Ovens Using Machine Learning and Deep Learning

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Nguyen Dinh Thuan,
  • Nguyen Xuan Truong

摘要

In this paper, the authors suggest and compare models for industrial oven Time-to-Failure (TTF) prediction within a critical 60-min timeframe using sensor data. They compare traditional methods such as LSTM, GRU + Attention, and XGBoost with a new hybrid approach: CNN-Autoencoder + XGBoost (CNN-AE + XGBoost). Experimental outcomes, in terms of RMSE, MAE, and R2, confirm the performance superiority of the proposed system. For the complete dataset, R2 for the hybrid model was 0.89, well ahead of LSTM (0.27), GRU + Attention (0.47), and XGBoost (0.83). Importantly, for the focused TTF ≤ 60 min frame, it also had a low Mean Absolute Error (MAE) of 6.57. These results present the CNN-AE + XGBoost model as an effective predictive maintenance tool for curbing production downtime within the food processing sector.