Remaining Useful-Life Prediction of the Milling Cutting Tool Using Time-Frequency-Based Features and Deep Learning...

Area of Science:

• Manufacturing Engineering
• Artificial Intelligence
• Machine Learning

Background:

• Milling machines are vital in manufacturing due to their versatility.
• Cutting tool accuracy and surface finishing directly impact industrial productivity.
• Monitoring cutting tool life is essential to prevent downtime from tool wear.

Purpose of the Study:

• To accurately predict the remaining useful life (RUL) of milling cutters.
• To enhance machining accuracy and surface finishing by preventing unplanned downtime.
• To optimize the utilization of cutting tool life in milling operations.

Main Methods:

• Utilized the IEEE NUAA Ideahouse dataset for RUL estimation.
• Employed time-frequency domain (TFD) feature extraction techniques, including short-time Fourier-transform (STFT) and wavelet transforms (WT).
• Applied deep learning (DL) models such as Long Short-Term Memory (LSTM) variants, Convolutional Neural Networks (CNN), and hybrid CNN-LSTM models.

Main Results:

• Feature engineering quality is critical for accurate RUL prediction.
• TFD features combined with LSTM variants and hybrid models demonstrated strong performance.
• The proposed methods achieved improved prediction accuracy for milling cutting tool RUL.

Conclusions:

• Accurate RUL prediction is essential for maximizing cutting tool life and industrial productivity.
• TFD feature extraction coupled with advanced DL models offers a promising approach for milling tool RUL estimation.
• This research contributes to reducing machining downtime and improving overall manufacturing efficiency.