Exponential Degradation Model Based Remaining Life Prediction for Tools of Milling Machine

Cutting tools of milling machines are prone to failure, and it’s essential to predict their remaining useful life to ensure cost-effective maintenance in the manufacturing industry. Recent studies have shown that deep learning techniques can effectively predict the remaining useful life. However, training a deep learning model on a small dataset can be challenging. Moreover, generating a sufficient training dataset that includes failure samples is even more complex. Therefore, this paper proposes an exponential degradation-based technique for predicting the remaining life of cutting tools due to a small dataset. The proposed method has five main steps: data processing, feature extraction, feature selection, and feature fusion to construct health indicators. Finally, using these health indicators, an exponential degradation model can estimate the remaining life. A case study of the proposed approach is demonstrated on a recently published cutting tools dataset. The experimental results show that the exponential model does not require large-size data to predict remaining life.