Deep Transfer Learning Based on Sparse Autoencoder for Remaining Useful Life Prediction of Tool in Manufacturing

TLDR

Deep learning has proven effective for machine fault prediction, yet transferring a network trained on historical failure data to new objects remains largely unexplored. This study introduces a deep transfer learning network based on a sparse autoencoder for remaining useful life prediction. The method trains a sparse autoencoder on run‑to‑failure data, then transfers it to a new tool using weight transfer, hidden‑feature transfer, and weight‑update strategies to enable online RUL prediction. The transferred model predicts the new tool’s remaining useful life accurately without supervised training, and the shared learned features improve prediction performance.

Abstract

Deep learning with ability to feature learning and nonlinear function approximation has shown its effectiveness for machine fault prediction. While, how to transfer a deep network trained by historical failure data for prediction of a new object is rarely researched. In this paper, a deep transfer learning (DTL) network based on sparse autoencoder (SAE) is presented. In the DTL method, three transfer strategies, that is, weight transfer, transfer learning of hidden feature, and weight update, are used to transfer an SAE trained by historical failure data to a new object. By these strategies, prediction of the new object without supervised information for training is achieved. Moreover, the learned features by deep transfer network for the new object share joint and similar characteristic to that of historical failure data, which is beneficial to accurate prediction. Case study on remaining useful life (RUL) prediction of cutting tool is performed to validate effectiveness of the DTL method. An SAE network is first trained by run-to-failure data with RUL information of a cutting tool in an off-line process. The trained network is then transferred to a new tool under operation for on-line RUL prediction. The prediction result with high accuracy shows advantage of the DTL method for RUL prediction.