Project Details
Description
Real-time tool life inspections are becoming increasingly important in today's industrial automation and have the potential to significantly improve productivity and product quality and avoid unexpected damage. In this study, deep learning techniques are applied to the evaluation of the remaining useful life (RUL) of milling tools. First, Short Time Fourier Transformation (STFT) is applied to convert 3-axis vibration data into time-frequency images, which are input to a conventional Convolutional Neural Network (CNN) as the core of the tool condition monitoring system. In this study, a new loss function, i.e., conservative loss function, is proposed to make the model prediction compatible with industrial applications. The performance of the proposed loss function is compared with the conventional loss function MSE, and the results showed that this new loss function can help the tool condition monitoring system to maintain its accuracy and make the model tend to underestimate the RUL, avoiding industrial application problems.
Status | Finished |
---|---|
Effective start/end date | 1/08/21 → 31/07/22 |
UN Sustainable Development Goals
In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. This project contributes towards the following SDG(s):
Keywords
- Tool Condition Monitoring
- Remaining Useful Life
- ResNet
- Loss function
Fingerprint
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.