Failure time prognosis in manufacturing process using multi-dislocated time series convolutional neural network
| Autor: | Liping Zhao, Yiyong Yao, Bohao Li |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
0209 industrial biotechnology
020901 industrial engineering & automation Series (mathematics) Manufacturing process Computer science Mechanical Engineering Face (geometry) 020208 electrical & electronic engineering 0202 electrical engineering electronic engineering information engineering 02 engineering and technology Convolutional neural network Industrial and Manufacturing Engineering Reliability engineering |
| Zdroj: | Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering. 235:832-840 |
| ISSN: | 2041-3009 0954-4089 |
| Popis: | Failure time prognosis in manufacturing process plays a crucial role in guaranteeing manufacturing safety and reducing maintenance loss. However, most current prognosis methods face great difficulty when handling massive data collected from manufacturing process. Convolutional neural network (CNN) provides an effective way to extract features with massive data. Due to the difference between images and multisensory signals, CNN is not suitable for machining process. Inspired by the idea of CNN, a novel prognosis framework is proposed based on the characteristics of multisensory signals, which is called multi-dislocated time series convolutional neural network (MDTSCNN). The proposed MDTSCNN is composed of multi-dislocate layer, convolutional layer, pooling layer and fully connected layer. By adding a multi-dislocate layer, this model can learn the relationship between different signals and different intervals in periodic multisensory signals. The effectiveness of proposed method is validated by a milling process. Compared to other prognosis method, the proposed MDTSCNN shows enhanced performances in prediction accuracy. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|