Trouble diagnosis of the grinding process by using acoustic emission signals
β Scribed by Jae-Seob Kwak; Ji-Bok Song
- Publisher
- Elsevier Science
- Year
- 2001
- Tongue
- English
- Weight
- 865 KB
- Volume
- 41
- Category
- Article
- ISSN
- 0890-6955
No coin nor oath required. For personal study only.
β¦ Synopsis
The focus of this study is the development of a credible diagnosis system for the grinding process. The acoustic emission signals generated during machining were analyzed to determine the relationship between grinding-related troubles and characteristics of changes in signals. Furthermore, a neural network, which has excellent ability in pattern classification, was applied to the diagnosis system. The neural network was optimized with a momentum coefficient (m), a learning rate (a), and a structure of the hidden layer in the iterative learning process. The success rates of trouble recognition were verified.
π SIMILAR VOLUMES
The systems for in-process quality assurance offer the possibility of estimating the workpiece quality during machining. Especially for finishing processes like grinding or turning of hardened steels, it is important to control the process continuously in order to avoid rejects and refinishing. This
Laboratory specimens with a smooth boundary (no notch) were fabricated from four dierent rock types (grain sizes from 0.1Β±10 mm) and were tested in three-point bending. The locations of acoustic emission that occurred around peak load were used to characterize the dimensions of the region of localiz