A Review on Scattering Wavelet Networks for Fault Detection, Structural Monitoring, and Material Classification in Machineries
Abstrak
Scattering Wavelet Networks (SWNs) have emerged as a very strong and mathematically sound competitor to conventional feature extraction and deep learning techniques. It is designed for signal and image processing; their scope has expanded to other domains in mechanical engineering where accurate and dependable interpretation of intricate data is critical. This review discusses the application of Scattering Wavelet Transforms (SWT) and Wavelet Scattering Networks (WSNs) in mechanical systems, particularly their application in fault detection, non-destructive testing, structural health monitoring, and material classification. Through the utilization of the multiscale, multi-resolution properties of wavelet transforms and the stability of scattering networks, researchers have made significant improvements in the classification accuracy and model interpretability. This provides an overview of important methodologies, performance comparison, and hybridization of SWNs with other machine learning models in various high-impact studies. The results validate the promise of SWNs as a revolutionary tool in the development of mechanical diagnostics reliability and intelligence.
Penulis (5)
Dhrishya Shetty
K. K
Nirupama G N
S. P
Keerthana B. Chigateri
Akses Cepat
PDF tidak tersedia langsung
Cek di sumber asli →- Tahun Terbit
- 2025
- Bahasa
- en
- Sumber Database
- Semantic Scholar
- DOI
- 10.1109/ICICV64824.2025.11085469
- Akses
- Open Access ✓