Mathematical Modeling of Learnable Discrete Wavelet Transform for Adaptive Feature Extraction in Noisy Non-Stationary Signals
Mathematics · 26.04.2026 · 14 (9) · 1457
DOI: 10.3390/math14091457 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 26.04.2026. Verfasst von Jiaxian Zhu und 7 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
The mathematical characterization of non-stationary signals remains a significant challenge, particularly when impulsive components are obscured by high-dimensional noise and structural coupling. This paper proposes an application-driven mathematical methodology for a learnable discrete wavelet transform (LDWT) that combines classical multi-resolution analysis with task-optimized data-driven adaptivity. Rather than introducing entirely new foundational theory, our approach strategically relaxes constraints from orthogonal wavelet theory within the non-perfect reconstruction filter bank framework, enabling controlled spectral decomposition optimized for supervised fault diagnosis. We introduce a specialized regularization term based on the half-band property to ensure spectral complementarity and minimize cross-band correlation, while a Jacobian-based stabilization approach is formulated to ensure the convergence of filter coefficients during optimization. The proposed algorithmic architecture, LDBRFnet, features a dual-branch encoder system designed to capture the mathematical synergy between sub-band-level global statistics and time-domain local morphology. This dual-view representation effectively mitigates feature leakage and overconfidence in classification. Theoretical analysis and numerical experiments demonstrate that the learned filters satisfy the frequency-shift property and maintain robust spectral partitioning even under low signal-to-noise ratios. Validation on complex vibration datasets confirms that the framework achieves superior diagnostic accuracy (over 95.5%) and computational efficiency, reducing model parameters by 96.7% compared to state-of-the-art baselines. This work provides a generalizable mathematical approach for adaptive signal decomposition and robust pattern recognition in interdisciplinary applications.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zhu, J., Zhang, C., Shi, Z., Chen, H., Lin, Z., Bai, W., Zhang, H., & Zhou, T. (2026). Mathematical Modeling of Learnable Discrete Wavelet Transform for Adaptive Feature Extraction in Noisy Non-Stationary Signals. Mathematics, 14(9), 1457. https://doi.org/10.3390/math14091457
Vancouver
Zhu J, Zhang C, Shi Z, Chen H, Lin Z, Bai W, et al. Mathematical Modeling of Learnable Discrete Wavelet Transform for Adaptive Feature Extraction in Noisy Non-Stationary Signals. Mathematics. 2026;14(9):1457. doi:10.3390/math14091457
BibTeX
@article{Zhu2026,
author = {Zhu, Jiaxian and Zhang, Chuanbin and Shi, Zhaoyin and Chen, Hang and Lin, Zhizhe and Bai, Weihua and Zhang, Huibing and Zhou, Teng},
title = {Mathematical Modeling of Learnable Discrete Wavelet Transform for Adaptive Feature Extraction in Noisy Non-Stationary Signals},
journal = {Mathematics},
year = {2026},
volume = {14},
number = {9},
pages = {1457},
doi = {10.3390/math14091457}
}
EUVIMED