Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.13828 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916796198551552 |
|---|---|
| author | Bereketoglu, Abdullah Burkan |
| author_facet | Bereketoglu, Abdullah Burkan |
| contents | We propose a hybrid meta-learning framework for forecasting and anomaly detection in nonlinear dynamical systems characterized by nonstationary and stochastic behavior. The approach integrates a physics-inspired simulator that captures nonlinear growth-relaxation dynamics with random perturbations, representative of many complex physical, industrial, and cyber-physical systems. We use CNN-LSTM architectures for spatio-temporal feature extraction, Variational Autoencoders (VAE) for unsupervised anomaly scoring, and Isolation Forests for residual-based outlier detection in addition to a Dual-Stage Attention Recurrent Neural Network (DA-RNN) for one-step forecasting on top of the generated simulation data. To create composite anomaly forecasts, these models are combined using a meta-learner that combines forecasting outputs, reconstruction errors, and residual scores. The hybrid ensemble performs better than standalone models in anomaly localization, generalization, and robustness to nonlinear deviations, according to simulation-based experiments. The framework provides a broad, data-driven approach to early defect identification and predictive monitoring in nonlinear systems, which may be applied to a variety of scenarios where complete physical models might not be accessible. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_13828 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hybrid Meta-Learning Framework for Anomaly Forecasting in Nonlinear Dynamical Systems via Physics-Inspired Simulation and Deep Ensembles Bereketoglu, Abdullah Burkan Machine Learning Systems and Control Accelerator Physics We propose a hybrid meta-learning framework for forecasting and anomaly detection in nonlinear dynamical systems characterized by nonstationary and stochastic behavior. The approach integrates a physics-inspired simulator that captures nonlinear growth-relaxation dynamics with random perturbations, representative of many complex physical, industrial, and cyber-physical systems. We use CNN-LSTM architectures for spatio-temporal feature extraction, Variational Autoencoders (VAE) for unsupervised anomaly scoring, and Isolation Forests for residual-based outlier detection in addition to a Dual-Stage Attention Recurrent Neural Network (DA-RNN) for one-step forecasting on top of the generated simulation data. To create composite anomaly forecasts, these models are combined using a meta-learner that combines forecasting outputs, reconstruction errors, and residual scores. The hybrid ensemble performs better than standalone models in anomaly localization, generalization, and robustness to nonlinear deviations, according to simulation-based experiments. The framework provides a broad, data-driven approach to early defect identification and predictive monitoring in nonlinear systems, which may be applied to a variety of scenarios where complete physical models might not be accessible. |
| title | Hybrid Meta-Learning Framework for Anomaly Forecasting in Nonlinear Dynamical Systems via Physics-Inspired Simulation and Deep Ensembles |
| topic | Machine Learning Systems and Control Accelerator Physics |
| url | https://arxiv.org/abs/2506.13828 |