Researchers have developed a new dual-domain fused long short-term memory (DDF-LSTM) model to improve the accuracy and efficiency of time-dependent reliability analysis for engineering systems. This model uniquely integrates time-independent variables into the initial hidden states and uses a fully connected layer to combine LSTM outputs with these variables. An enhanced loss function focuses on the model's sensitivity to minimum responses, leading to more precise failure probability estimations. The DDF-LSTM model effectively captures complex dependencies among variables, stochastic processes, and the temporal behavior of limit state functions, enabling rapid Monte Carlo simulations for reliability assessment. AI
IMPACT This research introduces a novel deep learning architecture for improved reliability analysis in engineering, potentially leading to more robust and efficient system designs.
RANK_REASON Academic paper introducing a novel model architecture. [lever_c_demoted from research: ic=1 ai=1.0]
- alphaXiv
- arXiv
- CatalyzeX
- DagsHub
- DDF-LSTM
- Gotit.pub
- Hugging Face
- IArxiv
- long short-term memory
- Monte Carlo method
- ScienceCast
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
