The proposed framework consists of four modules: high-fidelity flight dynamics simulation, FMEA-driven fault injection, multi-fidelity residual feature extraction, and large language model-enhanced interpretable report generation. The high-fidelity simulation module uses the JSBSim 6-DoF flight dynamics engine to generate 23-channel engine health monitoring data via semi-empirical sensor synthesis equations. The FMEA-driven fault injection module models the physical causal propagation of 19 engine fault types using a three-layer fault injection engine. The multi-fidelity residual computation framework comprises paired-mirror residuals and GRU surrogate prediction residuals, which achieve a 96.2% Macro-F1 on the 20-class task. The LLM diagnostic report engine enhanced with FMEA knowledge fuses classification results, residual evidence, and domain causal knowledge to generate interpretable natural language reports. The results demonstrate the effectiveness of the proposed framework in improving fault diagnosis accuracy and inference speed, with implications for real-time engine health monitoring and predictive maintenance.
Intelligent Fault Diagnosis for General Aviation Aircraft via Multi-Fidelity Digital Twin and FMEA Knowledge Enhancement
A novel framework for fault diagnosis in general aviation aircraft achieves 96.2% Macro-F1 using multi-fidelity digital twins and FMEA-driven fault injection.
External source stays available while the OJO article and comment thread stay local.
More in Artificial Intelligence & Machine Learning
view topicA new multimodal ML framework combines ECG and EHR features to classify LVEF, outperforming baselines and maintaining performance under temporal validation.
A systematic study of weight matrix singular value spectra during transformer pretraining reveals three phenomena that fundamentally change how we understand transformer training.
A novel framework for adaptive and reproducible medical image processing addresses the limitations of current medical imaging research by introducing adaptability and reproducibility.
A new methodology combines hardware and software techniques to reduce computational and memory requirements for multimodal foundation models, with implications for production systems and research.
Comments load interactively on the live page.