A dual-modal data fusion-driven approach for fatigue life estimation of cracked structures

Abstract To address the limitations of low accuracy and poor reliability in traditional fatigue life estimation methods for metal structures with macroscopic fatigue cracks, a dual-modal data fusion approach integrating a finite element model and an LSTM (long short-term memory) network is proposed. First, a finite element model incorporating boundary conditions and cyclic loading is developed to simulate crack propagation. To enhance the model’s accuracy, an improved particle filtering algorithm is employed to optimize high-sensitivity parameters, ensuring that the simulated strain and vibration modal data closely match the measured values, achieving an overall fatigue life fidelity of 97.7% for the calibrated finite element model. Furthermore, an LSTM network is introduced to refine the estimation of strain and vibration data based on the optimized finite element model, achieving an estimation error below 2% in crack length estimation. Experimental validation using a fatigue testing platform demonstrates an estimation error below 2% for fatigue life, surpassing single-modal methods by 4.6%. The results confirm the proposed method’s effectiveness in addressing data incompleteness in traditional approaches while significantly improving estimation robustness and reliability.

Hali tarjima qilinmagan