Fatigue life prediction method for rubber material based on Extreme Learning Machine
2022-01-0296
03/29/2022
- Event
- Content
- Uniaxial fatigue tests of rubber dumbbell specimens under different mean and amplitude of strain were carried out. An Extreme Learning Machine (ELM) model optimized by Dragonfly Algorithm (DA) is proposed to predict the fatigue life of rubber based on measured rubber fatigue life data. Mean and amplitude of strain and measured rubber fatigue life were taken as input variables and output variables respectively in DA-ELM model. For comparison, genetic algorithm (GA) and particle swarm optimization (PSO) were used to optimize ELM parameters, and GA-ELM and PSO-ELM models were established. The comparison results show that DA-ELM model performs better in predicting the fatigue life of rubber with least dispersion. The coefficients of determination for the training set and test set are 99.47% and 99.12%, respectively. In addition, a life prediction model equivalent strain amplitude as damage parameter is introduced to further highlight the superiority of the DA-ELM model. The life distribution diagrams shows that DA-ELM model prediction results are within 2 times dispersion line, and equivalent strain amplitude life model prediction results are mostly within 4 times dispersion line. The former has higher prediction accuracy.
- Citation
- Lai, W., Wang, Y., and Zhen, R., "Fatigue life prediction method for rubber material based on Extreme Learning Machine," SAE Technical Paper 2022-01-0296, 2022, .