Ultra-High-Cycle Fatigue Life Prediction of Metallic Materials Based on Machine Learning

The fatigue life evaluation of metallic materials plays an important role in ensuring the safety and long service life of metal structures. To further improve the accuracy and efficiency of the ultra-high-cycle fatigue life prediction of metallic materials, a new prediction method using machine learning was proposed. The training database contained the ultra-high-cycle fatigue life of different metallic materials obtained from fatigue tests, and two fatigue life prediction models were constructed based on the gradient boosting (GB) and random forest (RF) algorithms. The mean square error and the coefficient of determination were applied to evaluate the performance of the two models, and their advantages and application scenarios were also discussed. The ultra-high-cycle fatigue life of GCr15 bearing steel was predicted by the constructed models. It was found that only one datapoint of the GB model exceeded the triple error band, and the RF model had higher stability. The network model coefficient of determination and mean square error for the GB and RF models were 0.78, 0.79 and 0.69, 3.79, respectively. Both models could predict the ultra-high-cycle fatigue life of metallic materials quickly and effectively.

Automated summary

The evaluation of fatigue life in metallic materials is crucial for ensuring the safety and durability of metal structures. A new prediction method using machine learning was proposed to improve the accuracy and efficiency of ultra-high-cycle fatigue life prediction in metallic materials. Two prediction models were constructed based on the gradient boosting and random forest algorithms, using a training database containing fatigue life data from various metallic materials. The performance of the models was evaluated using mean square error and coefficient of determination, and their advantages and application scenarios were discussed. The constructed models were used to predict the ultra-high-cycle fatigue life of GCr15 bearing steel, with the GB model showing only one data point exceeding the triple error band and the RF model demonstrating higher stability. The coefficient of determination and mean square error for the GB and RF models were 0.78, 0.79 and 0.69, 3.79, respectively. Both models proved to be efficient and effective in quickly predicting the ultra-high-cycle fatigue life of metallic materials.