.png){kind=icon}
Return
Multi-axial vibration fatigue optimization strategy based on the artificial intelligence algorithm
.png){kind=icon}
PRE
AI
DOI：10.1016/j.engappai.2026.114084.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
To reduce the computational cost in the multi-criteria optimization process based on multi-axial vibration fatigue life and improve the fairness of multi-criteria decision-making, this paper proposes a multi-axial vibration fatigue optimization strategy based on artificial intelligence. This strategy combines a hybrid surrogate model using Random Forest (RF) and Radial Basis Function Neural Network (RBFNN), the Non-dominated Sorting Genetic Algorithm II (NSGA-II), and a Modified Preference Selection Index (MPSI). The multiaxial vibration fatigue formula is derived for calculating the fatigue life of structures. The RF-RBFNN hybrid surrogate model is used to fit the relationship between variables and responses. The NSGA-II is employed to mine the Approximation set from the hybrid surrogate model, and the Modified Preference Selection Index method is used to determine the best compromise solution. The research results indicate that, while satisfying all constraint indicators, the weight reduction rate of the vehicle frame is 4.9%, and the prediction accuracy of the fatigue life surrogate model is 97.015%. The main contribution of this paper is to extend the artificial intelligence algorithm to the field of multi-axis vibration fatigue optimization and apply it to the solution process of the fatigue life of the tractor frame.
Keywords:
Multi-axial vibration fatigue
Artificial intelligence
Surrogate model
NSGA-II
Fatigue life optimization
Journal
IF:
8
Papers:
5.8K
Citations:
3.5W
Organization
Cited Papers
Reliability-based buckling optimization with an accelerated Kriging metamodel for filament-wound variable angle tow composite cylinders.png)
COMPOSITE STRUCTURES
OAAI
COMPOSITE STRUCTURESIF7.1
OAAIShareSaveShareSaveShareSaveShareSaveShareSaveCrushing analysis and multiobjective crashworthiness optimization of honeycomb-filled single and bitubular polygonal tubesMATERIALS & DESIGN
MATERIALS & DESIGNIF7.9
PREAI
ShareSave
View more