A multi-axis variable amplitude fatigue life prediction method based on dynamic hysteresis image
Through the multi-axis amplitude fatigue life prediction method based on dynamic hysteresis image, the fatigue life prediction is performed using the convolutional neural network model, and the problem of insufficient complexity and accuracy of fatigue life prediction under multi-axis amplitude load in the prior art is solved, and simple and efficient fatigue life prediction is achieved.
Patent Information
- Application Number
- CN202311128266.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-09-04
- Publication Date
- 2025-03-25
- Estimated Expiration
- 2043-09-04
AI Technical Summary
The prior art fatigue life prediction under multi-axis amplitude load has complexity and lacks a widely accepted multi-axis cyclic counting method, resulting in cumbersome prediction process and insufficient accuracy.
The multi-axis amplitude fatigue life prediction method based on dynamic hysteresis image is adopted. By collecting multi-axis fatigue experimental data, dynamic hysteresis image is produced, and the fatigue life prediction is performed using a convolutional neural network model with a global pooling layer.
Accurate fatigue life prediction under multi-axis amplitude load is realized, the prediction process is simplified, and complex model fixed parameters and multi-axis cycle counting processes are not required, and has good generalization ability and operation simplicity.