Related Experiment Video
Updated: Jan 29, 2026

Full-field Strain Measurements for Microstructurally Small Fatigue Crack Propagation Using Digital Image Correlation Method
Published on: January 16, 2019
Accelerating the Measurement of Fatigue Crack Growth with Incremental Information-Based Machine Learning Approach.
Cheng Wen1,2, Haipeng Lu1, Yiliang Wang1,3
1School of Mechanical Engineering, Guangdong Ocean University, Zhanjiang 524088, China.
This study introduces a machine learning interpolation-extrapolation strategy (MLIES) to accelerate fatigue testing. MLIES significantly improves crack growth prediction accuracy and reduces testing time and costs.
Area of Science:
- Materials Science
- Mechanical Engineering
- Computational Science
Background:
- Fatigue crack growth rate measurement using a-N curves is time-consuming and labor-intensive.
- Existing methods often require extensive experimental data, limiting efficiency.
Purpose of the Study:
- To develop a machine learning interpolation-extrapolation strategy (MLIES) to accelerate fatigue testing and enhance prediction accuracy.
- To reduce the time and cost associated with fatigue crack growth experiments.
Main Methods:
- Data transformation of a-N curves (from N to ΔN and a to Δa/ΔN) to enrich data volume.
- Training a single-layer neural network on early-stage data using exponential data expansion and augmentation.
- Validating the MLIES approach on aluminum and titanium alloy fatigue tests.
Main Results:
- MLIES reduced testing time/cost by 15-32% compared to traditional methods.
- Achieved over 30% higher prediction accuracy for a-N curves.
- The model learned crack growth rules directly from data without explicit analytical laws.
Conclusions:
- MLIES offers an efficient, data-driven method for accurate crack growth prediction.
- The strategy enhances experimental efficiency, making fatigue testing faster and more cost-effective.
- This approach is effective for various alloys and experimental conditions.
Related Concept Videos
Measuring Acceleration Due to Gravity
A simple pendulum can be described as a point mass and a string. Meanwhile, a physical pendulum is any object whose oscillations are similar to a simple pendulum, but cannot be modeled as a point mass on a string because its mass is distributed over a larger area. The behavior of a physical pendulum can be modeled using the principles of...
Fatigue
Accelerators
The effectiveness of calcium chloride can...
Machines
A free-body diagram of the...
Types of Non-structural Cracks in Concrete
Plastic shrinkage cracks typically form within hours after the concrete is poured. The concrete's surface dries faster than the bottom, creating tensile stress that the still-plastic concrete cannot withstand, leading to diagonal or randomly patterned cracks on the concrete surface.
Microbial Growth Measurement: Direct Methods

