Related Experiment Video
Updated: Jun 30, 2025

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
Published on: January 5, 2024
Dynamic constitutive identification of concrete based on improved dung beetle algorithm to optimize long short-term
Ping Li1, Haonan Zhao2, Jiming Gu2
1School of Management Science and Engineering, Anhui University of Technology, Ma'anshan, 243032, China. 20150009@ahut.edu.cn.
This study introduces an Improved Dung Beetle Algorithm (IDBO) optimized Long Short-Term Memory (LSTM) network for accurate concrete dynamic principal identification. The IDBO-LSTM model effectively identifies concrete damage and predicts material behavior, demonstrating superior performance over existing methods.
Area of Science:
- Materials Science
- Civil Engineering
- Computational Mechanics
Background:
- Accurate identification of concrete dynamic properties is crucial for structural integrity.
- Existing methods for concrete damage identification face challenges with convergence accuracy and local optima.
- Understanding concrete's damage evolution and rheology is essential for reliable modeling.
Purpose of the Study:
- To develop a novel model for concrete dynamic principal identification with improved accuracy.
- To enhance the Dung Beetle Optimization Algorithm (DBO) for better performance in complex optimization tasks.
- To validate the proposed model's effectiveness in identifying concrete damage and predicting material behavior.
Main Methods:
- Utilized Split Hopkinson Pressure Bar (SHPB) tests to obtain concrete stress-strain curves and capture damage evolution.
- Developed an Improved Dung Beetle Algorithm (IDBO) by incorporating greedy lens imaging reverse learning, adaptive weighting factors, and PID control perturbation.
- Integrated the IDBO algorithm with a Long Short-Term Memory (LSTM) network to create the IDBO-LSTM model for dynamic homeostasis identification.
Main Results:
- The IDBO algorithm demonstrated superior optimization capabilities compared to DBO, Harris Hawk Optimization, Gray Wolf Optimization, and Fruit Fly Optimization algorithms.
- The IDBO-LSTM model successfully identified concrete material damage even without explicit damage consideration.
- Predictions from the IDBO-LSTM model closely matched experimental curves from SHPB tests when damage was considered.
Conclusions:
- The proposed IDBO-LSTM model offers a feasible and excellent approach for concrete dynamic principal identification.
- The enhanced IDBO algorithm overcomes limitations of the original DBO, leading to more accurate identification.
- This research provides a robust computational tool for analyzing concrete material behavior under dynamic loading conditions.
Related Concept Videos
Dynamic Modulus of Elasticity of Concrete
The sonic test is a common method to determine the dynamic modulus. In this test, a concrete beam, sized either 6 x 6 x 30 inches or 4 x 4 x 20 inches, is clamped at its center. Vibrations are initiated at one end of the beam by an electromagnetic exciter unit powered by...
Elasticity in Concrete
Creep in Concrete
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...

