Research on health monitoring of concrete structure based on G-S-G

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 9, 2025

An improved concrete structure health monitoring method based on G-S-G is proposed, which fully combines an optimized Gray-Level Co-occurrence Matrix (GLCM) with Self-Organizing Map (SOM) neural network to achieve accurate and real-time monitoring. First of all, in order obtain a dynamic image the crack damage region interest (ROI) clear contrast obvious target, acquisition system optimization are used process damaged image. Moreover, realize location damage, identification research GLCM-SOM effectively eliminates interference honeycomb pothole damage. In indicators for status structure, characteristics probability distribution gray level co-occurrence matrix combined extract range index (PRI). On basis extracting index, verify reliability sensitive feature starting from two dimensions texture data expansion, through reverse model, accurately locating was selected. It follows that final indicators: entropy (ENT) PRI can be structural because their strong characterization ability sensitivity characteristics. This shows helpful high precision intelligent modern

Language: Английский

---

A multi-task optimization algorithm via reinforcement learning for multimodal multi-objective optimization

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: 283, P. 127862 - 127862

Published: April 30, 2025

---

Variational graph autoencoder-driven balancing strategy for multimodal multi-objective optimization

Information Sciences, Journal Year: 2025, Volume and Issue: unknown, P. 122116 - 122116

Published: March 1, 2025

Language: Английский

---

Multi-objective cooperation search algorithm based on decomposition for complex engineering optimization problems

Applied Soft Computing, Journal Year: 2024, Volume and Issue: 167, P. 112442 - 112442

Published: Nov. 9, 2024

Language: Английский

---