An Intelligent Health Monitoring Model Based on Fuzzy Deep Neural Network.

Area of Science:

• Engineering
• Artificial Intelligence
• Materials Science

Background:

• Intelligent health detection models are crucial for self-care limitations, particularly for the elderly.
• Neural networks show promise in structural health monitoring but have limitations with insufficient training data.

Purpose of the Study:

• To develop an advanced structural health monitoring method using a hybrid intelligent algorithm.
• To enhance the accuracy of damage localization and assessment in composite structures.

Main Methods:

• A comprehensive review of intelligent algorithms for structural health monitoring.
• Development of a novel neural network training algorithm integrating genetic algorithms and fuzzy theory.
• Utilizing the finite element method to construct a genetic fuzzy Radial Basis Function (RBF) neural network for damage detection.

Main Results:

• The proposed finite element method effectively localizes and assesses delamination damage in composite beams.
• Achieved a 20% improvement in localization accuracy compared to traditional algorithms.
• Demonstrated a 10% enhancement in damage assessment performance.

Conclusions:

• The hybrid genetic fuzzy RBF neural network offers a robust solution for structural health monitoring.
• The finite element method effectively addresses the challenge of limited experimental data for neural network training.
• This approach significantly advances the capabilities of intelligent health detection systems for structural integrity.