Deep Learning for Structural Health Monitoring

• Bridge the knowledge gap between AI and structural/mechanical engineering

• Teach deep learning architectures tailored to SHM datasets

• Foster innovation in safe, automated, and scalable monitoring tools

• Enable participants to prototype real-world solutions for infrastructure safety

• Promote AI integration in regulatory, public safety, and industrial maintenance practices

📅 Day 1: Deep Learning Foundations for Structural Materials

Topics Covered

• Fundamentals of Artificial Intelligence and Deep Learning

• Applications of Deep Learning in Structural and Building Materials

• Model Training, Testing, and Validation Workflows

• Dataset Preparation, Processing, and Visualization Techniques

• Hands-on Training: Deep Learning Models for Structural Monitoring Data

• Frameworks and Libraries: Python, PyTorch, Keras, TensorFlow

Tools & Platforms

• Google Colab

• Python Programming Environment

Capstone Project

Convolutional Neural Networks (CNNs):
Detection and classification of structural cracks using image datasets.

📅 Day 2: Time Series Modeling with LSTM in Structural Applications

Topics Covered

• Introduction to Long Short-Term Memory (LSTM) Networks

• LSTM Architecture and Use Cases in Structural Engineering

• End-to-End Workflow: Training, Testing, and Validating LSTM Models

• Time Series Dataset Preparation and Visualization

• Practical Implementation on Real-World Structural Monitoring Data

• Frameworks and Libraries: Python, PyTorch, Keras, TensorFlow

Tools & Platforms

• Google Colab

• Python Programming Environment

Capstone Project

LSTM for Structural Dynamics:
Time-series prediction and vibration analysis using LSTM networks.

📅 Day 3: Generative AI & IoT Integration for Smart Infrastructure

Topics Covered

• Introduction to Generative AI: Concepts and Use Cases

• Overview of Internet of Things (IoT) in Smart Monitoring Systems

• Generative AI Model Development for Sensor Nodes and IoT Devices

• Training, Testing, and Validation of Generative AI on Time Series Data

• Dataset Handling and Visualization

• Frameworks and Libraries: Python, PyTorch, Keras, TensorFlow

Tools & Platforms

• Google Colab

• Hugging Face Transformers

• Python Programming Environment

Capstone Project

Generative AI for Edge Deployment:
Deploying generative AI models on IoT sensor nodes for predictive infrastructure monitoring.

• Understand key deep learning models applicable to SHM

• Analyze sensor and image data using AI for crack, stress, and defect detection

• Build predictive tools to estimate deterioration and structural failure

• Integrate SHM with IoT and real-time monitoring systems

• Earn a certification to validate your AI-engineering expertise

• Civil, mechanical, aerospace, and materials engineers

• AI/ML developers interested in engineering applications

• Researchers in smart infrastructure, IoT, and NDE (non-destructive evaluation)

• Urban safety and infrastructure monitoring teams

• PhD/MS students in engineering or data science