ZW’s AI Workshop Outline
This workshop focuses on the fundamentals and practical applications of Artificial Intelligence (AI) and Machine Learning (ML) in the advanced materials and specialty chemicals industries.
Day 1: Foundations & Core Processes
08:30–09:00 | Welcome & Introduction
• Trainer and participant introductions
• Course objectives and agenda overview
09:00–12:00 | Session 1: Foundations of AI/ML (Part 1)
• Role of AI/ML in R&D and manufacturing
• Overview of Supervised, Semi-supervised, Unsupervised, and Reinforcement Learning
• AI/ML Applications in prediction and optimization
10:00–10:15 | Break
10:15–12:30 | Session 1: Foundations of AI/ML (Part 2)
• Introduction to Deep Neural Networks, advanced AI models, and key algorithms
• Brief Introduction to Generative AI and Large Language Models (LLMs)
12:30–13:30 | Lunch
13:30–15:00 | Session 2: The AI Model Development Process (Part 1)
• Step 1: Define business problems with measurable goals
• Step 2: Collect high-quality historical data
• Step 3: Preprocess and structure data using feature engineering
• Step 4: Select the appropriate AI/ML models
15:00–15:15 | Break
15:15–17:30 | Session 2: The AI Model Development Process (Part 2)
• Step 5: Train and validate AI models (Deep Neural Networks)
• Step 6: Test and verify AI results via experimental/production trials
• Step 7: Deploy models in operations
• Step 8: Manage model updates and lifecycle
• Case Study
Day 2: Real-World Applications
08:30–10:30 | Session 3: Industry Challenges & Opportunities
R&D and Innovation:
• New materials and chemical discovery for end-customer applications
• Optimization of material properties for specific requirements
• New product development for emerging market opportunities
(Integrating new material compositions with manufacturing processes)
Manufacturing:
• Reduce energy consumption and overall costs
• Improve yield and throughput through root-cause identification
• Implement online quality control systems
• Predictive maintenance for equipment, machines, and furnaces
• Enable dynamic production planning and inventory management
10:30–10:45 | Break
10:45–12:00 | Session 4: Case Studies (Part 1)
• New material discovery (R&D)
• Optimization of material properties (R&D)
• Energy consumption reduction (Manufacturing)
12:00–13:00 | Lunch
13:00–15:00 | Session 4: Case Studies (Part 2)
• Throughput improvement (Manufacturing)
• Online quality control (Manufacturing)
• Predictive maintenance for equipment and furnaces
• Dynamic production planning
15:00–15:15 | Break
15:15–16:45 | Session 5: Team Exercise – Defining an AI Use Case
• Define a hypothetical problem and identify the required data
• Select appropriate AI/ML models for the use case
• Present a brief plan to the class
16:45–17:00 | Break
17:00–17:30 | Wrap-Up & Feedback
• Recap of key takeaways
• Open Q&A session
• Feedback survey and discussion of next steps