This workshop explores cutting-edge applications of artificial intelligence (AI), machine learning (ML), and transfer learning (TL) in optimizing injection molding processes to achieve superior part quality and uncover opportunities for further improvement. AI enables computer systems to simulate human intelligence and behavior. ML, a subset of AI, builds predictive models by learning from data—without relying on predefined mathematical formulations. TL extends the capabilities of ML by adapting pre-trained models to new but related problems, significantly reducing the need for extensive physical data and lowering the barriers to implementing AI/ML in manufacturing. Injection molding is one of the most important processes for mass-producing complex plastic components with excellent dimensional accuracy, surface quality, and repeatability. However, the nonlinear and intricate relationships between machine parameters and part quality present significant challenges. Integrating domain expertise with rapidly evolving AI/ML/TL technologies is essential for advancing the injection molding industry. This workshop provides a concise overview of AI, ML, and TL fundamentals, with a focus on their practical applications in process optimization and part quality improvement efficiently and effectively. Participants will gain insights into the benefits, limitations, and technical considerations of using AI/ML/TL to enhance their process efficiency and part quality.

Key Topics and Case Studies Include:

• Hierarchical control levels in injection molding: machine, process, and part quality, and their interdependencies
• Complex process dynamics of injection molding and the “black box” nature of AI/ML models
• Enhancing model accuracy and stability using computer simulations and robust data sampling
• Increasing transparency and trust in AI/ML through explainable AI (XAI) techniques and domain knowledge
• Process optimization using in-mold condition (IMC) data and its interpreted impact on part quality
• Leveraging transfer learning for multi-objective, model-based process parameter optimization
• Identifying new directions for quality improvement using IMC-XAI optimization
• Visualizing process perturbations and quality predictions with ML models and parallel coordinate plots

This workshop is designed for professionals in the plastics manufacturing industry who seek to apply Artificial Intelligence (AI), Machine Learning (ML), and Transfer Learning (TL) to optimize injection molding process parameters and enhance part quality. It will be particularly valuable for:

• Process, Manufacturing, and Tooling Engineers – responsible for setting up, running, and optimizing injection molding operations.
• Quality (QA/QC) Managers and Engineers – focused on improving part quality, reducing defects, and interpreting process data such as in-mold condition (IMC) data.
• R&D Engineers and Scientists – exploring advanced modeling and data-driven strategies to uncover new opportunities for process and product improvement.
• Senior Production and Operations Staff – including technicians, supervisors, and operations personnel dealing with the complex dynamics of injection molding.
• Technical Managers and Directors – such as plant managers or directors of innovation who need to understand the benefits, limitations, and implementation considerations of AI/ML in manufacturing.
• Data Scientists and ML Engineers – looking to apply their AI/ML expertise to injection molding systems, hierarchical control levels, and IMC data.
• Academics and Graduate Students – conducting research in polymer processing, smart manufacturing, or Industry 4.0 applications and seeking to connect theory with industrial practice.

Participants should have a basic understanding of injection molding processes. Prior experience with AI/ML is helpful but not required.

Are you working to optimize injection molding parameters but find that conventional trial-and-error or design of experiments (DOE) approaches are time-consuming and limited?
Do you struggle to link process variables to part quality due to the nonlinear and complex dynamics of the molding process?
Are you collecting in-mold condition (IMC) data but unsure how to extract actionable insights or connect it to product performance?
Do you want to explore AI-driven process optimization but lack the resources to generate large, high-quality datasets?
Are you looking for practical guidance on integrating AI, ML, and TL techniques into existing molding workflows without disrupting production?

If you face any of these challenges, this workshop is for you.

Key Questions You’ll Be Able to Answer:
How can AI and ML models be used to predict part quality and optimize process parameters in real time?
What role does transfer learning (TL) play in reducing data requirements and enabling faster implementation in manufacturing?
How can in-mold condition (IMC) data be leveraged to improve model accuracy and identify opportunities for quality enhancement?
What are the benefits and limitations of black-box vs. explainable AI (XAI) models in process control?
How can simulation data and domain knowledge be combined to increase model reliability and transparency?

What You’ll Learn:
The fundamentals of AI, ML, and TL and how they apply specifically to injection molding.
Techniques to optimize process parameters and enhance part quality through data-driven modeling.
How to use IMC data and simulation to improve prediction accuracy and reduce defects.
Practical strategies for implementing explainable AI (XAI) to build trust in AI-based decision-making.
How transfer learning enables model adaptation across machines, molds, and materials with minimal new data.
Case studies demonstrating how AI/ML tools accelerate troubleshooting, reduce cycle times, and improve product consistency.

Why This Workshop Matters:
As injection molding moves toward smart manufacturing and digital transformation, the ability to integrate AI-driven intelligence into process control is becoming a key competitive advantage. Traditional methods struggle to capture the full complexity of molding systems—especially as materials, geometries, and quality requirements become more demanding. This workshop provides a clear, practical roadmap for harnessing AI, ML, and TL to make injection molding processes more efficient, predictive, and adaptive. You’ll learn from real-world examples and leave equipped with actionable insights to begin implementing these technologies in your own environment.If you’re ready to move beyond intuition and toward data-driven precision in injection molding, this workshop is your next step.