WORKSHOP: AI and Data‑Driven Predictive Manufacturing in Polymer Extrusion

Workshop

AI and Data-Driven Predictive Manufacturing in Polymer Extrusion

May 5, 7 & 8, 2026
All workshop days are from 11:00 AM to 1:00 PM ET.
Online

Injection Molds: Challenges and Opportunities in Conventional and Emerging Technologies

Summary

This workshop introduces participants to the emerging field of predictive manufacturing of polymers with a focus on machine learning techniques applied to extrusion. Predictive manufacturing employs data-driven approaches to understand and predict material defects and potential anomalies in the processing operations. The course will cover foundational concepts in machine learning and extrusion, emphasizing the integration of these disciplines. Participants will learn how to apply various machine learning models, including regression, classification, and neural networks, to solve real-world problems in polymer manufacturing.

The workshop will address data collection, feature selection, model training, and evaluation, specifically tailored to the unique challenges of manufacturing datasets. Hands-on sessions will guide attendees through the process of building and deploying models using open-source tools and libraries. The course aims to equip researchers, engineers, and data scientists with the skills needed to leverage machine learning in the manufacturing of polymers and the optimization of existing ones. By the end of the course, participants will have a solid understanding of how machine learning can drive manufacturing innovation for polymer engineering, contributing to advancements in areas such as manufacturing automation and defect prediction of polymer production.

Agenda

(Click each session to expand)

May 5, 2026

Duration: 2.0 Hours

Outline

Basics of Polymer Extrusion
Python fundamentals; variables and data types, arithmetic operators, sets, dictionaries, lists, tuples, stacks, queues, for/while loops, functions, classes, inheritance, variable scope

May 7, 2026

Duration: 2.0 Hours

Outline

Introduction ML workflows: basic dataset inspection, feature/column understanding, missing-value checking, imputation, KNN, Linear Regression
Exploratory data analysis: data preparation, feature engineering, and feature selection (lag adjustment, correlation plots, missing data imputation

May 8, 2026

Duration: 2.0 Hours

Outline

Building predictive ML models for extrusion: model taining pipelines, evaluation metrics, basics of neural networks
Explainable AI and industrial deployment: analyzing model predictions, explaining the "black box" nature of models, engineering use case

If you can't attend one or several sessions live, or if you want to review some concepts, the recordings will be available after each session.

Registration Information

SPE Premium Member	$540
SPE Members	$600
Nonmembers	$800

Not an SPE member? Join today and attend this workshop at a discounted rate!

Workshop Packs

Strengthen your team’s skills and take advantage of group savings with an SPE Workshop Pack for AI and Data-Driven Predictive Manufacturing in Polymer Extrusion. Go here for Workshop Pack information and registration.

3 Sessions

Level: Intermediate

Total Hours: 6 Hours

Streaming access on desktop and mobile browsers

Instructor

Andres Urbina, Processing / Tooling Specialist, Carcoustics International GmbH

Ganesh Balasubramanian
Chair, Department of Mechanical and Industrial Engineering
University of New Haven

(Click for more information)

Ganesh Balasubramanian is the chair of the Department of Mechanical and Industrial Engineering and assumes the Lambrakis Professorship at the University of New Haven. He earned his BME in Mechanical Engineering (2007) from Jadavpur University, India, and his PhD in Engineering Mechanics (2011) from Virginia Tech. He is a recipient of an NSF CAREER award and his research in advanced materials and predictive manufacturing has been supported by the NSF, DOD, DOE, industry and state agencies.

Questions? Contact:

For questions, contact Iván D. López.

Who Should Attend?

This workshop is designed for professionals who work at the intersection of polymer processing, data, and advanced manufacturing and want to leverage AI for measurable performance improvements. It is especially valuable for:

Process and Manufacturing Engineers working in polymer extrusion who want to predict defects and improve process stability
Polymer, Materials, and R&D Engineers interested in data‑driven optimization of extrusion processes and formulations
Automation, Digital Manufacturing, and Industry 4.0 Teams implementing smart manufacturing initiatives
Data Scientists and Analysts looking to apply machine learning to real manufacturing datasets
Quality, Reliability, and Continuous Improvement Engineers focused on defect reduction and anomaly detection
Graduate Students and Researchers (MSc, PhD) working in polymer processing, manufacturing science, or applied AI
Technical Managers and Engineering Leaders evaluating AI‑based tools for competitive advantage in extrusion operations

Why Should You Attend?

Are you collecting large amounts of process data but not fully using it to prevent defects or optimize performance?

Do extrusion issues still rely on reactive troubleshooting instead of predictive insight?

Are you interested in applying AI and machine learning—but unsure where to start or how to adapt these tools to manufacturing data?

If these challenges sound familiar, this workshop was designed for you.

This course bridges polymer extrusion fundamentals and modern machine learning, showing how data‑driven approaches can move manufacturing from reactive problem‑solving to predictive control.

Everyday Problems You’ll Address

Why do defects appear even when all process settings seem “correct”?

Learn how hidden patterns in data reveal early signs of anomalies.

How can I predict quality issues before scrap is produced?

Shift from detection to prediction using regression and classification models.

Why are standard AI examples hard to apply to manufacturing data?

Understand how to work with noisy, incomplete, and time‑dependent extrusion datasets.

How do I choose the right process signals and features for modeling?

Learn feature engineering techniques tailored to extrusion.

How can I move beyond black‑box models and trust AI predictions?

Apply explainable AI methods to understand model behavior.

How do I integrate ML models into real engineering and production decisions?

What You’ll Learn

By the end of the workshop, you will be able to:

Understand the fundamentals of polymer extrusion from a data and modeling perspective
Use Python basics relevant to engineering workflows (data types, structures, loops, functions, and classes)
Build complete introductory ML workflows, including data inspection, preprocessing, and missing‑value handling
Perform exploratory data analysis (EDA) and feature engineering tailored to extrusion processes
Develop predictive models using techniques such as regression, KNN, and basic neural networks
Evaluate model performance using appropriate metrics for manufacturing problems
Apply explainable AI techniques to interpret predictions and support engineering decisions
Understand how AI models can be deployed for defect prediction, anomaly detection, and process optimization

Hands‑on sessions using open‑source tools guide you through building and evaluating models step by step.

Why This Course Matters

Polymer extrusion is increasingly data‑rich—but data alone does not create value. Competitive advantage comes from turning data into predictions and decisions.

This workshop matters because it:

Moves extrusion operations toward predictive manufacturing, not reactive firefighting
Connects polymer engineering knowledge with machine learning techniques that actually work in production environments
Helps organizations reduce scrap, unplanned downtime, and variability through early anomaly detection
Enables engineers and researchers to confidently adopt AI tools aligned with real manufacturing constraints
Builds a foundation for automation, digital twins, and smart manufacturing in polymer processing

If you are ready to move from intuition to insight—and from data collection to prediction—this workshop provides the knowledge and practical skills to make AI a real engineering tool in polymer extrusion.