Injection Molding Process Modelling: Statistics, CAE, and AI Applications

✍ Scribed by Tien-Chien Jen, Edwell Tafara Mharakurwa, Steven Otieno Otieno, Fredrick Madaraka Mwema, Job Maveke Wambua

• Publisher: CRC Press
• Year: 2024
• Tongue: English
• Leaves: 131
• Edition: 1
• Category: Library

✦ Synopsis

Injection Molding Process Modelling presents the application of CAE, statistics and AI in defect identification, control, and optimization of injection molding process for quality production. It showcases CAE in determining the optimal placement of injection points, designing cooling channels, and ensuring that the mold will produce parts with the desired specifications. The book illustrates the capability of the CAE tools to simulate molten plastic flow within a mold during the injection molding process.

Explaining how the use of CAE, statistical tools and AI enhances efficiency, accuracy, and collaboration, the book explores the contributions to injection molding in product design and visualization; prototyping and testing; mold design; and analysis and simulation. It emphasizes the integration of statistical tools for optimized efficiency and waste reduction, including statistical process control (SPC), Design of Experiments (DOE), Regression Analysis, Capability Indices, Interaction effects, and many more. The book also illustrates the predictive modelling of typical injection molded product defects using intelligent algorithms.

The book will interest industry professionals and engineers working in manufacturing, production, automation, and quality control.

✦ Table of Contents

Cover
Half Title
Title Page
Copyright Page
Dedication
Table of Contents
About the Authors
Foreword
Preface
Chapter 1: Injection Molding for Plastic Processing
1.1 Plastic Processing Methods
1.2 Injection Molding
1.3 Injection Molded Product Defects
1.3.1 Short Shots and Sink Marks
1.3.2 Shrinkage and Warpage
1.4 Strategies to Molded Product Defects Reduction
1.5 Conclusion
References
Chapter 2: Computer Aided Modelling for Plastic Injection Molding
2.1 Introduction
2.2 CAE Modelling of a Packaging Bottle Cap
2.2.1 Product Design
2.2.2 Mold Design
2.2.3 Injection Molding Governing Equations
2.2.3.1 Filling Phase
2.2.3.2 Packing Phase
2.2.3.3 Cooling Phase
2.2.3.4 Warpage Phase
2.2.3.5 Solution Method
2.2.3.6 Boundary Conditions
2.2.3.7 Model Assumptions
2.2.4 Finite Element Model Development
2.2.5 Mesh Convergence Test
2.2.6 Finite Element Model Verification
2.2.6.1 Numerical Density Results
2.2.6.2 Analytical Density Results
2.2.6.3 Density Comparison
2.2.7 Mold Design Validation
2.2.8 Process Parameter Settings
2.2.9 Numerical Data Validation
2.3 Conclusion
References
Chapter 3: Statistical Modelling of Plastic Injection Molding Defects
3.1 Introduction
3.2 Response Surface Designs
3.3 Taguchi Array Designs
3.4 Factorial Designs
3.5 Statistical Modelling of a Packaging Bottle Cap
3.5.1 Design of Experiment
3.5.2 CAE Results
3.5.3 Mains Effects
3.5.3.1 Warpage
3.5.3.2 Shrinkage
3.5.3.3 Short Shot
3.5.3.4 Sink Marks
3.5.3.5 Effect Sizes
3.5.4 Interaction Effects
3.5.4.1 Warpage
3.5.4.2 Shrinkage
3.5.4.3 Short Shot
3.5.4.4 Sink Mark
3.5.5 Effects on Molding Defect Index
3.6 Conclusion
References
Chapter 4: Predictive Modelling of Injection Molding Defects
4.1 Introduction
4.2 Injection Molding Defects Modelling
4.3 Fuzzy Logic for Injection Molding
4.4 Defects Prediction Based on Fuzzy Logic and Pattern Search
4.4.1 Study Design
4.4.2 Process Parameter Screening
4.4.3 Taguchi Design of Experiment
4.4.4 Fuzzification
4.4.5 Rule Base Generation
4.4.6 Defuzification
4.4.7 Fuzzy Inference System Structure
4.4.8 Fuzzy Logic Model Plots
4.4.9 Model Tuning and Validation
4.5 Conclusion
References
Chapter 5: State-of-the Art of Artificial Intelligence and Prospectives in Modelling of Plastic Injection Molding
5.1 Introduction
5.2 Current Advances in the Application of AI in Injection Molding and Industry 4.0
5.3 Prospects of CAE Modelling
5.4 Prospects in Statistical Modelling
5.5 Prospects in AI Modelling
5.6 Conclusion
References
Index