A Simulation-Data-Based Machine Learning Model for Predicting Basic Parameter Settings of the Plasticizing Process in Injection Molding
Problem
Finding optimal machine settings for the plasticizing process in injection molding normally requires time-consuming, expensive physical trials.
Why it matters
Trial-and-error machine setting wastes time and money in polymer processing.
What the AI did
A simulation-driven neural network, trained on pre-processed simulation datasets, predicts the back pressure and screw rotational speed needed for good melt quality from material, screw geometry, shot weight, and desired plasticizing time.
Results
Absolute mean error of 0.27% (standard deviation 0.37%) on unseen test data; validated in real-machine experiments with three materials
Impact
Could reduce trial-and-error machine setting in injection molding, demonstrated on a real machine with three materials.
Record
| Venue | Polymers |
|---|---|
| Published | 2021 |
| Work type | article |
| Authors | Matthias C. Schmid, Dominik Altmann, Georg Steinbichler |
| Citations | 18 (OpenAlex, at import time) |
| References | 15 |
| Model or method | Neural network (best among compared supervised machine learning algorithms) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3390/polym13162652 |
| Open access | gold |
| Keywords | injection molding, plasticizing process, machine learning, neural network, process parameters |
Importance rating
real but narrower advance
Reduces time-consuming, expensive trial-and-error machine setting in injection molding; real-machine validation with three materials, but narrow process-planning benefit, no stated scale.
More in Engineering & Materials
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Scaling deep learning for materials discovery | 2023 | 1,471 |
8
|
| 2 | Application of Machine Learning in Material Synthesis and Property Prediction | 2023 | 165 |
7
|
| 3 | Machine learning-guided discovery of ionic polymer electrolytes for lithium metal batteries | 2023 | 115 |
7
|
| 4 | Machine Learning for Structural Health Monitoring of Aerospace Structures: A Review | 2025 | 44 |
7
|
| 5 | Power System Transient Stability Assessment Based on Machine Learning Algorithms and Grid Topology | 2023 | 42 |
7
|