Evaluation of Machine Learning Models for Enhancing Sustainability in Additive Manufacturing
Additive manufacturing (AM) presents significant opportunities for advancing sustainability through optimized process control and material utilization. This research investigates the application of machine learning (ML) models to directly associate AM process parameters with sustainability metrics,...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Technologies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7080/13/6/228 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839652506445021184 |
|---|---|
| author | Waqar Shehbaz Qingjin Peng |
| author_facet | Waqar Shehbaz Qingjin Peng |
| author_sort | Waqar Shehbaz |
| collection | DOAJ |
| description | Additive manufacturing (AM) presents significant opportunities for advancing sustainability through optimized process control and material utilization. This research investigates the application of machine learning (ML) models to directly associate AM process parameters with sustainability metrics, which is often a challenge by experimental methods alone. Initially, experimental data are generated by systematically varying key AM parameters, layer height, infill density, infill pattern, build orientation, and number of shells. Subsequently, four ML models, Linear Regression, Decision Trees, Random Forest, and Gradient Boosting, are trained and evaluated. Hyperparameter tuning is conducted using the Limited-memory Broyden–Fletcher–Goldfarb–Shanno with Box constraints (L-BFGS-B) algorithm, which demonstrates the superior computational efficiency compared to traditional approaches such as grid and random search. Among the models, Random Forest yields the highest predictive accuracy and lowest mean squared error across all target sustainability indicators: energy consumption, part weight, scrap weight, and production time. The results confirm the efficacy of ML in predicting sustainability outcomes when supported by robust experimental data. This research offers a scalable and computationally efficient approach to enhancing sustainability in AM processes and contributes to data-driven decision-making in sustainable manufacturing. |
| format | Article |
| id | doaj-art-4bc3ececf4b849f19200715c88a5a63f |
| institution | Matheson Library |
| issn | 2227-7080 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Technologies |
| spelling | doaj-art-4bc3ececf4b849f19200715c88a5a63f2025-06-25T14:28:10ZengMDPI AGTechnologies2227-70802025-06-0113622810.3390/technologies13060228Evaluation of Machine Learning Models for Enhancing Sustainability in Additive ManufacturingWaqar Shehbaz0Qingjin Peng1Department of Mechanical Engineering, University of Manitoba, Winnipeg, MB R3T 2N2, CanadaDepartment of Mechanical Engineering, University of Manitoba, Winnipeg, MB R3T 2N2, CanadaAdditive manufacturing (AM) presents significant opportunities for advancing sustainability through optimized process control and material utilization. This research investigates the application of machine learning (ML) models to directly associate AM process parameters with sustainability metrics, which is often a challenge by experimental methods alone. Initially, experimental data are generated by systematically varying key AM parameters, layer height, infill density, infill pattern, build orientation, and number of shells. Subsequently, four ML models, Linear Regression, Decision Trees, Random Forest, and Gradient Boosting, are trained and evaluated. Hyperparameter tuning is conducted using the Limited-memory Broyden–Fletcher–Goldfarb–Shanno with Box constraints (L-BFGS-B) algorithm, which demonstrates the superior computational efficiency compared to traditional approaches such as grid and random search. Among the models, Random Forest yields the highest predictive accuracy and lowest mean squared error across all target sustainability indicators: energy consumption, part weight, scrap weight, and production time. The results confirm the efficacy of ML in predicting sustainability outcomes when supported by robust experimental data. This research offers a scalable and computationally efficient approach to enhancing sustainability in AM processes and contributes to data-driven decision-making in sustainable manufacturing.https://www.mdpi.com/2227-7080/13/6/228additive manufacturingsustainabilitymachine learningparameter optimizationhyperparameter optimization |
| spellingShingle | Waqar Shehbaz Qingjin Peng Evaluation of Machine Learning Models for Enhancing Sustainability in Additive Manufacturing Technologies additive manufacturing sustainability machine learning parameter optimization hyperparameter optimization |
| title | Evaluation of Machine Learning Models for Enhancing Sustainability in Additive Manufacturing |
| title_full | Evaluation of Machine Learning Models for Enhancing Sustainability in Additive Manufacturing |
| title_fullStr | Evaluation of Machine Learning Models for Enhancing Sustainability in Additive Manufacturing |
| title_full_unstemmed | Evaluation of Machine Learning Models for Enhancing Sustainability in Additive Manufacturing |
| title_short | Evaluation of Machine Learning Models for Enhancing Sustainability in Additive Manufacturing |
| title_sort | evaluation of machine learning models for enhancing sustainability in additive manufacturing |
| topic | additive manufacturing sustainability machine learning parameter optimization hyperparameter optimization |
| url | https://www.mdpi.com/2227-7080/13/6/228 |
| work_keys_str_mv | AT waqarshehbaz evaluationofmachinelearningmodelsforenhancingsustainabilityinadditivemanufacturing AT qingjinpeng evaluationofmachinelearningmodelsforenhancingsustainabilityinadditivemanufacturing |