Multi-Objective Optimization of Injection Parameters and Energy Consumption Based on ANN-Differential Evolution
Injection molding (IM) is one complex manufacturing process characterized by nonlinear behavior. Unlike classic linear modeling techniques like simple regression, many machine learning (ML) models have the ability to adjust to the nonlinear behaviors and interactions between input and output paramet...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/2/826 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589191368671232 |
|---|---|
| author | Devic Oktora Yu-Hung Ting Sukoyo |
| author_facet | Devic Oktora Yu-Hung Ting Sukoyo |
| author_sort | Devic Oktora |
| collection | DOAJ |
| description | Injection molding (IM) is one complex manufacturing process characterized by nonlinear behavior. Unlike classic linear modeling techniques like simple regression, many machine learning (ML) models have the ability to adjust to the nonlinear behaviors and interactions between input and output parameters. Artificial neural networks (ANNs) specifically have demonstrated exceptional performance in problems involving nonlinear modeling. This work will employ complete factorial design of experiments (DoE) to acquire a dataset which is both resilient and suitable for training, validation, and testing purposes. The predictive model demonstrated outstanding performance throughout the training, validation, and test sets. The aggregate R<sup>2</sup> values for the training, validation, and tests datasets were 97.58%, 93.76%, and 91.31%, respectively, demonstrating a strong ability to accurately foresee outcomes. Differential evolution (DE) successfully achieved a 2% decrease in weight and a notable 14% decrease in energy consumption. The results indicate that combining an ANN with DE is a viable approach for enhancing injection molding parameters, especially in scenarios with multiple objectives. |
| format | Article |
| id | doaj-art-726e230339fd43e9902a999b394fc1db |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-726e230339fd43e9902a999b394fc1db2025-01-24T13:20:58ZengMDPI AGApplied Sciences2076-34172025-01-0115282610.3390/app15020826Multi-Objective Optimization of Injection Parameters and Energy Consumption Based on ANN-Differential EvolutionDevic Oktora0Yu-Hung Ting1Sukoyo2Master Program in Industrial Engineering Department, Faculty of Industrial Technology, Bandung Institute of Technology, Jl. Ganesha 10, Bandung 40132, IndonesiaR&D Center for Smart Manufacturing, Chung Yuan Christian University, Taoyuan 32023, TaiwanFaculty of Industrial Technology, Industrial Engineering Department, Bandung Institute of Technology, Jl. Ganesha 10, Bandung 40132, IndonesiaInjection molding (IM) is one complex manufacturing process characterized by nonlinear behavior. Unlike classic linear modeling techniques like simple regression, many machine learning (ML) models have the ability to adjust to the nonlinear behaviors and interactions between input and output parameters. Artificial neural networks (ANNs) specifically have demonstrated exceptional performance in problems involving nonlinear modeling. This work will employ complete factorial design of experiments (DoE) to acquire a dataset which is both resilient and suitable for training, validation, and testing purposes. The predictive model demonstrated outstanding performance throughout the training, validation, and test sets. The aggregate R<sup>2</sup> values for the training, validation, and tests datasets were 97.58%, 93.76%, and 91.31%, respectively, demonstrating a strong ability to accurately foresee outcomes. Differential evolution (DE) successfully achieved a 2% decrease in weight and a notable 14% decrease in energy consumption. The results indicate that combining an ANN with DE is a viable approach for enhancing injection molding parameters, especially in scenarios with multiple objectives.https://www.mdpi.com/2076-3417/15/2/826injection moldingoptimizationartificial neural networksdifferential evolutionenergy consumption |
| spellingShingle | Devic Oktora Yu-Hung Ting Sukoyo Multi-Objective Optimization of Injection Parameters and Energy Consumption Based on ANN-Differential Evolution Applied Sciences injection molding optimization artificial neural networks differential evolution energy consumption |
| title | Multi-Objective Optimization of Injection Parameters and Energy Consumption Based on ANN-Differential Evolution |
| title_full | Multi-Objective Optimization of Injection Parameters and Energy Consumption Based on ANN-Differential Evolution |
| title_fullStr | Multi-Objective Optimization of Injection Parameters and Energy Consumption Based on ANN-Differential Evolution |
| title_full_unstemmed | Multi-Objective Optimization of Injection Parameters and Energy Consumption Based on ANN-Differential Evolution |
| title_short | Multi-Objective Optimization of Injection Parameters and Energy Consumption Based on ANN-Differential Evolution |
| title_sort | multi objective optimization of injection parameters and energy consumption based on ann differential evolution |
| topic | injection molding optimization artificial neural networks differential evolution energy consumption |
| url | https://www.mdpi.com/2076-3417/15/2/826 |
| work_keys_str_mv | AT devicoktora multiobjectiveoptimizationofinjectionparametersandenergyconsumptionbasedonanndifferentialevolution AT yuhungting multiobjectiveoptimizationofinjectionparametersandenergyconsumptionbasedonanndifferentialevolution AT sukoyo multiobjectiveoptimizationofinjectionparametersandenergyconsumptionbasedonanndifferentialevolution |