Integration of Functional Link Neural Networks into a Parameter Estimation Methodology
In the field of robust design, most estimation methods for output responses of input factors are based on the response surface methodology (RSM), which makes several assumptions regarding the input data. However, these assumptions may not consistently hold in real-world industrial problems. Recent s...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/19/9178 |
| _version_ | 1797516817447518208 |
|---|---|
| author | Tuan-Ho Le Mengyuan Tang Jun Hyuk Jang Hyeonae Jang Sangmun Shin |
| author_facet | Tuan-Ho Le Mengyuan Tang Jun Hyuk Jang Hyeonae Jang Sangmun Shin |
| author_sort | Tuan-Ho Le |
| collection | DOAJ |
| description | In the field of robust design, most estimation methods for output responses of input factors are based on the response surface methodology (RSM), which makes several assumptions regarding the input data. However, these assumptions may not consistently hold in real-world industrial problems. Recent studies using artificial neural networks (ANNs) indicate that input–output relationships can be effectively estimated without the assumptions mentioned above. The primary objective of this research is to generate a new, robust design dual-response estimation method based on ANNs. First, a second-order functional-link-NN-based robust design estimation approach has been proposed for the process mean and standard deviation (i.e., the dual-response model). Second, the optimal structure of the proposed network is defined based on the Bayesian information criterion. Finally, the estimated response functions of the proposed functional-link-NN-based estimation method are applied and compared with that obtained using the conventional least squares method (LSM)-based RSM. The numerical example results imply that the proposed functional-link-NN-based dual-response robust design estimation model can provide more effective optimal solutions than the LSM-based RSM, according to the expected quality loss criteria. |
| first_indexed | 2024-03-10T07:06:09Z |
| format | Article |
| id | doaj.art-dbcbc98b90b643c99d8ddb24cbb3f83f |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T07:06:09Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-dbcbc98b90b643c99d8ddb24cbb3f83f2023-11-22T15:49:12ZengMDPI AGApplied Sciences2076-34172021-10-011119917810.3390/app11199178Integration of Functional Link Neural Networks into a Parameter Estimation MethodologyTuan-Ho Le0Mengyuan Tang1Jun Hyuk Jang2Hyeonae Jang3Sangmun Shin4Department of Electrical Engineering, Faculty of Engineering and Technology, Quy Nhon University, Quy Nhon 591417, VietnamDepartment of Industrial & Management Systems Engineering, Dong-A University, Busan 49315, KoreaMaritime Safety and Environmental Research Division, Korea Research Institute of Ships & Ocean Engineering, Daejeon 34103, KoreaDepartment of Technology Management Engineering, Jeonju University, Jeonju 55069, KoreaDepartment of Industrial & Management Systems Engineering, Dong-A University, Busan 49315, KoreaIn the field of robust design, most estimation methods for output responses of input factors are based on the response surface methodology (RSM), which makes several assumptions regarding the input data. However, these assumptions may not consistently hold in real-world industrial problems. Recent studies using artificial neural networks (ANNs) indicate that input–output relationships can be effectively estimated without the assumptions mentioned above. The primary objective of this research is to generate a new, robust design dual-response estimation method based on ANNs. First, a second-order functional-link-NN-based robust design estimation approach has been proposed for the process mean and standard deviation (i.e., the dual-response model). Second, the optimal structure of the proposed network is defined based on the Bayesian information criterion. Finally, the estimated response functions of the proposed functional-link-NN-based estimation method are applied and compared with that obtained using the conventional least squares method (LSM)-based RSM. The numerical example results imply that the proposed functional-link-NN-based dual-response robust design estimation model can provide more effective optimal solutions than the LSM-based RSM, according to the expected quality loss criteria.https://www.mdpi.com/2076-3417/11/19/9178response surface methodologyestimationfunctional link neural network |
| spellingShingle | Tuan-Ho Le Mengyuan Tang Jun Hyuk Jang Hyeonae Jang Sangmun Shin Integration of Functional Link Neural Networks into a Parameter Estimation Methodology Applied Sciences response surface methodology estimation functional link neural network |
| title | Integration of Functional Link Neural Networks into a Parameter Estimation Methodology |
| title_full | Integration of Functional Link Neural Networks into a Parameter Estimation Methodology |
| title_fullStr | Integration of Functional Link Neural Networks into a Parameter Estimation Methodology |
| title_full_unstemmed | Integration of Functional Link Neural Networks into a Parameter Estimation Methodology |
| title_short | Integration of Functional Link Neural Networks into a Parameter Estimation Methodology |
| title_sort | integration of functional link neural networks into a parameter estimation methodology |
| topic | response surface methodology estimation functional link neural network |
| url | https://www.mdpi.com/2076-3417/11/19/9178 |
| work_keys_str_mv | AT tuanhole integrationoffunctionallinkneuralnetworksintoaparameterestimationmethodology AT mengyuantang integrationoffunctionallinkneuralnetworksintoaparameterestimationmethodology AT junhyukjang integrationoffunctionallinkneuralnetworksintoaparameterestimationmethodology AT hyeonaejang integrationoffunctionallinkneuralnetworksintoaparameterestimationmethodology AT sangmunshin integrationoffunctionallinkneuralnetworksintoaparameterestimationmethodology |