Robust Regularized Random Vector Functional Link Network and Its Industrial Application
Production quality indices of complex industrial processes are usually hard to be measured in real time, which leads to unavailability of closed-loop operational optimization and control. Therefore, data-driven modeling techniques have been extensively employed to estimate production quality indices...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2017-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8004428/ |
| _version_ | 1818853668388077568 |
|---|---|
| author | Wei Dai Qixin Chen Fei Chu Xiaoping Ma Tianyou Chai |
| author_facet | Wei Dai Qixin Chen Fei Chu Xiaoping Ma Tianyou Chai |
| author_sort | Wei Dai |
| collection | DOAJ |
| description | Production quality indices of complex industrial processes are usually hard to be measured in real time, which leads to unavailability of closed-loop operational optimization and control. Therefore, data-driven modeling techniques have been extensively employed to estimate production quality indices online. However, the conventional data-driven modeling methods often fail to achieve good performance because of interference from outliers. To solve the above-mentioned problem, this paper proposes an improved random vector functional link network (RVFLN) using a novel training method, which adopts a ridge regularized model with weighted factor for each training sample to evaluate the output weights. The robustness of the model has been achieved by employing a nonparametric kernel density estimation method to assign the weighted factors according to the training sample. To ensure the quality and computational load of the network in online applications, various online learning versions are presented according to the scope of data sampling. The improved RVFLN called robust regularized RVFLN has been validated using UCI, Statlib standard data sets, and an industrial grinding operation data. Results show that our proposed modeling technique perform favorably, and demonstrate its good potential for real world applications. |
| first_indexed | 2024-12-19T07:40:28Z |
| format | Article |
| id | doaj.art-9e746560fde64e81aa342b4036beef39 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T07:40:28Z |
| publishDate | 2017-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-9e746560fde64e81aa342b4036beef392022-12-21T20:30:27ZengIEEEIEEE Access2169-35362017-01-015161621617210.1109/ACCESS.2017.27374598004428Robust Regularized Random Vector Functional Link Network and Its Industrial ApplicationWei Dai0https://orcid.org/0000-0003-3057-7225Qixin Chen1Fei Chu2https://orcid.org/0000-0002-0891-6748Xiaoping Ma3Tianyou Chai4School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou, ChinaState Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, ChinaProduction quality indices of complex industrial processes are usually hard to be measured in real time, which leads to unavailability of closed-loop operational optimization and control. Therefore, data-driven modeling techniques have been extensively employed to estimate production quality indices online. However, the conventional data-driven modeling methods often fail to achieve good performance because of interference from outliers. To solve the above-mentioned problem, this paper proposes an improved random vector functional link network (RVFLN) using a novel training method, which adopts a ridge regularized model with weighted factor for each training sample to evaluate the output weights. The robustness of the model has been achieved by employing a nonparametric kernel density estimation method to assign the weighted factors according to the training sample. To ensure the quality and computational load of the network in online applications, various online learning versions are presented according to the scope of data sampling. The improved RVFLN called robust regularized RVFLN has been validated using UCI, Statlib standard data sets, and an industrial grinding operation data. Results show that our proposed modeling technique perform favorably, and demonstrate its good potential for real world applications.https://ieeexplore.ieee.org/document/8004428/Complex industrial processproduction quality indexrandom vector functional link network (RVFLN)nonparametric kernel density estimationrobustnessregularization |
| spellingShingle | Wei Dai Qixin Chen Fei Chu Xiaoping Ma Tianyou Chai Robust Regularized Random Vector Functional Link Network and Its Industrial Application IEEE Access Complex industrial process production quality index random vector functional link network (RVFLN) nonparametric kernel density estimation robustness regularization |
| title | Robust Regularized Random Vector Functional Link Network and Its Industrial Application |
| title_full | Robust Regularized Random Vector Functional Link Network and Its Industrial Application |
| title_fullStr | Robust Regularized Random Vector Functional Link Network and Its Industrial Application |
| title_full_unstemmed | Robust Regularized Random Vector Functional Link Network and Its Industrial Application |
| title_short | Robust Regularized Random Vector Functional Link Network and Its Industrial Application |
| title_sort | robust regularized random vector functional link network and its industrial application |
| topic | Complex industrial process production quality index random vector functional link network (RVFLN) nonparametric kernel density estimation robustness regularization |
| url | https://ieeexplore.ieee.org/document/8004428/ |
| work_keys_str_mv | AT weidai robustregularizedrandomvectorfunctionallinknetworkanditsindustrialapplication AT qixinchen robustregularizedrandomvectorfunctionallinknetworkanditsindustrialapplication AT feichu robustregularizedrandomvectorfunctionallinknetworkanditsindustrialapplication AT xiaopingma robustregularizedrandomvectorfunctionallinknetworkanditsindustrialapplication AT tianyouchai robustregularizedrandomvectorfunctionallinknetworkanditsindustrialapplication |