Curvature prediction of long‐period fibre grating based on random forest regression
Abstract This study proposes a long‐period fibre grating (LPFG) curvature estimation method based on random forest regression (RFR) to address the shortcomings of the existing curvature evaluation method, namely, polynomial fitting; these shortcomings cause difficulty in achieving adequate model reg...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-10-01
|
| Series: | IET Optoelectronics |
| Online Access: | https://doi.org/10.1049/ote2.12078 |
| _version_ | 1828143802290798592 |
|---|---|
| author | Xingliu Hu Haifei Si Quanyi Ye Yan Zhang |
| author_facet | Xingliu Hu Haifei Si Quanyi Ye Yan Zhang |
| author_sort | Xingliu Hu |
| collection | DOAJ |
| description | Abstract This study proposes a long‐period fibre grating (LPFG) curvature estimation method based on random forest regression (RFR) to address the shortcomings of the existing curvature evaluation method, namely, polynomial fitting; these shortcomings cause difficulty in achieving adequate model regularity and application universality. The resonant wavelength and resonant peak amplitude of the LPFG are used as input variables in this method to develop an RFR model for curvature estimation, allowing for accurate curvature prediction of the sample. The results show that the RFR‐based LPFG curvature prediction model can better characterise the input–output regression relationship than back‐propagation neural networks. The average R2 value of the RFR model is 0.9826, and the actual measured curvature value is highly correlated with the model predicted curvature value. Compared to that exhibited by back‐propagation neural networks, the RFR model exhibits higher accuracy for curvature estimation, with average values of 0.1314 and 0.1173 for root mean square and mean absolute errors, respectively. This method can provide a more comprehensive theoretical basis for the application of robot learning in the curvature measurement of LPFG and has practical value. |
| first_indexed | 2024-04-11T20:04:33Z |
| format | Article |
| id | doaj.art-500fd61e1c5f4a5b8eaa8f8e227201b0 |
| institution | Directory Open Access Journal |
| issn | 1751-8768 1751-8776 |
| language | English |
| last_indexed | 2024-04-11T20:04:33Z |
| publishDate | 2022-10-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Optoelectronics |
| spelling | doaj.art-500fd61e1c5f4a5b8eaa8f8e227201b02022-12-22T04:05:22ZengWileyIET Optoelectronics1751-87681751-87762022-10-0116522523310.1049/ote2.12078Curvature prediction of long‐period fibre grating based on random forest regressionXingliu Hu0Haifei Si1Quanyi Ye2Yan Zhang3School of Intelligence Science and Control Engineering Jinling Institute of Technology Nanjing ChinaSchool of Intelligence Science and Control Engineering Jinling Institute of Technology Nanjing ChinaSchool of Intelligence Science and Control Engineering Jinling Institute of Technology Nanjing ChinaSchool of Intelligence Science and Control Engineering Jinling Institute of Technology Nanjing ChinaAbstract This study proposes a long‐period fibre grating (LPFG) curvature estimation method based on random forest regression (RFR) to address the shortcomings of the existing curvature evaluation method, namely, polynomial fitting; these shortcomings cause difficulty in achieving adequate model regularity and application universality. The resonant wavelength and resonant peak amplitude of the LPFG are used as input variables in this method to develop an RFR model for curvature estimation, allowing for accurate curvature prediction of the sample. The results show that the RFR‐based LPFG curvature prediction model can better characterise the input–output regression relationship than back‐propagation neural networks. The average R2 value of the RFR model is 0.9826, and the actual measured curvature value is highly correlated with the model predicted curvature value. Compared to that exhibited by back‐propagation neural networks, the RFR model exhibits higher accuracy for curvature estimation, with average values of 0.1314 and 0.1173 for root mean square and mean absolute errors, respectively. This method can provide a more comprehensive theoretical basis for the application of robot learning in the curvature measurement of LPFG and has practical value.https://doi.org/10.1049/ote2.12078 |
| spellingShingle | Xingliu Hu Haifei Si Quanyi Ye Yan Zhang Curvature prediction of long‐period fibre grating based on random forest regression IET Optoelectronics |
| title | Curvature prediction of long‐period fibre grating based on random forest regression |
| title_full | Curvature prediction of long‐period fibre grating based on random forest regression |
| title_fullStr | Curvature prediction of long‐period fibre grating based on random forest regression |
| title_full_unstemmed | Curvature prediction of long‐period fibre grating based on random forest regression |
| title_short | Curvature prediction of long‐period fibre grating based on random forest regression |
| title_sort | curvature prediction of long period fibre grating based on random forest regression |
| url | https://doi.org/10.1049/ote2.12078 |
| work_keys_str_mv | AT xingliuhu curvaturepredictionoflongperiodfibregratingbasedonrandomforestregression AT haifeisi curvaturepredictionoflongperiodfibregratingbasedonrandomforestregression AT quanyiye curvaturepredictionoflongperiodfibregratingbasedonrandomforestregression AT yanzhang curvaturepredictionoflongperiodfibregratingbasedonrandomforestregression |