{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T15:05:33Z","timestamp":1785423933564,"version":"3.56.0"},"reference-count":28,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T00:00:00Z","timestamp":1783036800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Regional Fund of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62365009"],"award-info":[{"award-number":["62365009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"award":["62365009"],"award-info":[{"award-number":["62365009"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Fibre Bragg Grating (FBG) demodulation technology is central to structural health monitoring. However, spectral distortion and noise caused by complex environments, along with the challenge of balancing accuracy and real-time performance in existing deep learning algorithms, severely limit its application in large-scale dynamic sensing networks. To address this challenge, this paper proposes a hybrid learning framework named TimeMixer-LightGBM. The framework first employs a pure MLP-based TimeMixer model to efficiently extract multi-scale spectral sequence features from FBG reflection spectra, and then uses a LightGBM model (gradient boosted decision trees) to perform fast regression on these features for centre wavelength shift prediction. Experiments on synthetically distorted FBG spectra (including asymmetric shape variations and additive white noise) show that the method achieves picometre-level accuracy (RMSE = 2.128 pm) with an average processing time of only 0.08 ms per spectrum, representing a speedup of about 4.5 times over the latest deep learning models for FBG demodulation. It also exhibits excellent noise robustness, maintaining an average absolute error of 1.5 pm. Ablation experiments confirm the necessity and synergy of the hybrid architecture. The framework was further applied to demodulate double-peaked overlapping spectra, outperforming existing methods under mild, moderate and severe overlap conditions while keeping inference times in the sub-millisecond range. This study provides a novel and effective technical solution for real-time high-precision FBG demodulation, validates the effectiveness of pure MLP architectures in spectral analysis, and lays a theoretical foundation for deploying such demodulation on embedded edge devices, thereby achieving a favourable balance of accuracy, speed and scalability.<\/jats:p>","DOI":"10.3390\/s26134235","type":"journal-article","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T14:33:06Z","timestamp":1783089186000},"page":"4235","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Fast Demodulation Algorithm for Fibre Bragg Grating Based on the TimeMixer-LightGBM Hybrid Learning Framework"],"prefix":"10.3390","volume":"26","author":[{"given":"Hang","family":"Gao","sequence":"first","affiliation":[{"name":"School of Intelligent Systems Science and Engineering, Hubei Minzu University, Enshi 445000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4457-0086","authenticated-orcid":false,"given":"Yizhe","family":"Su","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Science and Engineering, Hubei Minzu University, Enshi 445000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Qian","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Science and Engineering, Hubei Minzu University, Enshi 445000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5497-6777","authenticated-orcid":false,"given":"Da","family":"Qiu","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Science and Engineering, Hubei Minzu University, Enshi 445000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Science and Engineering, Hubei Minzu University, Enshi 445000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tingting","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Science and Engineering, Hubei Minzu University, Enshi 445000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"101300","DOI":"10.1016\/j.rineng.2023.101300","article-title":"Structural condition assessment based strain-stress behaviour for railway welded rail joint using rosette fibre Bragg grating optical sensor","volume":"19","author":"Suhaimi","year":"2023","journal-title":"Results Eng."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Tian, Y., Zhang, Z., Wang, X., Li, W., and Xu, Y. (2025). Icing Monitoring of Wind Turbine Blade Based on Fiber Bragg Grating Sensors and Strain Ratio Index. Energies, 18.","DOI":"10.3390\/en18164295"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Ding, H., Guo, R., Xing, H., Chen, Y., He, J., Luo, J., Chen, M., Chen, Y., Tang, S., and Xu, F. (2025). Spatial\u2013Temporal Hotspot Management of Photovoltaic Modules Based on Fiber Bragg Grating Sensor Arrays. Sensors, 25.","DOI":"10.3390\/s25154879"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Chethana, K., Nandi, S., Prasad, A., and Asokan, S. (2025). Fiber Bragg Grating based optical sensor for pulse morphology. J. Opt.","DOI":"10.1007\/s12596-025-02895-1"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Baba, T., Saidin, N., Hasbullah, N.F., and Ahmad, I. (2025). Radiation tolerant fiber Bragg gratings: Review of FBG sensing. J. Opt.","DOI":"10.1007\/s12596-025-02861-x"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"24258","DOI":"10.3390\/s141224258","article-title":"Influence of fiber Bragg grating spectrum degradation on the performance of sensor interrogation algorithms","volume":"14","author":"Lamberti","year":"2014","journal-title":"Sensors"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Wu, J., Yu, M., Cao, Y., Jiang, S., Sun, S., and Wang, J. (2025). A 5 kW Near-Single-Mode Oscillating\u2013Amplifying Fiber Laser Employing a Broadband Output Coupler with Simultaneous Raman Suppression and Spectral Narrowing. Photonics, 12.","DOI":"10.3390\/photonics12080813"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Guo, X. (2020). Research on peak-detection algorithms of fiber Bragg grating demodulation. Proceedings of the International Conference on Telecommunications and Communication Engineering, Springer.","DOI":"10.1007\/978-981-16-5692-7_12"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"076005","DOI":"10.1088\/1402-4896\/addef5","article-title":"Intervention of machine learning and explainable artificial intelligence based polynomial transformation approach for improved measurement of oil-water emulsion using FBG sensor","volume":"100","author":"Dwivedi","year":"2025","journal-title":"Phys. Scr."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"22263","DOI":"10.1364\/OE.524549","article-title":"Wavelength detection of serial WDM ultra-short fiber Bragg grating sensor networks based on a CCD interrogator using deep belief networks and sparrow search algorithm","volume":"32","author":"Jiao","year":"2024","journal-title":"Opt. Express"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1007\/s44397-025-00014-0","article-title":"Developed machine learning algorithm for fiber Bragg grating sensor using Gaussian mixing method","volume":"1","author":"Kumar","year":"2025","journal-title":"Discov. Sens."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"20583","DOI":"10.1364\/OE.27.020583","article-title":"Wavelength detection of model-sharing fiber Bragg grating sensor networks using long short-term memory neural network","volume":"27","author":"Jiang","year":"2019","journal-title":"Opt. Express"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"e34214","DOI":"10.1002\/mop.34214","article-title":"Temperature prediction based on long short-term memory convolutional neural network Bragg grating sensing","volume":"66","author":"Shao","year":"2024","journal-title":"Microw. Opt. Technol. Lett."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"131505","DOI":"10.1016\/j.optcom.2025.131505","article-title":"Parallel processing of FBG spectral distortion recognition and temperature demodulation based on multi-task learning","volume":"578","author":"Tang","year":"2025","journal-title":"Opt. Commun."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"7095","DOI":"10.1364\/OE.550130","article-title":"Demodulation algorithm for temperature and pressure sensing in side-hole fiber Bragg gratings using a CNN-LSTM network","volume":"33","author":"Lai","year":"2025","journal-title":"Opt. Express"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"125385","DOI":"10.1016\/j.apenergy.2025.125385","article-title":"Enhanced strain assistance for SOC estimation of lithium-ion batteries using FBG sensors","volume":"383","author":"Sheng","year":"2025","journal-title":"Appl. Energy"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"110476","DOI":"10.1016\/j.optlastec.2023.110476","article-title":"Accurate and fast calibration for FBG demodulation based on deep learning and ensemble learning","volume":"172","author":"Sheng","year":"2024","journal-title":"Opt. Laser Technol."},{"key":"ref_18","unstructured":"Wang, L., Li, H., and Qiao, X. (2025). Fiber Bragg grating high-frequency seismic geophone based on bearing lever mechanism (in Chinese). Opt. Commun. Technol., 1\u201311. (In Chinese)."},{"key":"ref_19","unstructured":"Cao, H., Lyu, B., Li, C., and Wei, P. (2024). Development of contact detection for rotating blades based on Fiber Bragg Grating sensors (in Chinese). Aeronaut. Power, 39\u201342. (In Chinese)."},{"key":"ref_20","unstructured":"Zhang, Y., Zhang, Y., Lou, X., Sun, G., Li, H., Dong, M., Yu, M., and Zhu, L. (2025). Research status and prospect of fiber Bragg grating in aircraft structural load monitoring (in Chinese). J. Electron. Meas. Instrum., 1\u201316. (In Chinese)."},{"key":"ref_21","unstructured":"Wang, S., Wu, H., Shi, X., Hu, T., Luo, H., Ma, L., Zhang, J.Y., and Zhou, J. (2024). Timemixer: Decomposable multiscale mixing for time series forecasting. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2200","DOI":"10.1038\/s41598-025-85492-3","article-title":"Predicting EV battery state of health using long short term degradation feature extraction and FEA TimeMixer","volume":"15","author":"Tang","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"134060","DOI":"10.1016\/j.fuel.2024.134060","article-title":"Application of a composite parameter-driven TimeMixer model for Multi-Step prediction of NOx at the SCR Inlet of a 660 MW boiler","volume":"386","author":"Chen","year":"2025","journal-title":"Fuel"},{"key":"ref_24","first-page":"3146","article-title":"Lightgbm: A highly efficient gradient boosting decision tree","volume":"30","author":"Ke","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"5823","DOI":"10.1109\/JLT.2018.2879119","article-title":"Evaluating the effect on demodulation with a comprehensive model of distortions of fiber Bragg grating sensing signals","volume":"36","author":"Zhang","year":"2018","journal-title":"J. Light. Technol."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Gao, H., Liu, X., Qiu, D., Liu, J., Qian, K., Sun, Z., Liu, S., Chen, S., Zhang, T., and Long, Y. (2025). A Self-Adaptive K-SVD Denoising Algorithm for Fiber Bragg Grating Spectral Signals. Symmetry, 17.","DOI":"10.3390\/sym17070991"},{"key":"ref_27","first-page":"295","article-title":"A CNN-Based Demodulation Algorithm for Overlapped Spectra and Its FPGA Implementation","volume":"45","author":"Ren","year":"2024","journal-title":"Semicond. Optoelectron."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Mart\u00ednek, T., Ko\u0159enek, J., and \u010cejka, T. (2024). LGBM2VHDL: Mapping of LightGBM Models to FPGA. Proceedings of the 2024 IEEE 32nd Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), IEEE.","DOI":"10.1109\/FCCM60383.2024.00020"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/13\/4235\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T08:53:31Z","timestamp":1783587211000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/13\/4235"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,3]]},"references-count":28,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["s26134235"],"URL":"https:\/\/doi.org\/10.3390\/s26134235","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,3]]}}}