Scholarlink

<p>Fiber Bragg Grating (FBG)-based sensors have emerged as reliable optical devices for monitoring humidity owing to their wavelength-encoded response, compactness, and immunity to electromagnetic interference. Accurate humidity measurement is a critical requirement in nondestructive evaluation (NDE) and condition monitoring, as moisture strongly influences the degradation and long-term integrity of polymer-based and composite materials. However, the intrinsic humidity sensitivity of bare FBGs is minimal and can be enhanced using a polymer coating that swells upon moisture absorption, inducing Bragg wavelength shifts. This study presents an optical modeling and simulation framework for a polymer-coated FBG humidity sensor, supported by machine learning (ML) algorithms to address nonlinear polymer swelling, hysteresis, and temperature cross-sensitivity. Theoretical formulations governing Bragg wavelength variation were implemented for polyimide-coated FBGs under varying relative humidity levels (0–100% RH). Reflectivity spectra were simulated using the coupling coefficient model and analyzed using Random Forest (RF) and Support Vector Regression (SVR) algorithms. The results demonstrate that ML-assisted modeling effectively captures the nonlinear optical response, yielding significant improvements in sensitivity and accuracy. The proposed approach contributes to nondestructive environmental condition monitoring by improving the reliability of optical fiber sensing systems, thereby supporting material health assessment and structural monitoring applications.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Machine Learning-Assisted Fiber Bragg Grating Humidity Sensor for Nondestructive Condition Monitoring

  • 期刊论文

  • 发表日期：

    2026年6月26日

查看全文
  • Ahmad Adel Abu-Shareha,
  • K. Narsimha Reddy,
  • Manoranjan Parhi,
  • Mahendihasan S. Heera,
  • B. Jayaprakash,
  • Sudeep Varshney,
  • B. Bharathi,
  • Sumit Sharma,
  • Devendra Singh

摘要

Fiber Bragg Grating (FBG)-based sensors have emerged as reliable optical devices for monitoring humidity owing to their wavelength-encoded response, compactness, and immunity to electromagnetic interference. Accurate humidity measurement is a critical requirement in nondestructive evaluation (NDE) and condition monitoring, as moisture strongly influences the degradation and long-term integrity of polymer-based and composite materials. However, the intrinsic humidity sensitivity of bare FBGs is minimal and can be enhanced using a polymer coating that swells upon moisture absorption, inducing Bragg wavelength shifts. This study presents an optical modeling and simulation framework for a polymer-coated FBG humidity sensor, supported by machine learning (ML) algorithms to address nonlinear polymer swelling, hysteresis, and temperature cross-sensitivity. Theoretical formulations governing Bragg wavelength variation were implemented for polyimide-coated FBGs under varying relative humidity levels (0–100% RH). Reflectivity spectra were simulated using the coupling coefficient model and analyzed using Random Forest (RF) and Support Vector Regression (SVR) algorithms. The results demonstrate that ML-assisted modeling effectively captures the nonlinear optical response, yielding significant improvements in sensitivity and accuracy. The proposed approach contributes to nondestructive environmental condition monitoring by improving the reliability of optical fiber sensing systems, thereby supporting material health assessment and structural monitoring applications.