Enhanced Structural Health Monitoring Through LSTM-Enhanced Gradient Boosting Regressor

References

[1] Marani A. & Nehdi M.L.: Machine learning prediction of compressive strength for phase change materials integrated cementitious composites. Constr Build Mater. 265:120286. 10.1016/j.conbuildmat.2020.120286

[2] Mangalathu S. & Jeon J-S: Classification of failure mode and prediction of shear strength for reinforced concrete beam-column joints using machine learning techniques. Eng Struct. 160:85-94. 10.1016/j.engstruct.2018.01.008

[3] Naderpour H., Poursaeidi O. & Ahmadi M.: Shear resistance prediction of concrete beams reinforced by FRP bars using artificial neural networks. Measurement (Lond). 126:299-308. 10.1016/j.measurement.2018.05.051

[4] Aslam F, et. al.: Applications of gene expression programming for estimating compressive strength of high-strength concrete. Adv Civ Eng. 2020, 1-23. 10.1155/2020/8850535

[5] Nguyen T., Kashani A., Ngo T. & Bordas S.: Deep neural network with high-order neuron for the prediction of foamed concrete strength. Comput Aided Civ Infrastruct Eng. 34:316-332. 10.1111/mice.12422

[6] Ketabdari H., Karimi F. & Rasouli M.: Shear strength prediction of short circular reinforced-concrete columns using soft computing methods. Adv Struct Eng.. 10.1177/1369433220927270

[7] Ly H-B, Le T-T, Vu H-LT, Tran VQ, Le LM & Pham B.T.: Computational hybrid machine learning-based prediction of shear capacity for steel fiber reinforced concrete beams. Sustainability. 12:2709 10 3390 12072709. 10.3390/su12072709

[8] Golafshani EM, Rahai A, Sebt MH & Akbarpour H: Prediction of bond strength of spliced steel bars in concrete using artificial neural network and fuzzy logic. Constr Build Mater. 36:411-418. 10.1016/j.conbuildmat.2012.04.046

[9] Yaseen ZM, Deo RC, Hilal A, Abd AM, Bueno LC, Salcedo-Sanz S & Nehdi M.L.: Predicting compressive strength of lightweight foamed concrete using extreme learning machine model. Adv Eng Softw .. 10.1016/j.advengsoft.2017.09.004

[10] Le T.-T.: Practical machine learning-based prediction model for axial capacity of square CFST columns. Mech Adv Mater Struct .. 10.1080/15376494.2020.1839608

[11] Javed MF, Amin MN, Shah MI, et. al.: Applications of gene expression programming and regression techniques for estimating compressive strength of bagasse ash-based concrete. Numer Stud Concr .. 10.3390/cryst10090737

[12] Feng D-C, Liu Z-T, Wang X-D, Jiang Z-M & Liang S-X: Failure mode classification and bearing capacity prediction for reinforced concrete columns based on ensemble machine learning algorithm. Adv Eng Inform .. 10.1016/j.aei.2020.101126

[13] Jalal M, Grasley Z, Gurganus C & Bullard JW: Experimental investigation and comparative machine-learning prediction of strength behavior of optimized recycled rubber concrete. Constr Build Mater .. 10.1016/j.conbuildmat.2020.119478

[14] Hu G, Liu L, Tao D, Song J, Tse KT & Kwok K.C.S.: Deep learning-based investigation of wind pressures on tall buildings under interference effects. J Wind Eng Ind Aerodyn.. 10.1016/j.jweia.2020.104138

[15] Dataset from structural health monitoring of a steel bridge in Sweden. (2023). Accessed: August 26, 2024: https://zenodo.org/records/8300495.

@article{1707638,
      author = {Aryan Kesarkar, Chrisil Dabre, Raghav Agarwal, Yash Chavan, Prof. Ruhina Karani},
      title = {Enhanced Structural Health Monitoring Through LSTM-Enhanced Gradient Boosting Regressor},
      journal = {Iconic Research And Engineering Journals},
      year = {2025},
      volume = {8},
      number = {9},
      pages = {1221-1231},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1707638.pdf},
      abstract = {This research paper highlights a novel hybrid model, LSTM-Enhanced Gradient Boosting Regressor (LE-GBR), which aims to improve prediction of failure in critical infrastructure like bridges and buildings. Structures naturally degrade over time due to many factors like material fatigue and environmental pressures, making accurate predictions essential for safety and maintenance planning. Traditional models often miss complex interactions between these factors, but our method integrates Gradient Boosting Regressor (GBR) with Long Short-Term Memory (LSTM) networks, allowing us to capture both fixed and evolving patterns in structural health data. Through experiments on a collected dataset, LE-GBR model outperformed other approaches, providing more accurate forecasts of structural health conditions. This model offers a promising tool for enhancing structural safety by enabling more precise failure predictions, thereby supporting improved maintenance strategies and risk mitigation for critical infrastructure.},
      keywords = {Failure Prediction, Gradient Boosting Regressor, Hybrid Model, Infrastructure Safety, LSTM, Predictive Modeling, Structural Health Monitoring, Structural Integrity},
      month = {March},
  }