@revista_internacional{956,
  keywords = {shield construction parameter, multiobjective optimization, surface settlement, cutter wear, advance speed, BO-RF, NSGA-III},
  author = {Hongyu Chen and Jun Liu and Geoffrey Qiping Shen and Luis Martínez and Muhammet Deveci and Zhen-Song Chen and Yang Liu},
  title = {Multisource information fusion for real-time optimization of shield construction parameters},
  abstract = {This paper introduces a hybrid intelligent framework that combines Bayesian optimization (BO), a random forest (RF) model, and the nondominated sorting genetic algorithm-III (NSGA-III) for the optimization and control of tunnel shield construction parameters. The BO-RF method establishes a nonlinear mapping function between the input variables and three targets, surface settlement, cutter wear, and advance speed, serving as the fitness function for NSGA-III. Model interpretability analysis is conducted using Shapley Additive ExPlanations (SHAP). A multiobjective intelligent optimization model is formulated with NSGA-III, targeting surface settlement, cutter wear, and advance speed. A case study validates the applicability and effectiveness of this approach, leading to the following conclusions: (1) The BO-RF algorithm yields highly accurate prediction results, with R2 values ranging from 0.930 to 0.938, RMSE ranging from 0.138 to 0.172, and MAE ranging from 0.112 to 0.138 for the three targets. (2) The optimization results for surface settlement, cutter wear, and advance speed are outstanding, with an average improvement of 12.56%. The simultaneous adjustment of the three shield construction parameters leads to the best optimization results, with an average improvement of 19.67%. (3) The energy consumption of the shield drive system decreases by an average of 10.70%, and the optimization improvement for the first three objectives decreases by an average of 1.82%, 1.46%, and 2.23%, respectively. By introducing the integrated BO-RF-NSGA-III algorithm, this study contributes to the field of tunnel engineering optimization management.},
  year = {0},
  journal = {Knowledge-Based Systems},
  pages = {111413},
  issn = {0950-7051},
  url = {https://www.sciencedirect.com/science/article/pii/S0950705124000480},
  doi = {https://doi.org/10.1016/j.knosys.2024.111413},
}