Effective soil conditioning is critical for mechanized shield tunneling, yet the selection of conditioning parameters remains experience-oriented. This study presents a machine learning–informed soil conditioning strategy, aiming at enabling automatic decision-making for soil conditioning during tunneling. The proposed procedure includes feature engineering to process raw data, the selection of an optimal model, and a committee-based uncertainty quantification strategy to evaluate the reliability of models. High-dimensional data visualization techniques are leveraged to examine the influence of data distribution on the model's performance. Results demonstrate that feature engineering and the selection of models lay a foundation for machine learning–enabled automatic soil conditioning, while historical soil conditioning parameters should be incorporated in models to account for time-dependent features during tunneling. The committee-based uncertainty quantification strategy can effectively identify the reliability of both interpolated and extrapolated predictions. The proposed data-driven soil conditioning framework can promote the application of machine learning toward automating earth pressure balance (EPB) shield tunneling.

中文翻译：

---

机器学习——机械化盾构掘进的土壤调节

有效的土壤调理对于机械化盾构掘进至关重要，但调理参数的选择仍然以经验为导向。本研究提出了一种基于机器学习的土壤调节策略，旨在实现隧道挖掘过程中土壤调节的自动决策。所提出的程序包括处理原始数据的特征工程、最佳模型的选择以及基于委员会的不确定性量化策略来评估模型的可靠性。利用高维数据可视化技术来检查数据分布对模型性能的影响。结果表明，特征工程和模型的选择为机器学习支持的自动土壤调节奠定了基础，而历史土壤调节参数应纳入模型中，以考虑隧道挖掘过程中与时间相关的特征。基于委员会的不确定性量化策略可以有效地识别内插和外推预测的可靠性。所提出的数据驱动的土壤调节框架可以促进机器学习在土压平衡（EPB）盾构隧道掘进自动化方面的应用。