Multi-stage and multi-objective optimization framework for servo-controlled wall deflection during deep excavation
Bibliographic record
Abstract
Controlling excavation-induced deformation is essential for excavation safety and adjacent structure protection. To address the increasingly stringent deformation control requirements driven by growing building density in urban areas, this study proposes a multi-stage and multi-objective optimization framework for servo-controlled wall deflection during deep excavations. First, since the servo force optimization involves thousands of deflection evaluations, a pretrained surrogate model is developed to accelerate this computationally intensive process. Subsequently, a primary–secondary loss formulation is defined, with deformation control as the primary goal and unloading minimization as a secondary objective for stability. Finally, this formulation is optimized using a cross-stage coordinated algorithm. Unlike existing methods that treat stages independently, the proposed algorithm employs beam search to evolve top-ranked solutions in parallel, yielding globally optimal servo force configurations. A deep excavation project in Ningbo, China is used for illustration. The proposed surrogate model outperforms alternative approaches, achieving R 2 values above 0.95 across all stages. With a 10% unloading ratio, the optimization reduces the maximum wall deflection at each stage by approximately 30%–35%, demonstrating effective deformation control. For stricter requirements, a higher allowable unloading ratio can be adopted, potentially limiting deflection to within 0.2% of the excavation depth.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".