Multi-objective optimization and sensitivity analysis of forced-steering bogies using surrogate models and NSGA-III
Bibliographic record
Abstract
This research proposes a multi-objective optimization methodology to enhance the curving and tangent performance of forced-steering passenger trains. Using the Non-dominated Sorting Genetic Algorithm-III (NSGA-III), we optimize a set of parameters — primary suspension stiffness (longitudinal and lateral) and steering linkage — to minimize wheelset unloading, derailment risk, rail rollover risk, and car body lateral acceleration. A 167-degree-of-freedom high-fidelity simulation model of the train is developed and validated against conventional rail vehicle data. Sensitivity analysis via the Sobol’ method identifies key design parameters, reducing the number of variables for optimization. A Kriging surrogate model is then employed to approximate the simulation model, making optimization feasible. Post-optimization, the robustness of the Pareto optimal solutions is evaluated under varying track conditions. Key findings reveal that steering ratio and longitudinal primary suspension stiffness are critical, while yoke-to-yoke parameters have minimal impact. The optimization results show a trade-off between curving performance and car body lateral acceleration, with solutions varying based on lateral stiffness. Two out of four Pareto optimal sets demonstrated improved robustness under varying curve radii and equivalent conicity, while all Pareto optimal sets exhibit equal robustness and significant improvements in performance under varying track friction. These findings emphasize the importance of robust design optimization across different operational conditions to achieve balanced performance.
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 | 0.003 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".