Study on real-time adaptive optimization of energy dissipation in train collision
Bibliographic record
Abstract
Train operation safety has gained significant attention in recent years. Due to the large mass and high operation velocity, train collision accidents often result in catastrophic damage. Current train crashworthiness design focuses on fixed impact velocity by unchangeable energy absorption structures. However, the real train impact velocity is unpredictable and can vary significantly, thus the current train crashworthiness design strategy cannot achieve the optimal crashworthiness under various impact velocities. To address this limitation, this work proposes a real-time adaptive optimization method of energy dissipation in a train collision. First, a one-dimensional train collision model is established based on the multibody dynamic theory. The dynamic response and energy distribution during train collision are analyzed. Then, by adjusting the crushing force of each vehicle, the optimal crushing forces of the energy-absorbing device for the given impact velocity are obtained by the genetic algorithm, which regards the maximum average moving acceleration as the objective response. Results show that the safe collision velocity of the train is increased from 17 m/s to 27 m/s without changing the stroke of the energy-absorbing device. A back-propagation neural network is introduced and trained, which regards the velocities of two trains as input indicators and the optimal crashworthiness indicators of the energy-absorbing device as output indicators. Finally, a real-time prediction framework is established, which can predict the optimal crashworthiness indicators during train collisions under different impact velocities in real time. The results show that the maximum error of the maximum moving average acceleration between the optimization and prediction results is below 2%, which proves the accuracy of the prediction framework.
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 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| 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".