Research on point cloud data optimization and feature extraction during 3D reconstruction of high-speed rail wheelsets
Bibliographic record
Abstract
With the continuous development of the rail vehicle business, high-speed rail, locomotive, subway, light rail and other railroad transportation industry to reach the prosperity of the previous scene, the wheelset is an important support and walking parts of the rail train, so the detection of its geometric parameters and tread quality of the safe operation of the vehicle is of great significance.In this paper, based on the principle of binocular measurement vision, the mathematical model of bilinear structured light is used to calculate the three-dimensional coordinates of the spatial points of the wheel pairs of high-speed railways.The collected point cloud data are filtered and smoothed to eliminate the noise contained in the data.Integrate the two point data under the same coordinate system, perform data fusion on the overlapping part to complete the alignment of the point cloud.And extract its eigenvalues to realize the point cloud coordinate transformation.Through testing experiments, the accuracy of high-speed rail wheel pair data measurement and other indicators are studied and analyzed.The measurement accuracy of the journal diameter of the HSR wheelset has a deviation of about 0.003 mm compared with the CMM, meanwhile, the fluctuation range of the HSR wheelset diameter data in the left and right directions is within 0.04 mm and 0.03 mm, respectively, and the stability of the measurement data of the model is good.The point cloud rotation error is between -1.09 and 1.09, and the first quadrant angle error is between -1.114 and 0.829, and the model controls the error to be around 1, and the verification of the pairing accuracy is passed, which can meet the requirements of the production and operation activities.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".