A New Triaxial Apparatus Imposing Nonuniform Shearing for Deep Learning of Soil Behavior
Bibliographic record
Abstract
Abstract Soil behavior is commonly characterized based on laboratory tests with imposed or assumed uniform stress and strain distribution within a given soil specimen for convenient data reduction. This uniformity assumption limits the interpretation of each test to a single stress-strain path, and therefore, extensive laboratory testing is required to represent field soil behavior under a broad range of loading paths. This article presents the development of a modified, next-generation, triaxial device (NG-TX) to generate multiple loading paths in a single test that can be interpreted using an evolutionary deep-learning inverse analysis. This device inherits all features of a conventional triaxial test and adds lateral restraint clamps to increase nonuniformity in specimen deformation, combined with a digital photogrammetry system to measure the 3-D deformed shape of the specimen. The design of the restraint clamps was optimized using numerical simulations, which showed that the sheared specimen includes shear modes that cannot currently be mobilized with available testing devices. By coupling SelfSim, a deep-learning algorithm, with the modified triaxial device (NG-TX), the shear behavior of Ottawa sand was extracted. The SelfSim-extracted Neural Network material models were able to successfully capture the global behavior of each test and extract the nonuniform stress-strain behavior from within the specimens. The interpreted stress paths cover broad portions of stress space that current laboratory tests cannot cover. The stress-strain behavior is interpreted in terms of the mobilized secant friction angle using 2-D and 3-D failure criteria. The mobilized secant friction angle interpretation shows better agreement with empirically developed envelopes when computed along the octahedral plane accounting for the influence of intermediate principal stress.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 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".