Probabilistic damage and loss modeling for metal roof using artificial neural network
Bibliographic record
Abstract
Metal roofs are highly susceptible to hurricane wind damage. The damage to the roof is extremely significant in estimation of losses. Minor damage to the roof can augment the total loss because of the entrance of rain into the building, and subsequent interior and content loss. A probabilistic damage model is developed to predict the damage in a metal roof using Monte Carlo Simulation. Wind Tunnel data for five building models generated in University of Western Ontario is used to estimate the probability distribution of the extreme pressure coefficients. Wind tunnel data assist in giving more realistic loads and include significant factors such as building geometry, approach terrain and roof angle in the estimation of load. Probability distributions for the interior pressure, roll-up door failure and the resistances of the metal panels are obtained from various sources. Typical roof panels with different gages from United Steel Deck (USD) are used along with purlins of various gages and screws of different sizes to account for resistance in developing the damage model. These probability distributions are used to estimate the damage for all the wind tunnel building models. The damage dataset is then used to develop an Artificial Neural Network (ANN). This ANN is employed to estimate the damage to similar rectangular buildings where wind tunnel data is not available. The concept of a Normalized Damage Ratio (NDR) is introduced to consider variation in resistances. A large dataset of NDR’s is generated and used to develop a second ANN to address further variation in resistances. A methodology is suggested to use these ANN models to estimate losses in high wind events. Appropriate loss functions are used to estimate the losses. The damage model is also used to estimate the Average Annual Loss for a metal building in hurricane environment. Finally, a cost benefit study is performed to establish the cost effectiveness of mitigation.
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 | 0.000 | 0.000 |
| 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 | 0.000 |
| 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".