Inteligência Artificial Aplicada a Detecção de Vazamentos em Dutos e Canos
Bibliographic record
Abstract
Resumo-Vazamentos em dutos e canos podem gerar prejuízos significativos devido à perda do fluido, assim como, contaminação de solos e rios, dependendo do fluido vazado.Este trabalho, desenvolvido como projeto de iniciação científica, tem como objetivo criar uma ferramenta que permita aumentar a eficiência da inspeção aérea de dutos e canos utilizando técnicas de aprendizado de máquina para a detecção de vazamentos.Para isso, foram treinados e testados três modelos de redes neurais com pré-processamento de imagens para detecção de vazamentos utilizando um banco de imagens próprio.A rede teve desempenho satisfatório para a aplicação proposta com 87% de acurácia. Palavras-Chave-Aprendizado de máquina, visão computacional, detecção de vazamento.Abstract-Leaks in ducts and pipes can generate significant losses due to fluid loss, as well as contamination of soils and rivers, depending on the leaked fluid.This work, developed as a scientific initiation project, aims to create a tool to increase the efficiency of aerial inspection of pipelines and pipes using machine learning techniques for leak detection.For this, three models of neural networks with pre-processing of images for leak detection were trained and tested using a proprietary image bank.The network performed satisfactorily for the proposed application with 87% accuracy.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".