A BiLSTM Based Pipeline Leak Detection and Disturbance Assisted Localization Method
Bibliographic record
Abstract
Negative pressure wave (NPW) based fluid pipeline leak detection and localization method detects leaks by capturing the pressure inflecting trends and locates leaks by calculating the time difference of arrival (TDOA) of NPW between the upstream and downstream sensors. However, in practical situations, pressure variations under normal working conditions such as pump, valve operations etc., may be misidentified as leaks due to the similar pressure inflection transients caused. In addition, for leak localization, traditional TDOA method assumes the NPW propagation speed as a constant, which is inconsistent with the reality. In this paper, a deep learning based pipeline leak detection and disturbance assisted localization method is proposed. At first, unlike the traditional methods, which only focus on detecting pressure transients for leaks, a deep learning based pressure sequence classification scheme is proposed to identify not only the leaks but also the typical recurrent non-leak pressure disturbances. Secondly, instead of using an empirical constant as NPW speed to calculate leak locations, a disturbance assisted localization method is proposed to online update the NPW speed by exploiting non-leak disturbances. The proposed approach is data driven, i.e., only pressure signals are needed. For validation, the approach is tested on both simulation data and real-world pipeline leak experimental data. Comparison and case studies are also performed. It is shown that the proposed method achieves high detection accuracy with rare false alarms and significantly reduced leak localization errors.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".