Pipeline Corrosion Leakage Fire Deduction System Based on Bayesian Network Reasoning Model
A Bayesian network and pipeline technology, applied in the field of pipeline corrosion leakage fire deduction system, can solve problems such as pipeline leakage accidents, and achieve the effect of strengthening pre-disaster self-inspection and reducing fire accidents
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0069] as attached figure 1 As shown, the present invention is a pipeline corrosion leakage fire deduction system based on the Bayesian network reasoning model, mainly through the Labview system using the Bayesian network to realize the probability calculation of uncertain risks and generate emergency decisions, including:
[0070] A pipeline corrosion leakage fire deduction system based on a Bayesian network reasoning model, characterized in that it includes:
[0071] Pipeline detection module: used to monitor the pipeline in real time and obtain the real-time situation of the environment in the pipeline; for example: the staff installs distributed optical fiber sensors and video equipment in the pipeline, and the photoelectric detector detects an abnormality, and the Labview console opens the video equipment Monitoring the pipeline; the video recording equipment is a miniature night vision camera.
[0072] Pipeline risk preview module: used to predict the risk of the corros...
Embodiment 2
[0076] As an embodiment of the present invention, the pipeline detection module includes:
[0077] Data acquisition unit: used to install sensing equipment on the inner wall of the pipeline to obtain status data in the pipeline wall; among them,
[0078] The state data includes pressure data, temperature data, gas data and pH concentration data in the pipe wall; detect whether the pipe wall is damaged, the pH concentration of gas or liquid in the air, etc.; for example: the parameter difference of the pipe wall thickness becomes larger, It means that the pipe wall becomes thinner, and there may be a risk of leakage due to damage, or the acidity of the gas or liquid in the air is too low, or the alkalinity is too high, then the pipe wall may be corroded, and the anti-corrosion coating of the pipe wall should be checked; The state of the pipeline needs to be determined through the design equipment in the pipeline, because the pipeline is in a dark state for a long time, and micr...
Embodiment 3
[0084] As an embodiment of the present invention, the pipeline risk preview module includes:
[0085] Bayesian network module preview unit: it is used to preview the corrosion data by using the Bayesian conditional probability algorithm to determine the fire-causing factors on the inner wall of the pipeline. The present invention specifically uses the Bayesian conditional probability algorithm to calculate the probability of occurrence of leakage fire-causing factors; for example: the Bayesian conditional probability area deduces specific fire-causing factors to judge the impact of your pipeline corrosion on fire.
[0086] Bayesian network template clustering unit: It is used to judge the type of abnormal situation that has occurred, and send the judgment result to the fire deduction module for classification. The present invention specifically judges the types of abnormal events that have occurred, and the judgment results are sent to the Labview control system for classifica...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


