Impact of Associated Parameters on Pressure and Detection of Vandalism in Pipeline Using IoT.

Read full text Summarise with VIRAT
Authors: Edafe John Atajeromavwo, Okiemute Dickson Ofuyekpone, Ohis Grace Mega
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The impact of associated parameters on pressure and IoT-based vandalism detection in pipelines are the core subjects of this article. In order to conduct the research, pipeline pressure simulation was run, and the pressure prediction and abnormal pressure of the pipeline were modelled. The information gathered from the pipeline framework is predicated on a model of pipeline that held fluid in an Internet of Things system. A setup of equipment to collect vibration indicator data from each stated location along the crude pipeline was designed. Using a vast network of industrial vibration signals from the DAQ, the acquired signal data was made to communicate data from the station experiment. The estimate pressure involved were generated by loading specific vibration frequency and pressure signal captured by DAQ into Python script. And apply residual model to velocity, length, area, volume, mass, and density are the derivatives of the datasets for this study. In particular, the goals are to conceptualize the pipeline architecture of the Internet of Things, derive a Residual linear regression model for pipeline with associated parameters, predict the pressure of oil pipes and compute the abnormal pressure at a given velocity, predict the pressure of oil pipes with evaluation of their accuracy metrics performance, and visualize the actual pressure with the predicted of the pressure of oil pipes. The main goal is to develop an intelligent system of associated parameters on pressure for pipeline monitoring framework system. There is comparison of the residual model of liner regression and isolation forest model on the pipeline framework by evaluation and analysis of the outcome shows accuracy performance metric of 69%.

Fields of Study & Subjects

Water Systems and Optimization Structural Integrity and Reliability Analysis Fault Detection and Control Systems

Publication details

Journal / source
NIPES Journal of Science and Technology Research
Volume
8
Issue
1
Publication date
25 March 2026
Language
EN