Abstract
In order to decrease the false alarm rate and improve the sensitivity of pipeline fault diagnosis system, three artificial intelligence based methods are first proposed. Neural networks with the input matrix composed by stress wave characteristics in time domain or frequency domain is proposed to classify various situations of the pipeline, in order to detect the leakage from pipeline online running data. Context-free grammar of symbolic representation of the negative wave form is used and a negative wave form parsing system with application to syntactic pattern recognition based on the representation is described. New complex thermal and hydraulic models, in which the flow regime, viscosity-temperature characteristics, density-temperature characteristics and specific heat-temperature characteristics, etc., of the running fluid in the pipelines are set up for non-isothermal pipeline carrying higher temperature fluid or in ambient environment.Copyright © 1998 by ASME
Original document
The different versions of the original document can be found in:
- http://asmedigitalcollection.asme.org/IPC/proceedings-pdf/doi/10.1115/IPC1998-2097/2506998/835_1.pdf,
- https://computationalnonlinear.asmedigitalcollection.asme.org/IPC/proceedings/IPC1998/40238/835/258124,
- https://asmedigitalcollection.asme.org/IPC/proceedings/IPC1998/40238/835/258124,
- http://proceedings.asmedigitalcollection.asme.org/proceeding.aspx?articleid=2572776,
- https://academic.microsoft.com/#/detail/2536209943
Document information
Published on 01/01/1998
Volume 1998, 1998
DOI: 10.1115/ipc1998-2097
Licence: CC BY-NC-SA license
Share this document
Keywords
claim authorship
Are you one of the authors of this document?