Bayesian network inference and information fusion for accurate pipe strength and toughness estimation Bayesian network inference and information fusion for accurate pipe strength and toughness estimation Pipeline infrastructure and its safety are critical for the recovering of U.S. economy and our standard of living. Accurate pipe material strength estimation is critical for the integrity and risk assessment of aging pipeline infrastructure systems. Existing techniques focus on the single modality deterministic estimation of pipe strength and ignores inhomogeneousity. In view of this, a novel information fusion framework for multimodality diagnosis of pipe materials is proposed for accurate probabilistic pipe steel strength and toughness estimation under uncertainties. First, chemical composition, material microstructure, and basic surface mechanical properties are detected using various in situ and ex situ techniques. Advanced data analysis using Gaussian Processing model will be performed for surrogate modeling and uncertainty quantification. Following this, advanced sensing techniques using acoustic and electromagnetic sensing for subsurface material properties are proposed. Both simulation and prototype testing are proposed for model validation and demonstration. Finally, a generalized Bayesian network methodology is proposed to fuse multiple sources of information from the multimodality diagnosis results. Probabilistic pipe strength and toughness estimation is inferred based on posterior distribution after information fusion. If successful, this study can help to accurately and effectively assess the reliability of pipeline systems, and eventually help the decision making process to balance the pipeline safety and economical operations.
|Effective start/end date||9/30/15 → 9/29/18|
- US Department of Transportation (DOT): $305,637.00
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.