Gaussian Fields for Predicting Drift of Oil and Gas Pipes

Abstract

In the oil and gas industry, empirical models are used to estimate the drift of pipes. These models encode pipe geometrical features, measured along the pipe length. If the estimated drift does not meet the operability requirements, then the pipe is rejected. This improves the quality of the purchased pipes, but strongly affects their production costs. We rely on the Gaussian fields theoretical framework to address two issues: the a priori estimation of the probability of pipes rejection and the a posteriori estimation of the drift conformance probability, given the actual measured parameters. These are fundamental pieces of information for purchasing decisions. A case study is considered to show the application of the theoretical framework. The proposed methodology is applied to real pipe measurement data, which have been opportunely rescaled to avoid the disclosure of relevant information.