Echo state network-based metamodel for the problem of stagnant petroleum cooling in pipe-in-pipe flowlines

Abstract

The low temperatures found in subsea water combined with the transport of hydrocarbons in flowlines that are immersed in this environment brings the problem of solid deposition inside the flowlines, mainly of paraffin and hydrates, which consists of considerable problems to the petroleum industry. To overcome this issue, computational simulation might be an ally. However, such simulations sometimes can be computationally demanded, making their use unpractical. In these cases, metamodels, which are computationally cheaper models, can be an alternative. The present paper proposes using an Echo State Network as a surrogate model for the problem of stagnant production fluid cooling in a subsea pipe-in-pipe system with active electric heating. The implemented metamodel shows to be twenty-four times faster than the Finite Volume Method, although it showed consistent correlations for all lags when a residual autocorrelation analysis was performed.