Efficient and Robust Temperature Field Simulation of Long-Distance Crude Oil Pipeline Based on Bayesian Neural Network and PDE

The hydraulic and thermal simulation of crude oil pipeline transportation is greatly significant for the safe accurate regulation pipelines. With reasonable basic parameters, solution traditional partial differential equation (PDE) axial soil temperature field on can obtain results, yet it brings about a low calculation efficiency problem. In order to overcome low-efficiency problem, an efficient robust hybrid model coupling with Bayesian neural network PDE proposed, which considers dynamic changes boundary conditions. Four models, including proposed model, PDE, two kinds networks (NNs), are adopted predict single transient at outlet pipeline. It found that prediction results closer those than NNs, more stable reliable NNs training data sets different quantities On other hand, time method far less applicable situation small improve efficiency. This study provide scientific reference fast real-time