Efficient implementation of non-linear flow law using neural network into the Abaqus Explicit FEM code

Objective:The rheological properties of oil severely affect the determination of percolation theory, development program, production technology and oil-gathering and transferring process, especially for super heavy oil reservoirs. This paper illustrated the basic seepage morphology of super heavy oil in micro pores based on its rheological characteristics.Methods:The non-linear flow law and start-up pressure gradient of super heavy oil under irreducible water saturation at different temperatures were performed with different permeable sand packs. Meanwhile, the empirical formulas between start-up pressure gradient, the parameters describing the velocity-pressure drop curve and the ratio of gas permeability of a core to fluid viscosity were established.Results:The results demonstrate that temperature and core permeability have significant effect on the non-linear flow characteristics of super heavy oil. The relationship between start-up pressure gradient of oil, the parameters representing the velocity-pressure drop curve and the ratio of core permeability to fluid viscosity could be described as a power function.Conclusion:Above all, the quantitative description of the seepage law of super heavy oil reservoir was proposed in this paper, and finally the empirical diagram for determining the minimum and maximum start-up pressure of heavy oil with different viscosity in different permeable formations was obtained.

Download Full-text

A Hybrid Hidden Markov Model for Pipeline Leakage Detection

Applied Sciences ◽

10.3390/app11073138 ◽

2021 ◽

Vol 11 (7) ◽

pp. 3138

Author(s):

Mingchi Zhang ◽

Xuemin Chen ◽

Wei Li

Keyword(s):

Neural Network ◽

Markov Model ◽

Hidden Markov Model ◽

Gaussian Mixture Model ◽

Mixture Model ◽

Deep Neural Network ◽

Hidden Markov ◽

Gaussian Mixture ◽

State Sequence ◽

Non Linear

In this paper, a deep neural network hidden Markov model (DNN-HMM) is proposed to detect pipeline leakage location. A long pipeline is divided into several sections and the leakage occurs in different section that is defined as different state of hidden Markov model (HMM). The hybrid HMM, i.e., DNN-HMM, consists of a deep neural network (DNN) with multiple layers to exploit the non-linear data. The DNN is initialized by using a deep belief network (DBN). The DBN is a pre-trained model built by stacking top-down restricted Boltzmann machines (RBM) that compute the emission probabilities for the HMM instead of Gaussian mixture model (GMM). Two comparative studies based on different numbers of states using Gaussian mixture model-hidden Markov model (GMM-HMM) and DNN-HMM are performed. The accuracy of the testing performance between detected state sequence and actual state sequence is measured by micro F1 score. The micro F1 score approaches 0.94 for GMM-HMM method and it is close to 0.95 for DNN-HMM method when the pipeline is divided into three sections. In the experiment that divides the pipeline as five sections, the micro F1 score for GMM-HMM is 0.69, while it approaches 0.96 with DNN-HMM method. The results demonstrate that the DNN-HMM can learn a better model of non-linear data and achieve better performance compared to GMM-HMM method.

Download Full-text