论文信息 - Design of Smart Wellhead Controllers for Optimal Fluid Injection Policy and Producibility in Petroleum Reservoirs: A Neural Network-Model Predictive Approach

Design of Smart Wellhead Controllers for Optimal Fluid Injection Policy and Producibility in Petroleum Reservoirs: A Neural Network-Model Predictive Approach

In this paper we present the second generation of “smart” controllers for fluid injection and predictive techniques for developing optimal fluid injection policy. A neural network model is used to optimize the oil field management in terms of fluid injection and oil recovery. We illustrate performance of the neural network for model identification and control purposes. In particular, the neural network models are used to control and predict the behavior of individual injectors in CalResources’ Phase III steam drive pilot in the South Belridge Diatomite, CA, under different injection policies.

Masoud Soroush | Tadeusz W Patzek | Masoud Nikravesh

[1] Anthony R. Kovscek,et al. Interpretation of hydrofracture geometry during steam injection using temperature transients II. Asymmetric hydrofractures , 1996 .

[2] Masoud Soroush,et al. Design of Smart Wellhead Controllers for Optimal Fluid Injection Policy and Producibility in Petroleum Reservoirs: A Neuro-Geometric Approach , 1997 .

[3] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .

[4] Thomas Stanford,et al. Model identification of nonlinear time variant processes via artificial neural network , 1996 .

[5] Bernard Widrow,et al. 30 years of adaptive neural networks: perceptron, Madaline, and backpropagation , 1990, Proc. IEEE.

[6] Tadeusz W Patzek,et al. Prediction of Formation Damage During Fluid Injection into Fractured, Low Permeability Reservoirs via Neural Networks , 1996 .

[7] Mahmood R. Azimi-Sadjadi,et al. Fast learning process of multilayer neural networks using recursive least squares method , 1992, IEEE Trans. Signal Process..

[8] Dale E. Seborg,et al. Nonlinear internal model control strategy for neural network models , 1992 .