Method and system intended for real-time estimation of the flow mode of a multiphase fluid stream at all points of a pipe

• US 6,941,254 B2
• Filed: 07/06/2001
• Issued: 09/06/2005
• Est. Priority Date: 07/27/2000
• Status: Expired due to Fees

• Current Assignee: Institut Francais Du Petrole (IFP Energies Nouvelles)
• Original Assignee: Institut Francais Du Petrole (IFP Energies Nouvelles)
• Inventors: Duret, Emmanuel, Rey-Fabret, Isabelle, Heintze, Eric
• Primary Examiner(s): FREJD, RUSSELL WARREN
• Application Number:
  US09/899,039
• Publication Number:
  US 20020016701A1
• Time in Patent Office: 1,523 Days
• Field of Search: 123/25.A, 738/613.56, 703/2, 703/9, 706/15, 706/16, 706/25, 706/26, 706/44
• US Class Current: 703/9
• CPC Class Codes: G05B 17/02 electric

Abstract

The invention is a method and system for real-time estimation of the flow mode, at all points of a pipe whose structure is defined by a certain number of structure parameters, of a multiphase fluid stream defined by several physical quantities providing simplified implementation of hydrodynamic modules that can be integrated in modelling tools. A non-linear neural network is formed with an input layer having as many inputs as there are structure parameters and physical quantities, an output layer with as many outputs as there are quantities necessary for estimation of the flow mode and at least one intermediate layer. A learning base is created with predetermined tables connecting various values obtained for the output data to the corresponding values of the input data, with iterative determination of the weighting factors of the activation function allowing to properly connect the values in the input and output data tables. In order to avoid singularities of the network output data likely to distort the determination of the weighting factors, a sorting procedure is used to eliminate non-pertinent data. The main advantages of the method are: modelling simplification and time saving.

Claims

1. A method of real-time estimation of a flow mode, at all points of a pipe whose structure can be defined by structural parameters, of a multiphase fluid stream defined by physical quantities and comprising at least a liquid phase and at least a gas phase, the method comprising:

forming a non-linear neural network with an input layer having as many inputs as there are structural parameters and physical quantities, an output layer with as many outputs as there are quantities necessary for estimation of the flow mode and at least one intermediate layer;

creating a learning base with predetermined tables connecting values obtained for the output data to corresponding values of the input data;

determining by iterations weighting factors of activation function allowing connection of the values in input and output data table,

determining at least a velocity difference between gas and liquid and a stratified flow fraction with the neural network defined by the weighting factor; and

estimating the flow mode from at least the velocity difference and the stratified flow fraction.

2. A method as claimed in claim 1, further comprising:

analyzing the output data of the neural network to allow sorting, among the values of the output data of the neural network, only data to be taken into account in the iterative determination of weighting coefficients of the activation function.

3. A method as claimed in claim 1, wherein:

a totally connected network is formed.

4. A method as claimed in claim 1, wherein:

output neurons are linear.

5. A method as claimed in claim 1, wherein:

the activation function is an identity function.

6. A method as claimed in claim 2, wherein:

a totally connected network is formed.

7. A method as claimed in claim 2, wherein:

output neurons are linear.

8. A method as claimed in claim 3, wherein:

output neurons are linear.

9. A method as claimed in claim 6, wherein:

output neurons are linear.

10. A method as claimed in claim 2, wherein:

the activation function is an identity function.

11. A method as claimed in claim 3, wherein:

the activation function is an identity function.

12. A method as claimed in claim 6, wherein:

the activation function is an identity function.

13. A system providing real-time estimation of a flow mode, at all points of a pipe whose structure can be defined by structural parameters, of a multiphase fluid stream defined by physical quantities and comprising at least a liquid phase and at least a gas phase, the system comprising:

means for determining characteristics of a non-linear neural network with an input layer having as many inputs as there are structural parameters and physical quantities, an output layer having as many outputs as there are quantities necessary for estimation of the flow mode and at least one intermediate layer;

means for storing a learning base with predetermined tables connecting values obtained for the output data to corresponding values of the input data;

means for determining by iterations weighting factors of an activation function allowing connection of the values in input and output data table,

means for determining at least a velocity difference between gas and liquid and a stratified flow fraction with the neural network defined by the weighting factors; and

means for estimating the flow mode from at least the velocity difference and the stratified flow fraction.

14. A system as claimed in claim 13, comprising:

means for analyzing the output data of the neural network allowing sorting, among the values of the neural network, only data to be taken into account in the iterative determination of weighting coefficients of the activation function.