Method, System and Apparatus for Intelligent Management of Oil and Gas Platform Surface Equipment

• US 20110071963A1
• Filed: 09/16/2010
• Published: 03/24/2011
• Est. Priority Date: 09/18/2009
• Status: Active Grant

• Current Assignee: APO Offshore Incorporated
• Original Assignee: APO Offshore Incorporated
• Inventors: Kozman, Jess B., Piovesan, Carol M.
• Granted Patent: US 8,676,721 B2
• Time in Patent Office: Days
• US Class Current: 706/11
• CPC Class Codes: G06Q 10/00 Administration; Management

Abstract

A method, system, apparatus (and related computer program) for intelligent management of oil and gas offshore and onshore platform surface equipment over a computer network is disclosed. The system utilizes a data aggregator for gathering real-time data streams from surface equipment located on such platform(s), such surface equipment containing one or more sensors for monitoring in real time the performance of equipment operational parameters of interest. The data analysis engine is in network communication with the data aggregator, and comprises a trained neural network capable of generating self organizing maps, and creating predictive operational parameters regarding such surface equipment. An interface is provided for inputting into the neural network various data including, for example, the published performance operational parameters for such equipment. A network user interface is also provided for transmitting such predictive operational input to one or more end user terminals equipped with end user dashboard display software.

Claims

1. A computer implemented method for predictive analysis of surface equipment or systems used on one or more oil and gas field platforms located offshore or onshore comprising the steps of:

inputting to a data aggregator on a computer system real-time data streams from one or more sensors sensing parameters of interest on surface equipment located on such one or more platforms, such surface equipment containing one or more sensors for monitoring in real time the performance of such surface equipment based on such parameters of interest;

aggregating such sensor data into a common data format;

transmitting the aggregated, formatted sensor data to a computerized data analysis engine;

inputting into the data analysis engine multiple data streams containing information relevant to the operating equipment or systems;

providing a neural network within the data analysis engine;

generating self organizing maps within the data analysis engine;

using the neural network engine to transform the equipment data streams from a monitoring state, function or use to a predictive state, function or use;

generating status indicators in real-time relevant to the operation of the equipment or systems;

transmitting such status indicators to one or more end users over a network; and

providing a computer-based dashboard software-based display system for displaying to such end user(s) such transmitted data.

2. The method of claim 1 further comprising the step of training the neural network to cross-correlate the multiple data streams and look for relationships between the incoming data streams.

3. The method of claim 1 further comprising the step of operating the neural network in an untrained mode.

4. The method of claim 1 wherein the multiple data streams comprise:

manufacturer'"'"'s operational parameters for the equipment and systems and historical performance data obtained from monitoring the actual operation of a piece of equipment in different operating environments.

5. The method of claim 4 further comprising the step of training the neural network to cross-correlate the real-time sensor data and the manufacturer'"'"'s operational parameters and look for relationships between the incoming data streams.

6. The method of claim 4 further comprising the step of operating the neural network in an untrained mode.

7. The method of claim 1 further comprising the step of deriving functions from the data streams using the neural network, wherein the functions are both continuous and differentiable.

8. The method of claim 7 further comprising the step of deriving errors by comparing the input data streams with the predictive states from the neural network.

9. The method of claim 8 further comprising the step of using the derived errors to train the neural network.

10. The method of claim 1 further comprising the steps of:

providing a cascade-forward back-propagation network, having multiple layers, within the data analysis engine;

inputting the data streams directly into each layer of the cascade-forward back-propagation network; and

using higher-order polynomials within the cascade-forward back-propagation network to model nonlinear relationships among the data streams.

11. The method of claim 10 further comprising the steps of:

deriving functions from the data streams using the neural network, wherein the functions are both continuous and differentiable;

deriving errors by comparing the input data streams with the predictive states from the neural network; and

using the predictive states to limit the data streams input into the cascade-forward back-propagation network by eliminating data points that fall outside of the errors.

12. The method of claim 11 further comprising the step of comparing the predictive state to the input data stream for use in generating status indicators.

13. A system for remotely predicting the performance of surface equipment and systems used on one or more oil and gas field platforms located offshore or onshore comprising:

a. a data aggregator for gathering real-time data streams from surface equipment located on such one or more platforms, such surface equipment containing one or more sensors for monitoring in real time the performance of operational parameters of interest in such surface equipment;

b. a data analysis engine in network communication with the data aggregator, the data analysis engine comprising a neural network capable of generating self organizing maps, and creating predictive operational indicators regarding such surface equipment and systems;

c. an interface for inputting into the neural network multiple data streams containing information relevant to the operating equipment or systems;

d. a network user interface for transmitting such predictive operational indicators from the data analysis engine to one or more end user terminals equipped with end user dashboard display software, and

e. an interface for inputting sensor data to the data aggregator.

14. The system of claim 13 further comprising:

a cascade-forward back-propagation network, having multiple layers, within the data analysis engine and an interface for inputting the data streams directly into each layer of the cascade-forward back-propagation network.

15. A computer program product, comprising a computer usable medium having a computer readable program code embodied therein, said computer readable program code adapted to be executed to implement a method for the training of a neural network used to generate predictive operational parameters for surface equipment and systems used on oil and gas platforms, said method comprising:

providing a system, wherein the system comprises distinct software modules, and wherein the distinct software modules comprise a data input module (to provide instruction to a user to identify and parse multiple digital data streams containing information relevant to the operating equipment or systems), a data formatting module (to correlate, time synchronize and standardize the digital data streams) and a data loading module (to identify and transmit the data streams as training data to the neural network).