Cross-Sensor Standardization

Abstract

The disclosed embodiments include a method, apparatus, and computer program product for generating a cross-sensor standardization model. For example, one disclosed embodiment includes a system that includes at least one processor; at least one memory coupled to the at least one processor and storing instructions that when executed by the at least one processor performs operations comprising selecting a representative sensor from a group of sensors comprising at least one of same primary optical elements and similar synthetic optical responses and calibrating a cross-sensor standardization model based on a matched data pair for each sensor in the group of sensors and for the representative sensor. In one embodiment, the at least one memory coupled to the at least one processor and storing instructions that when executed by the at least one processor performs operations further comprises generating the matched data pair, wherein the matched data pair comprises calibration input data and calibration output data.

Description

BACKGROUND OF THE INVENTION[0001]Various multivariate models are used to predict chemical compositions and other properties of unknown reservoir fluid samples during formation fluid analysis that are based on the measurements of downhole optical tools. The application of pre-calibrated fluid prediction models is tool dependent, often requiring data standardization or transformation to convert measured sensor responses from the tool data space to the calibration data space. The costs associated with fluid prediction model development and management affects how instrument standardization is performed.BRIEF DESCRIPTION OF THE DRAWINGS[0002]Illustrative embodiments of the present invention are described in detail below with reference to the attached drawing figures, which are incorporated by reference herein and wherein:[0003]FIG. 1a illustrates an example data processing workflow for an individual sensor;[0004]FIG. 1b illustrates an example data processing workflow using multivariate m...

AI Technical Summary

Benefits of technology

The patent text describes a method for calibrating optical sensors in a cost-effective way using a cross-sensor standardization approach. This approach involves selecting a representative sensor based on the primary optical elements, and using the responses of the sensor to create a single set of fluid property prediction models. This reduces the number of models needed to be developed for each sensor and also reduces the complexity and cost associated with calibrating fluid property predictive models. The method uses a computer-based method to generate the cross-sensor standardization model and applies it to the optical sensor data to predict fluid properties. The technical effect of this method is to improve the accuracy and efficiency of calibrating optical sensors in fluid analysis.

Problems solved by technology

The costs associated with fluid prediction model development and management affects how instrument standardization is performed.

Images