Bp Exploration Operating Company Limited

Lytt Limited

Cambridge Enterprise Limited

Earzz Limited

Pradyumna Thiruvenkatanathan

Tommy Langnes

Ashwin Arunkuman Seshia

James Crofton Ramsay

Çagri Cerrahoglu

Cagri Cerrahoglu

Xudong Zou

Jize Yan

Ashwin Arunkumar Seshia

Guy Spyropoulos

Anindya Moitra

Ashwin A Seshia

James Ramsay

A method of identifying events within a wellbore comprises obtaining a first set of measurements of a first signal within a wellbore, identifying one or more events within the wellbore using the first set of measurements, obtaining a second set of measurements of a second signal within the wellbore, wherein the first signal and the second signal represent different physical measurements, training one or more event models using the second set of measurements and the identification of the one or more events as inputs, and using the one or more event models to identify at least one additional event within the wellbore.

Event model training using in situ data

A data processing system for identifying an audio signal includes an audio sensor, a receiver module, a signal recognition module, and a receiver device. The receiver module receives audio data from the audio sensor. The receiver module transmits the audio data to the signal recognition module. The signal recognition module calculates time-varying vector arrays of octave band energies, and/or of fractional octave band energies, and calculates time-varying vector arrays of Mel-Frequency Cepstral Coefficients (MFCC) values based on the received audio data. The signal recognition module generates audio feature image data based on the vector arrays. The signal recognition module includes binary classifier machine learning models and inference models to identify the audio signal based on the generated audio feature image data. The signal recognition module transmits a notification message to the receiver device.

Method for identifying an audio signal

A method of presenting sensor data can include receiving a request for data to be displayed on a display area of a display device, determining a data distribution per pixel within the display area for both the first axis and the second axis based on the pixel resolution, the first output range, and the second output range, fitting the data distribution per pixel for data associated with the first axis to provide first axis fitted data, fitting the data distribution per pixel for data associated with the second axis to provide second axis fitted data, and sending the first axis fitted data and the second axis fitted data. The request comprises a pixel resolution of the display area, a first output range of the data along a first axis, and a second output range of the data along a second axis.

Sensor data visualization and related systems and methods

A method of developing a predictive model for sand production from a wellbore includes receiving an indication of sand ingress at one or more production zones within a first wellbore using a sand monitoring system disposed within the first wellbore, detecting, using a pressure monitoring system, a pressure within the first wellbore while producing the one or more fluids and detecting the sand ingress, determining one or more geophysical properties of the one or more production zones of the first wellbore, and determining a model that correlates sand ingress at each of the one or more production zones with a plurality of variables. The sand ingress occurs while producing one or more fluids from the first wellbore.

Systems and methods for sand ingress prediction for subterranean wellbores

A monitoring system includes a flow line, an optical fiber coupled to the flow line, and a receiver coupled to an end of the optical fiber. The receiver is configured to detect at least one acoustic signal from the optical fiber. In addition, the monitoring system includes processor unit to detect a flow obstruction within the flow line based on the acoustic signal.

Detecting flow obstruction events within a flow line using acoustic frequency domain features

A method of identifying inflow locations along a wellbore includes obtaining an acoustic signal from a sensor within the wellbore, determining a plurality of frequency domain features from the acoustic signal, and identifying, using a plurality of fluid flow models, a presence of at least one of a gas phase inflow, an aqueous phase inflow, or a hydrocarbon liquid phase inflow at one or more fluid flow locations. The acoustic signal includes acoustic samples across a portion of a depth of the wellbore, and the plurality of frequency domain features are obtained across a plurality of depth intervals within the portion of the depth of the wellbore. Each fluid flow model of the plurality of fluid inflow models uses one or more frequency domain features of the plurality of the frequency domain features, and at least two of the plurality of fluid flow models are different.

DAS data processing to identify fluid inflow locations and fluid type

A method of detecting an event by: obtaining a first sample data set; determining a frequency domain feature(s) of the first sample data set over a first time period; determining a first threshold for the a frequency domain feature(s) using the first sample data set; determining that the frequency domain feature(s) matches the first threshold; determining the presence of an event during the first time period based on determining that the frequency domain feature(s) matches the first threshold; obtaining a second sample data set; determining a frequency domain feature(s) of the second sample data set over a second time period; determining a second threshold for the frequency domain feature(s) using the second sample data set; determining that the frequency domain feature(s) matches the second threshold; and determining the presence of the event during the second time period based on determining that the frequency domain feature(s) matches the second threshold.

Distributed acoustic sensing autocalibration

A method of detecting sand inflow into a wellbore is disclosed. The method can include obtaining a sample data set, detecting a broadband signal within the sample data set, comparing the broadband signal with a signal reference, determining that the broadband signal meets or exceeds the signal reference, and determining the presence of sand inflow into the wellbore based on determining that the broadband signal meets or exceeds the signal reference. The sample data set can be a sample of an acoustic signal originating within a wellbore including a fluid, and the broadband signal at least includes a portion of the sample data set at frequencies above 0.5 kHz.

Detecting downhole sand ingress locations

A method of determining fluid inflow rates within a wellbore comprises determining a plurality of temperature features from a distributed temperature sensing signal originating in a wellbore, determining one or more frequency domain features from an acoustic signal originating the wellbore, and using at least one temperature feature of the plurality of temperature features and at least one frequency domain feature of the one or more frequency domain features to determine a fluid inflow rate at one or more locations along the wellbore.

Fluid inflow characterization using hybrid DAS/DTS measurements

A method of monitoring fluid outflow along a wellbore includes obtaining an acoustic signal from a sensor within the wellbore, determining one or more frequency domain features from the acoustic signal, and identifying one or more fluid outflow locations along the portion of the depth of the wellbore using the one or more frequency domain features. The acoustic signal includes acoustic samples across a portion of a depth of the wellbore.

Systems and methods for subterranean fluid flow characterization

A system for processing acoustic data to identify an event includes a receiver unit including a processor and a memory. The receiver unit is configured to receive a signal from a sensor disposed along a sensor path or across a sensor area. A processing application is stored in the memory. The processing application, when executed on the processor, configures the processor to: receive the signal from the sensor, where the signal includes an indication of an acoustic signal received at one or more lengths along the sensor path or across a portion of the sensor area and the signal is indicative of the acoustic signal across a frequency spectrum; determine a plurality of frequency domain features of the signal across the frequency spectrum; and generate an output comprising the plurality of frequency domain features.

Detecting events using acoustic frequency domain features

A method of detecting an event within a wellbore includes obtaining a sample data set, determining a plurality of frequency domain features of the sample data set, comparing the plurality of frequency domain features with an event signature, determining that the plurality of frequency domain features matches the thresholds, ranges, or both of the event signature, and determining the presence of the event within the wellbore based on determining that the plurality of frequency domain features match the thresholds, ranges, or both of the event signature. The sample data set is a sample of an acoustic signal originating within a wellbore including a fluid. The sample data set is representative of the acoustic signal across a frequency spectrum. The event signature includes a plurality of thresholds, ranges, or both corresponding to the plurality of frequency domain features.

Detecting downhole events using acoustic frequency domain features

A method of detecting sand ingress within a wellbore includes obtaining a sample data set, determining a plurality of frequency domain features of the sample data set over a plurality of depth ranges, determining a presence of sand ingress at a first depth range of the plurality of depth ranges within the wellbore based on determining that the plurality of frequency domain features over the first depth range match a sand ingress signature, and determining a presence of sand migration along a second depth range of the plurality of depths within the wellbore based on determining that the plurality of frequency domain features over the second depth range match a sand migration signature. The sample data set is a sample of an acoustic signal originating within a wellbore including a fluid. The sample data set is representative of the acoustic signal across a frequency spectrum.

Growing community of inventors

London, United Kingdom

Pradyumna Thiruvenkatanathan