Distributed acoustic sensing data analysis system

• US 9,430,507 B2
• Filed: 12/07/2015
• Issued: 08/30/2016
• Est. Priority Date: 12/08/2014
• Status: Active Grant

• Current Assignee: Palantir Technologies Incorporated
• Original Assignee: Palantir Technologies Incorporated
• Inventors: Stowe, Geoff, Shankar, Ankit, Rogers, Chris, Cappellacci, Benedict, Sparling, Kimberly, Lemanowicz, Lucas, McRaven, John, Pettit, Andrew
• Primary Examiner(s): Woo, Isaac M
• Application Number:
  US14/961,481
• Publication Number:
  US 20160162519A1
• Time in Patent Office: 267 Days
• Field of Search: 707600-899
• US Class Current: 1/1
• CPC Class Codes: E21B 47/135 using light waves, e.g. infrared or ultraviolet waves
• CPC Class Codes: G01V 1/226 Optoseismic systems
• CPC Class Codes: G01V 1/247 Digital recording of seismic data, e.g. in acquisition units or nodes
• CPC Class Codes: G06F 16/217 Database tuning G06F16/2282 takes precedence; database performance monitoring G06F11/3409
• CPC Class Codes: G06F 16/2423 Interactive query statement specification based on a database schema
• CPC Class Codes: G06F 16/284 Relational databases
• CPC Class Codes: G06F 17/40 Data acquisition and logging for input to computer G06F3/00

Abstract

Various systems and methods are provided that retrieve data measured by various sensors associated with a sensor collection site and compress the retrieved data so that the compressed data can be transported to and stored in one or more databases in an efficient manner. The various systems and methods may further retrieve the data stored in the one or more databases and generate an interactive user interface to display the data. While each instance of measured data may include a plurality of parameters, the various systems and methods may flatten the measured data such that information pertaining to each parameter can be displayed in a two-dimensional graph. Features may be extracted from the stored data to identify events that have occurred or that may occur in the future during operation of the sensor collection site such that a user can take appropriate action.

Claims

1. A computing system configured to access one or more databases in substantially real-time in order to determine information related to measured data points and provide the determined information to a user in an interactive user interface, the computing system comprising:

one or more computer processors;

a database storing compressed sensor values; and

a computer readable storage medium storing program instructions configured for execution by the one or more computer processor in order to cause the computing system to;

receive raw sensor values from a plurality of sensors located at various depths in a physical structure, wherein the raw sensor values correspond to a first number of values a second;

bin the received raw sensor values such that the binned raw sensor values correspond to a second number of values a second, wherein the second number is less than the first number;

aggregate the binned sensor values, wherein the aggregated binned sensor values comprise a plurality of rows, and wherein each row in the plurality of rows comprises a time value, a depth value, a frequency range, and an amplitude;

traverse each row in the plurality of rows and place a representation of the time value in the respective row in a first row;

traverse each row in the plurality of rows and place the depth value in the respective row in a second row;

traverse each row in the plurality of rows and place the frequency range in the respective row in a third row;

traverse each row in the plurality of rows and place the amplitude in the respective row in a fourth row;

compress the first row, the second row, the third row, and the fourth row to generate compressed sensor values;

access the compressed sensor values from the database; and

generate user interface data for rendering the interactive user interface on a computing device, wherein the interactive user interface displays a representation of one or more of the compressed sensor values.

2. The computing system of claim 1, wherein the computer readable storage medium further stores program instructions that cause the computing system to for each time value in the first row after a first time value in the first row, identify a difference between a previous time value in the first row and the respective time value, wherein the representation of the respective time value comprises the identified difference.

3. The computing system of claim 2, wherein the computer readable storage medium further stores program instructions that cause the computing system to:

determine that each identified difference in the first row is a same value; and

replace all of the identified differences in the first row with the determined same value.

4. The computing system of claim 1, wherein the computer readable storage medium further stores program instructions that cause the computing system to zip the first row, the second row, the third row, and the fourth row to generate the compressed sensor values.

5. The computing system of claim 1, wherein the interactive user interface includes a first container and a second container, wherein the first container includes a list of selectable frequency ranges and the second container includes a graph, wherein each frequency range in the list of selectable frequency ranges corresponds to an octave at which the plurality of sensors detect sound, wherein the graph identifies a plurality of time intervals and a plurality of depth ranges, wherein the time value associated with each compressed sensor value corresponds with a time interval in the plurality of time intervals, wherein the depth value associated with each compressed sensor value corresponds with a depth range in the plurality of depth ranges, and wherein the computer readable storage medium further stores program instructions that cause the computing system to:

receive an identification of a selection by the user of a first frequency range within the list of selectable frequency ranges; and

for each time interval, frequency range, and depth range,

determine a variation in amplitudes of compressed sensor values,

based on the determined variations in amplitudes, determine one or more tiles having one or more characteristics indicating the determined variation in amplitudes, and

display the one or more tiles in the graph.

6. The computing system of claim 5, wherein each time indicates a single determined amplitude, and wherein the one or more tiles are shaded according to a value of the respective determined amplitude.

7. The computing system of claim 5, wherein the computer readable storage medium further stores program instructions that cause the computing system to:

receive an identification of a selection by the user of an outlier button;

compute a mean and standard deviation of the determined variation in amplitudes associated with the first frequency range; and

display the one or more tiles in the graph that have a characteristic indicating the determined variation in amplitudes exceeds two standard deviations from the computed mean.

8. The computing system of claim 5, wherein the computer readable storage medium further stores program instructions that cause the computing system to:

receive an identification of a selection by the user of an octave button;

compute a mean and standard deviation of the determined variation in amplitudes associated with each frequency range in the list of selectable frequency ranges; and

display the one or more tiles in the graph that have a characteristic indicating the determined variation in amplitudes exceeds two standard deviations from the computed mean over the first depth range and the first time period.

9. The computing system of claim 5, wherein the interactive user interface includes a third container that comprises a representation of equipment associated with the plurality of sensors, and wherein the representation of the equipment is located adjacent to the second container such that the representation corresponds with depth values in the first depth range.

10. The computing system of claim 5, wherein the computer readable storage medium further stores program instructions that cause the computing system to:

receive an identification of a selection by the user of a point of interest button;

compute a mean and standard deviation of the determined amplitudes associated with each frequency range in the list of selectable frequency ranges;

determine a second depth range within the first depth range and a second time period within the first time period in which the determined amplitudes exceed the standard deviation for a threshold time period;

retrieve event information from an event database for events that occurred during the second time period within the second depth range; and

update the user interface data such that the interactive user interface includes a third container that comprises the event information and such that the graph includes a marker identifying the one or more tiles that are located within the second time period and the second depth range.

11. The computing system of claim 10, wherein the computer readable storage medium further stores program instructions that cause the computing system to identify acoustic signatures based on the determined amplitudes that exceed the standard deviation for the threshold time period.

12. The computing system of claim 10, wherein the computer readable storage medium further stores program instructions that cause the computing system to identify thermal signatures based on the determined amplitudes that exceed the standard deviation for the threshold time period.

13. The computing system of claim 1, wherein the plurality of sensors extract at least one of acoustic data or temperature data from the physical apparatus.

14. A computer-implemented method comprising:

as implemented by one or more computer systems comprising computer hardware and memory, the one or more computer systems configured with specific executable instructions,

receiving raw sensor values from a plurality of sensors located at various depths in a physical structure, wherein the raw sensor values correspond to a first number of values a second;

binning the received raw sensor values such that the binned raw sensor values correspond to a second number of values a second, wherein the second number is less than the first number;

aggregating the binned sensor values, wherein the aggregated binned sensor values comprise a plurality of rows, and wherein each row in the plurality of rows comprises a time value, a depth value, a frequency range, and an amplitude;

traversing each row in the plurality of rows and place a representation of the time value in the respective row in a first row;

traversing each row in the plurality of rows and place the depth value in the respective row in a second row;

traversing each row in the plurality of rows and place the frequency range in the respective row in a third row;

traversing each row in the plurality of rows and place the amplitude in the respective row in a fourth row;

compressing the first row, the second row, the third row, and the fourth row to generate compressed sensor values;

accessing the compressed sensor values from the database; and

generating user interface data for rendering an interactive user interface on a computing device, wherein the interactive user interface displays a representation of one or more of the compressed sensor values.

15. The method of claim 14, further comprising for each time value in the first row after a first time value in the first row, identify a difference between a previous time value in the first row and the respective time value, wherein the representation of the respective time value comprises the identified difference.

16. The method of claim 15, further comprising:

determining that each identified difference in the first row is a same value; and

replacing all of the identified differences in the first row with the determined same value.

17. The method of claim 14, wherein compressing the first row, the second row, the third row, and the fourth row further comprises zipping the first row, the second row, the third row, and the fourth row to generate the compressed sensor values.

18. The method of claim 14, wherein the interactive user interface includes a first container and a second container, wherein the first container includes a list of selectable frequency ranges and the second container includes a graph, wherein each frequency range in the list of selectable frequency ranges corresponds to an octave at which the plurality of sensors detect sound, wherein the graph identifies a plurality of time intervals and a plurality of depth ranges, wherein the time value associated with each compressed sensor value corresponds with a time interval in the plurality of time intervals, wherein the depth value associated with each compressed sensor value corresponds with a depth range in the plurality of depth ranges, and wherein the method further comprises:

receiving an identification of a selection by the user of a first frequency range within the list of selectable frequency ranges; and

for each time interval, frequency range, and depth range,

determining a variation in amplitudes of compressed sensor values,

based on the determined variations in amplitudes, determining one or more tiles having one or more characteristics indicating the determined variation in amplitudes, and

displaying the one or more tiles in the graph.

19. The method of claim 18, further comprising:

receiving an identification of a selection by the user of an outlier button;

computing a mean and standard deviation of the determined variation in amplitudes associated with the first frequency range; and

displaying the one or more tiles in the graph that have a characteristic indicating the determined variation in amplitudes exceeds two standard deviations from the computed mean.

20. The method of claim 18, further comprising:

receiving an identification of a selection by the user of an octave button;

computing a mean and standard deviation of the determined variation in amplitudes associated with each frequency range in the list of selectable frequency ranges; and

displaying the one or more tiles in the graph that have a characteristic indicating the determined variation in amplitudes exceeds two standard deviations from the computed mean over the first depth range and the first time period.