# US 12,595,727 B2 · Automatic interpretation of drilling dynamics data > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,595,727 B2 - Document ID: US12595727B2 - Status: Granted - Kind: B2 - Application number: 18/484,604 - Filed: 2023-10-11 - Published: 2024-02-01 - Granted: 2026-04-07 - Earliest claimed: 2018-05-15 - Assignees: Schlumberger Technology Corporation - Applicants: Schlumberger Technology Corporation - Inventors: Wei Chen; Yingwei Yu; Yuelin Shen; Zhengxin Zhang; Velizar Vesselinov - Web page: https://patentgrep.com/patent/US12595727B2 ## CPC - E21B 44/005: {Below-ground automatic control systems} - E21B 44/00: Automatic control systems specially adapted for drilling operations, i.e. self-operating systems which function to carry out or modify a drilling operation without intervention of a human operator, e.g. computer-controlled drilling systems; Systems specially adapted for monitoring a plurality of drilling variables or conditions - E21B 49/003: {by analysing drilling variables or conditions (E21B49/005 takes precedence; systems specially adapted for monitoring a plurality of drilling variables or conditions E21B44/00)} - G06F 18/254: {of classification results, e.g. of results related to same input data} - E21B 2200/20: Computer models or simulations, e.g. for reservoirs under production, drill bits - E21B 2200/22: Fuzzy logic, artificial intelligence, neural networks or the like - E21B: EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract A system and method that include receiving drilling dynamics data simulated by a processor and drilling dynamics data collected by a sensor positioned in a drilling tool and extracting a feature map based on a combination of the drilling dynamics data simulated by the processor and the drilling dynamics data collected by the sensor positioned in the drilling tool. The system and method additionally include determining a feature zone from the feature map. The system and method further include selecting a drilling parameter for a drill string based on the feature zone. ## Claims ### Claim 1 A method for interpreting drilling dynamics data, the method comprising: receiving multi-dimensional drilling dynamics data collected by a sensor positioned in a drilling tool; determining a feature zone from a feature map based on the multi-dimensional drilling dynamics data, wherein; the feature map comprises a two-dimensional representation of a plurality of points that encodes multi-dimensional drilling dynamics data; the feature zone includes a subset of the plurality of points within a polygon region in the two-dimensional representation of the feature map; the feature zone corresponds to a predetermined dynamic state associated with the received multi-dimensional drilling dynamics data; and the feature zone is determined using a supervised neural network trained to associate a plurality of feature zones with a plurality of dynamic states; and selecting at least one drilling parameter for a drill string based on the dynamic state corresponding to the determined feature zone. ### Claim 2 (depends on 1) The method of claim 1, wherein the multi-dimensional drilling dynamics data encoded by the feature map includes drilling dynamics data simulated by a processor including data associated with a simulation of a load on the drill string based on one or more predetermined rock formation characteristics. ### Claim 3 (depends on 1) The method of claim 1, wherein the multi-dimensional drilling dynamics data collected by the sensor positioned in the drilling tool includes at least one of: a first acceleration value, a second acceleration value, or a revolutions per minute value. ### Claim 4 (depends on 1) The method of claim 1, further comprising generating a machine learning algorithm based on the multi-dimensional drilling dynamics data, wherein the multi-dimensional drilling dynamics data includes drilling dynamics data simulated by a processor and drilling dynamics data collected by the sensor positioned in the drilling tool, and wherein the feature map is based upon an output from the machine learning algorithm. ### Claim 5 (depends on 1) The method of claim 1, wherein the two-dimensional representation is of a plurality of input data streams for a time window. ### Claim 6 (depends on 5) The method of claim 5, wherein the plurality of input data streams includes at least one of: a drill string acceleration in a horizontal direction, a drill string acceleration in a vertical direction, or a rotation of a drill string. ### Claim 7 (depends on 1) The method of claim 1, wherein the dynamic state corresponding to the feature zone comprises an axial movement of the drill string, a torsional movement of the drill string, or a lateral movement of the drill string. ### Claim 8 (depends on 1) The method of claim 1, wherein selecting the at least one drilling parameter includes selecting at least one of: a rotation of the drill string or a flow rate of the drill string. ### Claim 9 (depends on 1) The method of claim 1, wherein determining the feature zone further comprises applying a distance-based clustering constraint that assigns sensor data values to the feature zone only when a Euclidean distance between the sensor data values and a centroid of the feature zone satisfies a predetermined threshold. ### Claim 10 (depends on 1) The method of claim 1, wherein the multi-dimensional drilling dynamics data is encoded in the two-dimensional representation in the feature map based on a regression-based neural network configured to update centroid positions of clusters until assignment of sensor data values converges. ### Claim 11 A computing system for interpreting drilling dynamics data, the computing system comprising: one or more processors; and a memory system comprising one or more non-transitory computer-readable media storing instructions that, when executed by at least one of the one or more processors, cause the computing system to perform operations, the operations comprising: receiving multi-dimensional drilling dynamics data collected by a sensor positioned in a drilling tool; determining a feature zone from a feature map based on the multi-dimensional drilling dynamics data, wherein; the feature map comprises a two-dimensional representation of a plurality of points that encodes multi-dimensional drilling dynamics data; the feature zone includes a subset of the plurality of points within a polygon region in the two-dimensional representation of the feature map; the feature zone corresponds to a predetermined dynamic state associated with the received multi-dimensional drilling dynamics data; and the feature zone is determined using a supervised neural network trained to associate a plurality of feature zones with a plurality of dynamic states; and selecting at least one drilling parameter for a drill string based on the dynamic state corresponding to the determined feature zone. ### Claim 12 (depends on 11) The system of claim 11, wherein the multi-dimensional drilling dynamics data encoded by the feature map includes drilling dynamics data simulated by a processor including data associated with a simulation of a load on the drill string based on one or more predetermined rock formation characteristics. ### Claim 13 (depends on 11) The system of claim 11, wherein the multi-dimensional drilling dynamics data collected by the sensor positioned in the drilling tool includes at least one of: a first acceleration value, a second acceleration value, or a revolutions per minute value. ### Claim 14 (depends on 11) The system of claim 11, wherein the operations further comprise generating a machine learning algorithm based on the multi-dimensional drilling dynamics data, wherein the multi-dimensional drilling dynamics data includes drilling dynamics data simulated by a processor and drilling dynamics data collected by the sensor positioned in the drilling tool, and wherein the feature map is based upon an output from the machine learning algorithm. ### Claim 15 (depends on 11) The system of claim 11, wherein the two-dimensional representation is of a plurality of input data streams for a time window. ### Claim 16 (depends on 15) The system of claim 15, wherein the plurality of input data streams includes at least one of: a drill string acceleration in a horizontal direction, a drill string acceleration in a vertical direction, or a rotation of a drill string. ### Claim 17 (depends on 11) The system of claim 11, wherein the dynamic state corresponding to the feature zone comprises an axial movement of the drill string, a torsional movement of the drill string, or a lateral movement of the drill string. ### Claim 18 (depends on 11) The system of claim 11, wherein selecting the at least one drilling parameter includes selecting at least one of: a rotation of the drill string or a flow rate of the drill string. ### Claim 19 A non-transitory computer-readable medium storing instructions that, when executed by one or more processors of a computing system, cause the computing system to perform a method for interpreting drilling dynamics data, the method comprising: receiving multi-dimensional drilling dynamics data collected by a sensor positioned in a drilling tool; determining a feature zone from a feature map based on of the multi-dimensional drilling dynamics data, wherein: the feature map comprises a two-dimensional representation of a plurality of points that encodes multi-dimensional drilling dynamics data; the feature zone includes a subset of the plurality of points within a polygon region in the two-dimensional representation of the feature map; the feature zone corresponds to a predetermined dynamic state associated with the received multi-dimensional drilling dynamics data; and the feature zone is determined using a supervised neural network trained to associate a plurality of feature zones with a plurality of dynamic states; and selecting at least one drilling parameter for a drill string based on the dynamic state corresponding to the determined feature zone. ### Claim 20 (depends on 19) The non-transitory computer-readable medium of claim 19, wherein the dynamic state corresponding to the feature zone comprises an axial movement of the drill string, a torsional movement of the drill string, or a lateral movement of the drill string.