# US 11,441,556 B2 · Utilizing analytical models to identify wells in which to install plunger lift for improved well production > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,441,556 B2 - Document ID: US11441556B2 - Status: Granted - Kind: B2 - Application number: 16/382,573 - Filed: 2019-04-12 - Published: 2020-10-15 - Granted: 2022-09-13 - Earliest claimed: 2019-04-12 - Assignees: Accenture Global Solutions Limited - Applicants: Accenture Global Solutions Limited - Inventors: Susarla Aditya; Subrahmanyam Vadrevu; Rabinarayan Mishra; Sangameshwar Kardkal; Anusha K K; Jitender G. Singh - Web page: https://patentgrep.com/patent/US11441556B2 ## CPC - E21B 43/121: {Lifting well fluids (monitoring of down-hole pump systems E21B47/008)} - F04B 47/12: having free plunger lifting the fluid to the surface - E21B 41/00: Equipment or details not covered by groups E21B15/00 - E21B40/00 - E21B 43/13: {specially adapted to dewatering of wells of gas producing reservoirs, e.g. methane producing coal beds} - F04B 41/02: having reservoirs - F04B 51/00: Testing machines, pumps, or pumping installations - G06F 16/909: using geographical or spatial information, e.g. location (spatiotemporally dependent retrieval from the web G06F16/9537) - G06N 3/0499: Feedforward networks - G06N 3/08: Learning methods - G06N 3/09: Supervised learning - G06N 7/00: Computing arrangements based on specific mathematical models - 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 - F04B: POSITIVE-DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS (machines for liquids, or pumps, of rotary-piston or oscillating-piston type F04C; non-positive-displacement pumps F04D; pumping of fluid by direct contact of another fluid or by using inertia of fluid to be pumped F04F) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A device receives first well data associated with first wells where plunger lift is installed, and receives second well data associated with a candidate well where plunger lift is not installed. The device processes the first well data to determine pre-plunger lift installation data associated with the first wells, and processes the first well data and the pre-plunger lift installation data to determine a set of performing wells and a set of underperforming wells, of the first wells. The device processes the second well data and data associated with the set of performing wells to determine a first metric associated with the candidate well, and processes the second well data and data associated with the set of underperforming wells to determine a second metric associated with the candidate well. The device determines whether to install plunger lift in the candidate well based on the first metric and the second metric. ## Claims ### Claim 1 A method, comprising: receiving, by a device, first well data associated with first wells where plunger lift is installed; training, by the device, one or more analytical models with the first well data to generate one or more trained analytical models; receiving, by the device, second well data associated with second wells where plunger lift is installed, wherein the second wells are located within a geographical area; receiving, by the device, third well data associated with a candidate well where plunger lift is not installed, wherein the candidate well is located within the geographical area, and wherein the candidate well is a candidate for plunger lift installation; processing, by the device, the second well data, with the one or more trained analytical models, to determine pre-plunger lift installation data associated with the second wells; processing, by the device, the second well data and the pre-plunger lift installation data, with the one or more trained analytical models, to determine a set of performing wells, of the second wells, and a set of underperforming wells of the second wells; processing, by the device, the third well data and data associated with the set of performing wells, with the one or more trained analytical models, to determine a first metric associated with the candidate well; processing, by the device, the third well data and data associated with the set of underperforming wells, with the one or more trained analytical models, to determine a second metric associated with the candidate well; determining, by the device, whether to install plunger lift in the candidate well based on the first metric and the second metric; and performing, by the device, one or more actions based on determining whether to install plunger lift in the candidate well, wherein the one or more actions include: causing a plunger to be ordered, dispatching, when the plunger is received, equipment to the candidate well, and causing the plunger lift to be installed in the candidate well. ### Claim 2 (depends on 1) The method of claim 1, wherein performing the one or more actions includes one or more of: providing, to a client device, information indicating whether to install plunger lift in the candidate well; or retraining the one or more analytical models based on the information indicating whether to install plunger lift in the candidate well. ### Claim 3 (depends on 1) The method of claim 1, wherein processing the second well data, with the one or more trained analytical models, to determine the pre-plunger lift installation data comprises: performing a correlation analysis on the second well data to determine a correlation between parameters of the second well data; performing, based on the correlation between the parameters, a decision tree analysis on the second well data to determine particular parameters of the parameters of the second well data; and determining the pre-plunger lift installation data based on the particular parameters. ### Claim 4 (depends on 1) The method of claim 1, wherein processing the second well data and the pre-plunger lift installation data, with the one or more trained analytical models, to determine the set of performing wells and the set of underperforming wells comprises: grouping a portion of the second wells into the set of performing wells based on particular parameters associated with the second well data; and grouping a remaining portion of the second wells into the set of underperforming wells based on the particular parameters associated with the second well data. ### Claim 5 (depends on 1) The method of claim 1, wherein processing the third well data and data associated with the set of performing wells, with the one or more trained analytical models, to determine the first metric associated with the candidate well comprises: calculating a first centroid associated with the set of performing wells based on the data associated with the set of performing wells; and calculating a first Euclidean distance between particular parameters associated with the third well data and the first centroid associated with the set of performing wells, wherein the first Euclidean distance is the first metric. ### Claim 6 (depends on 5) The method of claim 5, wherein processing the third well data and data associated with the set of underperforming wells, with the one or more trained analytical models, to determine the second metric associated with the candidate well comprises: calculating a second centroid associated with the set of underperforming wells based on the data associated with the set of underperforming wells; and calculating a second Euclidean distance between particular parameters associated with the third well data and the second centroid associated with the set of underperforming wells, wherein the second Euclidean distance is the second metric. ### Claim 7 (depends on 6) The method of claim 6, wherein determining whether to install plunger lift in the candidate well based on the first metric and the second metric comprises: determining that plunger lift is to be installed in the candidate well when the first Euclidean distance is less than or equal to the second Euclidean distance; and determining that plunger lift is not to be installed in the candidate well when the first Euclidean distance is greater than the second Euclidean distance. ### Claim 8 A device, comprising: one or more memories; and one or more processors, communicatively coupled to the one or more memories, to: receive one or more trained analytical models, wherein the one or more trained analytical models are trained with: first well data associated with first wells where plunger lift is installed; receive second well data associated with second wells where plunger lift is installed, wherein the second wells are located within a geographical area; receive third well data associated with a candidate well where plunger lift is not installed, wherein the candidate well is located within the geographical area, and wherein the candidate well is a candidate for plunger lift installation; process the second well data, with the one or more trained analytical models, to determine pre-plunger lift installation data associated with the second wells; process the second well data and the pre-plunger lift installation data, with the one or more trained analytical models, to determine a set of performing wells, of the second wells, and a set of underperforming wells of the second wells; process the third well data and data associated with the set of performing wells, with the one or more trained analytical models, to determine a first metric associated with the candidate well; process the third well data and data associated with the set of underperforming wells, with the one or more trained analytical models, to determine a second metric associated with the candidate well; determine that plunger lift is to be installed in the candidate well based on the first metric and the second metric; and perform one or more actions based on determining that plunger lift is to be installed in the candidate well, wherein the one or more processors, to perform the one or more actions, are to: cause a plunger to be ordered, dispatch, when the plunger is received, equipment to the candidate well, and cause the plunger lift to be installed in the candidate well. ### Claim 9 (depends on 8) The device of claim 8, wherein the first well data includes data identifying one or more of: reservoir pressures associated with the first wells, casing pressures associated with the first wells, tubing pressures associated with the first wells, line pressures associated with the first wells, bottom hole pressures associated with the first wells, production rates associated with the first wells, deferments associated with the first wells, drawdowns associated with the first wells, production volumes associated with the first wells, production efficiencies associated with the first wells, or well depths associated with the first wells. ### Claim 10 (depends on 8) The device of claim 8, wherein the one or more processors are further to: determine a probability of increasing production of the candidate well when plunger lift is installed in the candidate well; and provide information indicating the probability of increasing the production of the candidate well. ### Claim 11 (depends on 8) The device of claim 8, wherein the one or more processors are further to: determine an expected increase in production of the candidate well when plunger lift is installed in the candidate well; provide, to a client device, information indicating the expected increase in the production of the candidate well; receive, from the client device, a response indicating that plunger lift is to be installed in the candidate well; and cause plunger lift to be installed in the candidate well based on the response. ### Claim 12 (depends on 8) The device of claim 8, wherein the one or more processors, when processing the second well data and the pre-plunger lift installation data, with the one or more trained analytical models, to determine the set of performing wells and the set of underperforming wells, are to: group a portion of the second wells into the set of performing wells based on a first production performance calculation associated with the portion of the second wells; and group a remaining portion of the third wells into the set of underperforming wells based on a second production performance calculation associated with the remaining portion of the second wells. ### Claim 13 (depends on 8) The device of claim 8, wherein the set of performing wells, of the second wells, and the set of underperforming wells, of the second wells, are determined based on parameters associated with the second well data rather than the geographical area associated with the second wells. ### Claim 14 (depends on 8) The device of claim 8, wherein the first wells and the second wells comprise at least one of: gas wells, or liquid wells. ### Claim 15 A non-transitory computer-readable medium storing instructions, the instructions comprising: one or more instructions that, when executed by one or more processors, cause the one or more processors to: receive first well data associated with first wells where plunger lift is installed, wherein the first wells are located within a geographical area; receive second well data associated with a candidate well where plunger lift is not installed, wherein the candidate well is located within the geographical area, and wherein the candidate well is a candidate for plunger lift installation; process the first well data, with a first model and a second model, to determine pre-plunger lift installation data associated with the first wells; process the first well data and the pre-plunger lift installation data, with a third model, to determine a set of performing wells, of the first wells, and a set of underperforming wells of the first wells; process the second well data and data associated with the set of performing wells, with a fourth model, to determine a first metric associated with the candidate well; process the second well data and data associated with the set of underperforming wells, with the fourth model, to determine a second metric associated with the candidate well; determine whether to install plunger lift in the candidate well based on the first metric and the second metric; and perform one or more actions based on determining whether to install plunger lift in the candidate well, wherein the one or more instructions, that cause the one or more processors to perform the one or more actions, cause the one or more processors to: cause a plunger to be ordered, dispatch, when the plunger is received, equipment to the candidate well, and cause the plunger lift to be installed in the candidate well. ### Claim 16 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein: the first model includes a correlation analysis model, the second model includes a decision tree analysis model, the third model includes a clustering model, and the fourth model includes a Euclidean distance calculation model. ### Claim 17 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the set of performing wells, of the first wells, and the set of underperforming wells, of the first wells, are determined based on parameters associated with the first well data rather than the geographical area associated with the first wells. ### Claim 18 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the one or more instructions, that cause the one or more processors to process the second well data and data associated with the set of performing wells, with the fourth model, to determine the first metric associated with the candidate well, cause the one or more processors to: calculate a first centroid associated with the set of performing wells based on the data associated with the set of performing wells; and calculate a first Euclidean distance between particular parameters associated with the second well data and the first centroid associated with the set of performing wells, wherein the first Euclidean distance is the first metric. ### Claim 19 (depends on 18) The non-transitory computer-readable medium of claim 18, wherein the one or more instructions, that cause the one or more processors to process the second well data and data associated with the set of underperforming wells, with the fourth model, to determine the second metric associated with the candidate well, cause the one or more processors to: calculate a second centroid associated with the set of underperforming wells based on the data associated with the set of underperforming wells; and calculate a second Euclidean distance between particular parameters associated with the second well data and the second centroid associated with the set of underperforming wells, wherein the second Euclidean distance is the second metric. ### Claim 20 (depends on 19) The non-transitory computer-readable medium of claim 19, wherein the one or more instructions, that cause the one or more processors to determine whether to install plunger lift in the candidate well based on the first metric and the second metric, cause the one or more processors to: determine that plunger lift is to be installed in the candidate well when the first Euclidean distance is less than or equal to the second Euclidean distance; and determine that plunger lift is not to be installed in the candidate well when the first Euclidean distance is greater than the second Euclidean distance.