# US 8,786,288 B2 · Concentric buttons of different sizes for imaging and standoff correction > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 8,786,288 B2 - Document ID: US8786288B2 - Status: Granted - Kind: B2 - Application number: 13/212,624 - Filed: 2011-08-18 - Published: 2012-08-16 - Granted: 2014-07-22 - Earliest claimed: 2008-07-23 - Assignees: Baker Hughes Incorporated - Applicants: Matthias Gorek; Gregory B. Itskovich; Frank Daschner; Reinhard Knöchel; Assol Kavtorina - Inventors: Matthias Gorek; Gregory B. Itskovich; Alexandre N. Bespalov; Frank Daschner; Reinhard Knöchel - Web page: https://patentgrep.com/patent/US8786288B2 ## CPC - G01V 3/24: using AC - G01V: GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS (means for indicating the location of accidentally buried, e.g. snow-buried, persons A63B29/02) ## Abstract Disclosed is a method of estimating a property of an earth formation penetrated by a borehole. The method includes conveying a carrier through the borehole and performing a plurality of electrical measurements on the formation using a sensor disposed at the carrier and having a plurality of electrodes disposed in a concentric arrangement wherein a standoff distance between the sensor and a wall of the borehole has an influence on each electrical measurement in the plurality of electrical measurements. The method further includes determining an impedance for each electrical measurement in the plurality of electrical measurements and inputting the determined impedances into an artificial neural network implemented by a processor. The artificial neural network outputs the property wherein the outputted property compensates for the influence of sensor standoff distance on each electrical measurement in the plurality of electrical measurements. ## Claims ### Claim 1 A method of estimating a property of an earth formation penetrated by a borehole, the method comprising: conveying a carrier through the borehole; performing a plurality of electrical measurements on the formation using a sensor disposed at the carrier and having a plurality of electrodes disposed in a concentric arrangement wherein a standoff distance between the sensor and a wall of the borehole has an influence on each electrical measurement in the plurality of electrical measurements; determining an impedance for each electrical measurement in the plurality of electrical measurements; inputting each determined impedance into an artificial neural network implemented by a processor; and outputting the property from the artificial neural network wherein the outputted property compensates for the influence of sensor standoff distance on each electrical measurement in the plurality of electrical measurements. ### Claim 2 (depends on 1) The method as in claim 1, wherein the property is conductivity or resistivity. ### Claim 3 (depends on 1) The method as in claim 1, wherein the sensor comprises a central electrode surrounded concentrically by a ring electrode. ### Claim 4 (depends on 3) The method as in claim 3, wherein the ring electrode comprises a plurality of ring electrodes. ### Claim 5 (depends on 4) The method as in claim 4, wherein performing a plurality of electrical measurements comprises applying a voltage Vat frequency f to the central electrode. ### Claim 6 (depends on 5) The method as in claim 5, wherein performing a plurality of electrical measurements further comprises applying the voltage V at frequency f to one or more of the ring electrodes. ### Claim 7 (depends on 6) The method as in claim 6, wherein performing a plurality of electrical measurements further comprises switching one or more ring electrodes in the plurality of ring electrodes that concentrically surround the central electrode to ground or float using electrical switches that are configured to apply voltage to various combinations of the ring electrodes. ### Claim 8 (depends on 6) The method as in claim 6, wherein the frequency f comprises multiple frequencies. ### Claim 9 (depends on 1) The method as in claim 1, wherein each determined impedance comprises a real part and an imaginary part. ### Claim 10 (depends on 1) The method as in claim 1, further comprising training the artificial neural network by inputting a plurality of data sets into the artificial neural network each data set in the plurality of data sets comprising electrical data associated with a standoff value. ### Claim 11 (depends on 1) The method as in claim 1, further comprising adjusting the artificial network to reduce a difference between root mean square error of calibration data sets and root mean square error of validation data sets. ### Claim 12 An apparatus for estimating a property of an earth formation penetrated by a borehole, the apparatus comprising: a carrier configured to be conveyed through the borehole; a sensor disposed at the carrier and comprising a plurality of electrodes disposed in a concentric arrangement, the sensor being configured to perform a plurality of electrical measurements on the formation wherein a standoff distance between the sensor and a wall of the borehole has an influence on each electrical measurement in the plurality of electrical measurements; a processor coupled to the sensor and configured to receive the plurality of electrical measurements for determining an impedance for each electrical measurement, the processor comprising an artificial neural network configured to receive each determined impedance and to output the property wherein the outputted property compensates for the influence of sensor standoff distance on each electrical measurement in the plurality of electrical measurements. ### Claim 13 (depends on 12) The apparatus as in claim 12, wherein the sensor comprises a central electrode and surrounded concentrically by a ring electrode. ### Claim 14 (depends on 13) The apparatus as in claim 13, wherein the ring electrode comprises a plurality of ring electrodes. ### Claim 15 (depends on 14) The apparatus as in claim 14, further comprising a power source configured to apply a voltage Vat a frequency f to the central electrode. ### Claim 16 (depends on 15) The apparatus as in claim 15, further comprising one or more switches configured to apply the voltage V at the frequency f from the power source to various combinations of one or more selected ring electrodes that concentrically surround the central electrode. ### Claim 17 (depends on 16) The apparatus as in claim 16, wherein the one or more switches are further configured to switch the one or more selected ring electrodes to ground or float. ### Claim 18 (depends on 12) The apparatus as in claim 12, wherein the property is conductivity or resistivity. ### Claim 19 (depends on 18) The apparatus as in claim 18, wherein the conductivity or resistivity is presented as an image of the borehole. ### Claim 20 (depends on 12) The apparatus as in claim 12, wherein the artificial neural network comprises an input layer, a hidden layer, and an output layer, the hidden layer comprising at least sixteen neurons. ### Claim 21 (depends on 12) The apparatus as in claim 12, where in the carrier comprises a wireline, a slickline, a drill string or coiled tubing. ### Claim 22 A non-transitory computer readable medium comprising computer executable instructions for estimating a property of an earth formation penetrated by a borehole by implementing a method comprising: performing a plurality of electrical measurements on the formation using a sensor disposed at the carrier and having a plurality of electrodes disposed in a concentric arrangement wherein a standoff distance between the sensor and a wall of the borehole has an influence on each electrical measurement in the plurality of electrical measurements; determining an impedance for each electrical measurement in the plurality of electrical measurements; inputting each determined impedance into an artificial neural network implemented by a processor; and outputting the property from the artificial neural network wherein the outputted property compensates for the influence of sensor standoff distance on each electrical measurement in the plurality of electrical measurements. ### Claim 23 (depends on 1) The method as in claim 1, wherein the artificial neural network comprises a non-linear activation function that is a Tan-Sigmoid transfer function.