Abstract: A downhole tool including at least one transmitter, a receiver array, and a controller. Each receiver element of the receiver array is configured to apply variable amplification and a variable time delay to detected acoustic waveforms, wherein the variable amplification is controlled by an amplification factor assigned to the given receiver element, and wherein the variable time delay is controlled by a time delay assigned to the given receiver element. The controller assigns a set of amplification factors and time delays to the receiver elements of the receiver array and combines signals resulting from the application of the variable amplification and the variable time delay to the detected acoustic waveforms such that sensitivity of the receiver elements of the receiver array is focused at a desired zone-of-interest in a wellbore corresponding to the set of amplification factors and time delays assigned to the receiver elements of the receiver array.

Abstract: A sonic tool is activated in a well having multiple casings and annuli surrounding the casing. Detected data is preprocessed using slowness time coherence (STC) processing to obtain STC data. The STC data is provided to a machine learning module which has been trained on labeled STC data. The machine learning module provides an answer product regarding the states of the borehole annuli which may be used to make decision regarding remedial action with respect to the borehole casings. The machine learning module may implement a convolutional neural network (CNN), a support vector machine (SVM), or an auto-encoder.

Abstract: A method and downhole tool is provided that uses beamforming to localize acoustic energy at a desired zone-of-interest within a wellbore traversing a subterranean formation. The tool has an array of transmitter elements configured to emit guided mode acoustic signals at variable amplitude and variable time delay, which are individually controlled by an amplitude factor and time delay assigned to respective transmitter elements. A set of amplitude factors and time delays can be assigned to the transmitter elements of the transmitter array such that the transmitter elements produce a focused acoustic beam at the desired zone-of-interest by combination of guided mode acoustic signals transmitted by the transmitter elements.

Abstract: A method for estimating all five transversely-isotropic (TI)-elastic constants using borehole sonic data obtained from at least one subterranean borehole in a transversely isotropic formation. In an embodiment, the method includes: solving for a quasi-compressional qP-wave velocity VqP using inversion algorithms based on exact solutions of the Kelvin-Christoffel equations for plane wave velocities in arbitrarily anisotropic formations, where the five TI-elastic constants may include C11, C13, C33, C55, and C66.

Abstract: A method, computer program product, and computing system are provided for receiving sonic data associated with an inner casing of a well. Predicted ultrasonic data associated with an outer casing of the well may be generated based upon, at least in part, a nonlinear regression model and the received sonic data associated with the inner casing of the well.

Abstract: A method and downhole tool is provided that uses beamforming to localize acoustic energy at a desired zone-of-interest within a wellbore traversing a subterranean formation. The tool has an array of transmitter elements configured to emit guided mode acoustic signals at variable amplitude and variable time delay, which are individually controlled by an amplitude factor and time delay assigned to respective transmitter elements. A set of amplitude factors and time delays can be assigned to the transmitter elements of the transmitter array such that the transmitter elements produce a focused acoustic beam at the desired zone-of-interest by combination of guided mode acoustic signals transmitted by the transmitter elements.

Abstract: A sonic tool is activated in a well having multiple casings and annuli surrounding the casing. Detected data is preprocessed using slowness time coherence (STC) processing to obtain STC data. The STC data is provided to a machine learning module which has been trained on labeled STC data. The machine learning module provides an answer product regarding the states of the borehole annuli which may be used to make decision regarding remedial action with respect to the borehole casings. The machine learning module may implement a convolutional neural network (CNN), a support vector machine (SVM), or an auto-encoder.

Abstract: Aspects described herein provide for methods and apparatus for characterizing azimuthal heterogeneities in a barrier installed outside an outer casing in a borehole traversing a formation in a cased hole configuration including an inner and outer casing. The approach is based on specific attributes in sonic signals acquired with an azimuthal and axial array receiver system located inside the inner casing. The methods include slowness-time-coherence (STC) processing based on specific arrivals identified in data acquired by axial arrays associated with multiple azimuthal sections of the receiver system. The specific arrivals contain STC signatures that can be examined in terms of coherence amplitude and localization within STC maps. Based on specific attributes in the sonic signals, an azimuthal coverage of the outer casing annular contents can be created.

Abstract: A method for determining properties of a laminated formation traversed by a well or wellbore employs measured sonic data, resistivity data, and density data for an interval-of-interest within the well or wellbore. A formation model that describe properties of the laminated formation at the interval-of-interest is derived from the measured sonic data, resistivity data, and density data for the interval-of-interest. The formation model represents the laminated formation at the interval-of-interest as first and second zones of different first and second rock types. The formation model is used to derive simulated sonic data, resistivity data, and density data for the interval-of-interest. The measured sonic data, resistivity data, and density data for the interval-of-interest and the simulated sonic data, resistivity data, and density data for the interval-of-interest are used to refine the formation model and determine properties of the formation at the interval-of-interest.

Abstract: Cement in a wellbore is evaluated by using cement evaluation tools to obtain ultrasonic image information and flexural wave image information. Flexural wave imager waveforms are applied to a trained machine learning system that predicts the presence or lack thereof of a clinging P as a function of depth and azimuth, while the ultrasonic imager impedance maps are applied to a trained machine learning system that identifies galaxy patterns for depths and azimuths, indicating the presence of a third interface echo (TIE) close to the casing. Locations of clinging Ps are compared to locations of galaxy patterns to identify when a TIE could cause a false clinging P determination. Where a disambiguated clinging P is found, contaminated cement is identified that may also locate the top of the cement in the annulus.

Abstract: A method, computer program product, and computing system for generating high resolution slowness logs. The method computer program product, and computing system includes receiving a plurality of sonic logs from at least one sensor array and generating at least one high-resolution slowness log from the plurality of sonic logs based upon, at least in part, monopole and dipole data from the plurality of sonic logs.

Abstract: Methods are provided for estimating a quality of cement in the annuli of a multi-string wellbore. Wideband acoustic energy signals are generated and detected in the wellbore and are processed to obtain indications of wideband casing-formation phase slowness dispersions in the wellbore. The indications are compared to reference wideband model casing-formation phase slowness dispersions in order to estimate status of cement or lack of cement in the annuli at that location based on the results of the comparison.

Abstract: Methods and systems are provided that characterize and evaluate well integrity of a cased well using unsupervised machine learning of acoustic data. Sonic waveform data generated by the receiver array of a sonic logging tool is collected and processed to determine a high-dimensional representation of the sonic waveform data. The high-dimensional representation is input to an unsupervised machine learning system to determine a low-dimensional representation of the sonic waveform data. A clustering method is applied to the low-dimensional representation to identify a set of clusters therein. At least one well integrity property of the depth interval of the cased well is determined based on the set of clusters. In embodiments, the at least one well integrity property can characterize cement condition in an annulus of the cased well as a function of azimuth and depth and can be used to evaluate cement integrity in a depth interval of the cased well.

Abstract: A method, computer program product, and computing system are provided for receiving sonic data associated with an inner casing of a well. Predicted ultrasonic data associated with an outer casing of the well may be generated based upon, at least in part, a nonlinear regression model and the received sonic data associated with the inner casing of the well.

Abstract: A method and computing system device for receiving a plurality of well logs. A depth shift between at least one well log of the plurality of well logs and at least one other well log may be determined based upon, at least in part, processing the plurality of well logs with a neural network. The plurality of well logs may be matched with one another based upon, at least in part, the depth shift between the at least one well log and the at least one other well log.

Abstract: A sonic tool is activated in a well having multiple casings and annuli surrounding the casing. Detected data is preprocessed using slowness time coherence (STC) processing to obtain STC data. The STC data is provided to a machine learning module which has been trained on labeled STC data. The machine learning module provides an answer product regarding the states of the borehole annuli which may be used to make decision regarding remedial action with respect to the borehole casings. The machine learning module may implement a convolutional neural network (CNN), a support vector machine (SVM), or an auto-encoder.

Abstract: Methods and systems are provided that identify relatively large anisotropic horizontal stresses in a formation based on (i) azimuthal variations in the compressional and shear slownesses or velocities of the formation measured from ultrasonic data acquired by at least one acoustic logging tool as well as (ii) cross-dipole dispersions of the formation measured from sonic data acquired by the at least one acoustic logging tool. In addition, the azimuthal variations in the compressional and shear slownesses or velocities of the formation and dipole flexural dispersions of the formation can be jointly inverted to obtain the elastic properties of the rock of the formation in terms of linear and nonlinear constants and the magnitude of maximum horizontal stress of the formation. A workflow for estimating the magnitude of the maximum horizontal stress can employ estimates of certain formation properties, such as overburden stress, magnitude of minimum horizontal stress, and pore pressure.

Abstract: Methods arc provided for using sonic tool data to investigate a multi-string wcllbore. The sonic data is processed to obtain indications of phase slowness dispersions for multiple locations in the wellbore. The dispersions are aggregated. The aggregated dispersions are compared with a plurality of cut-off mode templates to identify the presence of cut-off modes or the lack thereof in the aggregated phase slowness dispersions. Features of the multi-string wellbore are identified based on the presence of the cut-off modes or the lack thereof. In another method, the sonic data is processed to obtain indications as a function of depth of at least one of an energy spectrum, a semblance projection, a slowness dispersion projection, an attenuation dispersion projection, and a wavenumber dispersion projection. The indications are inspected to locate a shift at a particular depth indicat- ing a transition in at least oneannulus of the multi-string wellbore.

Abstract: Cement in a wellbore is evaluated by using cement evaluation tools to obtain ultrasonic image information and flexural wave image information. Flexural wave imager waveforms are applied to a trained machine learning system that predicts the presence or lack thereof of a clinging P as a function of depth and azimuth, while the ultrasonic imager impedance maps are applied to a trained machine learning system that identifies galaxy patterns for depths and azimuths, indicating the presence of a third interface echo (TIE) close to the casing. Locations of clinging Ps are compared to locations of galaxy patterns to identify when a TIE could cause a false clinging P determination. Where a disambiguated clinging P is found, contaminated cement is identified that may also locate the top of the cement in the annulus.

Abstract: Methods and systems are provided for determining cement quality in an outer annulus of a multi-string cased wellbore having an inner annulus of mud. Data from a sonic logging tool is processed to obtain a slowness dispersion. The slowness dispersion is compared to a plurality of model slowness dispersions generated for a plurality of different values for cement quality in the outer annulus. The cement quality in the outer annulus is determined based on the comparison.