Abstract: A computer implemented method that enables reconstruction of flange ellipses to detect misalignment is described. The method includes applying a smoothing filter to an image comprising a flange joint. At least two edges corresponding to respective flanges of the flange joint are determined. A transformation to extract a first ellipse and a second ellipse corresponding to the at least two detected edges is performed. A position and orientation of the first ellipse and the second ellipse is estimated, and an alignment of the flanges is quantified based on the position and the orientation of the first ellipse and the second ellipse.

Abstract: Systems and methods for detecting passing valves in pipe systems include receiving acoustic emission data from a set of piezoelectric sensors attached to a pipe with at least a first piezoelectric sensor of the set positioned upstream of a valve and at least a second piezoelectric sensor of the set positioned downstream of the valve. A data processing system filters the acoustic emission data using a bandpass filter, and extracts features from the filtered acoustic emission data. The extracted features include time-domain features, frequency domain features, or a combination thereof derived from statistical analysis of the filtered acoustic emission data. The data processing system predicts an operational state of the valve using a machine learning model that receives as input the extracted features and in response to predicting that the operational state of the valve is a passing valve, performs a corrective action.

Abstract: Systems and methods are provided for predictive volumetric and structural evaluation of petroleum product containers. The system includes a computing device in communication with data input devices and implementation tools including calibration devices for measuring tank volume among other physical parameters bearing on tank volume. The computing device receives sets of historical physical parameter data for a plurality of tanks and, using machine learning (ML), generates predictive ML models for estimating volumetric parameters of tanks. The predictive model is applied by the system to historical and current data values to estimate current volumetric parameters for a given tank and, based on the results, the system performs or coordinates further operations for the given tank using an implementation tool. The further operations can include inventory management, physical calibration, maintenance and inspection as well as system evaluation and control operations.

Abstract: Wheels have controllable suction devices for adhesion on surfaces. The wheel has an axle and an outer circumferential surface. The outer circumferential surface has a plurality of apertures and a plurality of stretchable materials. Each aperture has a respective stretchable material therein. Rotating the wheel moves a first stretchable material adjacent to a surface of a structure. A portion of the first stretchable material moves in the direction radial to the axle, to control adhesion of a portion of the outer circumferential surface to the surface of the structure. A method implements use of the wheel to adhere to the surface of the structure.

Abstract: A passive noise management system includes a housing that includes a volume defined by an outer surface and an inner surface; and an opening in the housing configured to access the volume. The volume is configured to at least partially enclose an acoustic device configured to measure acoustic energy generated by an object. The housing is configured to couple to the object to form an enclosure around the acoustic device that is fluidly decoupled from an ambient environment. The enclosure includes the housing and at least a portion of the object. The passive noise management system includes at least one sound reducer coupled to the housing or enclosed within the volume. The at least one sound reducer is configured to reduce an amount of environmental noise transferred from the ambient environment, through the housing, and to the acoustic device.

Abstract: System and methods are disclosed relating to cloud edge based anomaly detection. In an example, an edge monitoring node can include a thermal camera to capture a thermal image of equipment that is under monitoring for an an anomaly event. The node further includes a machine learning (ML) model to process the thermal image of the equipment to detect the anomaly event. The node further includes a network interface to communicate the detected anomaly event over a network to a remote computing platform to determine one or more recommendations for proactive maintenance of the equipment.

Abstract: A computer-implemented method for flange integrity classification using artificial intelligence is described. The method includes obtaining images of a flange, wherein an image of the images is captured at a predetermined angle of image capture. The method includes classifying a condition of the flange using a trained machine learning model. Further, the method includes rendering an indication of the condition of the flange.

Abstract: Adhesion devices for transport assemblies are configured to engage non-metallic surfaces. The transport assemblies can be wheels, such as omni-directional wheels, or can be a tractor tread assembly. The transport assembly is configured to move adjacent to a non-metallic surface of a structure. The transport assembly comprises an outer surface disposed adjacent to the non-metallic surface as the transport assembly moves, and a plurality of adhesion devices are each mounted to the outer surface and extend at least in a normal direction away from the outer surface. Each adhesion device is responsive to proximity to the non-metallic surface to adhere to the non-metallic surface. The adhesion devices in one or more embodiments include a Van der Waals-type adhesion device, a micro spine-type adhesion device, a suction cup-type adhesion device, or a combination of such devices.

Abstract: Systems and methods include a sensor device for detecting passing valves. The sensor device includes a housing including a first side configured to contact a wall of a pipe in a pipe system. A cover plate is coupled to a second side of the housing opposite the first side. A piezoelectric sensor is disposed in the housing and configured to detect acoustic emissions from a valve in the pipe system. A sensor holder is disposed within the housing to maintain a position of the piezoelectric sensor. A spring is positioned around a portion of the sensor holder and configured to bias the sensor holder away from the cover plate and toward the first side of the housing. A computer system is mounted to the housing and configured to determine that a valve is a passing valve based on acoustic emissions detected by the piezoelectric sensor.

Abstract: Methods, systems, and apparatus operate to determine a health profile of a mechanical device including using a mobile robotic system to determine a location of a mechanical device. The mobile robotic system determines a location of a component of the mechanical device and measures a vibration parameter at the location of the component of the mechanical device. If the vibration measurement is outside a predetermined range, the system alerts personnel.

Abstract: Systems and methods for dynamically magnetizing a chassis of a robotic vehicle are provided. The system can include a chassis having a fixed first section with a first magnet, and a moveable a second section having a second magnet with an opposition orientation relative to the first magnet. The second section is located above or below the first section and includes a mechanism that moves the second section relative to the first magnet. The system also includes an actuator connected to the second section, and a control system operatively connected to the actuator. In the systems and methods, the control system can send commands to the actuator to selectively move the mechanism, thereby moving the second section relative to the location of the first magnet to activate or inactivate a magnetic force on a portion of the chassis.

Abstract: This disclosure describes systems and methods for detecting passing valves. A method includes acquiring vibrational data from one or more sensors associated with passing valves and non-passing valves; extracting a plurality of features from the vibrational data; determining, based on a feature importance criterion, a subset of the plurality of features having more significance than other features of the plurality of features; training a machine learning model, where inputs to the machine learning model include the set of features; detecting that a valve is a passing valve based on the trained machine learning model, where an input to the trained machine learning model includes the subset of features extracted from vibrational data; and in response to detecting the passing valve, performing a corrective action to resolve the passing valve.

Abstract: Example methods and systems for detecting flange anomalies using image data fusion are disclosed. One example method includes obtaining one or more RGB images and one or more thermal images of a flange. The one or more RGB images and the one or more thermal images are processed to generate a fused image data set. The fused image data set is provided as input to a first machine learning (ML) model that is trained to detect one or more anomaly types of flanges. One or more anomalies of the flange are determined using the first ML model. The determined one or more anomalies of the flange are provided for maintenance of the flange.

Abstract: A method and an assembly for determining a volume of a tank. A measuring tape having multiple magnets is attached to a first location of the tank. A first circumference of the tank at the first location of the tank is measured. A value of the first circumference is recorded. Multiple wheels coupled to the measuring tape are rotated. Responsive to rotating the wheels, the measuring tape is moved from the first location to a second location of the tank. A second circumference of the tank at the second location is measured. A value of the second circumference is recorded. Based on the value of the first circumference and the value of the second circumference, the volume of the tank is calculated.

Abstract: Disclosed are methods, systems, and computer-readable medium to perform operations including: receiving a plurality of three-dimensional (3D) models of a plurality of assembly parts of a physical object; displaying, on a display device and over a live video of the plurality of assembly parts, an augmented reality (AR) overlay including the plurality 3D models; providing the plurality 3D models to a remote device for display on the remote device; receiving, from the remote device, data indicative of instructions for assembling the plurality of assembly parts into the physical object; and modifying, based on the received data, the AR overlay displayed on the display device to provide the instructions for assembling the plurality of assembly parts into the physical object.

Abstract: A system for deploying a magnetic robotic crawler onto a surface of an elevated asset, the crawler being of the type that is capable of magnetically attaching to and traversing the surface. The system comprises an extendable pole having a proximal end and a distal end. The system also comprises a docking station having a housing for receiving the crawler. The docking station is provided at the distal end of the pole. The docking station also includes magnetic feet mounted at a distal end of the housing and configured to magnetically couple with the surface. The system can also comprise an extendable pole having a proximal end and a distal end and an end effector attached to the distal end. Specifically, the end effector is configured to selectively attach to and detach from a complementary shaped receiver provided on the crawler.

Abstract: A digital retrofit device comprises a camera, a processor coupled to the camera and configured with computer-executable instructions that cause the processor to activate the camera to capture an image and process the image so as to identify measurement data being displayed on an analog measurement instrument which is within the image captured by the camera, wherein the processing includes: identifying a type of the analog measurement instrument, identifying features of the analog measurement instrument, extract the measurement data displayed on the analog instrument based on the identified type and features of the analog instrument measurement, convert the extracted data into converted digital information, and obtain supplemental information from a database related to the analog instrument.

Abstract: A computer-implemented method for detection of abnormalities in flanges using embedded devices and tiny machine learning is described. The method includes obtaining sensor data associated with at least one flange, wherein the sensor data is captured by at least one sensor communicatively coupled with an embedded device on a mesh network. The method also includes executing a trained tiny machine learning model at the embedded device, wherein the sensor data is input to the trained tiny machine learning model and the trained tiny machine learning model predicts a state of the at least one flange. Additionally, the method includes transmitting the state to a master node across the mesh network, wherein further actions are performed responsive to the state of the at least one flange.

Abstract: A system for deploying a magnetic robotic crawler onto a surface of an elevated asset, the crawler being of the type that is capable of magnetically attaching to and traversing the surface. The system comprises an extendable pole having a proximal end and a distal end. The system also comprises a docking station having a housing for receiving the crawler. The docking station is provided at the distal end of the pole. The docking station also includes magnetic feet mounted at a distal end of the housing and configured to magnetically couple with the surface. The system can also comprise an extendable pole having a proximal end and a distal end and an end effector attached to the distal end. Specifically, the end effector is configured to selectively attach to and detach from a complementary shaped receiver provided on the crawler.

Abstract: An in-pipe apparatus for pipe inspection or maintenance is provided. The apparatus includes: a rotational deployment mechanism to rotationally deploy a probe or tool about an inner circumference of a pipe with respect to an axis of rotation; a radial deployment mechanism to radially deploy the probe or tool in a radial direction from the axis of rotation toward a target point on the inner circumference; and a passive centering mechanism to passively align the axis of rotation with the axis of the pipe. In some embodiments, the rotational deployment mechanism includes a motor to rotate the radial deployment mechanism about the axis of rotation. In some embodiments, the apparatus further includes a longitudinal deployment mechanism to longitudinally deploy the probe or tool along the pipe axis, with the passive centering mechanism passively maintaining alignment of the axis of rotation with the pipe axis during the longitudinal deployment.