A method of repairing a component using an additive manufacturing process is presented. The method includes submerging the component into a powder bed so that a portion of the component to be repaired is level with a surface of the powder bed and a protruding portion of the component protrudes above the surface of the powder bed, positioning a split wiper that includes a first wiper segment and a second wiper segment in the powder bed at the surface, advancing a quantity of powder by translating the first wiper segment and the second wiper segment across the surface of the powder bed, and directing a laser beam across the surface to fuse powder particles of the powder bed to the underlying substrate forming a layer of the component. Each of the first wiper segment and the second wiper segment follow a different contour of the protruding portion at the surface.

This invention is directed to a method of efficiently improving a relative density of a shaped object using an evaluation criterion having a higher correlation with a density of an object to be shaped. The method according to this invention includes acquiring three-dimensional point group data of a surface of a shaping object, calculating at least one of three-dimensional surface texture parameters extended to a plane region using the three-dimensional point group data, and evaluating a quality of the object to be shaped using the at least one of the three-dimensional surface texture parameters.

This invention is directed to a method of efficiently improving a relative density of a shaped object using an evaluation criterion having a higher correlation with a density of an object to be shaped. The method according to this invention includes acquiring three-dimensional point group data of a surface of a shaping object, calculating at least one of three-dimensional surface texture parameters extended to a plane region using the three-dimensional point group data, and evaluating a quality of the object to be shaped using the at least one of the three-dimensional surface texture parameters.

Embodiments relate to in-situ process monitoring of a part being made via additive manufacturing. The process can involve capturing computed tomography (CT) scans of a post-built part. A neural network (NN) can be used during the build of a new part to process multi-modal sensor data. Spatial and temporal registration techniques can be used to align the data to x,y,z coordinates on the build plate. During the build of the part, the multi-modal sensor data can be superimposed on the build plate. Machine learning can be used to train the NN to correlate the sensor data to a defect label or a non-defect label by looking to certain patterns in the sensor data at the x,y,z location to identify a defect in the CT scan at x,y,z. The NN can then be used to predict where defects are or will occur during an actual build of a part.

Embodiments relate to in-situ process monitoring of a part being made via additive manufacturing. The process can involve capturing computed tomography (CT) scans of a post-built part. A neural network (NN) can be used during the build of a new part to process multi-modal sensor data. Spatial and temporal registration techniques can be used to align the data to x,y,z coordinates on the build plate. During the build of the part, the multi-modal sensor data can be superimposed on the build plate. Machine learning can be used to train the NN to correlate the sensor data to a defect label or a non-defect label by looking to certain patterns in the sensor data at the x,y,z location to identify a defect in the CT scan at x,y,z. The NN can then be used to predict where defects are or will occur during an actual build of a part.

Embodiments relate to in-situ process monitoring of a part being made via additive manufacturing. The process can involve capturing computed tomography (CT) scans of a post-built part. A neural network (NN) can be used during the build of a new part to process multi-modal sensor data. Spatial and temporal registration techniques can be used to align the data to x,y,z coordinates on the build plate. During the build of the part, the multi-modal sensor data can be superimposed on the build plate. Machine learning can be used to train the NN to correlate the sensor data to a defect label or a non-defect label by looking to certain patterns in the sensor data at the x,y,z location to identify a defect in the CT scan at x,y,z. The NN can then be used to predict where defects are or will occur during an actual build of a part.

A downhole component including a first portion; a second portion; a controlled failure structure between the first portion and second portion. A method for improving efficiency in downhole components.

An inspection system for in situ evaluation of an additive manufacturing (AM) build part is provided. The inspection system comprises a build plane induction coil sensor configured and positionable so that during construction of the build part, the sensor's magnetization and sensor coils surround at least the last-produced layer of the AM build part in the build plane. The inspection system further comprises an energization circuit and a central processing system. The central processing system comprises a communication processor configured for sending command signals to the energization circuit and receiving impedance data from the build plane induction coil sensor, and energization controller configured for determining energization commands for transmission to the energization circuit, and an induction data analyzer configured for processing build part impedance data using complex impedance plane analysis and for identifying anomalies in the AM build part.

An inspection system for in situ evaluation of an additive manufacturing (AM) build part is provided. The inspection system comprises a build plane induction coil sensor configured and positionable so that during construction of the build part, the sensor's magnetization and sensor coils surround at least the last-produced layer of the AM build part in the build plane. The inspection system further comprises an energization circuit and a central processing system. The central processing system comprises a communication processor configured for sending command signals to the energization circuit and receiving impedance data from the build plane induction coil sensor, and energization controller configured for determining energization commands for transmission to the energization circuit, and an induction data analyzer configured for processing build part impedance data using complex impedance plane analysis and for identifying anomalies in the AM build part.

A component includes a multiplicity of individual powder particles of Mo, a Mo-based alloy, W or a W-based alloy that have been fused together to give a solid structure by a high-energy beam via an additive manufacturing method. The component has an oxygen content of not more than 0.1 at %. An additive manufacturing method includes producing the powder via the melt phase and providing a carbon content in the region of not less than 0.15 at %. The components are crack-free and have high grain boundary strength.