Patent classifications
B22F5/04
Additive manufacturing based multi-layer fabrication/repair
A method of additively manufacturing includes generating a thermal model driven scan map that identifies an equiaxed cap region, a single crystal (SX) region, and a columnar to equiaxed transition (CET) region; and forming an active melt pool with respect to the thermal model driven scan map such that a depth of the active melt pool is greater than a thickness of the equiaxed transition (CET) region.
Additive manufacturing based multi-layer fabrication/repair
A method of additively manufacturing includes generating a thermal model driven scan map that identifies an equiaxed cap region, a single crystal (SX) region, and a columnar to equiaxed transition (CET) region; and forming an active melt pool with respect to the thermal model driven scan map such that a depth of the active melt pool is greater than a thickness of the equiaxed transition (CET) region.
Method and system of additive manufacturing contour-based hatching
A system and method including receiving a data model representation of a part, the data model representation including at least one layer of the part and inner and outer contours for the at least one layer; determining a hatch pattern for each layer of the at least one layer of the part, the hatch pattern for each layer being dependent on the inner and outer contours for each respective layer; generating a record of the determined hatch pattern for each layer, the record including locations for the hatch pattern for each layer; and saving the record of the determined hatch pattern for each layer of the part. In some aspects, the record of the determined hatch pattern for each layer of the part may be used in an additive manufacturing process.
TWO-PIECE BAFFLE
An airfoil vane includes an airfoil section which includes an outer wall that defines an internal cavity. A baffle is situated in the internal cavity. The baffle includes a leading edge portion and a trailing edge portion which is bonded to the leading edge portion at a joint. The leading edge portion and the trailing edge portion define an internal cavity therewithin. Both the leading edge portion and the trailing edge portion include a plurality of cooling holes which are configured to provide cooling air to the airfoil outer wall. The trailing edge portion is formed of sheet metal and the leading edge portion is formed of non-sheet-metal. A method of making a baffle for a vane arc segment and a method of assembling a ceramic matrix composite airfoil vane are also disclosed.
Additive manufacturing systems and methods of calibrating for additively printing on workpieces
Additive manufacturing systems, methods, and computer readable media may be configured to perform a calibration. Calibrating an additive manufacturing system may include comparing a digital representation of one or more calibration marks to a calibration-CAD model that includes one or more model calibration marks, and applying a calibration adjustment to one or more CAD models based at least in part on the comparison. The digital representation of the one or more calibration marks may have been obtained using a vision system, and the one or more calibration marks may have been printed on a calibration surface according to the calibration-CAD model using an additive manufacturing machine. The calibration adjustment may be configured to align the one or more CAD models with one or more coordinates of the additive manufacturing system.
Additive manufacturing systems and methods of calibrating for additively printing on workpieces
Additive manufacturing systems, methods, and computer readable media may be configured to perform a calibration. Calibrating an additive manufacturing system may include comparing a digital representation of one or more calibration marks to a calibration-CAD model that includes one or more model calibration marks, and applying a calibration adjustment to one or more CAD models based at least in part on the comparison. The digital representation of the one or more calibration marks may have been obtained using a vision system, and the one or more calibration marks may have been printed on a calibration surface according to the calibration-CAD model using an additive manufacturing machine. The calibration adjustment may be configured to align the one or more CAD models with one or more coordinates of the additive manufacturing system.
COLD SPRAY DUCT FOR A GAS TURBINE ENGINE
A component for a turbine engine may be formed by spraying particulate with a nozzle toward a substrate. The particulate may be deposited to form one or more annular layers and a reinforcing structure. The component may be a closed loop annular component having a reinforcing structure of specific dimensions enabled by the methods described.
Non-dimensionalization of variables to enhance machine learning in additive manufacturing processes
A method for training a machine learning engine for modeling of a physical system includes receiving process data representing measurements of a physical system. The method includes applying a transform to values of the at least two variables of the process data to generate a dimensionless parameter having a parameter value corresponding to each measurement of the physical system for the at least two variables. The method includes training the machine learning engine using a set of generated training data including the non-dimensionalized parameter, to output a prediction of a value of a physical effect of the physical system for values of the variables that are not included in the process data. The method includes controlling an additive manufacturing process for the material by setting the at least one physical property to the value of the at least one process variable during fabrication of a part.
Non-dimensionalization of variables to enhance machine learning in additive manufacturing processes
A method for training a machine learning engine for modeling of a physical system includes receiving process data representing measurements of a physical system. The method includes applying a transform to values of the at least two variables of the process data to generate a dimensionless parameter having a parameter value corresponding to each measurement of the physical system for the at least two variables. The method includes training the machine learning engine using a set of generated training data including the non-dimensionalized parameter, to output a prediction of a value of a physical effect of the physical system for values of the variables that are not included in the process data. The method includes controlling an additive manufacturing process for the material by setting the at least one physical property to the value of the at least one process variable during fabrication of a part.
Turbine rotor blade root with hollow mount with lattice support structure by additive manufacture
A turbine rotor blade root is additively manufactured and includes a shank having a radially extending chamber defined therein. A blade mount is at a radial inner end of the shank. The blade mount has a hollow interior defined therein with the hollow interior in fluid communication with the radially extending chamber. A lattice support structure is disposed within the hollow interior of the blade mount.