United Technologies Corporation

Raytheon Technologies Corporation

Rtx Corporation

Nagendra Somanath

Keshava Basavapatna Kumar

William Arthur Sowa

Christopher Marc Dye

Michael J Giering

Ryan B Noraas

Glenn Levasseur

Kurt R Heinemann

Olusegun T Oshin

Evan Selin

Edgar A Bernal

Joseph Brent Staubach

Joseph James Sedor

Justin R Urban

Quan Long

Alexandria Dorgan

Brendan T McAuliffe

Anya B Merli

A repair system for gas turbine engine components includes a computer system configured to receive a set of measured parameters for each gas turbine engine component in a plurality of substantially identical gas turbine engine components, and determine a variation model based on the set of measured parameters wherein each of the gas turbine engine components is an as-run component and has been exposed to a substantially identical general wear pattern. The computer system includes at least one simulated engine model. The simulated engine model is configured to determine a predicted operation of each gas turbine engine component in the plurality of substantially identical gas turbine engine components. A correlation system is configured to correlate variations in the set of parameters for each of the gas turbine engine components in the plurality of substantially identical gas turbine engine components with a set of the predicted operations of each gas turbine engine component in the plurality of substantially identical gas turbine engine components, thereby generating a predictive model based on the variations. A repair module is configured to generate a repair formula based on the predictive model. The repair formula is configured to receive a set of measured parameters of an as-run gas turbine engine component and determine a suggested repair capable of repairing the as-run gas turbine engine component.

Aircraft component repair system and process

A method for designing a material for an aircraft component according to one example includes training a neural network to correlate microstructural features of an alloy with material properties of the alloy by at least providing a set of images of the alloy. Each of the images in the set of images has varied constituent compositions and at least one patch of corresponding data is embedded into the image. The method also includes determining non-linear relationships between the microstructural features and corresponding empirically determined material properties via a machine learning algorithm, receiving a set of desired material properties of the alloy for aircraft component, and determining a set of microstructural features capable of achieving the desired material properties of the alloy based on the determined non-linear relationships.

Machine learning based rotor alloy design system

A method for designing a material for an aircraft component includes training a neural network to correlate microstructural features of an alloy with material properties of the alloy by at least providing a set of images of the alloy to the neural network. Each of the images in the set of images has varied constituent compositions. The method further includes providing the neural network with a set of determined material properties corresponding to each image, associating the microstructural features of each image with the set of empirically determined data corresponding to the image, and determining non-linear relationships between the microstructural features and corresponding empirically determined material properties via a machine learning algorithm, receiving a set of desired material properties of the alloy for aircraft component, and determining a set of microstructural features capable of achieving the desired material properties of the alloy based on the determined non-linear relationships.

Material selection and optimization process for component manufacturing

A maintenance scheduling system for gas turbine engine components includes a computer system configured to receive a set of measured parameters for each gas turbine engine component in a plurality of substantially identical gas turbine engine components, and determine a variation model based on the set of measured parameters. Each of the gas turbine engine components is a single route component and has been utilized in a substantially identical single route. The computer system includes at least one simulated engine model. The simulated engine model is configured to determine a predicted operation of each gas turbine engine component in the plurality of substantially identical gas turbine engine components. A correlation system is configured to correlate variations in the set of parameters for each of the gas turbine engine components in the plurality of substantially identical gas turbine engine components with a set of the predicted operations of each gas turbine engine component in the plurality of substantially identical gas turbine engine components, thereby generating a predictive model based on the variations. A maintenance schedule module is configured determine a predictive model operable to determine a predicted wear pattern of a second single route component that is substantially identical to the gas turbine engine components.

Aircraft component repair scheduling system and process

A tool for monitoring a part condition includes a computerized device having a processor and a memory. The computerized device includes at least one of a camera and an image input and a network connection configured to connect the computerized device to a data network. The memory stores instructions for causing the processor to perform the steps of providing an initial micrograph of a part to a trained model, providing a data set representative of operating conditions of the part to the trained model, and outputting an expected state of the part from the trained model based at least in part on the input data set and the initial micrograph.

Intelligent learning device for part state detection and identification

A system for providing real time aircraft engine sensor analysis includes a computer system configured to receive an engine operation data set in real time. The computer system includes a machine learning based analysis tool and a user interface configured to display a real time analysis of the engine operation data set. The user interface includes at least one portion configured to identify a plurality of anomalies in the engine operation data set.

System and method for analyzing engine test data in real time

A gas turbine engine includes a primary flowpath fluidly connecting a compressor section, a combustor section, and a turbine section. A heat exchanger is disposed in the primary flowpath downstream of the turbine section. The heat exchanger includes a first inlet for receiving fluid from the primary flowpath and a first outlet for expelling fluid received at the first inlet. The heat exchanger further includes a second inlet fluidly connected to a supercharged CO2 (sCO2) bottoming cycle and a second outlet connected to the sCO2 bottoming cycle. The sCO2 bottoming cycle is an overexpanded, recuperated Brayton cycle.

Work recovery system for a gas turbine engine utilizing an overexpanded, recuperated supercritical CO2 bottoming cycle

Systems and methods for aircraft ice detection and mitigation. The system for aircraft ice detection and mitigation may comprise a controller, and a tangible, non-transitory memory configured to communicate with the controller, the tangible, non-transitory memory having instructions stored thereon that, in response to execution by the controller, cause the controller to perform operations comprising receiving, by the controller, a video signal from a first data, mapping, by the controller, the video signal to a discriminative feature space in response to a mapping function, generating, by the controller, a first extracted feature in response to the mapping function and the discriminative feature space, generating, by the controller, a behavioral model in response to the first extracted feature, and determining, by the controller, an icing condition of the aircraft in response to the extracted feature and the behavioral model.

Ice detection and real time ice estimation using innovative sensor data learning approaches

An expandable mid-turbine frame assembly includes a first bearing cone, a second bearing cone and a mid-turbine frame. The mid-turbine frame assembly connects to a gas turbine engine casing and transfers a first load from a first bearing and a second load from a second bearing towards the engine casing. The first bearing cone transfers the first load from the first bearing. The second bearing cone transfers the second load from the second bearing. The mid-turbine frame is connected to the first and second bearing cones and includes segments. Each segment includes a pre-stressed support for equilibrating the first and second loads.

Tailorable design configuration topologies for aircraft engine mid-turbine frames

A gas turbine engine is provided that includes a low pressure spool, a high pressure spool, a stationary support frame, and at least one support arch. The low pressure spool extends between a low pressure compressor and a low pressure turbine. The high pressure spool extends between a high pressure compressor and a high pressure turbine. The spools are rotatable about a center axis of the engine. The support arch has a stationary support mount disposed between a low spool mount and a high spool mount. The support arch is disposed relative to the spools and the stationary support frame so that a load from each spool caused by the rotation of that spool can be transferred to the stationary support frame through the support arch. The support arch can freely rotate about the center axis of the engine relative to the spools and the stationary structural frame.

Spool support structure for a multi-spool gas turbine engine

A method for varying the geometry of a mid-turbine frame includes detecting a strain in a mid-turbine frame with a piezoelectric material; applying a deformation voltage to the piezoelectric material as a function of the detected strain; deforming the piezoelectric material to actuate an actuation plate; and repositioning an engine casing through the actuation of the actuation plate.

Method for varying the geometry of a mid-turbine frame

A mid-turbine frame connected to at least one mount of a gas turbine engine transfers a first load from a first bearing and a second load from a second bearing to the mount. The mid-turbine frame includes a single point load shell structure and a plurality of struts. The single point load shell structure combines the first load and the second load into a combined load. The plurality of struts is connected to the single point load structure and transfers the combined load from the single point load shell structure to the mount.

Mid-turbine frame

A single point load structure transfers a first load from a first bearing cone and a second load from a second bearing cone of a gas turbine engine to a plurality of struts. The single point load structure includes a stem, a branch connected to the stem and a torque box connected to the plurality of struts for absorbing the first and second loads from the stem and the branch. The stem has a concave surface that opens in a radially outward direction with respect to a rotational axis of the gas turbine engine.

Mid-turbine frame torque box having a concave surface

A mid-turbine frame assembly includes a mid-turbine frame, a ring structure and a plurality of actuated struts. The ring structure surrounds the mid-turbine frame, and has an interior surface and an exterior surface. The actuated struts connect the ring structure to the mid-turbine frame. The actuated struts are strain actuated so that the actuated struts reposition the ring structure in response to a strain.

Actuated variable geometry mid-turbine frame design

The turbine engine assembly has a frame and a turbine engine spool. A strut couples the frame to the spool and an actuator couples the strut to the frame. The actuator has a spring.

Growing community of inventors

Manchester, CT, United States of America

Nagendra Somanath