公开(公告)号：US11481664B2

公开(公告)日：2022-10-25

申请号：US16122184

申请日：2018-09-05

Applicant: General Electric Company

Inventor： Subhrajit Roychowdhury ,  Naresh Iyer

IPC: G06N20/00 ,  B33Y40/00 ,  B33Y50/02 ,  G06F30/23 ,  G06F119/18

Abstract: A method of transferring operational parameter sets between different domains of additive manufacturing machines includes creating a first machine domain parameter set in a first machine domain, accessing a model of a second additive manufacturing in a second machine domain, creating a second machine domain parameter set by applying transfer learning techniques including learning differences between the first machine domain and the second machine domain, adjusting the first machine domain parameter set using the differences before incorporation into the second machine domain to obtain the second machine domain parameter set, the second machine domain parameter set representing operational settings for the second additive manufacturing machine, the second additive manufacturing machine producing a product sample, determining if the product sample is within quality assurance metrics, and if the product sample is not within the quality assurance metrics, adjusting the second machine domain parameter set.

公开(公告)号：US11144035B2

公开(公告)日：2021-10-12

申请号：US16441792

申请日：2019-06-14

Applicant: General Electric Company

Inventor： Vipul Kumar Gupta ,  Natarajan Chennimalai Kumar ,  Anthony J Vinciquerra, III ,  Randal T Rausch ,  Subhrajit Roychowdhury ,  Justin John Gambone, Jr.

IPC: G05B19/4099 ,  G06N5/02

Abstract: A method of additive manufacturing machine (AMM) build process control includes obtaining AMM machine and process parameter settings, accessing sensor data for monitored physical conditions in the AMM, calculating a difference between expected AMM physical conditions and elements of the monitored conditions, providing the machine and process parameter settings, monitored conditions, and differences to one or more material property prediction models, computing a predicted value or range for the monitored conditions, comparing the predicted value or range to a predetermined target range, based on a determination that predicted value(s) are within the predetermined range, maintaining the machine and process parameter settings, or based on a determination that one or more of the predicted value(s) is outside the predetermined range, generating commands to compensate the machine and process parameter settings, and repeating the closed feedback loop at intervals of time during the build process. A system and a non-transitory medium are also disclosed.

公开(公告)号：US20210120031A1

公开(公告)日：2021-04-22

申请号：US16654319

申请日：2019-10-16

Applicant: GENERAL ELECTRIC COMPANY

Inventor： Mustafa Tekin Dokucu ,  Subhrajit Roychowdhury ,  Olugbenga Anubi ,  Masoud Abbaszadeh ,  Justin Varkey John

IPC: H04L29/06 ,  G06N20/00 ,  G01R19/00

Abstract: An industrial asset may have monitoring nodes that generate current monitoring node values. An abnormality detection computer may determine that an abnormal monitoring node is currently being attacked or experiencing fault. A dynamic, resilient estimator constructs, using normal monitoring node values, a latent feature space (of lower dimensionality as compared to a temporal space) associated with latent features. The system also constructs, using normal monitoring node values, functions to project values into the latent feature space. Responsive to an indication that a node is currently being attacked or experiencing fault, the system may compute optimal values of the latent features to minimize a reconstruction error of the nodes not currently being attacked or experiencing a fault. The optimal values may then be projected back into the temporal space to provide estimated values and the current monitoring node values from the abnormal monitoring node are replaced with the estimated values.

公开(公告)号：US10814429B2

公开(公告)日：2020-10-27

申请号：US15881147

申请日：2018-01-26

Applicant: General Electric Company

Inventor： Subhrajit Roychowdhury ,  Matthias Hoebel ,  Lang Yuan ,  Prabhjot Singh ,  Michael Evans Graham ,  Robert John Filkins ,  Thomas Etter ,  Felix Martin Gerhard Roerig

IPC: B23K26/342 ,  B23K26/02 ,  B23K26/06 ,  B23K26/064 ,  B23K26/08 ,  B23K26/082 ,  B33Y50/02 ,  B33Y10/00 ,  B33Y30/00 ,  B22F3/105

Abstract: An additive manufacturing system includes a laser device, a build plate, and a scanning device. The laser device is configured to generate a laser beam with a variable intensity. The build plate is configured to support a powdered build material. The scanning device is configured to selectively direct the laser beam across the powdered build material to generate a melt pool on the build plate. The scanning device is configured to oscillate a spatial position of the laser beam while the laser device is configured to simultaneously modulate the intensity of the laser beam to thermally control the melt pool.

公开(公告)号：US20190240781A1

公开(公告)日：2019-08-08

申请号：US15888727

申请日：2018-02-05

Applicant: General Electric Company

Inventor： William Thomas Carter ,  Todd Jay Rockstroh ,  Brian Scott McCarthy ,  Subhrajit Roychowdhury ,  Younkoo Jeong ,  David Charles Bogdan, JR.

IPC: B23K26/342 ,  B33Y10/00 ,  B33Y30/00 ,  B23K26/082 ,  B23K26/08 ,  B23K26/06 ,  B23K26/144 ,  B23K26/16

CPC classification number: B23K26/342 ,  B23K26/0608 ,  B23K26/082 ,  B23K26/0823 ,  B23K26/144 ,  B23K26/16 ,  B33Y10/00 ,  B33Y30/00

Abstract: A direct metal laser melting (DMLM) system includes a rotatable base, and a build plate mounted on and supported by the rotatable base, where the build plate includes a build surface. The DMLM system also includes a first actuator assembly, a first powder dispenser disposed proximate the build plate and configured to deposit a weldable powder on the build surface of the build plate. In addition, the DMLM system includes a first powder spreader disposed proximate the build plate and configured to spread the weldable powder deposited on the build surface of the build plate, and a first laser scanner supported by the first actuator assembly in a position relative to the build plate, such that at least a portion of the build surface is within a field of view of the first laser scanner. The first laser scanner is configured to selectively weld the weldable powder. The first laser scanner is further configured to translate axially relative to the build surface on the first actuator assembly.

公开(公告)号：US12222838B2

公开(公告)日：2025-02-11

申请号：US17724704

申请日：2022-04-20

Applicant: General Electric Company

Inventor： Harry Kirk Mathews, Jr. ,  Sarah Felix ,  Subhrajit Roychowdhury ,  Saikat Ray Majumder ,  Thomas Spears

IPC: G06F11/34 ,  B29C64/393 ,  B33Y50/02 ,  G06F17/18 ,  G06F30/00

Abstract: Generating fault indications for an additive manufacturing machine based on a comparison of the outputs of multiple process models to measured sensor data. The method receiving sensor data from the additive manufacturing machine during manufacture of at least one part. Models are selected from a model database, each model generating expected sensor values for a defined condition. Difference values are computed between the received sensor data and an output of each of the models. A probability density function is computed, which defines, for each of the models, a likelihood that a given difference value corresponds to each respective model. A probabilistic rule is applied to determine, for each of the models, a probability that the corresponding model output matches the received sensor data. An indicator is output of a defined condition corresponding to a model having the highest match probability.

公开(公告)号：US12076814B2

公开(公告)日：2024-09-03

申请号：US15615163

申请日：2017-06-06

Applicant: General Electric Company

Inventor： Subhrajit Roychowdhury ,  James William Sears ,  Harry Kirk Mathews, Jr.

IPC: B23K26/067 ,  B22F7/06 ,  B22F10/28 ,  B22F10/366 ,  B22F12/00 ,  B22F12/44 ,  B22F12/49 ,  B23K26/342 ,  B33Y10/00 ,  B33Y30/00

CPC classification number: B23K26/0676 ,  B22F7/064 ,  B22F10/28 ,  B22F12/44 ,  B22F12/49 ,  B23K26/342 ,  B33Y10/00 ,  B33Y30/00 ,  B22F10/366 ,  B22F12/38

Abstract: A powder melting device for an additive manufacturing system including a laser device configured to emit an energy beam and a beam modulator. The beam modulator is configured to selectively induce an angular deflection in the energy beam for a predetermined time period such that the energy beam generates a plurality of melt pools in a powder bed.

公开(公告)号：US20230305196A1

公开(公告)日：2023-09-28

申请号：US18321349

申请日：2023-05-22

Applicant: General Electric Company

Inventor： Robert John Filkins ,  Subhrajit Roychowdhury ,  Juan Borja ,  Thomas Adcock

IPC: G02B5/00 ,  B33Y10/00 ,  B29C64/153 ,  B29C64/268 ,  B23K26/06 ,  B22F12/44 ,  B22F12/49 ,  B22F1/00

CPC classification number: G02B5/001 ,  B33Y10/00 ,  B29C64/153 ,  B29C64/268 ,  B23K26/0648 ,  B22F12/44 ,  B22F12/49 ,  B22F1/00 ,  B22F10/28

Abstract: A system includes a first group of optic lenses within a focusing unit positioned along the propagation direction of a collimated laser beam, the first group of optic lenses separated by a predetermined fixed distance. The first group of optic lenses in conjunction cause the collimated beam to form as an annular beam as it passes through the first group of optic lenses. An axicon lens located distal from the first group of optic lenses along the propagation direction, the axicon lens operable to bifurcate the annular beam into two deflected collimated beam sections, and the axicon lens having a focus that causes the two deflected collimated beam sections to merge at a distance distal from the axicon lens to create an interference pattern region.

公开(公告)号：US11472115B2

公开(公告)日：2022-10-18

申请号：US16360180

申请日：2019-03-21

Applicant: General Electric Company

Inventor： Vipul Kumar Gupta ,  Natarajan Chennimalai Kumar ,  Anthony Joseph Vinciquerra ,  Laura Cerully Dial ,  Voramon Supatarawanich Dheeradhada ,  Timothy Hanlon ,  Lembit Salasoo ,  Xiaohu Ping ,  Subhrajit Roychowdhury ,  Justin John Gambone

IPC: G06F19/00 ,  B29C64/393 ,  B29C64/153 ,  B22F10/20 ,  B33Y10/00 ,  B33Y30/00 ,  B33Y40/00 ,  B33Y50/02 ,  B22F3/24 ,  B22F10/30

Abstract: According to some embodiments, system and methods are provided comprising receiving, via a communication interface of a parameter development module comprising a processor, a defined geometry for one or more parts, wherein the parts are manufactured with an additive manufacturing machine, and wherein a stack is formed from one or more parts; fabricating the one or more parts with the additive manufacturing machine based on a first parameter set; collecting in-situ monitoring data from one or more in-situ monitoring systems of the additive manufacturing machine for one or more parts; determining whether each stack should receive an additional part based on an analysis of the collected in-situ monitoring data; and fabricating each additional part based on the determination the stack should receive the additional part. Numerous other aspects are provided.

公开(公告)号：US11411983B2

公开(公告)日：2022-08-09

申请号：US16654319

申请日：2019-10-16

Applicant: GENERAL ELECTRIC COMPANY

Inventor： Mustafa Tekin Dokucu ,  Subhrajit Roychowdhury ,  Olugbenga Anubi ,  Masoud Abbaszadeh ,  Justin Varkey John

IPC: H04L12/26 ,  H04L9/40 ,  G01R19/00 ,  G06N20/00

Abstract: An industrial asset may have monitoring nodes that generate current monitoring node values. An abnormality detection computer may determine that an abnormal monitoring node is currently being attacked or experiencing fault. A dynamic, resilient estimator constructs, using normal monitoring node values, a latent feature space (of lower dimensionality as compared to a temporal space) associated with latent features. The system also constructs, using normal monitoring node values, functions to project values into the latent feature space. Responsive to an indication that a node is currently being attacked or experiencing fault, the system may compute optimal values of the latent features to minimize a reconstruction error of the nodes not currently being attacked or experiencing a fault. The optimal values may then be projected back into the temporal space to provide estimated values and the current monitoring node values from the abnormal monitoring node are replaced with the estimated values.