-
公开(公告)号：US12011760B2
公开(公告)日：2024-06-18
申请号：US17449043
申请日：2021-09-27
Applicant: XEROX CORPORATION
Inventor： David K. Biegelsen , Jeng Ping Lu
CPC classification number: B22D23/003 , B22F10/22 , B22F12/53 , B33Y10/00 , B33Y30/00
Abstract: A 3D printer includes an ejector device for mixing and ejecting print material. The ejector device includes a substrate and a plurality of ejector conduits on the substrate. The ejector conduits are arranged in an array. Each ejector conduit includes a first passageway fluidly connecting a first end of the ejector conduit to a conduit junction. The first end is configured to accept a first print material. Each ejector conduit also includes a second passageway fluidly connecting a second end of the ejector conduit to the conduit junction. The second end is configured to accept a second print material. Each ejector conduit also includes a third passageway fluidly connecting a third end of the ejector conduit to the conduit junction. The third end includes an ejector nozzle. The ejector nozzle includes a first electrode and a second electrode.
-
公开(公告)号：US11762348B2
公开(公告)日：2023-09-19
申请号：US17326902
申请日：2021-05-21
Applicant: XEROX CORPORATION
Inventor： Anne Plochowietz , Anand Ramakrishnan , Warren Jackson , Lara S. Crawford , Bradley Rupp , Sergey Butylkov , Jeng Ping Lu , Eugene M. Chow
CPC classification number: G05B13/048 , G05B13/027 , G05B13/042 , G06N3/08 , G06N7/08
Abstract: Control loop latency can be accounted for in predicting positions of micro-objects being moved by using a hybrid model that includes both at least one physics-based model and machine-learning models. The models are combined using gradient boosting, with a model created during at least one of the stages being fitted based on residuals calculated during a previous stage based on comparison to training data. The loss function for each stage is selected based on the model being created. The hybrid model is evaluated with data extrapolated and interpolated from the training data to prevent overfitting and ensure the hybrid model has sufficient predictive ability. By including both physics-based and machine-learning models, the hybrid model can account for both deterministic and stochastic components involved in the movement of the micro-objects, thus increasing the accuracy and throughput of the micro-assembly.
-
Patent Agency Ranking
3.发明授权公开(公告)号：US12053818B2
公开(公告)日：2024-08-06
申请号：US17449046
申请日：2021-09-27
Applicant: XEROX CORPORATION
Inventor： David K. Biegelsen , Jeng Ping Lu
CPC classification number: B22D23/003 , B33Y10/00 , B33Y30/00 , B41J2/14 , B41J2/16 , B41J2/14201 , B41J2/1607
Abstract: A method of making an ejector device. The method includes providing a substrate and forming one or more ejector conduits on the substrate. The one or more ejector conduits comprise: a first end configured to accept a print material; a second end comprising an ejector nozzle, the ejector nozzle comprising a first electrode pair that includes a first electrode and a second electrode, at least one surface of the first electrode being exposed in the ejector nozzle and at least one surface of the second electrode being exposed in the ejector nozzle; and at least one passageway for allowing the print material to flow from the first end to the second end. A method of printing a three-dimensional object and a method for jetting print material from a printer jetting mechanism are also disclosed.
-
4.发明公开公开(公告)号：US20230418273A1
公开(公告)日：2023-12-28
申请号：US18460175
申请日：2023-09-01
Applicant: XEROX CORPORATION
Inventor： Ion Matei , Jeng Ping Lu , Saigopal Nelaturi , Julie A. Bert , Lara S. Crawford , Armin R. Volkel , Eugene M. Chow
CPC classification number: G05B19/41885 , G05B17/02 , B01L3/50273 , G06T7/194 , G06T2207/30164 , G06T7/155 , H04N7/183 , G05B2219/32359 , G06T2207/20021 , G06T7/74
Abstract: The system and method described allow for real-time control over positioning of a micro-object. A movement of at least one micro-object suspended in a medium can be induced by a generation of one or more forces by electrodes proximate to the micro-object. Prior to inducing the movement, a simulation is used to develop a model describing a parameter of an interaction between each of the electrodes and the micro-object. A function describing the forces generated by an electrode and an extent of the movement induced due to the forces is generated using the model. The function is used to design closed loop policy control scheme for moving the micro-object towards a desired position. The position of the micro-object is tracked and taken into account when generating voltage patterns in the scheme.
-
公开(公告)号：US11747796B2
公开(公告)日：2023-09-05
申请号：US17391381
申请日：2021-08-02
Applicant: XEROX CORPORATION
Inventor： Ion Matei , Jeng Ping Lu , Saigopal Nelaturi , Julie A. Bert , Lara S. Crawford , Armin R. Volkel , Eugene M. Chow
CPC classification number: G05B19/41885 , B01L3/50273 , G05B17/02 , G06T7/155 , G06T7/194 , G06T7/74 , H04N7/183 , G05B2219/32359 , G06T2207/20021 , G06T2207/30164
Abstract: The system and method described allow for real-time control over positioning of a micro-object. A movement of at least one micro-object suspended in a medium can be induced by a generation of one or more forces by electrodes proximate to the micro-object. Prior to inducing the movement, a simulation is used to develop a model describing a parameter of an interaction between each of the electrodes and the micro-object. A function describing the forces generated by an electrode and an extent of the movement induced due to the forces is generated using the model. The function is used to design closed loop policy control scheme for moving the micro-object towards a desired position. The position of the micro-object is tracked and taken into account when generating voltage patterns in the scheme.
-
6.发明公开公开(公告)号：US20240036534A1
公开(公告)日：2024-02-01
申请号：US18462332
申请日：2023-09-06
Applicant: XEROX CORPORATION
Inventor： Anne Plochowietz , Anand Ramakrishnan , Warren Jackson , Lara S. Crawford , Bradley Rupp , Sergey Butylkov , Jeng Ping Lu , Eugene M. Chow
CPC classification number: G05B13/048 , G05B13/042 , G06N7/08 , G06N3/08 , G05B13/027
Abstract: Control loop latency can be accounted for in predicting positions of micro-objects being moved by using a hybrid model that includes both at least one physics-based model and machine-learning models. The models are combined using gradient boosting, with a model created during at least one of the stages being fitted based on residuals calculated during a previous stage based on comparison to training data. The loss function for each stage is selected based on the model being created. The hybrid model is evaluated with data extrapolated and interpolated from the training data to prevent overfitting and ensure the hybrid model has sufficient predictive ability. By including both physics-based and machine-learning models, the hybrid model can account for both deterministic and stochastic components involved in the movement of the micro-objects, thus increasing the accuracy and throughput of the micro-assembly.
-
公开(公告)号：US11893327B2
公开(公告)日：2024-02-06
申请号：US17121411
申请日：2020-12-14
Applicant: XEROX CORPORATION
Inventor： Ion Matei , Anne Plochowietz , Saigopal Nelaturi , Johan de Kleer , Jeng Ping Lu , Lara S. Crawford , Eugene M. Chow
IPC: G06F30/27 , G06F30/17 , G06N3/04 , G06F111/04
CPC classification number: G06F30/27 , G06F30/17 , G06N3/04 , G06F2111/04
Abstract: System and method that allow utilize machine learning algorithms to move a micro-object to a desired position are described. A sensor such as a high speed camera or capacitive sensing, tracks the locations of the objects. A dynamic potential energy landscape for manipulating objects is generated by controlling each of the electrodes in an array of electrodes. One or more computing devices are used to: estimate an initial position of a micro-object using the sensor; generate a continuous representation of a dynamic model for movement of the micro-object due to electrode potentials generated by at least some of the electrodes and use automatic differentiation and Gauss quadrature rules on the dynamic model to derive optimum potentials to be generated by the electrodes to move the micro-object to the desired position; and map the calculated optimized electrode potentials to the array to activate the electrodes.
-
-
-
-
-
-
Search Results
7
records
(took 0.013 seconds)
