公开(公告)号：US20220101105A1

公开(公告)日：2022-03-31

申请号：US17486684

申请日：2021-09-27

Applicant: DASSAULT SYSTEMES ,  ECOLE POLYTECHNIQUE ,  CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE

Inventor： Mariem MEZGHANNI ,  Maks OVSJANIKOV ,  Malika BOULKENAFED

IPC: G06N3/04 ,  G06N3/08

Abstract: A computer-implemented method for training a deep-learning generative model configured to output 3D modeled objects each representing a mechanical part or an assembly of mechanical parts. The method comprises obtaining a dataset of 3D modeled objects and training the deep-learning generative model based on the dataset. The training includes minimization of a loss. The loss includes a term that penalizes, for each output respective 3D modeled object, one or more functional scores of the respective 3D modeled object. Each functional score measures an extent of non-respect of a respective functional descriptor among one or more functional descriptors, by the mechanical part or the assembly of mechanical parts. This forms an improved solution with respect to outputting 3D modeled objects each representing a mechanical part or an assembly of mechanical parts.

公开(公告)号：US20250117528A1

公开(公告)日：2025-04-10

申请号：US18908244

申请日：2024-10-07

Applicant: DASSAULT SYSTEMES

Inventor： Pierre CLAROU ,  Mariem MEZGHANNI ,  Julien BOUCHER

IPC: G06F30/12 ,  G06N3/0464 ,  G06N3/08

Abstract: A machine-learning method including obtaining a training dataset of B-rep graphs. Each B-rep graph represents a respective B-rep. Each B-rep graph includes graph nodes each representing an edge, a face or a co-edge of the respective B-rep and being associated with one or more geometrical and/or topological features. Each B-rep graph further comprises graph edges each between a respective first graph node representing a respective co-edge and a respective second graph node representing a face, an edge, an adjacent co-edge, or a mating co-edge associated with the respective co-edge. The method further includes learning, based on the training dataset, a local Deep CAD neural network. The local Deep CAD neural network takes as input a B-rep graph and to output, for each graph node of the input B-rep graph, a local topological signature of the B-rep element represented by the graph node.

公开(公告)号：US20240061980A1

公开(公告)日：2024-02-22

申请号：US18451551

申请日：2023-08-17

Applicant: DASSAULT SYSTEMES

Inventor： Mariem MEZGHANNI ,  Julien BOUCHER ,  Rémy SABATHIER

IPC: G06F30/27

CPC classification number: G06F30/27

Abstract: A computer-implemented method of machine-learning including obtaining a training dataset of B-rep graphs. Each B-rep graph represents a respective B-rep. Each B-rep graph comprises graph nodes each representing an edge, a face or a co-edge of the respective B-rep and being associated with one or more geometrical and/or topological features. Each B-rep graph includes graph edges each between a respective first graph node representing a respective co-edge and a respective second graph node representing a face, an edge, an adjacent co-edge, or a mating co-edge associated with the respective co-edge. The method further includes learning, based on the training dataset, a Deep CAD neural network. The Deep CAD neural network is configured to take as input a B-rep graph and to output a topological signature of the B-rep represented by the input B-rep graph.

公开(公告)号：US20240251103A1

公开(公告)日：2024-07-25

申请号：US18413163

申请日：2024-01-16

Applicant: DASSAULT SYSTEMES ,  ECOLE POLYTECHNIQUE ,  CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE

Inventor： Mariem MEZGHANNI ,  Kawtar ZAHER ,  Malika BOULKENAFED ,  Maks OVSJANIKOV

IPC: H04N19/597 ,  G06T17/00 ,  H04N19/94

CPC classification number: H04N19/597 ,  G06T17/00 ,  H04N19/94

Abstract: A computer-implemented method of machine-learning. The method includes obtaining a training dataset of 3D models of real-world objects. The method further includes learning, based on the training dataset and on a patch-decomposition of the 3D models of the training dataset, a finite codebook of quantized vectors and a neural network. The neural network comprises a rotation-invariant encoder. The rotation-invariant encoder is configured for rotation-invariant encoding of a patch of a 3D model into a quantized latent vector of the codebook. The neural network further includes a decoder. The decoder is configured for decoding a sequence of quantized latent vectors of the codebook into a 3D model. The sequence corresponds to a patch-decomposition. This constitutes an improved solution for 3D model generation.

公开(公告)号：US20240078353A1

公开(公告)日：2024-03-07

申请号：US18460054

申请日：2023-09-01

Applicant: DASSAULT SYSTEMES

Inventor： Julien BOUCHER ,  Mariem MEZGHANNI ,  Arthur NDOKO

IPC: G06F30/13 ,  G06F30/20 ,  G06T7/564

CPC classification number: G06F30/13 ,  G06F30/20 ,  G06T7/564 ,  G06T2207/10028

Abstract: A computer-implemented method for generating a 3D model representing a factory. The method includes obtaining a point cloud from a scan of the factory and fitting the point cloud with linear CAD extrusions. Such a method is an improved solution for generating a 3D model representing a factory.

公开(公告)号：US20230014934A1

公开(公告)日：2023-01-19

申请号：US17866193

申请日：2022-07-15

Applicant: DASSAULT SYSTEMES

Inventor： Mariem MEZGHANNI ,  Julien BOUCHER ,  Paul VILLEDIEU

IPC: G06T17/10 ,  G06T17/20 ,  G06F30/27 ,  G06F30/12 ,  G06F30/17

Abstract: The disclosure relates to a computer-implemented method comprising inputting a representation of a 3D modeled object to an abstraction neural network which outputs a first set of a first number of first primitives fitting the 3D modeled object; and determining, from the first set, one or more second sets each of a respective second number of respective second primitives. The second number is lower than the first number. The determining includes initializing a third set of third primitives as the first set and performing one or more iterations, each comprising merging one or more subsets of third primitives together each into one respective single fourth primitive, to thereby obtain a fourth set of fourth primitives. Each iteration further comprises setting the third set of a next iteration as the fourth set of a current iteration and setting the one or more second sets as one or more obtained fourth sets.

公开(公告)号：US20220405448A1

公开(公告)日：2022-12-22

申请号：US17829987

申请日：2022-06-01

Applicant: DASSAULT SYSTEMES ,  ECOLE POLYTECHNIQUE ,  CNRS

Inventor： Mariem MEZGHANNI ,  Théo BODRITO ,  Malika BOULKENAFED ,  Maks OVSJANIKOV

IPC: G06F30/27 ,  G06F30/17 ,  G06N3/08

Abstract: A computer-implemented method of machine-learning. The method comprises providing a dataset of 3D modeled objects each representing a mechanical part. Each 3D modeled object comprises a specification of a geometry of the mechanical part. The method further comprises learning a set of parameterization vectors each respective to a respective 3D modeled object of the dataset and a neural network configured to take as input a parameterization vector and to output a representation of a 3D modeled object usable in a differentiable simulation-based shape optimization. The learning comprises minimizing a loss that penalizes, for each 3D modeled object of the dataset, a disparity between the output of the neural network for an input parameterization vector respective to the 3D modeled object and a representation of the 3D modeled object. The representation of the 3D modeled object is usable in a differentiable simulation-based shape optimization.