Modeling operations for functional structures

The method trains a generative autoencoder to represent mechanical assemblies as a tree structure, addressing the hierarchical nature of CAD data to generate realistic functional structures suitable for design and manufacturing, enhancing topology optimization.

JP7579073B2Active Publication Date: 2024-11-07DASSAULT SYSTEMES SA
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
JP2020114167
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Priority Date
2019-07-07
Filing Date
2020-07-01
Publication Date
2024-11-07
Estimated Expiration
2040-07-01

AI Technical Summary

Technical Problem

Existing methods for training generative autoencoders to generate functional structures, such as mechanical assemblies of rigid parts, fail to effectively capture their hierarchical structure, leading to unrealistic results due to the lack of consideration for the inherent hierarchical nature of CAD data.

Method used

A computer-implemented method for training a generative autoencoder that represents mechanical assemblies as a tree structure, where leaf nodes describe the shape and forces of rigid parts, and non-leaf nodes represent mechanical links or duplications, using a recursive bottom-up encoding process and top-down decoding process to generate realistic functional structures.

Benefits of technology

The method enables the generation of physically realistic CAD data that can be directly used in design and manufacturing processes, supporting topology optimization and enabling the creation of diverse mechanical assemblies with accurate representation of parts and their relationships.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007579073000072
    Figure 0007579073000072
  • Figure 0007579073000073
    Figure 0007579073000073
  • Figure 0007579073000074
    Figure 0007579073000074
Patent Text Reader

Abstract

To provide a method for learning a generation auto-encoder configured to generate a functional structure.SOLUTION: A generation auto-encoder generates a data structure that represents a mechanical assembly of a rigid component as a functional structure. The data structure includes a tree having leaf nodes. Each leaf node represents the shape and placement of each rigid component and the force acting on each rigid component. The tree further includes non-leaf nodes having a plurality of children. Each non-leaf node represents a mechanical link between sub-assemblies. Each sub-assembly is represented by each one of the plurality of children. The tree further includes non-leaf nodes having one child. Each non-leaf node having one child represents a copy of a sub-assembly represented by the one child. The method includes providing a dataset including the functional structure and learning generation auto-encoder on the dataset.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to the field of computer programs and systems, and more particularly to methods, systems and programs for training a generative autoencoder configured to generate functional structures. [Background technology]

[0002] A large number of systems and programs are offered on the market for designing, engineering and manufacturing objects. CAD is an abbreviation for Computer-Aided Design, which relates, for example, to software solutions for designing objects. CAE is an abbreviation for Computer-Aided Engineering, which relates, for example, to software solutions for simulating the physical behavior of future products. CAM is an abbreviation for Computer-Aided Manufacturing, which relates, for example, to software solutions for defining manufacturing processes and operations. In such computer-aided design systems, the graphical user interface plays a key role with regard to the efficiency of the technology. These technologies can be incorporated into Product Lifecycle Management (PLM) systems. PLM refers to a business strategy that helps companies share product data, apply common processes and leverage corporate knowledge for product development, starting from conception to the end of the product life, across the concept of the extended enterprise. Dassault Systèmes' PLM solutions (product names: CATIA, ENOVIA, DELMIA) provide an Engineering Hub to organize product engineering knowledge, a Manufacturing Hub to manage product engineering knowledge, and an Enterprise Hub to enable enterprise integration and connectivity to both the Engineering and Manufacturing Hubs. All systems provide an open object model that connects products, processes and resources, enabling dynamic knowledge-based product creation and decision support that drives optimized product definition, manufacturing preparation, production and service.

[0003] In this and other contexts, machine learning is becoming more and more important.

[0004] Existing methods are relevant to the task of learning 3D shapes, but they give unrealistic results in CAD. Indeed, unlike images and videos, 3D shapes have no natural parameterization on a regular grid. Existing methods choose to represent 3D shapes with meshes, point clouds, voxels, or multi-view representations. These 3D representations do not take into account a fundamental property of 3D shapes, namely their hierarchical structure. CAD 3D data inherently includes this aspect through the definition of the product structure.

[0005] In recent years, the success of deep neural networks in computer vision, speech recognition, and natural language processing has led researchers to apply such models to 3D shape analysis. Most of these studies focus on extending computer vision techniques developed for images, i.e., 2D grids of pixels, to 3D grids of voxels. Approaches such as J. Wu et al.'s work (J. Wu, C. Zhang, T. Xue, WT Freeman, JB Tenenbaum, Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling, 2016) have been successful in learning a probabilistic latent space of object shapes in voxel form. At its core, the model is a generative decoder that takes a shape code as input and produces a voxel grid as output. The decoder is trained adversarially and can be chained with a traditional encoder that maps, for example, a 2D image to a corresponding shape code. The method supports simple arithmetic and interpolation of the codes, allowing, for example, topology-changing morphs between different shapes. However, these approaches cannot process hierarchically structured data, such as CAD data. Summary of the Invention [Problem to be solved by the invention]

[0006] In this context, there remains a need for improved methods for training generative autoencoders configured to generate feature structures. [Means for solving the problem]

[0007] In accordance with the present invention, a computer-implemented method for training a generative autoencoder is provided. The generative autoencoder is configured to generate a functional structure. The functional structure is a data structure representing a mechanical assembly of rigid parts. The data structure includes a tree. The tree includes leaf nodes. Each leaf node represents a shape and a configuration of each rigid part and forces acting on each rigid part. The tree further includes non-leaf nodes each having a number of children. Each non-leaf node each having a number of children represents a mechanical link between sub-assemblies. Each sub-assembly is represented by a respective one of the number of children. The tree further includes non-leaf nodes each having a child. Each non-leaf node each having a child represents a copy of a sub-assembly represented by a child. The method includes providing a dataset including the functional structure. The method further includes training a generative autoencoder on the dataset.

[0008] The method may include one or more of the following.

[0009] Said mechanical links are adjacency relations between said sub-assemblies, said adjacency relations optionally belonging to a predefined set of adjacency relations.

[0010] The replication is a symmetrical relationship between instances of the subassembly, optionally belonging to a predefined set of symmetrical relationships.

[0011] The shape and geometry of each rigid part is represented by data that includes the specification of a bounding box around each rigid part, and the forces acting on each rigid part are the resultant forces.

[0012] The generating autoencoder An encoder including a leaf encoding module, a mechanical link encoding module, and a duplicate encoding module; A decoder including a node classifier, a leaf decoding module, a mechanical link decoding module, and a duplicate decoding module.

[0013] the encoder is configured to encode the tree into a latent vector according to a recursive bottom-up process for a given functional structure; the leaf encoding module outputs, for each leaf node, a respective latent vector based on data including the bounding box specification and the resulting forces; the mechanical link encoding module outputs, for each non-leaf node representing a mechanical link, a respective latent vector based on the plurality of latent vectors encoding the plurality of children of the non-leaf node; the duplicate encoding module outputs, for each non-leaf node that represents a duplicate, a respective latent vector based on the latent vector encoding the one child of each of the non-leaf nodes; the decoder is configured to, for a given latent vector, decode the given latent vector into a tree of functional structures according to a recursive top-down process; the node classifier classifies each latent vector generated during decoding as corresponding to a leaf node, a non-leaf node representing a mechanical link, or a non-leaf node representing a duplicate; the leaf decoding module outputs, for each latent vector classified during decoding as corresponding to a leaf node, data including a respective bounding box specification and a respective resulting force based on the latent vector; the mechanical link decode module, for each latent vector classified during decoding as corresponding to a non-leaf node representing a mechanical link, outputs a plurality of child latent vectors based on the latent vector; the duplicate decoding module, for each latent vector classified during decoding as corresponding to a non-leaf node representing a duplicate, outputs a child latent vector based on the latent vector; one or more nodes of a tree of at least a portion of the functional structure of the dataset are each tagged with a label from a list of predefined labels, the method further comprising training a latent space classifier configured to receive a latent vector as input and tag the latent vector with a label from the list of predefined labels; and / or The bounding box and the resulting force are represented by the first and second coordinates, respectively, of the same vector.

[0014] Furthermore, a generative autoencoder that can be trained by the method is proposed, which comprises an encoder and a decoder.

[0015] Further, a computer-implemented method of using the generating autoencoder is proposed, the method of use comprising providing one or more latent vectors, the method of use further comprising generating a functional structure, the generating comprising decoding each latent vector with the decoder.

[0016] The method of use may include one or more of the following:

[0017] · Perform topology optimization of a mechanical assembly of rigid parts represented by the generated functional structure.

[0018] said generating generates forces, the forces being represented by leaf nodes of a tree included in said generated functional structure, said generated forces forming input to said topology optimization; and / or the autoencoder is trainable according to claim 6, the one or more latent vectors include a first latent vector and a second latent vector; the decoding includes generating a latent vector including an intermediate latent vector for each of the first latent vector and the second latent vector; The generating of the functional structure includes performing an interpolation operation between a first intermediate latent vector of the first latent vector and a second intermediate latent vector of the second latent vector based on the same labels tagging the first intermediate latent vector and the second intermediate latent vector.

[0019] Further provided is a computer program comprising instructions for carrying out said method and said method of use.

[0020] Furthermore, an apparatus is provided comprising the generated autoencoder and / or a data storage medium having the computer program recorded thereon.

[0021] The apparatus may form or function as a non-transitory computer readable medium, such as on a Software as a service (SaaS) or other server or cloud-based platform. Alternatively, the apparatus may comprise a processor connected to the data storage medium. Thus, the apparatus may form, in whole or in part, a computer system (e.g., the apparatus is a subsystem of an overall system). The system may further include a graphical user interface connected to the processor. Embodiments of the invention will now be described, by way of non-limiting example, with reference to the accompanying drawings, in which: [Brief description of the drawings]

[0022] [Figure 1] 1 shows a flow chart of a process for integrating the method and the method of use of the present application. [Diagram 2] 1 shows an example of the system of the present application. [Diagram 3] 1 illustrates the methods of the present application. [Figure 4] 1 illustrates the methods of the present application. [Diagram 5] 1 illustrates the methods of the present application. [Figure 6] 1 illustrates the methods of the present application. [Figure 7] 1 illustrates the methods of the present application. [Figure 8] 1 illustrates the methods of the present application. [Figure 9] 1 illustrates the methods of the present application. [Figure 10] 1 illustrates the methods of the present application. [Figure 11] 1 illustrates the methods of the present application. [Figure 12] 1 illustrates the methods of the present application. [Figure 13] 1 illustrates the methods of the present application. [Figure 14] 1 illustrates the methods of the present application. [Figure 15] 1 illustrates the methods of the present application. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0023] A computer-implemented method for training a generative autoencoder is proposed. The generative autoencoder is configured to generate a functional structure. The functional structure is a data structure representing a mechanical assembly of rigid parts. The data structure includes a tree. The tree includes leaf nodes. Each leaf node represents a shape and a configuration of each rigid part and forces acting on each rigid part. The tree further includes non-leaf nodes each having a number of children. Each non-leaf node with a number of children represents a mechanical link between sub-assemblies. Each sub-assembly is represented by a respective one of the number of children. The tree further includes non-leaf nodes each having one child. Each non-leaf node with a child represents a copy of a sub-assembly represented by one child. The method includes providing a dataset including the functional structure. The method further includes training a generative autoencoder on the dataset. Such a method is also referred to as a "learning method".

[0024] This constitutes an improved method for training a generative autoencoder configured to generate feature structures.

[0025] In particular, a generative autoencoder trained by the learning method is configured to generate on the fly (because it is generative) functional structures representing the respective mechanical assemblies of each rigid part, since it is trained on a dataset that includes such functional structures. The generative autoencoder generates these functional structures accurately (i.e., the level of realism of the generated functional structures is as close as possible to that of the dataset's functional structures), since it is trained to do so. Such functional structures are hierarchical data structures, since they include a tree that includes: leaf nodes, each representing the shape and arrangement of each rigid part and the forces acting on each rigid part; non-leaf nodes, each having multiple children, each representing a mechanical link between sub-assemblies (each sub-assembly is represented by one of the multiple children); and non-leaf nodes, each having one child, each representing a copy of the sub-assembly represented by the one child. In other words, the tree captures the relationships between parts and / or subassemblies of parts in a mechanical assembly of parts, i.e., mechanical links (e.g., adjacency relationships) and duplications (e.g., symmetric relationships), and their hierarchical arrangement. In other words, the present learning method produces an autoencoder that can process hierarchical data structures for mechanical assemblies of parts and can also generate such data structures on the fly. Thus, the present learning method allows the generation of physically realistic CAD data that can be directly utilized in the design and / or manufacturing process, as described below.

[0026] Moreover, feature structures are particularly suited to be used in (e.g., as) datasets for training generative autoencoders, e.g., they enable the generative autoencoder to achieve robust training on a provided dataset that includes feature structures. In addition, feature structures are much more compact data structures than low-level 3D models.

[0027] Moreover, each tree contained in the data set on which the generative autoencoder is trained by the present learning method has a leaf node representing the shape and arrangement of each rigid part. This means that the functional structure generated by the generative autoencoder contains a tree with such leaf nodes. The functional structures thus generated are thereby suitable for topology optimization (i.e. for performing a topology optimization on them). Indeed, as known per se from the field of topology optimization, a topology optimization algorithm / method / process executed on a mechanical assembly of parts (or a data structure or 3D modeling object representing it) takes as input notably physical forces, such as loads acting on the parts of said assembly. The present learning method produces an autoencoder capable of generating a data structure, i.e. leaf nodes, that contain data representing such forces. The present learning method thus produces an autoencoder capable of generating on the fly a data structure representing a mechanical assembly of parts and suitable for topology optimization.

[0028] In one example of the learning method, described further below, the generative autoencoder includes an encoder configured to, for a given functional structure, encode the tree into a latent vector according to a recursive bottom-up process. In one of these examples, the generative autoencoder includes a decoder configured to, for a given latent vector, decode the given latent vector into a tree of functional structures according to a recursive top-down process. In these examples, one or more nodes of the trees of at least some (e.g., all) of the functional structures of the dataset may each be tagged with a label from a list of predefined labels, and the method may further include training a latent space classifier. The latent space classifier is a neural network configured to take a latent vector as input and tag the latent vector with a label from a list of predefined labels.

[0029] In other words, the intermediate latent vector is generated by a recursive top-down decoding process that generates a tree contained in the functional structure by decoding a given latent vector into a tree. The intermediate latent vector is a latent vector that encodes three nodes, which may be a root node or a leaf or non-leaf node, neither of which is a root node. Each of these nodes may correspond to a significant substructure of the mechanical assembly of the parts. This means that an intermediate latent vector is generated during the decoding process that encodes a node that corresponds to a significant substructure of the mechanical assembly of the parts, such as a particularly significant subassembly of the parts. By training a latent space classifier on a tree in which the nodes corresponding to such substructures are tagged with a label from a predefined list of labels, the learning method produces a latent space classifier that can take as input the intermediate latent vector generated during the decoding process and tag it with a label from the list. The label indicates that the intermediate latent vector encodes a node that corresponds to a significant substructure or does not correspond to a substructure in particular (e.g., there may be a label corresponding to the absence of a label). In the first case, the latent space classifier, in other words, can identify and tag the intermediate significant substructure during the decoding process. This allows operations to be performed on and / or between sub-structures, such as interpolation operations and, which is a limiting case of interpolation, blending operations (as will be explained further below). Thus, a larger and / or more diverse number of functional structures can be generated by the generative autoencoder.

[0030] Furthermore, a generative autoencoder that can be trained by the present training method is proposed, which comprises an encoder and a decoder.

[0031] Further, a computer-implemented method of using the generating autoencoder is proposed, the method of use comprising providing one or more latent vectors. The method of use further comprises generating a functional structure, the generating comprising decoding each latent vector with the decoder. The method of use is also referred to as a "generating method."

[0032] In this manner, the method generates one or more functional structures. The method may generate multiple functional structures. For example, the generation may include fully decoding each latent vector into a respective functional structure (i.e., until the recursive top-down decoding is complete). In this manner, the method generates on the fly hierarchical data structures, each of which represents a physically realistic mechanical assembly of parts.

[0033] Alternatively or additionally, the one or more latent vectors may include a first latent vector and a second latent vector. In such a case, the decoding generates a latent vector including an intermediate latent vector for each of the first latent vector and the second latent vector. The generation of the functional structure may then include performing an interpolation operation between the first intermediate latent vector of the first latent vector and the second intermediate latent vector of the second latent vector based on the same label tagging the first intermediate latent vector and the second intermediate latent vector. The same label may in particular be obtained by applying a latent space classifier to both the first intermediate latent vector and the second intermediate latent vector. In either case, performing such an interpolation operation (or a blending operation, which is a limit case of the aforementioned interpolation) generates more and / or more diverse functional structures by merging / mixing significant substructures of the generated data structure.

[0034] The method may further comprise performing a topology optimization of the mechanical assembly of rigid parts represented by the generated functional structures. This is possible because, as described above, the tree of generated functional structures has leaf nodes representing the shape and the arrangement of each rigid part and the forces acting on each rigid part. The topology optimization may take as input, in particular, these forces (or at least a part of them) represented by the generated functional structures. The topology optimization may be performed on the mechanical assembly of rigid parts represented by all functional structures generated by the method, or at least a part of them. In this way, the method may produce as many topologically optimized mechanical assemblies of parts as there are generated functional structures.

[0035] The training and generation methods may be performed independently, e.g., by different users and / or on different computers, or they may be included in the same computer-implemented modeling process, which will now be briefly described with reference to Figure 1, which shows a flow chart of the modeling process.

[0036] The modeling process includes an offline phase. The offline phase includes the present learning method. The offline phase therefore includes in particular providing a dataset including the functional structure by the learning method (S10) and training a generative autoencoder on the dataset by the learning method (S20). The offline phase may further include training a latent space classifier by the learning method (S30). The modeling process may further include storing the trained generative autoencoder and, where appropriate, the trained latent space classifier in a memory.

[0037] The process further includes an online phase. The online phase includes a generation method of a generative autoencoder trained by a learning method in an offline phase. The online phase may in particular include obtaining (e.g., from a remote computer) the generative autoencoder trained in an offline phase and stored in memory as described above, and, if appropriate, the latent space classifier. In either case, the online phase includes providing one or more latent vectors by the generation method (S100) and generating a functional structure by the generation method (S200). The online phase may further include performing a topology optimization of a mechanical assembly of rigid parts represented by the generated functional structure by the generation method (S300).

[0038] It should be noted that the offline and online phases may be performed independently, for example by different users, at different times / phases, and / or on different computers.

[0039] The learning method, the generation method, and / or the modeling process may be included in a design process for designing a mechanical assembly of rigid parts. The design of the mechanical assembly of parts specifies any action or sequence of actions that is at least part of creating a 3D modeled object representing the mechanical assembly of parts. The design process may include generating a functional structure representing the mechanical assembly of parts, in particular using a generative autoencoder learned by the learning method and / or an offline phase of the modeling process. The generation may be generated in a generation method and / or in an online phase of the modeling process. In either case, the generated data structure may be such that a 3D modeled object representing the mechanical assembly of rigid parts can be directly deduced from the generated data structure, and the design process may include estimating and possibly displaying the 3D modeled object.

[0040] The design process may be a design process for designing a mechanical assembly of rigid parts or a 3D modeled object representing it via topology optimization. In such a case, the design process may in particular include the execution of topology optimization (S300) by a generative method and / or an online phase of the modeling process. As known per se, topology optimization is a computer-implemented technique that bridges the fields of product design and physical simulation. It is applied to the design of modeled objects representing mechanical parts (e.g. mechanical assemblies of rigid parts) that are formed in materials, subjected to loads in use and have one or more constraint boundaries. The technique focuses on automatically generating optimized generative designs based on changes in physical properties and behaviors that are typically simulated through finite element analysis (FEA). More specifically, topology optimization works by, for example, discretizing the data associated with the design space and meshing in small elements to provide a finite element mesh (FEM). The technique then finds the optimal distribution and layout of material in a given discretized space by iteratively finding the most efficient elements with respect to a particular objective function (e.g. related to the stiffness of the design) and a set of constraints (e.g. related to the total amount of material allowed).

[0041] The design process may further be included in a manufacturing process, which may include, after performing the design process, manufacturing a physical product corresponding to the 3D modeled object designed / generated by the design process. In either case, the 3D modeled object designed by the design process may represent a manufacturing object. In this way, the modeled object may be a modeled solid (i.e., a modeled object representing a solid).

[0042] The learning methods, generation methods and modeling processes are computer-implemented. Computer-implemented methods (or processes) are now described.

[0043] By "a method (or process) is computer-implemented" it is meant that the steps (or substantially all steps) of the method (or process) are performed by at least one computer or any similar system. Thus, the steps of the method (or process) may be performed fully automatically or semi-automatically by a computer. In one example, at least some of the steps of the method (or process) may be triggered via user interaction. The level of user-computer interaction required may depend on the level of automaticity envisaged, balancing the need to implement the user's wishes. In one example, this level may be user-set and / or predefined.

[0044] A typical example of implementing the method (or process) by a computer is carrying out the method (or process) using a system suitable for this purpose. The system may comprise a processor connected to a memory having a computer program recorded thereon, the computer program including instructions for carrying out the method (or process), and a graphical user interface (GUI). The memory may store a database. The memory is any hardware suitable for such storage, and optionally includes multiple physically distinct parts (e.g. one for the program and optionally one for the database).

[0045] FIG. 2 shows an example of the system, which is a client computer system, such as a user's workstation.

[0046] The client computer of this example comprises a central processing unit (CPU) 1010 connected to an internal communication bus 1000, and a random access memory (RAM) 1070 also connected to the bus. The client computer further comprises a graphics processing unit (GPU) 1110 associated with a video random access memory 1100 connected to the bus. The video RAM 1100 is also known in the art as a frame buffer. A mass storage controller 1020 manages access to mass storage devices such as a hard drive 1030. Mass memory devices suitable for embodying computer program instructions and data include all types of non-volatile memory including, by way of example, semiconductor memory devices such as EPROM, EEPROM and flash memory devices, magnetic disks such as internal hard disks and removable disks, magneto-optical disks, and CD-ROM disks 1040. Any of the foregoing may be supplemented by or incorporated in specially designed ASICs (application specific integrated circuits). A network adapter 1050 manages access to a network 1060. The client computer may also include a tactile device 1090 such as a cursor control device, a keyboard, etc. A cursor control device is used within the client computer to allow a user to selectively position a cursor at any desired location on the display 1080. In addition, the cursor control device allows a user to select various commands and input control signals. The cursor control device includes a number of signal generating devices for inputting control signals into the system. Typically, the cursor control device may be a mouse, with the buttons of the mouse being used to generate the signals. Alternatively, or additionally, the client computer system may include a sensing component and / or a sensing screen.

[0047] A computer program may include instructions executable by a computer, the instructions including means for causing said system to carry out the learning, generating and / or modeling process. The program may be recordable on any data storage medium including the memory of the system. The program may be implemented, for example, in digital electronic circuitry, or computer hardware, firmware, software, or a combination thereof. The program may be implemented as an apparatus, such as an article of manufacture tangibly embodied in a machine-readable storage device for execution by a programmable processor. The steps of the process / method may be carried out by a programmable processor executing a program of instructions and performing the functions of the process by manipulating input data to generate output. Thus, the processor may be programmable to receive data and instructions from, and may be connected to, a data storage system, at least one input device, and at least one output device. The application program may be implemented in a high level procedural or object oriented programming language, or in assembly or machine language as appropriate. In either case, the language may be a compiled or interpreted language. The program may be a full installation program or an update program. In either case, the program is applied to the system to provide instructions for carrying out the learning, generating, and / or modeling process.

[0048] A mechanical assembly of rigid parts represented by a functional structure intended in the method, the generation method and / or the modeling process may further be represented by a modeled object, for example deduced from the functional structure as described above. A modeled object is any object defined by data stored in, for example, a database. Furthermore, the expression "modeled object" also refers to the data itself. Depending on the type of system, the modeled object may be defined by different kinds of data. The system may be a CAD system. In such a system, the modeled object is defined by the corresponding data. Thus, one may speak of a CAD object.

[0049] A CAD system also means any system suitable for designing a modeled object based on at least a graphical representation of the modeled object, such as CATIA. In this case, the data defining the modeled object includes data allowing the modeled object to be represented. The CAD system may provide a representation of the CAD modeled object, for example using edges and lines, and possibly also using faces and surfaces. The lines, edges or surfaces may be represented in various ways, for example using Non-Uniform Rational B-Splines (NURBS). In particular, a CAD file contains a specification based on which a geometry and thus a representation can be generated. The specification of the modeled object may be stored in one or more CAD files. A typical size of a file representing a modeled object in a CAD system is in the range of one megabyte per part. A modeled object may also typically be a collection of several thousand parts.

[0050] In the context of CAD, a modeled object is typically a 3D modeled object, e.g., a product, such as a part or a collection of parts, or may represent a collection of products. "3D modeled object" means any object modeled by data capable of a 3D representation. The 3D representation allows the part to be viewed from all angles. For example, a 3D modeled object represented in 3D can be manipulated and rotated about any of its axes or about any axis in the display on which the representation is displayed. This specifically excludes 2D icons that are not 3D modeled. Displaying 3D representations facilitates design (i.e., statistically speeds up the speed at which designers accomplish their tasks). Since designing products is part of the manufacturing process, this speeds up the manufacturing process in the industry.

[0051] A 3D modeled object may represent the geometry of a product, such as a part (e.g., a machine), a collection of parts (or equivalently a collection of parts, since a collection of parts can be viewed as a part in terms of this disclosure), or more generally any collection of rigid bodies (e.g., a moving mechanism), that is manufactured in the real world after completion of a virtual design using a CAD software solution, CAD system, etc. CAD software solutions enable the design of products in various industry sectors, including, but not limited to, aerospace, architecture, construction, consumer goods, high tech equipment, industrial equipment, transportation, marine, and / or offshore oil / gas production, or traffic. The 3D modeled objects designed according to the present disclosure may thus represent industrial products that may be any mechanical part, such as ground vehicle parts (including, for example, automobiles and light truck equipment, racing cars, motorcycles, trucks and motor equipment, trucks, buses, trains), air vehicle parts (including, for example, airframe equipment, aerospace equipment, propulsion equipment, defense products, airline equipment, space equipment), naval vehicle parts (including, for example, naval equipment, commercial vessels, offshore equipment, yachts and workboats, marine equipment), general mechanical parts (including, for example, industrial manufacturing machinery, large mobile machines or equipment, installation equipment, industrial equipment products, fabricated metal products, tire manufacturing products), electromechanical parts, or electronic parts (including, for example, appliances, security and / or control and / or instrumentation products, computing and communications equipment, semiconductors, medical devices and equipment), consumer products (including, for example, furniture, home and garden products, leisure products, fashion products, durable consumer retail products, textile retail products), packaging (including, for example, food and beverage and tobacco, beauty and personal care, household product packaging), etc.

[0052] The concept of mechanical assembly of rigid parts will now be described.

[0053] A mechanical assembly of rigid parts specifies a set of rigid parts linked into an assembly by a set of relations. Rigid parts specify parts that have negligible deformation capabilities when compared to other types of parts, such as deformable parts. Each relation is a relationship between two or more rigid parts that describes a relative arrangement between the two or more rigid parts such that the two or more rigid parts satisfy one or more geometric constraints (such as a symmetrical arrangement of the two or more parts) and / or one or more physical constraints (such as a mechanical link linking the two or more parts). Such a relationship determines a position or a set of possible positions of the two or more rigid parts involved in the relationship. However, the set of relations incorporates multiple relations in a hierarchical manner such that all rigid parts in the set of rigid parts are positioned relative to each other to satisfy all the relations in a particular order, thereby forming a 3D mechanical assembly of rigid parts. Thus, an assembly of rigid parts and the way in which rigid parts are assembled together is captured by a basic hierarchy of relations that organizes rigid parts and / or subassemblies of rigid parts in relation to each other. An assembly is referred to as a "mechanical assembly" because the relationships between rigid parts and their hierarchies are driven by mechanical constraints (such as structural, functional, and / or manufacturing constraints) and / or mechanical requirements (such as structural, functional, and / or manufacturing requirements). An assembly of rigid parts includes subassemblies of rigid parts which are themselves assemblies of rigid parts contained in the assembly. It should be understood that a rigid part can be considered to be a subassembly.

[0054] A subassembly may be what is referred to as a "significant substructure." A significant substructure specifies a subassembly of a mechanical assembly of parts that satisfies any one or any combination of the following:

[0055] · Subassemblies are functional groups, i.e. they perform a specific mechanical function.

[0056] Sub-assemblies have a specific function.

[0057] · A subassembly contains certain independent subassemblies.

[0058] · Subassemblies are subject to a particular set of manufacturing, structural, and / or functional constraints.

[0059] The subassembly is manufactured using a specific manufacturing process (e.g., different from other manufacturing processes used to manufacture other subassemblies); and / or The subassembly is produced at a particular step in a manufacturing process (e.g., distinct from other steps in the manufacturing process used to produce the mechanical assembly), e.g., that step involves particular mechanical and / or manufacturing considerations.

[0060] The generative autoencoder is configured to generate a functional structure, which is a data structure that represents a mechanical assembly of rigid parts. The data structure will now be described.

[0061] The data structure includes (e.g. is) a tree. A tree is a data structure that describes and captures relationships between rigid parts in a mechanical assembly of rigid parts, and the organization and hierarchy between the relationships and parts. The tree may be any tree, for example a binary tree. As known per se, each non-leaf node of a binary tree has one or two child nodes. The tree includes a root node, which represents (e.g. corresponds to) the entire mechanical assembly of rigid parts. The tree further includes leaf nodes, each corresponding to a rigid part of the assembly, and non-leaf nodes (also called internal nodes), each corresponding to a subassembly of rigid parts within the assembly. Leaf nodes and non-leaf nodes will now be described.

[0062] The tree includes leaf nodes that represent the shape and location of each rigid part and the forces acting on each rigid part. In other words, a leaf node corresponds to an inseparable part of a mechanical assembly of rigid parts, i.e., one rigid part of the assembly. Such leaf nodes will now be described.

[0063] "Representing the shape and arrangement of each rigid part, and the forces acting on each rigid part" means that the leaf includes data representing the shape and arrangement of each rigid part, and data representing the forces acting on each rigid part.

[0064] The data describing the shape and geometry of each rigid part may include any information describing the shape, geometry, type of geometry (e.g., type of geometric primitive), and / or position in space (e.g., position relative to other rigid parts and / or a 3D coordinate system) and / or semantics of each rigid part. Such information may be based on simple representations of each rigid part, such as bounding boxes and / or canonical shapes.

[0065] The data representing the forces acting on each rigid part may include any information representing a resultant external force acting on each rigid part. Thus, the data representing the forces acting on each rigid part may specify a resultant external force acting on each rigid part. The resultant force is a resultant of limit external forces that may act on each rigid part before each rigid part breaks and / or each rigid part satisfies a constraint (e.g., manufacturing constraints, structural constraints, and / or functional constraints).

[0066] In one example, the shape and location of each rigid part is represented by data including a specification of a bounding box around each rigid part, e.g., parameters characterizing the bounding box and / or coordinates. In these examples, the forces acting on each rigid part are resultant forces, as described above. The data including the bounding box specification may further include a specification of the shape of each rigid part, such as one or more parameters characterizing (e.g., identifying) a type of geometric primitive.

[0067] In one example, the bounding box and the resulting force are represented by a first coordinate and a second coordinate, respectively, of the same vector. In other words, a leaf node includes a vector having a first coordinate and a second coordinate. The first coordinate is a parameter that characterizes a bounding box around each rigid part. The second coordinate is a parameter that characterizes the resulting force, such as the coordinate of a resultant vector of external forces corresponding to the sum of all external force vectors applied to (e.g., a point on) the bounding box around each rigid part. The vector may optionally include one or more third coordinates that characterize (e.g., identify) a type of geometric primitive corresponding to the shape of each rigid part.

[0068] The tree further includes non-leaf nodes, each having a number of children, each representing a mechanical link between sub-assemblies, each sub-assembly being represented by a respective one of the children. Such non-leaf nodes will now be described.

[0069] Each child of the plurality of children is either a leaf node (i.e., corresponds to a rigid part of an assembly that is also a subassembly of the part itself) or another non-leaf node (i.e., corresponds to a subassembly of a rigid part in an assembly). A mechanical link is a relationship that links a part and a subassembly of a part, each represented by a child. Thus, a mechanical link characterizes the placement of said part and subassembly of a part relative to each other, as described above. In one example, a mechanical link is described by a vector of mechanical link parameters. In other words, in these examples, a non-leaf node includes a vector of mechanical link parameters, i.e., a vector having coordinates that are parameters that characterize the mechanical link. In other words, in addition to describing the placement of the subassemblies or parts relative to each other, a non-leaf node may include a vector of parameters that further specify the mechanical links between the subassemblies that will place them relative to each other. In an alternative example, a non-leaf node may not include such a vector of parameters, and in such an alternative, a mechanical link is completely characterized by its children.

[0070] In one example, the mechanical link is an adjacency relationship between subassemblies, possibly belonging to a set of predefined adjacency relationships. The predefined set of adjacency relationships may include (e.g., consist of) adjacency relationships called static adjacency relationships and / or adjacency relationships called kinematic relationships. In other words, the mechanical link may be one of static adjacency relationships and kinematic adjacency relationships. A static adjacency relationship between two or more subassemblies of a rigid part is a relationship that describes the static contact and / or relative positioning (e.g., by a static mechanical link) between the two or more subassemblies. A static adjacency relationship may be defined as an adjacency relationship with a degree of freedom equal to zero. Subassemblies mechanically linked by static adjacency relationships have a fixed relative positioning, i.e., cannot move relative to each other. A kinematic adjacency relationship between two or more subassemblies of a rigid part is a relationship that describes the kinematic contact and / or relative positioning (e.g., by a kinematic mechanical link) between the two or more subassemblies. A kinematic adjacency relationship may be defined as an adjacency relationship with a degree of freedom equal to one or more. Subassemblies that are mechanically linked by kinematic abutment relationships do not have fixed relative orientation, i.e., they can move relative to one another.

[0071] The tree further includes non-leaf nodes, which have one child and each represent a copy of the sub-assembly represented by the child. Such non-leaf nodes are now described.

[0072] A child may be a leaf node or another non-leaf node. "Representing a copy of a sub-assembly represented by a child" means that the non-leaf node represents multiple instances of the same rigid part or sub-assembly of a rigid part within an assembly. The non-leaf node may further include data specifying the placement of these multiple instances relative to each other and / or the number of these instances.

[0073] In one example, the replication is a symmetry relationship between instances of the subassembly, which possibly belongs to a set of predefined symmetry relationships. The symmetry relationship between instances of the subassembly is a relationship that specifies a symmetric arrangement of the instances with respect to each other. The predefined set of symmetry relationships may include (e.g., consist of) pairwise mirror symmetry, k-fold rotational symmetry, and k-fold translational symmetry. In other words, the symmetry relationship may be one of mirror symmetry, k-fold rotational symmetry, and k-fold translational symmetry.

[0074] Pairwise mirror symmetry is a symmetric relationship between two instances of the same subassembly. It is parameterized by a reflection plane, and specifies that the arrangement of the two instances is symmetric with respect to this plane.

[0075] k-fold rotational symmetry is a symmetry relationship between k instances of the same subassembly, where k is an integer greater than or equal to 2. It is parameterized by a number k and an axis of rotation. It specifies that the arrangement of the instances is such that they are two by two images of each other with the same rotation about the axis of rotation.

[0076] k-fold translational symmetry is a symmetry relationship between k instances of the same subassembly, where k is an integer greater than or equal to 2. It is parameterized by a count k and a translation offset. It specifies that the arrangement of the instances is a 2x2 image of each other with the same translation characterized by the translation offset.

[0077] In one example, the symmetric relationship is described by a vector of symmetric relationship parameters. In other words, the non-leaf node includes a vector having coordinates that are symmetric relationship parameters. The coordinates may include one or more first coordinates that specify a type of symmetric relationship among pairwise mirror symmetry, k-fold rotational symmetry, and k-fold translational symmetry. The coordinates may include one or more second coordinates that specify a number of instances that are replicated by the symmetric relationship. The coordinates may include one or more third coordinates that specify a geometric parameter of the symmetric relationship, such as a reflection plane, a rotation axis, or a translation offset as described above.

[0078] An example of a mechanical assembly of parts and their functional structure will now be described.

[0079] In the context of this disclosure, a mechanical assembly of parts may be a chair, which often (but not always) may include four significant substructures: a leg substructure (i.e., the group of chair legs), an arm substructure (i.e., the group of chair arms), a seat, and a back.

[0080] An example of such a chair and its functional structure will now be described with reference to Figures 3 and 4. Figure 4 shows a 3D representation 30 of the chair displayed together, and Figure 3 shows a functional structure tree 32 representing the chair 30.

[0081] The tree 32 includes a leaf node "arm.1" that represents the shape and configuration of one of the chair's two arms and the forces acting on it. The leaf node "arm.1" is a child of the non-leaf node "arm" that represents a duplication of "arm.1". The duplication is a symmetrical relationship between the arm represented by "arm.1" and the other arm of the chair. The node "arm.2" that represents the other arm of the chair is shown in FIG. 3 as another child of "arm" for convenience. The symmetrical relationship is pairwise mirror symmetry (with reference to FIG. 4, mirror symmetry is symmetry with respect to a vertical mid-plane of the chair 30 that is generally perpendicular to the chair back 4000, and may be stored as a vector that specifies the configuration of that plane and the type of symmetry). The non-leaf node "arm" represents a significant substructure formed by the arms of the chair.

[0082] The tree 32 further includes two leaf nodes, "leg.1.1.1" and "leg.1.1.2", which respectively represent the shape and arrangement of one of the two parts 34 and 36 of the chair leg and the forces acting on said one of the two parts 34 and 36. The tree 32 further includes a non-leaf node, "leg.1.1", which represents the adjacency relationship that assembles the two parts 34 and 36 represented by the two child nodes, "leg.1.1.1" and "leg.1.1.2", of "leg.1.1". "leg.1.1" is a child of "leg.1", which represents a duplication of the assembly represented by "leg.1.1". The duplication is a symmetric relationship between the assembly represented by "leg.1.1" and another instance of it. The node "leg.1.2", which represents the other instance, is shown for convenience as another child of "leg.1". This symmetric relationship is pairwise mirror symmetry. "leg.1.2" represents the other of the two legs of the chair, which consists of the assembly of parts 340 and 360. Parts 340 and 360 are conveniently represented in FIG. 3 as leaf nodes "leg.1.2.1" and "leg.1.2.2", respectively, which are images of parts 34 and 36, respectively, with paired mirror symmetry. The tree 32 further includes a leaf node "leg.2", which represents the shape and arrangement of part 38 and the forces acting on it. The leaf node "leg.2" and the non-leaf node "leg.1" are two children of the non-leaf node "leg", which represent the adjacency relationship that combines the two symmetric legs of the chair, represented by "leg.1", with part 38, represented by node "leg.2". The non-leaf node "leg" represents a significant substructure formed by the legs of the chair.

[0083] The tree 32 further includes a leaf node "back.1.1" that represents the shape and arrangement of the part 40 and the forces acting on it. The node "back.1.1" is a child of the non-leaf node "back.1" that represents a duplication of the part 40. Duplication is a symmetrical relationship between the part 40 and another instance of it, namely the part 400. The node "back.1.2" that represents the part 400 is shown in FIG. 3 as another child of "back.1" for convenience. The leaf node "back.2" represents the shape and arrangement of the part 4000 and the forces acting on it. The tree 32 further includes a non-leaf node "back" that represents an adjacency relationship that combines the part 400 with the two instances of the part 40 represented by the node "back.1". The node "back" represents a significant substructure formed by the back of the chair.

[0084] Tree 32 further includes a non-leaf node "assembly 1," which represents an adjacency relationship combining the seat of the chair, represented by the leaf node "seat," with the arm of the chair, represented by the non-leaf node "arm."

[0085] Tree 32 further includes a non-leaf node "assembly 2," which represents an adjacency relationship combining the subassembly represented by node "assembly 1" with the chair leg represented by non-leaf node "leg."

[0086] Tree 32 further includes a root node "chair," which represents the entire chair, and an adjacency relationship that combines a subassembly, represented by node "assembly 2," with the back of the chair, represented by the non-leaf node "back."

[0087] In the context of this disclosure, a mechanical assembly of rigid parts may be an automobile, which often (but not always) may include significant substructures such as:

[0088] ·Body substructure, which may include one or more of the following: hood, bumpers, fenders, pillars, rockers, roof, quarter panels, trunk, doors, windows, and / or floor.

[0089] The interior substructure, which may include seats and / or dashboard; and ·The chassis substructure, which may include one or more of the following: suspension, wheels, drive shafts, braking system, steering system, and / or engine components.

[0090] A tree of functional structures representing automobiles will often (but not always) contain one or more of the following nodes:

[0091] Non-leaf nodes, each of which represents a pairwise mirror relationship between an instance of a front door (represented by a leaf node), a back door (represented by a leaf node), a mirror (represented by a leaf node), a headlight (represented by a leaf node), or a seat (represented by a leaf node).

[0092] · A non-leaf node “a_1” that represents the adjacency relationship between the left front wheel (represented by a leaf node) and the left front suspension (represented by a leaf node).

[0093] A non-leaf node "s_1" representing the pairwise mirror symmetry between instances of the symmetric assembly represented by node "a_1", one of which is the assembly consisting of the right front wheel and the right front suspension.

[0094] A non-leaf node "s_2" representing the pairwise mirror symmetry between instances of the symmetric assembly represented by node "s_1", one of which is the rear wheels and rear suspension.

[0095] · A non-leaf node “a_2” representing the adjacency relationship between the symmetric assembly represented by node “s_2” and the drive shaft (represented by a leaf node).

[0096] A non-leaf node "s_3" representing the pairwise mirror image between instances of rear seats (represented by leaf nodes) of which one is a front seat.

[0097] · A non-leaf node “a_3” which represents the adjacency relationship between the car floor (represented by a leaf node) and the symmetric assembly represented by node “s_3”.

[0098] A non-leaf node “a_4” that represents an adjacency relationship between the assembly represented by node “a_3” and the dashboard of the car (represented by a leaf node). Node “a_4” also represents the “interior” substructure of the car.

[0099] In the context of this disclosure, a mechanical assembly of parts may be a chair. An articulated robot may contain significant substructures, each of which corresponds to a particular function of the robot, such as a grasping function, and each of which may be represented by an adjacency relationship.

[0100] Other examples of mechanical assemblies of parts and their functional structures will now be described.

[0101] In the context of this disclosure, the mechanical assembly of rigid parts may be any type of vehicle, such as an automobile (see above), a motorcycle, a truck, or an airplane. Alternatively, the mechanical assembly of rigid parts may be any type of furniture, such as a chair (see above). Alternatively, the mechanical assembly of rigid parts may be any type of robot, such as an articulated robot (see above). In one example, these object classes / categories all represent high-level symmetrical relationships between parts and / or subassemblies. For example, these object classes / categories may be such that at least 50% of the parts and / or subassemblies are directly or indirectly involved in symmetrical relationships. Alternatively or additionally, these object class categories may be such that parts are organized into multiple (e.g., four or more) coherent substructures. Adjacency relationships allow such substructures to be represented / created. These substructures may correspond to meaningful substructures in terms of functionality or independent subassemblies. Such representation of substructures allows designers to focus on specific substructures.

[0102] Here, the provision of the functional structure data set (S10) will be described.

[0103] Providing the data set (S10) may include retrieving at least some of the functional structures (e.g. all of them) from a memory (e.g. from a remote computer). Providing the functional structures (S10) may additionally or alternatively include creating at least another part of the functional structures, respectively. Creating the functional structures may consist of creating the functional structures from scratch (e.g. graphically) and may in particular include identifying nodes and their arrangement to form a tree of the functional structures. Alternatively, creating the functional structures may include retrieving existing initial functional structures (e.g. from a memory or a library, such as the Shapenet library for chair models) and modifying them to obtain the functional structures. For example, the initial functional structure may include a tree, but the leaf nodes of the tree (or at least some of them) may not include data representing forces acting on the rigid parts represented by the leaf nodes. In such a case, the modification may consist of adding said data representing forces to said leaf nodes. Providing the data set (S10) may be performed by a user.

[0104] The data set may consist of, or consist essentially of, feature structures representing mechanical assemblies of rigid parts that all belong to the same class of mechanical assemblies of rigid parts. In one example, mechanical assemblies of rigid parts form a class of mechanical assemblies of rigid parts if they all satisfy one or more criteria. These one or more criteria may each be any one or combination of the following conditions:

[0105] · Mechanical assemblies of rigid parts are all manufactured using the same manufacturing process or the same combination of manufacturing processes.

[0106] · Mechanical assemblies of rigid parts all from the same technical field and / or industry.

[0107] · Mechanical assemblies of rigid parts all perform the same or similar mechanical functions.

[0108] · A mechanical assembly of rigid parts consists of rigid parts that are all identical or at least substantially similar.

[0109] · Mechanical assemblies of rigid parts all have the same, or at least a similar, basic hierarchy.

[0110] Mechanical assemblies of rigid parts have significant substructures of similar types.

[0111] The mechanical assemblies of rigid parts all have the same or substantially the same shape; and / or · Mechanical assemblies of rigid parts are all subject to the same mechanical, functional, manufacturing, and / or structural constraints.

[0112] In one example, the data set consists or consists essentially of functional structures each representing an automobile, i.e. a mechanical assembly of parts belonging to a class of automobiles.

[0113] In another example, the data set consists or consists essentially of functional structures each representing an airplane, i.e., a mechanical assembly of parts belonging to a class of airplanes.

[0114] In another example, the data set consists or consists essentially of functional structures each representing a chair, i.e. a mechanical assembly of parts belonging to a class of chairs.

[0115] In another example, the data set consists or consists essentially of functional structures each representing an articulated robot, i.e. a mechanical assembly of parts belonging to a class of articulated robots.

[0116] We now describe training of the generative autoencoder (S20). First, we explain the general concepts of "machine learning" and "training neural networks", as well as other related concepts.

[0117] As known from the field of machine learning, the processing of an input by a neural network involves applying an operation to the input, the operation being defined by data including the weight values. Thus, training a neural network involves determining the values ​​of the weights based on a data set configured for such training, which may be called a learning or training data set. To that end, the data set includes data each forming a training sample. The training samples represent the diversity of situations in which the neural network will be used after training. The data set referred to here may include 1000, 10000, 100000 or even more than 1000000 training samples. In the context of the present disclosure, "training a neural network on a data set" means that the data set is the learning / training set of the neural network.

[0118] A generative autoencoder is a deep neural network (DNN) that is a combination of a variational autoencoder (VAE) and a generative adversarial network (GAN). A generative autoencoder is a VAE with an additional discriminative network, which is added during training (S20). This discriminative network is trained (during training (S20)) to perform a binary classification by classifying the output of the VAE into two classes: “real” or “fake”. As it is known per se, “fake” means that it is actually generated by the VAE and “real” means that it comes from the dataset of the feature structure provided (S10). A generative autoencoder is sometimes called a VAE-GAN. A generative autoencoder can be trained / learned (S30) by using any machine learning technique adapted to train such neural networks. The training may include minimizing multiple losses, including, inter alia, a reconstruction loss, an adversarial loss, a cross-entropy loss, and a GAN loss, for example by one or more gradient descent algorithms. The reconstruction loss may include a so-called KL divergence term. The generative autoencoder may be trained (S20) to faithfully reconstruct the input tree of the functional structure, in particular, and the reconstruction loss measures the (e.g., L2) distance between the input tree and the output tree reconstructed by the autoencoder. Thus, the encoding and decoding functions of the autoencoder are bijective functions.

[0119] Deep Neural Networks, as they are known per se, are neural networks trained by deep learning techniques, which are a powerful set of techniques for training neural networks, a biologically inspired programming paradigm that allows computers to learn from observed data. In image recognition, DNNs can learn rich mid-level media representations, as opposed to the manually designed low-level features (Zernike moments, HOG, Bag-of-Words, SIFT, etc.) used in other image classification methods (SVM, Boosting, Random Forest, etc.). More specifically, DNNs focus on end-to-end learning based on raw data. In other words, they move away from feature engineering as much as possible by achieving an end-to-end optimization starting from raw features and ending with labels.

[0120] As they are known per se, a discriminative deep neural network is a function that is trained to estimate a discrete or continuous value y given an input x. It is trained on a dataset of pairs (x, y).

[0121] Deep generative models, as they are known per se, are a class of deep neural networks that learn to replicate the data distribution of the dataset they are trained on. There are two classes of deep generative models: variational autoencoders and generative adversarial networks. Hybrid generative models can be built from these two, namely, variational autoencoders and generative adversarial networks such as generative autoencoders.

[0122] As it is known per se, a variational autoencoder consists of two parts: an encoder and a decoder. The encoder receives an input x and outputs a distribution probability. This distribution is set to be Gaussian, so the encoder outputs two vectors of equal size, mu and sigma. The decoder then tries to reconstruct x given z sampled from the distribution output by the encoder.

[0123] As it is known per se, GANs are trained to generate “realistic” samples when given a dataset of real-world samples during the training phase. For example, if a GAN is trained on a dataset of flower images, once training is complete, the GAN can generate images of flowers that look very realistic. A GAN consists of two networks: a generator and a discriminator. The generator takes as input low-dimensional latent variables z sampled from a Gaussian distribution. The output of the generator, f(z), is a sample of the same type as the data in the training dataset. For example, if the training data is 512x512 images, then f(z) is 512x512 images, and if the training data is a binary tree, then f(z) is a binary tree. The trick to training the generator is to use a discriminator trained to perform a binary classification on the input, between two classes, i.e. “real” and “fake”. That input needs to be classified as “real” if it comes from the training dataset, or as “fake” if it comes from the generator. During training, the discriminator is trained to perform its binary classification task, while the generator is trained to "fool" the discriminator by generating samples that are classified as "real" by the discriminator. To train both networks together, a special loss called the adversarial loss can be used.

[0124] Thus, generative autoencoders are generative. As explained above, a neural network is said to be "generative" if it learns the distribution of training data. Only generative models can generate new data. Non-generative autoencoders can only reduce and reconstruct latent vectors for small-sized input data (images 3D shapes), but cannot generate new data (e.g., from random latent vectors). Thus, generative autoencoders can generate new feature structures on the fly that generate "realistic" feature structures similar to those of the provided (S10) dataset.

[0125] Furthermore, the generative autoencoders are recurrent neural networks, such that each is trained on a training (S20) dataset of functional structures that include a tree.

[0126] As known per se, a recurrent neural network is a kind of deep neural network consisting of recurrent modules. These modules are of two types: encoding modules and decoding modules. An encoding module takes multiple (e.g., two) fixed-size vectors as input and outputs one fixed-size vector. The number of inputs of the encoding module is fixed. An encoding module takes multiple (e.g., two) fixed-size vectors as input and outputs one fixed-size vector. The number of outputs of the decoding module is fixed and equal to the number of inputs of the corresponding encoding module. Thus, a generative autoencoder is a VAE-GAN with a recurrent module as described above. The encoder network converts a variable-size input tree structure into a fixed-size latent vector by repeatedly folding the child nodes represented as codes into a merged code in a bottom-up manner. By the reverse process, the decoder network is trained to recover the input tree structure from the final latent code output by the encoder network. For training (S20) of the generative neural network, any machine learning technique can be used that can train a VAE-GAN with a recurrent module.

[0127] We now further explain the recurrent module of the generative autoencoder.

[0128] In one example, the generating autoencoder includes an encoder and a decoder. In one of these examples, the encoder includes a leaf encoding module, a mechanical link encoding module, and a duplicate encoding module. The leaf encoding module, the mechanical link encoding module, and the duplicate encoding module are recursive modules as described above. In one of these examples, the decoder includes a node classifier, a leaf decoding module, a mechanical link decoding module, and a duplicate decoding module. The leaf decoding module, the mechanical link decoding module, and the duplicate decoding module are recursive modules.

[0129] These examples will now be further explained.

[0130] In one example described herein, the encoder is configured to encode a tree (i.e., a tree of a given functional structure) into a latent vector according to a recursive bottom-up process for a given functional structure. In other words, the encoder takes a tree of a given functional structure as input and outputs a latent vector. The encoder does this by recursively aggregating (or collapsing) the nodes of the tree into successive latent vectors until a root node is reached, using its encoding module. At the end of this recursive bottom-up encoding process, the tree is encoded into a latent vector.

[0131] During the bottom-up encoding process, the leaf encoding module outputs, for each leaf node, a respective latent vector. The leaf encoding module does this based on data including bounding box specifications and resulting forces. In one example, this means that for each leaf node, the leaf encoding module takes as input data including bounding box specifications (i.e., bounding boxes around the rigid parts whose shape and position are represented by the leaf node) and resulting forces (i.e., forces acting on said rigid parts) and outputs a respective latent vector. As mentioned above, this data is or includes a vector having a first coordinate characterizing the bounding box around the respective rigid part, a second coordinate characterizing the resulting forces, and possibly a third coordinate characterizing the type of geometric primitive. In such a case, the leaf encoding module converts this vector into a respective latent vector.

[0132] During the bottom-up encoding process, the mechanical link encoding module outputs a respective latent vector for each non-leaf node representing a mechanical link. The mechanical link encoding module does so based on a plurality of latent vectors encoding a plurality of children of each non-leaf node. In one example, this means that for each non-leaf node representing a mechanical link, each child of the non-leaf node is previously encoded in a latent vector, the mechanical link encoding module takes as input all these latent vectors and outputs the respective latent vector. As mentioned above, the non-leaf node may further include a vector of mechanical link parameters. In such a case, the mechanical link encoding module may take as input, in addition to the above-mentioned latent vector, a vector of mechanical link parameters and output a respective latent vector, where if no mechanical link exists, the vector of mechanical link parameters is, for example, null. Alternatively, the encoder may include a first mechanical link encoding module and a second mechanical link encoding module. For each non-leaf node representing a mechanical link that does not have a vector of mechanical link parameters, the first mechanical link encoding module takes as input all latent vectors representing the child nodes of the non-leaf node and outputs the respective latent vector. A second mechanical link encoding module takes as input, for each non-leaf node representing a mechanical link having a vector of mechanical link parameters, all latent vectors representing child nodes of the non-leaf node and the vector of mechanical link parameters, and outputs the respective latent vector.

[0133] During the bottom-up encoding process, the duplication encoding module outputs a respective latent vector for each non-leaf node that represents a duplication. The duplication encoding module does so based on a latent vector encoding one child of each non-leaf node. In one example, this means that for each non-leaf node that represents a duplication for which one child of the non-leaf node has been previously encoded in a latent vector, the duplication encoding module takes as input this latent vector and outputs a latent vector. The duplication encoding module may further take as input the above-mentioned data specifying the arrangement of the multiple instances of the subassembly represented by the one child node relative to each other. In particular, as mentioned above, this data may be or include a vector of symmetrical relationship parameters in examples where the duplication is a symmetrical relationship. In such a case, the duplication encoding module takes as input the above-mentioned latent vector and the vector of symmetrical relationship parameters and outputs a respective latent vector.

[0134] In one example described herein, the decoder is configured to decode a given latent vector into a tree of functional structures according to a recursive top-down process for a given latent vector. In other words, the decoder takes a given latent vector as input and outputs a tree. The decoder uses its decoding module to recursively decode successive latent vectors (i.e., latent vectors successively generated by it during the decoding process) into a child latent vector, until the child latent vector is finally decoded into a leaf node.

[0135] During the top-down decoding process, the node classifier classifies each latent vector generated during decoding as corresponding to a leaf node, corresponding to a non-leaf node representing a mechanical link, or corresponding to a non-leaf node representing a duplication. In other words, for each successive latent vector generated in decoding (i.e., a given latent vector and a latent vector output by the decode module), the node classifier takes the latent vector as input and classifies it as corresponding to a leaf node, corresponding to a non-leaf node representing a mechanical link, or corresponding to a non-leaf node representing a duplication. In other words, the node classifier guides the recursive decoding by classifying each successive latent vector as corresponding to one of the types of nodes so that an appropriate decode module is applied to the latent vector. In fact, the node classifier may select a decode module to apply to the latent vector when classifying the latent vector. In one example, decoding the latent vector includes classifying the latent vector by invoking the node classifier, selecting an appropriate decode module for decoding the latent vector as a result of the classification, and applying the selected decode module to the latent vector.

[0136] During the top-down decoding process (and, for example, when selected by the node classifier), the leaf-decoding module outputs data including, for each latent vector classified during decoding as corresponding to a leaf node, a specification of the respective bounding box and the respective resulting force. The leaf-decoding module does this based on the latent vector. In one example, this means that, as a result of classifying a latent vector as corresponding to a leaf node, the leaf-decoding module takes the latent vector as input and outputs data including a specification of each bounding box (i.e., a bounding box around a rigid part) and each resulting force (i.e., a force acting on that rigid part). This data is or includes a vector having a first coordinate characterizing the bounding box around each rigid part, a second coordinate characterizing the resulting force, and possibly a third coordinate characterizing the type of geometric primitive. This corresponds to the leaf-decoding module outputting a leaf node.

[0137] During the top-down decoding process (and, for example, when selected by the node classifier), the mechanical link decode module outputs a number of child latent vectors for each latent vector classified during decoding as corresponding to a non-leaf node representing a mechanical link. The mechanical link decode module does this based on the latent vector. In one example, this means that as a result of classifying a latent vector as corresponding to a non-leaf node representing a mechanical link, the mechanical link decode module takes the latent vector as input and outputs a number of child latent vectors. In other words, the mechanical link decode module outputs a number of latent vectors that respectively encode a number of child nodes of the non-leaf node to which the latent vector corresponds. In one example, the mechanical link decode module may further output a vector of mechanical link parameters, and if no mechanical link exists, the vector of mechanical link parameters is, for example, null. Alternatively, the decoder may include a first mechanical link decode module and a second mechanical link decode module. The first mechanical link decode module takes, for each latent vector classified as corresponding to each non-leaf node representing a mechanical link that does not have a vector of mechanical link parameters, the latent vector as input, and outputs a plurality of latent vectors that respectively encode a plurality of child nodes of the non-leaf node to which the latent vector corresponds. The second mechanical link decode module takes, for each latent vector classified as corresponding to each non-leaf node representing a mechanical link that has a vector of mechanical link parameters, the latent vector as input, and outputs a plurality of latent vectors that respectively encode a plurality of child nodes of the non-leaf node to which the latent vector corresponds, together with the vector of mechanical link parameters.

[0138] During the top-down decoding process (and, for example, when selected by the node classifier), the overlap decode module outputs a child latent vector for each latent vector classified during decoding as corresponding to a non-leaf node representing an overlap. The overlap decode module does this based on the latent vector. In one example, this means that as a result of classifying a latent vector as corresponding to a non-leaf node representing an overlap, the overlap decode module takes the latent vector as input and outputs a child latent vector. In other words, the mechanical link decode module outputs a latent vector that encodes a child node of the non-leaf node to which the latent vector corresponds. The mechanical link decode module, in one example, may also output data specifying the arrangement of multiple instances of the subassembly represented by the child node relative to each other, such as a vector of symmetry parameters.

[0139] In one example of a training method (or offline stage of a modeling process), one or more nodes (e.g., all of) the tree of at least some (e.g., all of) the functional structures of the dataset are each tagged with one label from a list of predefined labels. In one of these examples, the training method (or offline stage of the modeling process) further includes training (S30) a latent space classifier. The latent space classifier is a neural network configured to take latent vectors as input and tag the latent vectors with one label from a list of predefined labels.

[0140] Here, such an example will be described.

[0141] The dataset may be provided (S10) with each tree of the at least part already tagged with a label from a predetermined list. A tree is tagged with a label from a predetermined list means that one or more first nodes of the tree are tagged with a first label from the predetermined list. One or more second nodes of the tree may be tagged with a second label from the predetermined list. One or more third nodes may be tagged with a third label from the predetermined list, and so on, for example, each node of the tree is tagged with each label belonging to the predetermined list. Additionally or alternatively, providing (S10) may include tagging, for example by user action, one or more trees (e.g. all trees) of the at least part with a label from the predetermined list.

[0142] The predefined list of labels may be provided by a user (e.g. before or during the provision (S10)). The predefined list of labels may be relative (e.g. specific) to a class of mechanical assemblies of rigid parts of the provided dataset of functional structures. This means that all or substantially all functional structures of the provided dataset represent mechanical assemblies of rigid parts that all belong to the same class of mechanical assemblies of rigid parts, as described above, and that the predefined list of labels relates to this class. The predefined list of labels may in particular consist of a special label and other labels. The special label indicates the absence of a label, while the other labels each represent (e.g. indicate) a significant substructure typical of the class. One of the other labels may be a label indicating the class, and only the root node is tagged. In other words, a tree representing a mechanical assembly of rigid parts belonging to a class and tagged with the labels of such a list may be tagged as follows:

[0143] Any node that represents a subassembly that is also a meaningful substructure of a mechanical assembly of rigid parts may be tagged with a label indicating the meaningful substructure. Note that if the node has child nodes, then all of them are also part of the meaningful substructure and therefore are not tagged with a label indicating the meaningful substructure. Only the parent node of the substructure is tagged. However, if there are child nodes, they may be tagged with another label from the list (e.g. if they correspond to another meaningful substructure within the substructure).

[0144] The other nodes are tagged with a special label because none of them are parent nodes of any significant substructure.

[0145] For example, if the class of mechanical assemblies of rigid parts in the provided functional structure dataset is the class of automobiles, then the predefined list of labels consists of the following labels: the label “Car” which is a special label (to tag the root node and thus indicate the class), the label “Body Substructure”, the label “Interior Substructure”, and the label “Chassis”.

[0146] For example, if the class of mechanical assemblies of rigid parts in the provided functional structure dataset is the class of chairs, then the predefined list of labels consists of the following labels: the special label label “Chairs” (to tag the root node and thus indicate the class), the label “Arm”, the label “Leg”, the label “Seat”, and the label “Back”.

[0147] The latent space classifier may be trained together with the generative autoencoder (i.e., training the latent space classifier (S30) and training the generative autoencoder (S20) are performed together) or subsequently (i.e., training the latent space classifier (S30) is performed after training the generative autoencoder (S20)) using any machine learning technique that can train a neural network configured to take a latent vector as input and tag the latent vector with one label from a predefined list of labels.

[0148] As described above, both the recursive bottom-up encoding process and the recursive top-down decoding process recursively generate successive latent vectors. Each such successive latent vector corresponds to or encodes a node of the tree (i.e., the tree of the functional structure), which is one of the leaf nodes, the root node, or the internal node (i.e., the non-leaf node that is not the root node). In other words, the successive latent vectors may belong to an intermediate latent space, i.e., a latent space that includes latent vectors corresponding to the leaf nodes, the root node, or the non-leaf nodes in between. The latent space classifier takes such latent vectors as input and tags the corresponding nodes with a list of labels. In other words, the latent space classifier can recognize intermediate latent vectors, i.e., vectors that belong to the intermediate latent space, and tag each of them with a predetermined list of labels. Note that all intermediate latent vectors that belong to the same intermediate latent space are tagged with the same label. Conversely, all intermediate latent vectors tagged with the same label belong to the same intermediate latent space.

[0149] In one example, an intermediate latent vector corresponding to a node that represents a significant substructure is tagged with a label that indicates the significant substructure. As mentioned above, if there are any child nodes of this node, they correspond (e.g., are encoded) to child latent vectors of the intermediate latent vector. The latent space classifier takes each of these child latent vectors as input (e.g., at a later stage / step of the decoding process) and tags them with a label that is not indicative of a significant substructure. This is because only parent nodes that represent substructures are tagged with this label. However, such a child latent vector may be tagged with a label that corresponds to another significant substructure, e.g., a substructure of the substructure represented by the parent node. Otherwise, the child is tagged with a special label.

[0150] Once latent vectors corresponding to significant substructures have been tagged, applying a latent space classifier to such latent vectors allows these substructures to be recognized during recursive decoding based solely on the intermediate latent vectors that encode them. This allows operations such as interpolation operations to be performed on the significant substructures, as described further below. Interestingly, such operations may be performed on the entire mechanical assembly of rigid parts, as well as on its significant subassemblies.

[0151] The functional structure and implementation of the generative autoencoder will now be described with reference to Figs.

[0152] In this example, the dataset comprises a functional structure including (e.g., consisting of) a binary tree including leaf nodes, non-leaf nodes having two children each representing an adjacent relationship between two subassemblies represented by a respective one of the two children, and non-leaf nodes having one child each representing a symmetric relationship between instances of the subassemblies represented by one child, as described above. For simplicity, in the description of this example, the non-leaf nodes having two children are referred to as "adjacent nodes" and the non-leaf nodes having one child are referred to as "symmetric nodes." In this example, each tree, or substantially each node of each tree in the dataset is tagged with one label from a predefined list, as described above, and a latent space classifier is trained (S30) on the dataset.

[0153] Here we further explain the nodes of the tree: For clarity, in this description, the notation nD means "n-dimensional" or "n-dimensional".

[0154] Each leaf node of the tree corresponds to a (e.g., indivisible) rigid part (i.e., the mechanical assembly represented by the tree) and represents information about the geometry, external physical forces, and semantics of the rigid part in a fixed-size vector. In other words, as described above, a leaf node includes a vector having a first coordinate characterizing a bounding box around the rigid part and a resulting second coordinate characterizing the forces acting on the rigid part. Specifically, a leaf node is

number

number

number

number

number

number

[0155] Each adjacent node in the tree has two children, which may be a leaf node, or one leaf node and an interior node, or two interior nodes. The adjacent node may further include a fixed-size vector of adjacency parameters that characterize the mechanical link between the two subassemblies represented by the two children. This fixed-size vector may be

number

number

number

number

number

number

number

number

number

number

number

number

[0156] As mentioned above, each symmetric node has one child. In the embodiment described herein, as mentioned above, the symmetric node further includes a vector of symmetric relation parameters, which are defined as:

number

number

number

number

[0157] The generative autoencoder will now be described. FIG. 5 shows a schematic diagram of the VAE-GAN structure of the generative autoencoder. The generative autoencoder further includes an encoder and a decoder, each of which includes a recursive encoding module and a decoding module, respectively. These will now be described with reference to FIG. 6 and FIG. 7. Each recursive encoding module and each decoding module may be a two-layer perceptron network, for example with a 100-D hidden layer and an 80-D output layer.

[0158] FIG. 6 shows a schematic diagram of the recursive encoding module and the recursive bottom-up encoding process of the encoder described above. As shown in FIG. 6, the encoder takes a tree 60 of a given functional structure as input and encodes it into one fixed-size latent vector. The adjacent nodes of the tree 60 are represented as circles containing "A", the symmetric nodes of the tree are represented as circles containing "S", and the leaf nodes are represented as circles without letters. The encoder includes three recursive encoding modules (represented as bounding boxes 64, 66, and 68 in FIG. 6): a leaf encoding module 64, a mechanical link encoding module 66 (also referred to as "adjacent encoding module" in this embodiment), and a duplicate encoding module 68 (also referred to as "symmetric encoding module" in this embodiment). The recursive bottom-up encoding process recursively collapses / aggregates the nodes of the tree 60 by going from the lowest level of the nodes of the tree 60 to the root node of the tree 60 according to the direction indicated by the arrow 60, and each time a node is encountered, it encodes the node by applying the appropriate encoding module as described below.

[0159] During the encoding process, Leaf Encoding Module 64 encodes the leaf nodes encountered by taking as input the vector contained in the leaf node (i.e., a vector having first and second coordinates that characterize the bounding box and resulting forces, respectively) and outputting one fixed-size latent vector. Specifically, Leaf Encoding Module 64 has one 18-D input (or optionally 19-D, if the vector has a third coordinate as described above) corresponding to the leaf node's vector and one nD output, the parameters of which are given by the formula

number

number

number

number

[0160] During the encoding process, the neighbor encoding module 66 encodes the encountered neighbor nodes by:

[0161] If the adjacent node does not contain a vector of adjacent relationship parameters (the situation shown in Figure 6), it takes two latent vectors encoding each of the two children of the adjacent node as input and outputs one latent vector. The adjacent encoding module has two nD inputs and one nD output, where n is an integer. Its parameters are expressed as follows:

number

number

number

number

number

[0162] Alternatively, if the neighbor node further includes a vector of adjacency parameters, it takes as input the vector and two latent vectors encoding each one of the neighbor node's two children, and outputs one latent vector. In this case, the adjacency encoding module has two nD inputs, one mD input corresponding to the vector of adjacency parameters, and one nD output, where n and m are integers. The parameters are given by the formula

number

number

number

number

number

number

[0163] During the encoding process, the symmetric encoding module 68 takes as input a latent vector encoding one child of the symmetric node and a vector of symmetric relation parameters, and encodes the encountered symmetric node by outputting one latent vector. Specifically, the symmetric encoding module has two inputs, one nD input and one sD input (s=8), and one nD output. The parameters are expressed as follows:

number

number

number

number

number

[0164] FIG. 7 shows a schematic diagram of the recursive decoding module and the recursive top-down decoding process of the decoder described above. As shown in FIG. 7, the decoder takes one latent vector 70 of a given functional structure as input and decodes it into a tree 80 of functional structures. The adjacent node of the tree is represented as a circle containing "A", the symmetric node of the tree is represented as a circle containing "S", and the leaf node is represented as a circle without a letter. The encoder includes three recursive decoding modules (represented as bounding boxes 74, 76, and 78 in FIG. 7): a leaf decoding module 74, a mechanical link decoding module 76 (also referred to as "adjacent decoding module" in this embodiment), and a duplicate decoding module 78 (also referred to as "symmetric decoding module" in this embodiment). The recursive top-down decoding process recursively decodes the latent vectors generated in the previous decoding steps into child latent vectors, each of which represents a node of tree 80, by following the direction indicated by arrow 72 from a given latent vector of a node of tree 80 (which represents the root node of tree 80) to the last child latent vector generated during decoding (which represents the lowest level node of tree 80). Each time a generated latent vector is encountered, it is decoded by applying an appropriate decoding module, as described below.

[0165] The decoder further includes a node classifier 700, which, starting from a given latent vector 70, takes as input each latent vector generated during decoding, classifies it as corresponding to a leaf node, an adjacent node, or a symmetric node, and selects the appropriate decoding module, which is then applied to the latent vector. In other words, the decoder guides the decoding as described above.

[0166] During the decoding process, leaf decode module 74 takes the latent vector as input and decodes the generated latent vector classified as corresponding to a leaf node by outputting an 18-D vector (or possibly a 19-D vector) having first and second coordinates (and possibly a third coordinate specifying the type of geometric primitive) that respectively characterize the bounding box and the resulting forces. Specifically, leaf decode module 64 has one nD input and one 18-D output (or optionally 19-D if the vector has a third coordinate as described above) corresponding to the vector of the leaf node. Its parameters are expressed as follows:

number

number

number

number

[0167] During the decoding process, the neighbor decoding module 76 decodes the generated latent vectors classified as corresponding to neighbor nodes by:

[0168] If a latent vector is classified as corresponding to an adjacent node that does not contain a vector of adjacency parameters (the situation shown in FIG. 7), it takes the latent vector as input and outputs two child latent vectors. Specifically, the Adjacency Decode module 76 performs the exact mirror operation of one of the Adjacency Encode modules. It has one nD input and two nD outputs. The Adjacency Decode module 76 calculates its parameters by the formula

number

number

number

number

number

number

[0169] If a latent vector is classified as corresponding to a neighbor node that does not contain a vector of adjacency parameters (the situation shown in Figure 7), it takes the latent vector as input and outputs two child latent vectors and a vector of adjacency parameters. In this case, the adjacency decoding module has one nD input, two nD outputs, and one mD output corresponding to the vector of adjacency parameters, where n and m are integers. The parameters are expressed as

number

number

number

number

number

number

[0170] During the decoding process, the symmetric decoding module 78 decodes the generated latent vectors classified as corresponding to symmetric nodes by taking the latent vectors as input and outputting one child latent vector and a vector of symmetric relationship parameters. Specifically, the symmetric decoding module 78 performs an exact mirror operation of one of the symmetric encoding modules, as follows:

number

number

number

number

number

number

number

[0171] 7 further shows a latent space classifier 7000 that takes as input the generated latent vector during the decoding process and tags it with one label from a predefined list as described above. The latent space classifier 7000 and the node classifier 700 can be trained together or separately as described above, and in this embodiment they are both trained by minimizing the so-called "multinomial logistic loss" (also called "cross-entropy loss") of the following type:

number

number

number

number

[0172] Providing one or more latent vectors (S100) will now be described.

[0173] Each latent vector in at least a portion (e.g., all of them) of the one or more latent vectors may be provided by sampling a Gaussian distribution (S100), the sampling resulting in a latent vector. Alternatively, or additionally, each latent vector in at least another portion (e.g., all of them) of the one or more latent vectors may be provided by applying an encoder to the tree to encode each tree of the functional structure (e.g., of the provided (S10) dataset or of another dataset, such as a test dataset; the concept of a test dataset is known per se in the field of machine learning), thereby encoding the tree into a latent vector.

[0174] Here, the generation of the functional structure (S200) will be described.

[0175] The generating (S200) includes decoding each latent vector (i.e., a latent vector of the one or more provided (S100) latent vectors) with a decoder. In other words, for each latent vector, the generating (S200) includes applying a decoder to the latent vector. Applying the decoder to the latent vector generates successive child latent vectors, as described above, until, for example, the decoding eventually outputs a tree of functional structures. In one example, particularly in an example where the one or more provided (S100) latent vectors consist of a single latent vector, the generating (S200) may consist of decoding each provided (S100) latent vector, which outputs, for each latent vector, a tree of functional structures. For each provided (S100) latent vector, there is one generated (S200) functional structure including each tree resulting from the decoding of the single latent vector.

[0176] In one example, when the latent space classifier is trained (S30), the one or more latent vectors include a first latent vector and a second latent vector. In one example, the decoding generates latent vectors including an intermediate latent vector for each of the first latent vector and the second latent vector. In one of these examples, the generating of the functional structure (S200) includes performing an interpolation operation between a first intermediate latent vector of the first latent vector and a second intermediate latent vector of the second latent vector. The performing of the interpolation operation is based on the same labels tagging the first intermediate latent vector and the second intermediate latent vector.

[0177] In other words, decoding the first (or second) latent vector produces a first (or second) intermediate latent vector. The first (or second) latent vector encodes the first (or second) tree of the functional structure, and the first (or second) intermediate latent vector encodes each node of the first (or second) tree, each representing a respective subassembly of the mechanical assembly of rigid parts represented by the first (or second) tree. As mentioned above, each intermediate latent vector may represent any one of a leaf node, an internal node, or a root node. Thus, each of those subassemblies may be either the entire mechanical assembly of rigid parts, or a strict subassembly of the mechanical assembly of rigid parts, such as one rigid part.

[0178] During the decoding of the first (or second) latent vector, for each of the first (or second) intermediate latent vectors, the latent space classifier takes the respective first (or second) intermediate latent vector as input and tags it with one label from a predefined list. The first intermediate latent vector and the second intermediate latent vector, on which the interpolation operation is performed, are tagged with the same label by the latent space classifier. This means that the first intermediate latent vector encodes a node of a first tree representing a first significant substructure of a first mechanical assembly of rigid parts, and the second intermediate latent vector encodes a node of a second tree representing a second significant substructure of a second mechanical assembly of rigid parts. This also means that the first intermediate latent vector and the second intermediate latent vector both belong to the same intermediate latent vector space. This further means that the first significant substructure and the second significant substructure are of the same type, i.e., corresponding substructures of two mechanical assemblies of rigid parts of the same class.

[0179] Here, the interpolation operation will be described. Let v1 and v2 be the first and second intermediate latent vectors, respectively. The interpolation operation takes v1 and v2 as inputs,

number

number

[0180] Once the interpolation operation has been performed, the decoding continues. More precisely, suppose that as a result of the interpolation operation, v1 has been replaced by v3 (or simply v2 in case of blending with α=0). The decoding of the first latent vector then continues, which consists of the decoding of v1, where v1 is now equal to v3 and other child latent vectors of the first latent vector that have not yet been decoded. The decoding of the first latent vector then produces a first tree of functional structures representing mechanical assemblies of rigid parts, including the significant subassemblies represented by vector v3. The decoding of the second latent vector may continue in a similar manner until it produces a second tree.

[0181] It should be noted that multiple operations may be performed using different values ​​of α.

[0182] Figures 8, 9 and 10 show the interpolation (or blending) operation in an example where the generative autoencoder has been trained (S20) on a dataset of feature structures representing chairs. As mentioned above, the tree is tagged with the labels "chair", "seat", "back", "arms" and "legs".

[0183] As shown in Fig. 8, chair 82 is a 3D view of the functional structure obtained by decoding the first latent vector without performing an interpolation operation. Chair 84 is a 3D view of the functional structure obtained by decoding the second latent vector without performing an interpolation operation. The other chairs represent the results of performing an interpolation operation between the intermediate latent vectors representing the leg substructures of chair 82 and chair 84 for different values ​​of α.

[0184] FIG. 9 shows another example of the result of interpolation between substructures of a chair leg.

[0185] FIG. 10 shows a chair 104 resulting from a blending interpolation performed on chair 102, where the legs of chair 102 have been replaced with the legs of another chair.

[0186] In either case, whether or not generation (S200) involves interpolation (or blending), generation (S200) results in a generated functional structure representing a mechanical assembly of parts on which topology optimization can be performed as described above.

[0187] Here, the execution of topology optimization (S300) will be described. Before this description, the concept will be explained.

[0188] Performing a topology optimization on a mechanical assembly of rigid parts (S300) means performing any topology optimization method, process, or algorithm on the mechanical assembly of rigid parts, or on a data structure representing it and suitable for topology optimization. Such a data structure may in particular be a generated functional structure or may be inferred therefrom. Thus, performing a topology optimization (S300) includes providing inputs for the topology optimization (i.e., providing inputs to a topology optimization method, process, or algorithm).

[0189] As known per se from the field of topology optimization, the input of the topology optimization includes a FEM. The FEM represents a space containing a mechanical assembly of rigid parts or a modeled object representing it. The FEM may be 2D or 3D. The FEM may be regular or irregular. A regular FEM facilitates the operations during topology optimization. The FEM may be of any type, for example, where each finite element is a tetrahedron or a hexahedron. Providing the FEM may include defining a design space and a mesh of the design space. The execution of the topology optimization (S300) may include displaying the FEM to a user and the user defining other inputs of the topology optimization, including for example by graphical user interaction on the displayed FEM. "Graphical user interaction" with respect to the definition of an element means any user interaction in which the designer activates one or more locations on a display unit with a haptic system (for example, a mouse or a touch device such as a sensitive / touch screen or a sensitive / touch pad) to place an element. Activating a scene location may include positioning a mouse cursor over it or performing a touch on it. After activation, a representation of the defined element may be displayed, substantially in real time.

[0190] As is known per se from the field of topology optimization, the input of the topology optimization further comprises data associated with the FEM and dependent on the mechanical assembly of the rigid parts.

[0191] As known per se from the field of topology optimization, these associated data include material-related parameters, in other words data representative of the materials from which the mechanical assembly of rigid parts is formed. These material parameters may in particular represent mechanical properties of the material. The material parameters may include, for example, the Young's modulus of the material and / or the Poisson's ratio of the material. In one example, the user may specify the material, for example by selection from a list, and / or the system may automatically determine the material parameters and / or suggest the selection to the user, for example based on one or more formulas and / or databases. The material may be any material, for example a solid and / or isotropic material, such as a metal (for example steel, silver, gold, titanium), a plastic (for example nylon, ABS, polycarbonate, resin), a ceramic, or a composite.

[0192] As known per se from the field of topology optimization, the associated data further includes global quantity constraints. The global quantity constraints relate to the global quantity of material in the FEM. In other words, the global quantity constraints limit the value of the total amount of material in the entire FEM. The global quantity constraints may for example be provided as a boundary for the percentage that can be satisfied with the material of the FEM (overall), for example an upper limit for said percentage. Alternatively, the global quantity constraints may provide a value to be reached, rather than a boundary. However, topology optimization optimizes an objective function that, in an optimal result, tends to use as much material as possible, such an equality constraint may be equivalent to an upper limit constraint. In all cases, the percentage may be a volume fraction (in such a case also called GVC, as in "Global Volume Constraint"). In another example, the global quantity constraint may include a value representing the weight of the material.

[0193] As known per se from the field of topology optimization, the associated data further comprises data representative of the utilization conditions of the mechanical assembly of the rigid parts, based on which the topology optimization can optimize the mechanical assembly of the rigid parts taking into account such anticipated use.

[0194] As known per se from the field of topology optimization, the associated data includes in particular forces, such as those represented in the leaf nodes of the functional structure of the present disclosure. In other words, the associated data includes linked vectors (e.g., magnitudes in Newtons or multiples thereof) that are applicable to one or more finite elements of the FEM, respectively. These forces partially represent the loads that the mechanical assembly of rigid parts undergoes when in use. In other words, for each one or more finite elements of the FEM for which a respective force is present in the data, the data represents the fact that the material of the mechanical assembly of rigid parts at the location corresponding to said one or more finite elements will undergo the corresponding load. However, not all loads are represented by the forces present in the data, since the mechanical assembly of rigid parts can theoretically undergo an infinite number of loads. The forces represent only constraints of the entire set of loads, for example the most important and / or most representative loads. The forces are determined for each modeling problem and selected to be the largest (i.e. highest magnitude) forces that the object may undergo during its lifetime, since these forces tend to cause the largest deformations and mechanical stresses. These forces may be grouped into sets called load cases. An industrial problem, in one example, may have load cases 1-12. In one example, a user may select a finite element through the FEM's graphical user interaction and then specify forces applicable to it.

[0195] As known per se from the field of topology optimization, the associated data also include boundary conditions. Each boundary condition is applied to one or more finite elements of the mesh and is linked to represent a respective constraint of the boundary applied in use to the mechanical assembly of rigid parts. In other words, each boundary condition represents the fact that the material of the mechanical assembly of rigid parts is subjected to a constraint for its displacement at the location corresponding to said one or more finite elements, for example by means of Dirichlet boundary conditions. An element may have a displacement constrained along a plane, along a curve, along / around an axis or to / around a point, and / or its displacement may be constrained only in translation, only in rotation or both in translation and rotation. In case of displacements constrained to a point in both translation and rotation, the element is said to be fixed and "clamped" in 3D space. However, an element may have its displacement constrained to translation along a plane but free to move on that plane (e.g. when belonging to an object mounted on a bearing), constrained to translation along an axis but free to move on that axis (e.g. in a piston), or constrained to rotation about an axis (e.g. the joints of a robot arm).

[0196] In one example, the boundary conditions represent all constrained boundaries. In other words, for each finite element of the FEM that is intended to ultimately contain constrained (e.g., remain fixed) material, a boundary (e.g., clamp) condition may be associated to integrate this fact into the topology optimization. In one example, a user may select a finite element through graphical user interaction in the FEM and then specify the applicable boundary conditions for it.

[0197] In one example, one or more constrained boundaries of a mechanical assembly of rigid parts include or consist of one or more fixed boundaries (i.e., material at said one or more boundaries cannot move), and the corresponding one or more boundary conditions are clamped conditions.

[0198] Topology optimization, as is widely known, may involve automatically optimizing an objective function based on inputs. The objective function may represent any mechanical property to be optimized. Topology optimization may in particular maximize stiffness. The objective function for this may be a compliance function. Compliance, for a structure, is the inverse of the stiffness of the structure. Thus, compliance encapsulates the amount of deformation of the structure given a specified loading scenario and fixed boundary conditions. Thus, if the optimization process minimizes compliance, this corresponds to maximizing the stiffness of the design for a given mass. A free variable of the objective function may be the distribution (i.e., layout) of the amount (e.g., volume fraction) of material on the FEM. Thus, topology optimization optimizes the objective function by varying the amount (e.g., volume fraction) of material in each finite element of the mesh. The objective function may depend on material parameters (i.e., the fixed variables of the objective function may include material parameters) and the optimization may be performed under constraints including global quantity constraints. The optimization may be performed according to any algorithm, for example an iterative algorithm. If the amount of material is a volume fraction of material, the optimization process results in a distribution of the volume fraction of material per finite element. In such a case, the topology optimization or performing the topology optimization (S300) may include a further step of (e.g., automatic) filtering, i.e., determining whether each finite element is (completely) filled with material based on such volume fraction distribution. For example, this may be based on a comparison with a (e.g., predetermined) threshold value (e.g., greater than 0.1 or 0.2 and / or less than 0.9 or 0.8, e.g., around 0.5), and if the volume fraction resulting from the optimization is greater (or smaller) than the threshold value, the finite element is considered to be completely filled with material (or completely empty). The performing the topology optimization (S300) may, in one example, further include (e.g., automatically) calculating a 3D modeled object, such as a boundary representation (B-Rep) model, based on the results.For example, performing a topology optimization (S300) may calculate a swept volume based on and along a set of finite elements resulting from the optimization and / or filtering.

[0199] As shown in Fig. 11, which illustrates the specification of a topology optimization scenario, a typical topology optimization workflow requires as input a design space 112 (here subdivided into small square elements), a set of load cases 114 (forces applied to the design) and boundary conditions 116 (where the design is constrained, e.g., "clamped", against deformation, here the entire left side of the design space 112). Additional parameters can be defined, such as the outer shell that needs to be preserved, the mechanical constituent properties of the selected material, the target mass, the maximum allowable deformation, or other constraints. The design workflow can exclude the prescription of an initial geometry other than the design space definition, since the objective of topology optimization is to generate an optimized design from an empty canvas (design space).

[0200] The output of a typical topology optimization workflow is an optimized design geometry that adheres as closely as possible to the entered specifications. Figure 12 shows one such design under optimization and shows the design evolving during the optimization process. In this example, the overall volume fraction is set to 30%. Figure 12 shows the initial design 122, the design after five optimization iterations 124, the design after ten optimization iterations 126, and the final converged design after 25 optimization iterations 128.

[0201] As shown in FIG. 13, a typical topology optimization workflow may follow the eight steps shown below in one example.

[0202] 1. Meshing the Design Space Create a discretization of the design space, as shown in Figure 11. This means dividing the space into small connected simple elements, e.g. tetrahedrons or hexahedrons. These small elements may later serve as both FEMs for simulation and design variables for optimization.

[0203] 2. Application of Load Cases and Boundary Conditions Here, a typical topology optimization workflow may take forces and boundary conditions as input specifications and apply them to the nodes of a FEM. Figure 11 shows a mesh where the design space has been subdivided into regular square elements. The nodes on the left are clamped (fixed in 2D space) and a downward force is applied to the center-right of the design space.

[0204] 3. Initialize design variables Each element has a predefined relative density value that defines whether it is empty or filled with material, defined by values ​​of “0” and “1”, respectively. Furthermore, to make the optimization problem continuous, a typical topology optimization workflow may allow elements to take any value between 0-1. This is also known as “relaxation”. Because the interpretation of elements with intermediate densities can be ambiguous, a typical topology optimization workflow may introduce a penalty approach that forces intermediate element densities to have less efficient overall structural behavior than elements with lower and upper bounds of 0 or 1, respectively. This has the effect of driving the optimizer to generate a final design with less intermediate density, while still maintaining a continuous formation as shown in Figure 12.

[0205] 4. Calculating the equilibrium solution At this point, the typical topology optimization workflow may have a fully defined finite element model that has been meshed and has forces and boundary conditions added, where each element has a relative density value. From this, the typical topology optimization workflow may assemble a global stiffness matrix and calculate a solution for nodal displacements of the structure equilibrium. In other words, the typical topology optimization workflow may calculate the deformation of the structure in its current state for the applied forces and boundary conditions.

[0206] 5. Calculation of Objective Function Values ​​and Derivatives An objective function that can be used in any topology optimization is the compliance of the structure. It is the inverse of stiffness, and therefore encapsulates the amount of deformation of the structure given a specified loading scenario and boundary conditions. Thus, if the optimization process minimizes compliance, this is equivalent to maximizing the stiffness of the design for a given mass. Furthermore, since there are many design variables in the process, the optimization can be performed in a gradient-based manner. Thus, a typical topology optimization workflow may also calculate the derivatives of the objective function with respect to each design variable. In other words, a typical topology optimization workflow may calculate how to modify the relative density of each element to improve compliance and satisfy the constraints. For compliance, this may be performed using the well-known classical "adjoint sensitivity analysis". Furthermore, after the derivatives are calculated, these derivatives may be smoothed by filtering to improve numerical stability. A typical topology optimization workflow may also reduce spurious grid patterns and introduce length scales into the optimization to make them well-defined.

[0207] 6. Calculating constraints and derivatives A constraint function in a typical topology optimization workflow may be the overall volume fraction of the structure. Such a GVC defines the maximum volume of material allowed to be used, and therefore the maximum mass of material that the design comprises. The optimizer must therefore find the optimal distribution of this mass in the design space to maximize stiffness. Figure 12 shows intermediate designs 124 and 126 in the optimization workflow where the overall volume fraction is the same, but the distribution of material changes during the optimization iterations in the process. The derivative with respect to this constraint is equal to the volume of the element, and can be easily calculated since the derivative is constant for each element when the element sizes are equal.

[0208] 7. Updating design variables using mathematical programming If the objective function and constraint values ​​are known, along with their derivatives, a typical topology optimization workflow may use gradient-based mathematical programming to modify the relative density of each element to improve structural compliance without violating the specified GVC. If the mathematical programming modifies the relative density values ​​of each element and the optimization process has not yet converged to the specified modified design, the typical topology optimization workflow may loop back to step 4. A simple mathematical programming approach for this problem is the so-called Optimality Criteria (OC). Other known mathematical programming approaches may be used.

[0209] 8. Output of the final design Once convergence is achieved, the general topology optimization workflow may present a final design in the design space where each element has an optimized relative density value. Through a simple thresholding process, the general topology optimization workflow may extract the geometry defined by the set of elements whose relative density values ​​exceed a certain threshold (e.g., selected to be 0.5). The general topology optimization workflow may now present the geometry of the optimized design that is the output of the general topology optimization workflow. Figure 12 shows the final design 128 optimized to the specifications described in step 2 and shown in Figure 11.

[0210] Performing a topology optimization on a mechanical assembly of rigid parts represented by the generated functional structure (S300) may implement all steps of this general topology optimization workflow.

[0211] In particular, performing a topology optimization (S300), in one example, includes providing a topology optimization algorithm, such as any algorithm that implements the general topology optimization workflow described above.

[0212] In one of these instances, performing the topology optimization (S300) further includes providing inputs to the topology optimization algorithm, which includes obtaining at least a portion of said inputs from the generated functional structure. For example, generating (S300) may generate forces, each of which is a force represented by a leaf node of a tree of the generated functional structure. These generated forces may form inputs of the topology optimization, obtained from the thus generated functional structure. As mentioned above, the topology optimization algorithm may further take as inputs the FEM, mechanical assembly dependent data associated with the FEM, global quantity constraints, utilization conditions of mechanical assemblies of rigid parts, and / or boundary conditions (e.g., clamps).

[0213] In one of these examples, performing a topology optimization (S300) includes running a topology optimization algorithm on a mechanical assembly of rigid parts (or, for example, any data structure representing the same and suitable as input to the algorithm).

[0214] Figure 14 shows an example of the results of performing topology optimization (S300) on a generated functional structure representing a chair. Figure 14 shows a 3D view of the generated chair 142 and a 3D view of the results 144 of performing topology optimization (S300) on the generated chair 142.

[0215] FIG. 15 is a pipeline illustrating an embodiment of the modeling process.

Claims

1. 1. A computer-implemented method for training a generative autoencoder configured to generate a plurality of feature structures, comprising: one functional structure is a data structure representing a mechanical assembly of rigid parts; The data structure comprises: A plurality of leaf nodes each representing the shape, arrangement and forces acting on each rigid part; a plurality of non-leaf nodes, each having a plurality of children, each representing a mechanical link between a plurality of subassemblies represented by a corresponding one of said plurality of children; a plurality of non-leaf nodes, each having a child and each representing a copy of the subassembly represented by the child; a tree consisting of Providing a dataset comprising the plurality of functional structures (S10); Training the generative autoencoder (S20); The method according to claim 1, further comprising:

2. The mechanical links are adjacency relationships between the subassemblies, the adjacency relationships belonging to a predetermined set of adjacency relationships.

2. The method of claim 1 .

3. The replication is a symmetric relationship between instances of the plurality of subassemblies, the symmetric relationship belonging to a predetermined set of symmetric relationships.

3. The method according to claim 1 or 2.

4. The shape and geometry of each rigid part is represented by data including the specification of a bounding box around that rigid part, and the forces acting on each rigid part are resultant forces The method according to any one of claims 1 to 3.

5. The generating autoencoder may be an encoder including a leaf encoding module, a mechanical link encoding module, and a duplicate encoding module; a decoder including a node classifier, a leaf decoding module, a mechanical link decoding module, and a duplicate decoding module; Including, the encoder is configured to, for a given functional structure, encode the tree into a latent vector according to a recursive bottom-up process; the leaf encoding module outputs a latent vector for each leaf node based on data including the bounding box specifications and the resulting forces; the mechanical link encoding module outputs, for each non-leaf node representing a mechanical link, a latent vector based on the latent vectors encoding the children of the non-leaf node; the duplicate encoding module outputs, for each non-leaf node that represents a duplicate, a latent vector based on the latent vector that encodes a corresponding child of the non-leaf node; the decoder is configured to, for a given latent vector, decode the given latent vector into a tree of functional structures according to a recursive top-down process; the node classifier classifies each latent vector generated during decoding as corresponding to a leaf node, a non-leaf node representing a mechanical link, or a non-leaf node representing a duplicate; the leaf decoding module outputs, for each latent vector classified during decoding as corresponding to a leaf node, data including a respective bounding box specification and a respective resulting force based on the latent vector; the mechanical link decode module, for each latent vector classified during decoding as corresponding to a non-leaf node representing a mechanical link, outputs a plurality of child latent vectors based on the latent vector; The duplicate decoding module outputs, for each latent vector classified during decoding as corresponding to a non-leaf node that represents a duplicate, a child latent vector based on the latent vector.

5. The method of claim 4.

6. One or more nodes of a tree of at least some of the functional structures of the dataset are each tagged with a label from a list of predefined labels, and the method further comprises training (S30) a latent space classifier configured to receive a latent vector as input and tag the latent vector with a label from the list of predefined labels.

6. The method of claim 5 .

7. The bounding box and the resulting force are expressed by the first and second coordinates, respectively, of the same vector: The method according to any one of claims 4 to 6.

8. The method further comprising the step of: using the generated autoencoder by the computer; Providing one or more latent vectors (S100); generating a functional structure (S200), where each latent vector is decoded by the decoder; 6. The method of claim 5, comprising:

9. Using the generating autoencoder, performing a topology optimization of a mechanical assembly of rigid parts represented by the generated functional structure (S300); The method of claim 8 further comprising:

10. The generation (S200) generates forces, which are forces represented by leaf nodes of a tree included in the generated functional structure, and the generated forces form an input to the topology optimization.

10. The method of claim 9.

11. One or more nodes of at least some of the trees of the functional structures of the dataset are each tagged with a label from a list of predetermined labels; The method further comprises training (S30) a latent space classifier; the latent space classifier is configured to receive a latent vector as input and tag the latent vector with a label from the predefined list of labels; the one or more latent vectors include a first latent vector and a second latent vector; the decoding generates a latent vector including an intermediate latent vector for each of the first latent vector and the second latent vector; The generating (S200) of the functional structure includes performing an interpolation operation between a first intermediate latent vector of the first latent vector and a second intermediate latent vector of the second latent vector based on the same labels tagging the first intermediate latent vector and the second intermediate latent vector. The method according to any one of claims 8 to 10.

12. A computer program comprising instructions for carrying out the method according to any one of claims 1 to 11.

13. An apparatus comprising a data storage medium on which the computer program according to claim 12 is recorded.

14. The apparatus of claim 13 further comprising a processor coupled to the data storage medium.

Citation Information

Patent Citations

  • Identification of individuals in a digital file using media analysis techniques

    US20190073520A1

  • Methods and apparatus for unsupervised multimodal anomaly detection for autonomous vehicles

    US20190135300A1

  • Manufacturing support system and method

    WO2019043425A1