Deep learning approaches have been shown to be capable of recognizing shape features (e.g. machining features) in Computer-Aided Design (CAD) models in certain circumstances, yet still have issues when the features intersect, and in exploiting the geometric and topological information which comprises the boundary representation (B-Rep) of the typical CAD model. This paper presents a novel hierarchical B-Rep graph shape representation which encodes information about the surface geometry and face topology of the B-Rep. To learn from this new shape representation, a novel hierarchical graph convolutional network called Hierarchical CADNet has been created, which has been shown to outperform other state-of-the-art neural architectures on feature identification, including machining features that intersect, with improvements in accuracy for some more complex CAD models.

Generating structured meshes is often an expensive process, limiting the use of high-fidelity numerical simulation methods for design, especially when the design is not yet fixed and design updates are likely. For hexahedral meshes generated by decomposing a B-Rep model into regions for which simple meshing strategies are known, robustly propagating design modifications to the decomposed representation and subsequent mesh is very challenging. In this paper, an approach is presented to propagate parametric update and feature changes to structured meshes. Geometric and topological modifications on the design model are identified first, enabling the equivalent modifications to be identified on the decomposition of the design model. Virtual topology operations used to generate the initial decomposition are combined with the meshing constraints of individual sub-regions to update the decomposition and associated mesh locally. The approach is demonstrated for a number of design updates.

Defining Simulation Intent involves capturing high level modelling and idealisation decisions in order to create an efficient and fit-for-purpose analysis. These decisions are recorded as attributes of the decomposed design space. An approach to defining Simulation Intent is described utilising three known technologies: Cellular Modelling, the subdivision of space into volumes of simulation significance (structures, gas paths, internal and external airflows, etc.); Equivalencing, maintaining functional links between different analysis representations of the same region of design space across multiple analysis models; and Virtual Topology, which offers tools for partitioning and de-partitioning the model without disturbing the manufacturing oriented design geometry. The end result is a convenient framework to which high-level analysis attributes can be applied, and from which detailed analysis models can be generated with a high degree of controllability, repeatability and automation. There are multiple novel aspects to the approach, including its reusability, robustness to changes in model topology and the inherent links created between analysis models at different levels of fidelity and physics. By utilising Simulation Intent, CAD modelling for simulation can be fully exploited and simulation work-flows can be more readily automated, reducing many repetitive manual tasks (e.g. the definition of appropriate coupling between elements of different types and the application of boundary conditions). The approach has been implemented and tested with practical examples, and significant benefits are demonstrated.