CAD Objects Research Articles

From CAD to representations suitable for isogeometric analysis: a complete pipeline

AbstractNext generation CAD/CAE systems shall integrate design and analysis procedures as a means to simplify workflows, boost performance, and speed up time to market. In the present paper we demonstrate a proof of concept of such a unification using subdivision surfaces and the enabling technology of isogeometric analysis. In particular, we present a complete pipeline to convert CAD models into smooth $$G^1$$ G 1 spline representations, which are suitable for isogeometric analysis. Starting from a CAD boundary representation of a mechanical object, we perform an automatic control cage extraction by means of quadrangular faces, such that its limit Catmull-Clark subdivision surface approximates accurately the input model. We then compute a basis of the $$G^1$$ G 1 spline space over the quad mesh in order to carry out least squares fitting over a point cloud, acquired by sampling the original CAD geometry. The resulting surface is a collection of Bézier patches with $$G^1$$ G 1 regularity. Finally, we use the basis functions to perform isogeometric analysis simulations of realistic PDEs on the reconstructed $$G^1$$ G 1 model. The quality of the construction is demonstrated via several numerical examples performed on a collection of CAD objects presenting various challenging realistic shapes.

Discretisation of the Hough parameter space for fitting and recognising geometric primitives in 3D point clouds

Research in recognising and fitting simple geometric shapes has been ongoing since the 1970s, with various approaches proposed, including stochastic methods, parameter methods, primitive-based registration techniques, and more recently, deep learning. The Hough transform is a method of interest due to its demonstrated robustness to noise and outliers, ability to handle missing data, and support for multiple model instances. Unfortunately, one of the main limitations of the Hough transform is how to properly discretise its parameter space, as increasing their number or decreasing the sampling frequency can make it computationally expensive.The relationship between the approximation accuracy and the parameter space’s discretisation is investigated to address this. We present two distinct discretisations to illustrate how the fitting and recognition quality can be improved by selecting an appropriate parameter discretisation. Our parameter-driven space discretisation is shown to significantly improve the parameter recognition quality over the classical method and reduce computational time and space by decreasing the discretisation’s dimension, as demonstrated by an extensive validation on a benchmark of geometric primitives. Preliminary experiments are also presented on segmenting datasets from urban buildings and CAD objects.

DiffCAD: Weakly-Supervised Probabilistic CAD Model Retrieval and Alignment from an RGB Image

Perceiving 3D structures from RGB images based on CAD model primitives can enable an effective, efficient 3D object-based representation of scenes. However, current approaches rely on supervision from expensive yet imperfect annotations of CAD models associated with real images, and encounter challenges due to the inherent ambiguities in the task - both in depth-scale ambiguity in monocular perception, as well as inexact matches of CAD database models to real observations. We thus propose DiffCAD, the first weakly-supervised probabilistic approach to CAD retrieval and alignment from an RGB image. We learn a probabilistic model through diffusion, modeling likely distributions of shape, pose, and scale of CAD objects in an image. This enables multi-hypothesis generation of different plausible CAD reconstructions, requiring only a few hypotheses to characterize ambiguities in depth/scale and inexact shape matches. Our approach is trained only on synthetic data, leveraging monocular depth and mask estimates to enable robust zero-shot adaptation to various real target domains. Despite being trained solely on synthetic data, our multi-hypothesis approach can even surpass the supervised state-of-the-art on the Scan2CAD dataset by 5.9% with 8 hypotheses.

An overview of artificial intelligence based applications for assisting digital data acquisition and implant planning procedures.

To provide an overview of the current artificial intelligence (AI) based applications for assisting digital data acquisition and implant planning procedures. A review of the main AI-based applications integrated into digital data acquisitions technologies (facial scanners (FS), intraoral scanners (IOSs), cone beam computed tomography (CBCT) devices, and jaw trackers) and computer-aided static implant planning programs are provided. The main AI-based application integrated in some FS's programs involves the automatic alignment of facial and intraoral scans for virtual patient integration. The AI-based applications integrated into IOSs programs include scan cleaning, assist scanning, and automatic alignment between the implant scan body with its corresponding CAD object while scanning. The more frequently AI-based applications integrated into the programs of CBCT units involve positioning assistant, noise and artifacts reduction, structures identification and segmentation, airway analysis, and alignment of facial, intraoral, and CBCT scans. Some computer-aided static implant planning programs include patient's digital files, identification, labeling, and segmentation of anatomical structures, mandibular nerve tracing, automatic implant placement, and surgical implant guide design.

Multiobjective Optimization of Stereolithography for Dental Bridge Based on a Simple Shape Model Using Taguchi and Response Surface Methods

Stereolithography (SLA) has become an essential photocuring 3D printing process for producing parts of complex shapes from photosensitive resin exposed to UV light. The selection of the best printing parameters for good accuracy and surface quality can be further complicated by the geometric complexity of the models. This work introduces multiobjective optimization of SLA printing of 3D dental bridges based on simple CAD objects. The effect of the best combination of a low-cost resin 3D printer’s machine parameter settings, namely normal exposure time, bottom exposure time and bottom layers for less dimensional deviation and surface roughness, was studied. A multiobjective optimization method was utilized, combining the Taguchi method with response surface methodology and the desirability function technique. The predicted optimal values for the cube’s dimensional deviation and surface roughness were 0.0517 mm and 2.8079 µm, respectively. The experiments’ validation of the findings confirmed the results, which were determined to be 0.0560 and 0.064667 mm and 2.770 and 2.6431 µm for the dimensional deviation and surface roughness for the cube and bridge, respectively. The percentages of prediction errors between the predicted optimum results and the printed response were 7.68% and 1.36% for dimensional deviation and surface roughness, respectively. This study demonstrates that the robust method used produced a dental bridge with good accuracy and a smooth surface.

Testing for acceptance of an assistive social robot for dementia and caregiving

AbstractBackgroundApproximately 5.8 million older adults in the U.S. are living with AD and it is estimated that by 2060, this number is projected to triple. People with AD often require high levels of care and assistance to maintain daily activities. The majority of care provided to a person living with AD or other forms of dementia is from a family caregiver, representing 18.6 billion hours of unpaid care valued at $244 billion. The long duration, time‐intensive nature of caregiving imposes high burdens on caregivers. There is a great need for assistive technologies and innovative solutions for the future of dementia care because of the increasing rise in adults with dementia.MethodA multidisciplinary team of faculty and undergraduate and graduate students was created to design a low‐cost social robot to serve as assistive companions for people with AD. Focus group meetings with caregivers and those with beginning stages of dementia were held, where the team worked in identifying the audience’s needs and robot’s responsibilities. Initial sketches were formulated before being brought to life in Fusion 360 as 3D CAD objects and printed using a 3D printer. Several rounds of iterations of the social robot’s body and user interfaces were created and two final robot designs were tested with undergraduate students (N = 15) for general attitudes of acceptance and feelings of overall experience.ResultResults from our user testing showed that users preferred one design more than another. Users wanted options in their interactions – having the ability to have speech conversation and touch‐screen abilities. Overall, the results from the user testing were positive, and the team is currently working on a final robot design before testing at nursing homes and assisted living facilities.ConclusionEstimated to be less than $300, our socially assistive robot holds promise to help address the disparity issues in the underserved.

Recognizing geometric primitives in 3D point clouds of mechanical CAD objects

Recognizing geometric primitives in 3D point clouds of mechanical CAD objects

Feature-aware reconstruction of trimmed splines using Ricci flow with metric optimization

The lack of a compelling tool to automatically or semi-automatically create analysis-suitable spline spaces hampers the progress of the isogeometric framework. In this work, we review current techniques to analyze so-called “trimmed” CAD models and present a new approach, based on surface Ricci flow with metric optimization, that can be used for rebuilding trimmed CAD objects. The method is both theoretically grounded and suitable for use on real engineering objects. We demonstrate its efficacy by rebuilding both the US Army’s DEVCOM Generic Hull vehicle and the chassis of the National Crash Analysis Center’s 1996 Dodge Neon into sets of watertight splines. These reconstructed splines are used in isogeometric analysis on model parts and in performing hybrid finite element/isogeometric crash analysis for the Neon vehicle.

Multithreaded wedge detection method on triangular 3D CAD objects using mesh traversal method

In this study, a multithreaded method for triangular mesh three-dimensional computer aided design objects is proposed to detect and extract wedges. Wedge detection is time consuming process for such objects that have large number of facets. To take the advantage of parallel computing opportunities, the algorithm is refactored in this study. Scope of variables, memory management and stack use are optimized for efficient use of computational resources. The proposed method is focused to calculation efficiency and performance on multicore / multithreaded processors and it is evaluated with benchmark, complex and realistic objects.

High-Resolution 3D FEM Stability Analysis of the Sabereebi Cave Monastery, Georgia

This study assesses the static stability of the artificial Sabereebi Cave Monastery southeast of Georgia's capital, Tbilisi. The cliff into which these Georgian-Orthodox caverns, chapels, and churches were carved consists of a five-layered sequence of weak sedimentary rock—all of which bear a considerable failure potential and, consequently, pose the challenge of preservation to geologists, engineers, and archaeologists. In the first part of this study, we present a strategy to process point cloud data from drone photogrammetry as well as from laser scanners acquired in- and outside the caves into high-resolution CAD objects that can be used for numerical modeling ranging from macro- to micro-scale. In the second part, we explore four distinct series of static elasto-plastic finite element stability models featuring different levels of detail, each of which focuses on specific geomechanical scenarios such as classic landsliding due to overburden, deformation of architectural features as a result of stress concentration, material response to weathering, and pillar failure due to vertical load. With this bipartite approach, the study serves as a comprehensive 3D stability assessment of the Sabereebi Cave Monastery on the one hand; on the other hand, the established procedure should serve as a pilot scheme, which could be adapted to different sites in the future combining non-invasive and relatively cost-efficient assessment methods, data processing and hazard estimation.

Fit4CAD: A point cloud benchmark for fitting simple geometric primitives in CAD objects

We propose Fit4CAD, a benchmark for the evaluation and comparison of methods for fitting simple geometric primitives in point clouds representing CAD objects. This benchmark is meant to help both method developers and those who want to identify the best performing tools. The Fit4CAD dataset is composed by 225 high quality point clouds, each of which has been obtained by sampling a CAD object. The way these elements were created by using existing platforms and datasets makes the benchmark easily expandable. The dataset is already split into a training set and a test set. To assess performance and accuracy of the different primitive fitting methods, various measures are defined. To demonstrate the effective use of Fit4CAD, we have tested it on two methods belonging to two different categories of approaches to the primitive fitting problem: a clustering method based on a primitive growing framework and a parametric method based on the Hough transform.

A new approach for reusable 3D CAD objects detection, by similarity calculation based on Bayesian network models (BNM)

ABSTRACT Nowadays, 3D CAD systems (Computer Aided Design) are extremely important in many sectors related to the modern industry. The wide range of modelling software and their increasingly advanced functionalities have considerably extended the uses of CAD models. Indexing and searching in huge databases for the purpose of reusing a 3D CAD model is still a big challenge for both the industrial and for scientific research fields. This highlights the need for an effective approach that provides accurate results within an acceptable time-frame and that takes into account the re-usability of the model regardless of its modelling software. From this perspective, this paper proposes a new data-intensive approach for the detection of reusable CAD models, similar to a reference one. The proposed method is based on the probabilistic graphical model Bayesian network. The suggested approach is mainly based on two phases: (1) first, the construction of a Bayesian network of models (MBN). The developed network is based on an index of association calculated according to the common reusable sub-parts between the candidate models. (2) Then, the detection of reusable models (through the indirect similarity extracted from the built MBN) based on the graph structure and the probabilistic inference.

LoopyCuts

We present a new fully automatic block-decomposition algorithm for feature-preserving, strongly hex-dominant meshing, that yields results with a drastically larger percentage of hex elements than prior art. Our method is guided by a surface field that conforms to both surface curvature and feature lines, and exploits an ordered set of cutting loops that evenly cover the input surface, defining an arrangement of loops suitable for hex-element generation. We decompose the solid into coarse blocks by iteratively cutting it with surfaces bounded by these loops. The vast majority of the obtained blocks can be turned into hexahedral cells via simple midpoint subdivision. Our method produces pure hexahedral meshes in approximately 80% of the cases, and hex-dominant meshes with less than 2% non-hexahedral cells in the remaining cases. We demonstrate the robustness of our method on 70+ models, including CAD objects with features of various complexity, organic and synthetic shapes, and provide extensive comparisons to prior art, demonstrating its superiority.

Modeling of an X-ray grating-based imaging interferometer using ray tracing.

X-ray imaging by means of a grating-based Talbot-Lau interferometer has become an important tool for a wide variety of application areas such as security, medical and materials analysis. Imaging modalities include attenuation, differential phase contrast, and visibility contrast (or so-called dark field). We have developed a novel modeling approach based on ray tracing with commercially available software (Zemax OpticStudio) that yields image projections for all three modalities. The results compare favorably with experimental findings. Our polychromatic ray-based model accommodates realistic 3-D CAD objects with tailored materials properties and also allows for both surface and bulk scattering. As such, the model can simulate imaging of complicated objects as well as assist in a physical understanding of experimental projection details.

CAD Based Electric Transporter Path Planning and Production Storage Optimization Using Genetic Algorithm – Industrial Case Study

Štore Steel Ltd. is one of the largest flat spring steel producers in Europe. There are two production lines after rolling – one for flat bars and the other for round bars. The flat bars production generally consists of visual examination, straightening and cutting operation. In addition, heat treatment or magnetic particle testing could be conducted. On the other hand, the round bars production consists generally of straightening, automatic control line control, chamfering and cutting. In addition, heat treatment is possible. For manipulation of the material in the rolling plant, the electric transporter and several cassettes are used. In the paper path planning and production storage optimization (i.e. storage spaces for cassettes) were conducted using genetic algorithm. The production storage is actually the space between main transport passage and individual operations. In the research the universal system using CAD geometry is presented where AutoCAD environment and in-house developed AutoLISP system were used. The production storage – storage spaces for cassettes (location and orientation) with corresponding electric transporter trajectories are represented as CAD objects and thus form individual solution/organism. The organisms undergo simulated evolution. The results of the evolution are compared with actual production storage in the steel plant.

Par3DNet: Using 3DCNNs for Object Recognition on Tridimensional Partial Views

Deep learning-based methods have proven to be the best performers when it comes to object recognition cues both in images and tridimensional data. Nonetheless, when it comes to 3D object recognition, the authors tend to convert the 3D data to images and then perform their classification. However, despite its accuracy, this approach has some issues. In this work, we present a deep learning pipeline for object recognition that takes a point cloud as input and provides the classification probabilities as output. Our proposal is trained on synthetic CAD objects and is able to perform accurately when fed with real data provided by commercial sensors. Unlike most approaches, our method is specifically trained to work on partial views of the objects rather than on a full representation, which is not the representation of the objects as captured by commercial sensors. We trained our proposal with the ModelNet10 dataset and achieved a 78.39 % accuracy. We also tested it by adding noise to the dataset and against a number of datasets and real data with high success.

A Neural Network with Convolutional Module and Residual Structure for Radar Target Recognition Based on High-Resolution Range Profile.

In the conventional neural network, deep depth is required to achieve high accuracy of recognition. Additionally, the problem of saturation may be caused, wherein the recognition accuracy is down-regulated with the increase in the number of network layers. To tackle the mentioned problem, a neural network model is proposed incorporating a micro convolutional module and residual structure. Such a model exhibits few hyper-parameters, and can extended flexibly. In the meantime, to further enhance the separability of features, a novel loss function is proposed, integrating boundary constraints and center clustering. According to the experimental results with a simulated dataset of HRRP signals obtained from thirteen 3D CAD object models, the presented model is capable of achieving higher recognition accuracy and robustness than other common network structures.

Quality edge extraction of mechanical CAD parts for intelligent manufacturing

Computer aided testing (CAT) is the latest technique. It is because CAT involve in a different stages of manufacturing like designing, production and quality control by 3D measuring instrument that is time consuming. If the object position is known before examined, time can be managed. Machine vision dependent inspection of mechanical CAD parts has become demanding area in the field of industrial inspection. In this work, we developed the procedure to detect the mechanical CAD parts with the edge-based algorithms. The data has been taken with 3D model that has been designed using solid edge ST8 CAD/CAM PLM software and analysed using MATLAB for automated production checking system. Our proposed method uses the edge-based recognition of CAD object by fuzzy-based approach in order to create image information of shape before it can be used for pose estimation in computer aided testing system. From the experimental results, it has been found that with the proposed vision system more accurate and reliable products can be manufactured intelligently.

Quality edge extraction of mechanical CAD parts for intelligent manufacturing

Computer aided testing (CAT) is the latest technique. It is because CAT involve in a different stages of manufacturing like designing, production and quality control by 3D measuring instrument that is time consuming. If the object position is known before examined, time can be managed. Machine vision dependent inspection of mechanical CAD parts has become demanding area in the field of industrial inspection. In this work, we developed the procedure to detect the mechanical CAD parts with the edge-based algorithms. The data has been taken with 3D model that has been designed using solid edge ST8 CAD/CAM PLM software and analysed using MATLAB for automated production checking system. Our proposed method uses the edge-based recognition of CAD object by fuzzy-based approach in order to create image information of shape before it can be used for pose estimation in computer aided testing system. From the experimental results, it has been found that with the proposed vision system more accurate and reliable products can be manufactured intelligently.

The optimal design of a 3D pentagonal toroid with circular cross-section used in manufacturing of LPG storage tanks

This paper presents a 3D solid modelling to generate a pentagonal toroid with circular cross-section used in manufacturing of LPG storage tanks from the automotive industry. Stress and linear deformation analysis are applied to optimize the geometrical product shape. As a result, in numerical simulation a feasible time-cost integrated project schedule was developed to formulate a construction sequence of product components based on the physical relationships between CAD objects.