•Feature detection using randomised plane cutting in a CAD mesh model.•The algorithm uses graph traversals and without using threshold values.•Geometry of most of the extracted features is identified ...using Gauss map.•Interacting features have also been extracted and separated.•Our approach can also correctly process many types of interacting features.
Display omitted
This paper presents a method to identify regions that make up features like holes, slots, pockets as well as interacting features in a three-dimensional mesh of a computer-aided design (CAD)/Engineering model. Feature recognition is an important area in the field of CAD/Engineering with applications in model retrieval, creating an analysis model by defeaturing of the designed model for finite element applications, etc. Most feature recognition methods use either a cluster-based decomposition or feature line extraction through solid angles or curvature values, followed by graph-based heuristics. Such approaches require a user parameter for clustering or a threshold value for angle/curvature, neither of which is an easily deterministic one. The proposed algorithm identifies the features using contours generated by random cutting planes, followed by graph traversals (and not using heuristics) and without using parameter/threshold values. The algorithm can identify blind holes, through holes, slots and pockets. The geometry of most of the extracted features has also been identified using Gauss map. Interacting features have also been extracted and separated, which normally pose difficulty for most algorithms. Extensive experiments on CAD models from various benchmarks show that the algorithm is robust. Comparison with different algorithms (of which code was available) shows that our approach performs admirably and in the case of interacting features, the algorithm performs better than the existing ones.
In the context of increased maintenance operations and generational renewal work, a nuclear owner and operator, like Electricité de France (EDF), is invested in the scaling-up of tools and methods of ...“as-built virtual reality” for whole buildings and large audiences. In this paper, we first present the state of the art of scanning tools and methods used to represent a very complex architecture. Then, we propose a methodology and assess it in a large experiment carried out on the most complex building of a 1300-megawatt power plant, an 11-floor reactor building. We also present several developments that made possible the acquisition, processing and georeferencing of multiple data sources (1000+ 3D laser scans and RGB panoramic, total-station surveying, 2D floor plans and the 3D reconstruction of CAD as-built models). In addition, we introduce new concepts for user interaction with complex architecture, elaborated during the development of an application that allows a painless exploration of the whole dataset by professionals, unfamiliar with such data types. Finally, we discuss the main feedback items from this large experiment, the remaining issues for the generalization of such large-scale surveys and the future technical and scientific challenges in the field of industrial “virtual reality”.
We propose a Point-Voxel DeConvolution (PVDeConv) module for 3D data autoencoder. To demonstrate its efficiency we learn to synthesize high-resolution point clouds of 10k points that densely describe ...the underlying geometry of Computer Aided Design (CAD) models. Scanning artifacts, such as protrusions, missing parts, smoothed edges and holes, inevitably appear in real 3D scans of fabricated CAD objects. Learning the original CAD model construction from a 3D scan requires a ground truth to be available together with the corresponding 3D scan of an object. To solve the gap, we introduce a new dedicated dataset, the CC3D, containing 50k+ pairs of CAD models and their corresponding 3D meshes. This dataset is used to learn a convolutional autoencoder for point clouds sampled from the pairs of 3D scans - CAD models. The challenges of this new dataset are demonstrated in comparison with other generative point cloud sampling models trained on ShapeNet. The CC3D autoencoder is efficient with respect to memory consumption and training time as compared to stateof-the-art models for 3D data generation.
A two-scale calculation method is described that makes it possible to optimize the material composition of machine components and structural elements on the basis of the requirements for their ...deformation-strength and tribotechnical characteristics. The proposed method provides the combined use of analytical micromechanical modelling of structurally inhomogeneous structural materials in the form of disperse-reinforced composites and numerical (finite element) analysis of the stress-strain state of a particular product. The advantage of the method is ensuring of maximum strength, stiffness and wear resistance of the product with simultaneous correction of its geometric shape and the possibility of using the resulting refined CAD model for 3D printing of components of complex shape by extruded composites of optimized composition.
The enhancement of the early design stages, in the production of aeronautical engines, has been shown decisive, for developing efficient and reliable final products. Nevertheless, in most of ...industrial engineering design problems, the amount of design variables is large. Moreover, several nonlinearities characterize the behaviour of the physical phenomena involved and the derivatives are seldom known for all the functions. Besides, objective functions exhibit several local extremes, whereas the designer as well as the practitioner is usually interested in the global one. In this context, stochastic and evolutionary optimization have been shown capable to provide reliable solutions while keeping the computational cost at a reasonable level. Existing tools for the design and optimization of engine components deal with the optimal and detailed design of specific engine components, thus requiring several computational time and efforts to gain optimized design parameters. Hence, existing tools fit for later design phases. Conversely, this paper proposes an integrated design and optimization environment, for automatically designing optimal aeronautical piston engine configuration, still in the conceptual design stage. The optimization is performed using the MATLAB genetic algorithm (GA) toolbox®, while the automatic design of the optimized components is carried out in cascade to the optimization phase. In particular, a single-objective GA is used to evaluate the optimal dimensions of engine components related to motion, namely: crankshaft, connecting rods and screws, flywheel, propeller shaft and torsional vibration damper. For testing the efficiency of the integrated environment, the conceptual design of components of a 4-in-line Diesel aeronautical piston engine is proposed, starting from an existing similar engine. Results show a reduction of the 20 % of weight of the crankshaft in comparison to the original configuration. The proposed environment seems to be a promising tool for a fast and reliable conceptual design of piston engines for aeronautical purposes.
Thanks to the proliferation of commodity 3D devices such as HoloLens, one can have easy access to the 3D model of indoor building objects. However, this model does not match 2D available ...computer-aided design (CAD) models as the as-built model. To address this problem, in this study, a 3-step registration method is proposed. First, binary images, including walls and background, are generated for the 3D point cloud (PC) and the 2D CAD model. Then, 2D-to-2D corresponding pixels (CPs) are extracted based on the intersection of walls in each binary image of PC (BIPC) and binary CAD (BCAD) model. Since the 3D PC space coordinates (XYZ) of all BIPC's pixels are known, BIPC part of the 2D-to-2D CPs can be considered 3D. Lastly, the parameters of the 8-parameter affine are estimated using the 2D-to-3D CPs, which are pixel coordinates in BCAD model as well as their correspondences in the 3D PC space. Experimental results indicate the efficiency of our proposed method compared to manual registration.
PurposeDigital computing and machine learning-driven predictive analysis in the diagnosis of non-communicable diseases are gaining significance. Globally many research studies are focusing on ...developing comprehensive models for such detection. Categorically in the proposed diagnosis for arrhythmia, which is a critical diagnosis to prevent cardiac-related deaths, any constructive models can be a value proposition. In this study, the focus is on developing a holistic system that predicts the scope of arrhythmia from the given electrocardiogram report. The proposed method is using the sequential patterns of the electrocardiogram elements as features.Design/methodology/approachConsidering the decision accuracy of the contemporary classification methods, which is not adequate to use in clinical practices, this manuscript coined a new dimension of features to perform supervised learning and classification using the AdaBoost classifier. The proposed method has titled “Electrocardiogram stream level correlated patterns as features (ESCPFs),” which takes electrocardiograms (ECGs) signal streams as input records to perform supervised learning-based classification to detect the arrhythmia scope in given ECG record.FindingsFrom the results and comparative reports generated for the study, it is evident that the model is performing with higher accuracy compared to some of the earlier models. However, focusing on the emerging solutions and technologies, if the accuracy factors for the model can be improved, it can lead to compelling predictions and accurate outcome from the process.Originality/valueThe authors represent complete automatic and rapid arrhythmia as classifier, which could be applied online and examine long ECG records sequence efficiently. By releasing the needs for extraction of features, the authors project an application based on raw signals, one result to heart rates date, whose objective is to lessen computation time when attaining minimum classification error outcomes.
Using Virtual Reality as a Support Tool for the Offline Robot Programming Holubek, Radovan; Ružarovský, Roman; Delgado Sobrino, Daynier Rolando
Vedecké práce Materiálovotechnologickej fakulty Slovenskej technickej univerzity v Bratislave so sídlom v Trnave/Vedecké práce Materiálovotechnologickej fakulty Slovenskej technickej univerzity v Bratislave so sídlom v Trnave,
06/2018, Volume:
26, Issue:
42
Journal Article
Peer reviewed
Open access
The present article focuses on the possibilities of using Virtual Reality (VR) as a supporting tool by using the offline programming method for industrial robots. The philosophy of using such a ...process is hierarchically linked to the observance of methodological procedures for the proposal new workstations with using industrial robots. First, it is necessary to develop CAD models of the projected workplace, which can be imported into a suitable simulation environment for the creation of robotic simulations with support for visualization to the immersive VR environment. In our case, the CAD software Catia was used to develop a workstation, followed by integration of the CAD database into the simulation environment of Process Simulate (PS). Support for the visualization in the immersive environment of the Virtual Reality of Process Simulate was vested using the glasses headset HTC VIVE.
As-built CAD data reconstructed from Terrestrial Laser Scanner (TLS) data are used for more than two decades by Electricité de France (EDF) to prepare maintenance operations in its facilities. But ...today, the big picture is renewed: "as-built virtual reality" must address a huge scale-up to provide data to an increasing number of applications. In this paper, we first present a wide multi-sensor multi-purpose scanning campaign performed in a 10 floor building of a power plant in 2013: 1083 TLS stations (about 40.109 3D points referenced under a 2 cm tolerance) and 1025 RGB panoramic images (340.106 pixels per point of view). As expected, this very large survey of high precision measurements in a complex environment stressed sensors and tools that were developed for more favourable conditions and smaller data sets. The whole survey process (tools and methods used from acquisition and processing to CAD reconstruction) underwent a detailed follow-up in order to state on the locks to a possible generalization to other buildings. Based on these recent feedbacks, we have highlighted some of these current bottlenecks in this paper: sensors denoising, automation in processes, data validation tools improvements, standardization of formats and (meta-) data structures.
Documentation of maritime heritage is essential for its protection, and for reference in restoration and renovation processes. These functions become problematic in the case of historical ships and ...boats that lack lines drawings. The purpose of this paper is to describe a procedure for creation of lines drawings based on the shape analysis of surviving historical boats or their small-scale models with the help of reverse engineering (RE) techniques. The paper describes how digital photogrammetry and the iterative method were used to analyze the shape of three historical boats: Tomahawk, Refola and Nada. The application of the proposed procedure produced the lines drawings of the boats as its result. The accuracy of the 3D CAD model obtained with the photogrammetric technique was verified by comparing it against a more accurate 3D model produced with the help of a RE laser scanner. The examination of the resulting lines drawings proves that the digital photogrammetry process and the proposed iterative method are adequate tools for developing lines plans of boat models. The research offers the methodological basis for the creation of an archive of lines drawings of historical boats. Such an archive would provide reference for philologically correct restorations, and permit definition and classification of distinctive elements of various types of historical boats, particularly those produced in the Campania Region.
PDF
