An Optimized Deep Neural Network for Overhead Contact System Recognition from LiDAR Point Clouds

As vital infrastructures, high-speed railways support the development of transportation. To maintain the punctuality and safety of railway systems, researchers have employed manual and computer vision methods to monitor overhead contact systems (OCSs), but they have low efficiency. Investigators have also used light detection and ranging (LiDAR) to generate point clouds by emitting laser beams. The point cloud is segmented for automatic OCS recognition, which improves recognition efficiency. However, existing LiDAR point cloud segmentation methods have high computational/model complexity and latency. In addition, they cannot adapt to embedded devices with different architectures. To overcome these issues, this article presents a lightweight neural network EffNet consisting of three modules: ExtractA, AttenA, and AttenB. ExtractA extracts the features from the disordered and irregular point clouds of an OCS. AttenA keeps information flowing in EffNet while extracting useful features. AttenB uses channel and spatialwise statistics to enhance important features and suppress unimportant ones efficiently. To further speed up EffNet and match it with diverse architectures, we optimized it with a generation framework of tensor programs and deployed it on embedded systems with different architectures. Extensive experiments demonstrated that EffNet has at least a 0.57% higher mean accuracy, but with 25.00% and 9.30% lower computational and model complexity for OCS recognition than others, respectively. The optimized EffNet can be adapted to different architectures. Its latency decreased by 51.97%, 56.47%, 63.63%, 82.58%, 85.85%, and 91.97% on the NVIDIA Nano CPU, TX2 CPU, UP Board CPU, Nano GPU, TX2 GPU, and RTX 2,080 Ti GPU, respectively.

A Strong-Form Off-Lattice Boltzmann Method for Irregular Point Clouds

Radial basis function generated finite differences (RBF-FD) represent the latest discretization approach for solving partial differential equations. Their benefits include high geometric flexibility, simple implementation, and opportunity for large-scale parallel computing. Compared to other meshfree methods, typically based upon moving least squares (MLS), the RBF-FD method is able to recover a high order of algebraic accuracy while remaining better conditioned. These features make RBF-FD a promising candidate for kinetic-based fluid simulations such as lattice Boltzmann methods (LB). Pursuant to this approach, we propose a characteristic-based off-lattice Boltzmann method (OLBM) using the strong form of the discrete Boltzmann equation and radial basis function generated finite differences (RBF-FD) for the approximation of spatial derivatives. Decoupling the discretizations of momentum and space enables the use of irregular point cloud, local refinement, and various symmetric velocity sets with higher order isotropy. The accuracy and computational efficiency of the proposed method are studied using the test cases of Taylor–Green vortex flow, lid-driven cavity, and periodic flow over a square array of cylinders. For scattered grids, we find the polyharmonic spline + poly RBF-FD method provides better accuracy compared to MLS. For Cartesian node layouts, the results are the opposite, with MLS offering better accuracy. Altogether, our results suggest that the RBF-FD paradigm can be applied successfully also for kinetic-based fluid simulation with lattice Boltzmann methods.

VB-Net: Voxel-Based Broad Learning Network for 3D Object Classification

Point clouds have been widely used in three-dimensional (3D) object classification tasks, i.e., people recognition in unmanned ground vehicles. However, the irregular data format of point clouds and the large number of parameters in deep learning networks affect the performance of object classification. This paper develops a 3D object classification system using a broad learning system (BLS) with a feature extractor called VB-Net. First, raw point clouds are voxelized into voxels. Through this step, irregular point clouds are converted into regular voxels which are easily processed by the feature extractor. Then, a pre-trained VoxNet is employed as a feature extractor to extract features from voxels. Finally, those features are used for object classification by the applied BLS. The proposed system is tested on the ModelNet40 dataset and ModelNet10 dataset. The average recognition accuracy was 83.99% and 90.08%, respectively. Compared to deep learning networks, the time consumption of the proposed system is significantly decreased.

Expected performances of the Characterising Exoplanet Satellite (CHEOPS)

The CHaracterizing ExOPlanet Satellite (CHEOPS) is set to be launched in December 2019 and will detect and characterize small size exoplanets via ultra high precision photometry during transits. CHEOPS is designed as a follow-up telescope and therefore it will monitor a single target at a time. The scientific users will retrieve science-ready light curves of the target that will be automatically generated by the CHEOPS data reduction pipeline of the Science Operations Centre. This paper describes how the pipeline processes the series of raw images and, in particular, how it handles the specificities of CHEOPS data, such as the rotating field of view, the extended irregular point spread function, and the data temporal gaps in the context of the strict photometric requirements of the mission. The current status and performance of the main processing stages of the pipeline, that is the calibration, correction, and photometry, are presented to allow the users to understand how the science-ready data have been derived. Finally, the general performance of the pipeline is illustrated via the processing of representative scientific cases generated by the mission simulator.

Experimental study of wind impact on multilevel industrial scaffolding

In the article, the local stress-strain state of structures and constructions is investigated, various variants for the design of the boundary are taken into account: special lines, points. The acting forced deformations don’t satisfy the compatibility conditions. They have a finite discontinuity along the contact line (surface) of the domains, including the irregular point of the boundary, causing stresses. The subject of article is stress concentrators the singularity of the stress-strain state of structures and constructions exhibiting “constructive heterogeneity” and discontinuous forced deformations determined on polymer models of photoelasticity and defrosting of deformations. A complex theoretical-numerical-experimental approach, for obtaining and analyzing the stress state in the neighborhood of the irregular point of the plane domain boundary, is proposed to extrapolate reliable experimental data to a domain where the fringe contour is not readable.

Stress and Strain Intensity Factors of the Corner Area of the Structure Boundary

The Stress and strain state of building structures in zones with bird's mouths and cuts of the boundary is characterized by stress concentration zones emergence and requires an evaluation of strength and reliability of objects, which is the engineering practice actual task. Theoretical analysis of stress and strain state of bird's mouth areas of the region boundary is confined to the study of singular solutions of the elasticity problem with power singularities. In this case, the concept of stress or strain concentration at an irregular point of the region boundary becomes meaningless. In the present article, stress and strain state is considered in the neighborhood of the bird's mouth vertex of the boundary of a plane region, which is written with the help of the intensity factors. Two approaches are given to obtaining the expressions for displacements, stresses in the neighborhoods of an irregular point of the boundary of a plane region by means of stress intensity factors and strain intensity factors. The difference in the expressions for stresses and displacements obtained for the limiting values of stresses and strains determines the practical significance of the work during the experiments and the determination of the critical values of stresses and strains.

Comparison of the stress and strain intensity factors for the corner area of the structure boundary

The stress-strain state of structures in areas with corner cut-outs and cuts of boundaries features the occurrence of areas of stress concentration and requires assessment of strength and reliability of facilities, which is a relevant task in engineering practice. Theoretical analysis of stress-strain state (SSS) of corner cut-outs zones of the area boundary is reduced to the study of singular solutions of the elasticity theory problem with exponential features. At that, the concept of stress or strain concentration in an irregular point of the area boundary is meaningless. This paper considers the stress-strain state in the vicinity of the top of the corner cut-out of the flat area boundary, which is recorded using the intensity factors as limit values of stresses and strains. We give two approaches for obtaining the limit values for stress and strain in the vicinity of an irregular point of the plane area boundary using the stress intensity factors and the strain intensity factors. The stress-strain state in the corner cut-outs zone of structures and buildings boundary recorded in the form of limit values of stresses and strains may further be used to determine and record the influence of changing the factors of intensity of stresses and strains on SSS of structures, which is a separate task of solid mechanics. The difference in the expressions of stresses and displacements obtained for limit values of stresses and strains determines practical significance of the work when carrying out experiments and at determination of critical values of stresses and strains.

Non-equispaced B-spline wavelets

This paper has three main contributions. The first is the construction of wavelet transforms from B-spline scaling functions defined on a grid of non-equispaced knots. The new construction extends the equispaced, biorthogonal, compactly supported Cohen–Daubechies–Feauveau wavelets. The new construction is based on the factorization of wavelet transforms into lifting steps. The second and third contributions are new insights on how to use these and other wavelets in statistical applications. The second contribution is related to the bias of a wavelet representation. It is investigated how the fine scaling coefficients should be derived from the observations. In the context of equispaced data, it is common practice to simply take the observations as fine scale coefficients. It is argued in this paper that this is not acceptable for non-interpolating wavelets on non-equidistant data. Finally, the third contribution is the study of the variance in a non-orthogonal wavelet transform in a new framework, replacing the numerical condition as a measure for non-orthogonality. By controlling the variances of the reconstruction from the wavelet coefficients, the new framework allows us to design wavelet transforms on irregular point sets with a focus on their use for smoothing or other applications in statistics.