Similarity assessment between 3D models is an important problem in many fields including medicine, biology and industry. As there is no direct method to compare 3D geometries, different model representations (shape signatures) are developed to enable shape description, indexing and clustering. Even though some of those descriptors proved to achieve high classification precision, their application is often limited. In this work, a different approach to similarity assessment of 3D CAD models was presented. Instead of focusing on one specific shape signature, 45 easy-to-extract shape signatures were considered simultaneously. The vector of those features constituted an input for 3 machine learning algorithms: the random forest classifier, the support vector classifier and the fully connected neural network. The usefulness of the proposed approach was evaluated with a dataset consisting of over 1600 CAD models belonging to 9 separate classes. Different values of hyperparameters, as well as neural network configurations, were considered. Retrieval accuracy exceeding 99% was achieved on the test dataset.
Automation of earth moving machineries is a widely studied problem. This paper focusses on one of the main challenges in automation of the earth moving industry, estimation of loading torque acting on the machinery. Loading torque acting on the excavation machinery is a very significant aspect in terms of both machine and operator safety. In this study, a disturbance observer-assisted control system for the estimation of loading torque acting on a robotic backhoe during excavation process is presented. The proposed observer does not use any acceleration measurements, rather, is proposed as a function of joint velocity. Numerical simulations are performed to demonstrate the effectiveness of the proposed control scheme in tracking the reaction torques for a given dig cycle. Co-simulation experiments demonstrate robust performance and accurate tracking of the proposed control in both disturbance torque and position tracking. Further, the performance and sensitivity of the proposed control are also analyzed through the help of performance error quantifiers, the root-mean-square (RMS) values of the position and disturbance tracking errors.
A brief review of the existing autonomous underwater vehicles, their types, design, movement abilities and missions is presented. It is shown, the shape optimization design and enhancement of their efficiency is the main problem for further development of multipurpose glider technologies. A comparative study of aerodynamic performance of three different shape designs (the airfoil NACA0022 based (I), flattened ellipsoidal (II) and cigar-type (III) bodies of the same volumes) has been carried out. Geometrical modelling, meshing and computational fluid dynamics (CFD) simulations have been carried out with AnSys15.0. The pathlines and wall shear stress distributions have been computed to understand the advantages and disadvantages of each shape. The lift and drag coefficients, aerodynamic quality, power index and pitching moment have been computed. The higher efficiency of the shape I/shape II at higher/lower angles of attack (> 20o and < 20o) has been found. The shape III develops high speeds at the same angles of attack and has higher manoeuvrability at relatively low aerodynamic quality. The comparative analysis of the flow capabilities of studied autonomous undersea vehicles proposes some design improvement for increasing their energy efficiency and flow stability.
The paper presents a simulation model of the hybrid magnetic bearing dedicated to simulations of transient state. The proposed field-circuit model is composed of two components. The first part constitutes a set of ordinary differential equations that describes electrical circuits and mechanics. The second part of the simulation model consists of parameters such as magnetic forces, dynamic inductances and velocity-induced voltages obtained from the 3D finite element analysis. The MATLAB/Simulnik softwarewas used to implement the simulation model with the required control system. The proposed field-circuit model was validated by comparison of time responses with the prototype of the hybrid magnetic bearing.
en
pl
