Study on effect of TiB2 reinforcement on the microstructural and mechanical properties of magnesium RZ5 alloy based metal matrix composites

A self-propagating high-temperature synthesis route is adopted for the fabrication of TiB2-reinforced magnesium RZ5 alloy-based in-situ metal matrix composites.Ti-B is used according to the appropriate stoichiometry to obtain 4,6 and 8 wt.%TiB2 reinforcements.The base alloy and cast composites are solutionised to enhance the mechanical properties of the materials.A microstructural study of the composites is carried out using optical microscopy and field emission seanning electron microscopy(FESEM)and revealed near-uniform distribution of TiB2 particles in the magnesium RZ5 alloy matrix.X-ray diffraction revealed the formation of the TiB2 reinforcement along with the transient phase TiB and MgB7.The hardness of the RZ5 alloy-based composites increases by 7.12%,17.06%and 32.07%with the addition of 4,6 and 8 wt.%TiB2 reinforcements,respectively.The ultimate tensile strength of the as-cast composite increases by 30.47%with the addition of 8 wt.%TiB2.The tensile strength and ductility of the materials is improved by using the solutionising heat treatment.The heat-treated composite containing 8 wt.%TiB2 results in an ultimate tensile strength of 178.7 MPa.The tensile fracture surfaces are analysed using FESEM.The wear loss of the materials decreased from 25.826 mm^(3)to 22.949 mm^(3)by the adding 8 wt.%TiB2 for the sliding distance of 2000 m.Micrographs of the worn surfaces obtained from FESEM of both the base alloy and composites are also studied which indicate delamination,wear groove and oxide formation.

Design of computer vision assisted machine learning based controller for the Stewart platform to track spatial objects

The present work aims to develop an object tracking controller for the Stewart platform using a computer vision-assisted machine learning-based approach.This research is divided into two modules.The first module focuses on the design of a motion controller for the Physik Instrumente(PI)-based Stewart platform.In contrast,the second module deals with the development of a machine-learning-based spatial object tracking algorithm by collecting information from the Zed 2 stereo vision system.Presently,simple feed-forward neural networks(NN)are used to predict the orientation of the top table of the platform.While training,the x,y,and z coordinates of the three-dimensional(3D)object,extracted from images,are used as the input to the NN.In contrast,the orientation information of the platform(that is,rotation about the x,y,and z-axes)is considered as the output from the network.The orientation information obtained from the network is fed to the inverse kinematics-based motion controller(module 1)to move the platform while tracking the object.After training,the optimised NN is used to track the continuously moving 3D object.The experimental results show that the developed NN-based controller has successfully tracked the moving spatial object with reasonably good accuracy.