Neural Networks for Predicting the Wear Properties of Sintered Ti-6Al-4V Composite Reinforced with Nano B4 C Particle and Classification using Data Mining Tools

This proposed work is to improve the strength and wear resistance of materials by reinforcing the composite preform (Ti-6Al-4V) with an addition of (2-10) wt. % of nano boron carbide particles. The characterization was performed through Scanning electron microscope of above composites. While measuring wear using pin-on-disk testing machine, the temperature, load, sliding distance are varied for identifying the nature of dry and high temperature wear of prepared composite. The output of this wear experimental work is fed to the soft computing based tool like Artificial Neural Network for predicting the wear properties such as specific wear rate and coefficient of friction. Further, with respect to the temperature and B4 C%, the wear properties are analysed using data mining tool like Decision Tree. Moreover, fixing the range of metal powders for classifying the wear properties of composite preforms can be automated by using Fuzzy logic.