Abstract: When estimating low damage probability of a building to the ten raise to the power minus six level, even with subset MCMC, response analysis of over 150,000 times is necessary. It requires much CPU time and therefore unrealistic. In this paper, once after reducing the number of response analysis without using subset method, we create a n dimensional regression hypersurface (a deep learning regression model) that predicts low damage probability of a building. This enables quantitative estimation with dramatically less effort.

• Publication Date: 24-Apr-2019
• DOI: 10.15224/978-1-63248-170-2-04
• Views: 0
• Downloads: 0

Abstract: Manufacturing of Titanium alloy miniature gear is one of the biggest challenge in recent past. Wire electric discharge machining is widely used to cut hard material. Selection of the wire electric discharge machining process parameters to obtain the minimum dimensional deviation such as Dimensional deviation in outer diameter, dimensional deviation in inner diameter and dimensional deviation in land is very crucial. In this work, suitable process parameters such as Current, Pulse on time, Pulse off time, Wire tension and Dielectric fluid, have been identified to achieve low deviation in dimensions of miniature gear. Different dielectric fluids have been prepared using the mixture of ethylene glycol, alumina nano powder and oxygen in demineralized water. The dimensional deviations are measured using profile projector and suitable parameters ranges are identified. Titanium alloy based miniature gear will be useful in industries.

• Publication Date: 24-Apr-2019
• DOI: 10.15224/978-1-63248-170-2-05
• Views: 0
• Downloads: 0