/* ---- Google Analytics Code Below */

Monday, July 23, 2018

Combining Bayesian Network and Machine Learning

Interesting because of the analytics design, but the domain is something I looked at in a previous area of work.  Probably useful when thinking more broadly about maintenance methodology. Note how the ML and Bayesian are connected.

Understanding Small Fatigue Cracking Force   

Notable Research with BayesiaLab: Using machine learning and a data-driven approach to identify the small fatigue crack driving force in polycrystalline materials.  .... via Bayesia

Crack propagation: machine learning identifies micromechanical variables

A machine learning technique can identify the complex variables behind the propagation direction of small cracks in a titanium alloy. A team led by Michael Sangid at Purdue University in the U.S.A built two separate Bayesian networks using machine learning to analyse diffraction and tomography data acquired during in situ fatigue cycling of a titanium alloy. The orientation of the first principal stress axis in a specific direction and the maximum resolved shear stress were the most strongly correlated with crack propagation, and were incorporated into an analytical relationship to describe the probability of the crack propagation direction. This analytical expression reproduced experimental results and was more reliable than previous literature predictions. This sort of semi-supervised machine learning methodology may help us identify driving forces in other complex engineering problems.  ... "

No comments: