Professional Documents
Culture Documents
Microstructure Recognition of Steel Using Machine Learning: Ntroduction
Microstructure Recognition of Steel Using Machine Learning: Ntroduction
Keywords— Metallography;
I.INTRODUCTION
Material alloys, or even pure materials, present different
structure, since they can have specific grain boundaries, phase
boundaries, inclusion distribution, and so forth. Thus, during
microscope observation, material engineer has to focus on
many details to get a better identification. However, observing
material structure is hard even for the most trained engineer,
since different materials have different characteristics and
specific protocol. Learning the whole set of protocols and
procedures for all materials, is not just almost impossible, but
also useless since, protocols are reviewed frequently. Since
metallography studies relies on imaging observation and
decision making by observers, this work presents an approach Fig. Architectural Design
for metallography of commercially available materials by
image classification with machine learning algorithms. Hence
The inner structure of a material is called microstructure. It
stores the genesis of a material and determines all its We used different problem Solving
physical and chemical properties. While microstructural
characterization is widely spread and well known, the methodologies for our project:
microstructural classification is mostly done manually by
human experts, which gives rise to uncertainties due to 1 –Split large complex goals into small, simpler ones.
subjectivity. Since the microstructure could be a
The ability to split work into tasks is natural to humans,
combination of different phases or constituents with
and a required skill to get most things done. Making the above
complex substructures its automatic classification is very
list doesn’t require any particular study or practice other than
challenging and only a few prior studies exist. Prior works
knowing how to make coffee. In other words, more or less
focused on designed and engineered features by experts and
anyone can do it.
classified microstructures separately from the feature
extraction step. Recently, ,Machine Learning methods have
shown strong performance in vision applications by learning However, the difference between a practical everyday
the features from data together with the classification step. problem like making coffee and a more complex challenge
like software building is that the steps to build software are
Algorithm: rarely heavily rehearsed. To be able to list what tasks are
In this work, we compared K-Nearest Neighbors necessary to build a particular piece of software requires
(KNN),Decision Tree (DT) and Linear having done it many times before. That is not very common in
software building. That’s why experienced software engineers
Discriminant Analysis (LDA) algorithms on don’t jump immediately to writing a task list. Instead, they
metallographic specimen classification.Euclidean split the overall problem into more straightforward ones.
distance is used as metric for K-Nearest
Neighbors,as on Equation 5, Engineers refer to the problems to resolve as the “what,”
and as the tasks to accomplish as the “how.”
References: