STUDY THE EFFECT OF ALLOYING ELEMENT AND TESTING TEMPERATURE ON MECHANICAL PROPERTIES OF FE-18CR-12NI-NB BASED AUSTENITIC STAINLESS STEEL USING ARTIFICIAL NEURAL NETWORK MODELING
because they have good corrosion resistance, high temperature creep resistance, impact resistance at low temperatures, and good workability. This alloy most commonly used in chemical reactors, heat exchangers, and other uses. Material failure in one of its uses can be caused by combination of its...
Saved in:
| Main Author: | |
|---|---|
| Format: | Final Project |
| Language: | Indonesia |
| Subjects: | |
| Online Access: | https://digilib.itb.ac.id/gdl/view/51419 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | because they have good corrosion resistance, high temperature creep resistance,
impact resistance at low temperatures, and good workability. This alloy most
commonly used in chemical reactors, heat exchangers, and other uses. Material
failure in one of its uses can be caused by combination of its exposure due to high
temperatures and mechanical loads. The current challenge is how to design the
desired steel properties to reduce the experimental time and costs of its alloy
development. As an alternative, the artificial intelligence method is used. In this
study, the effect of alloying element and testing temperature on mechanical
properties of the Fe-18Cr-12Ni-Nb based alloy was studied using artificial neural
network modeling method.
Series of experiments artificial neural network modeling have been carried out to
study the effect of alloying element (16 elements) and testing temperature as input
on Fe-18Cr-12Ni-Nb based alloy mechanical properties such as Yield Strength,
Ultimate Tensile Strength, %Elongation, and %Reduction of Area as output. The
modeling process begins with searching for a database of mechanical properties of
the Fe-18Cr-12Ni-Nb based alloy that obtained from NIMS (Japan), then the data
is divided into train data and test data. Modeling was carried out in MATLAB
R2019b software with certain modeling parameters and then the optimal number of
neurons and hidden layers was determined. The importance of each input variable
(i) alloying element and (ii) the testing temperature is determined using index of
relative importance (IRI) method. A simple Graphical User Interface (GUI)
program is made to make it easier for users to simulate the determination of
mechanical properties of the Fe-18Cr-12Ni-Nb alloy based on certain input.
Based on modeling results, the optimal ANN architectural model for determining
the mechanical properties for YS and %RA is 17-13-13-1 and for UTS and %EL is
17-12-12-1. The average MAPE values obtained for predicting mechanical
properties of YS, UTS, %EL, and %RA were 2.9977; 0.7879; 2.9528; 1.8297
respectively and categorized as highly accurate. The effect of alloying element on
mechanical properties using the IRI method cannot be determined because it still
requires more data to validate the correlation. The effect of testing temperature on
mechanical properties with ANN modeling is good enough according to the actual
data, although there are still errors. Prediction of the value of mechanical properties
can be done faster using Grapical User Interface program that more time efficient. |
|---|