optimization of rebar production process
DESCRIPTION
optimization of rebar production process in metallurgy. Uses data analysis tools like Artificial Neural Network (ANN), Clustering, Fuzzy logic, Multiple Regression to arrive at the best solution to manufacturing of rebar steels.TRANSCRIPT
Metallurgical and Materials Engineering
IIT Kharagpur
Summer Internship Presentation
Developing correlation for product properties
as a function of operating conditions
in Rebar Mill
Objective• Explore the feasibility of a predictive model for property estimation
in NBM.
After Implementation:A machine learning model trained with all possible data can be used for online prediction of controlling parameters.
Current status:Theoretical model based on heat transfer calculations which is highly inaccurate.The operator uses his experience.
YS distribution
NBM LAYOUT
WB1 WB2
FRT
A
B
Billet Temperature Pyrometer
Chemistry (C, Mn)
Testing(YS,UTS,C,Mn
)
Approach
UTS/Y
S>
1.1
550
0D
CS=16 mm
YSUTS
FRT<0
WB1flow rate
WB2 flow rate
Billet Temperature
Mill Speed
Carbon Equivalent
>0
Carbon
Manganese
CS=12 mm
CS=10 mm
Relationship between individual variables
CE was found to be insignificant in predicting YS.Multiple Regression did not give any satisfactory results.Problem with YS: Taken from any random point of rebar.
500D,16mm
YS vs FRT
The operator operates at atleast 2 different ranges of water flow
rates.Towards Clustering
• Fuzzy clustering• K-means clustering
Cluster Analysis
• Satisfactory relation was obtained only for cluster which contained low values of water box flow rate implying negligible leakage.
• The results of Cluster Analysis varied for different data periods.
K means clustering:• 3 clusters created by taking into
consideration WB1, WB2, FRT• All the clusters had similar range of
FRT and Billet Temperature but differed in WB1 and WB2 ranges.
Multiple Linear Regression
LeakageSplit nozzle design
Fuzzy Approach
• Takes into account the error in taking readings.
• Inputs and outputs are assigned membership functions.
• Membership functions create fuzzy sets.
• Results:• RMSE in FRT ~ 11.6C• Predicted values are
concentrated around the mean
BLT
WB1
WB2
FRT
1 23
WB1 values
WB1 Membership Fcn
ANN Model
ANN Architecture: ANN with 1 hidden layer having 10 neurons.
Tansig transfer function=-1
WB1WB2Billet TempSpeed
Backpropagation Learning Algorithm: Works by minimizing error with respect to weights.
FRT
Linear transfer function
Training Data=70%Validation Data=15%Test Data=15%
ANN Results
r2=0.88Results for data on which network was trained
• ANN model predicted extremely well (r2>0.84) for unseen test data on which it was trained.
• Predicted well (r2>0.60) for untrained data which followed a recognizable pattern. • Failed to predict data which didn’t follow any trained pattern. • This showed that data varied considerably with time. • Nozzle wear out increases with time.
Rebar Diameter
Nozzle Bore Diameter
Sufficient water pressure keeps the rebar floating in the water channel
and do uniform circumferential cooling
Insufficient pressure built up could not hold the bar in place
and thus uniform circumferential cooling is not
possible
Cooling in Nozzles
Nozzle wear out
Conclusions
• Efficiency of water quenching decreases with time due to nozzle wear-out.
A dynamic fuzzy based ANN model with sufficient training can be developed for online prediction of product properties within a range of +-5 MPa.
Plant Recommendations :• Leakage minimization.• Identification of sample taken for tensile testing to
correctly map YS with corresponding FRT.• Bringing uniformity among operators in different shifts to
reduce data variation with time.
Thank You