Professional Documents
Culture Documents
Lecture 7
Lecture 7
CHE F315
Recap
Feature extraction
Principal component analysis
Applications
Procedure
Algorithm
3 February 2024 4
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers
3 February 2024 5
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers
Example
s(i) x1 x2
s(1) 0.69 0.49
s(2) –1.31 –1.21
s(3) 0.39 0.99
s(4) 0.09 0.29
s(5) 1.29 1.09
s(6) 0.49 0.79
s(7) 0.19 –0.31
s(8) –0.81 –0.81
s(9) –0.31 –0.31
s(10) -0.71 -1.01
3 February 2024 6
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers
Example
3 February 2024 7
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers
Example
covx =
0.6166 0.6154
0.6154 0.7166
>> [eigv,eigv1]=eig(covx)
eigv =
-0.7352 0.6779
0.6779 0.7352
eigv1 =
0.0491 0
0 1.2840
3 February 2024 8
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers
Example
s(i) x1 x2
s(1) 0.69 0.49 0.107503 0.839459
s(2) –1.31 –1.21
0.001543 -1.78337
s(3) 0.39 0.99 -0.46347 0.957849
s(4) 0.09 0.29 -0.1522 0.262759
0.073123 1.687319
s(5) 1.29 1.09
-0.24864 0.895789
s(6) 0.49 0.79
0.356713 -0.07046
s(7) 0.19 –0.31
s(8) –0.81 –0.81 0.046413 -1.14461
s(9) –0.31 –0.31 0.017763 -0.43806
s(10) -0.71 -1.01 0.261243 -1.20667
3 February 2024 10
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers
Example
3 February 2024 11
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers
Example
3 February 2024 12
BITS Pilani, Pilani Campus
Case Study
(Coal Fired Thermal Power Plant)
Inputs Outputs
Steam Flow (TPH) CO
Feed Water Flow
SA Flow
PA Flow
Furnace Temp
Flue Gas Temp (APH Outlet)
IDF Current
SAF Current
Steam Temp
Steam Pr
Case Study
(Coal Fired Thermal Power Plant)
Case Study
(Coal Fired Thermal Power Plant)
[m,n] = size(X);
average = mean(X);
stdv = std(X)
for j = 1:n
for i = 1:m
Xscaled(i,j) = (X(i,j) - average(j))/stdv(j);
end
end
covx = (Xscaled'*Xscaled)/(m-1);
Case Study
(Coal Fired Thermal Power Plant)
[evect,eval]=eig(covx);
eval = diag(eval);
[eval1,index] = sort(eval,'descend');
plot(eval1);
evect1 = evect(:,8:10);
modX = Xscaled*evect1;
3 February 2024 16
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers
More datasets
https://data.mendeley.com/
3 February 2024 17
BITS Pilani, Pilani Campus
CHE F315 Machine Learning for Chemical Engineers
3 February 2024
18 BITS Pilani, Pilani Campus