Research Article
Generative Adversarial Network-based Missing Data Handling and Remaining Useful Life Estimation for Smart Train Control and Monitoring Systems
Table 5
General learning algorithm of GAN.
| | Input/parameters | (i) Training data: X
(ii) Learning epoch: k1/· Training epoch: k2
(iii) Step length:
(iv) Mini-batch size: m |
| | Output | (v) Optimal parameters for G:
(vi) Optimal parameters for D: |
| Learning
algorithm | for 1:k1
Initialize ,
for 1:k2
mini-batch partitioning from X,
calculate gradient for D and update
Generate random vector,
Calculate gradient for G and update
end
end |
|
|
