Generative Adversarial Network-based Missing Data Handling and Remaining Useful Life Estimation for Smart Train Control and Monitoring Systems

Table 9

Test accuracy for each RUL estimation method (case for fault code ID 31).

RUL prediction method	GAN-based RUL estimation (the proposed method)	ARIMA-based RUL estimation (%)	RUL estimation using “missing value pruning” (%)	RUL estimation using “mean-value estimation” of missing values (%)
Test accuracy	83.5%	56.7	69.7	76.3