International Journal of Aerospace Engineering / 2018 / Article / Tab 12

Research Article

Aircraft Gas Turbine Engine Health Monitoring System by Real Flight Data

Table 12

Comparison of the feedforward neural network training algorithms for their test MSE value.

Training algorithmElapsed time (sec)Training RValidation RTest RTraining MSETest MSE

trainlm4.2039570.997670.997970.9971962.850174.6465
traincgb4.5658350.995860.992990.99656111.493291.2834
trains10.0476080.995610.995170.99653118.407191.8717
trainrp57.1181790.994580.992970.9963146.126397.9763
traincgp3.6994020.994010.995150.99501161.8084133.9647
trainscg3.4589040.993810.990840.99474166.9843139.1074
trainbfg13.7483630.992130.991760.99394211.9474160.1871
traincgf7.6679960.991790.991760.99395222.3323164.4613
trainoss4.4326610.990530.991970.99183255.8224215.3883
traingdx3.6148690.988380.988930.9893312.1862285.3237
traingda4.0083020.983120.984180.98733459.2168342.6505