EGT Baseline Model of Aeroengine Based on Kernel Principal Component Analysis and Deep Belief Network

Establishing an Exhaust Gas Temperature (EGT) baseline model is an important way to realize the overall performance real time monitoring and health management of an aeroengine. An EGT baseline model of aeroengine was constructed by combining Kernel Principal Component Analysis (KPCA) with Deep Belief Network (DBN). The Quick Access Recorder (QAR) data of the airplane with CFMS6-7B aeroengine was taken as the original data sample. The data dimensions were first reduced using KCPA, where Gaussian function was selected as Kernel function. The dimensionality-reduced data was put into DBN to establish the EGT baseline model. The validity and superiority of the model were verified by a large number of QAR data. Compared with traditional neural network modeling techniques, the proposed method not only reduces the complexity of the network structure, but also improves the accuracy of the model.