Turbofan engine remaining service life prediction method based on improved stacked sparse auto-encoder and attention echo state network

Abstract

An engine remaining service life prediction method based on an improved stacked sparse auto-encoder (SSAE) and an attention echo state network (Attention-ESN) comprises the following steps: firstly, removing original noise by using a 3sigma criterion to obtain high-quality original data and realize data reconstruction, extracting features of each cycle of an engine by using the improved SSAE, and performing feature dimension reduction; adopting a BN layer and a Dropout layer in an encoder to solve the problems of gradient disappearance and overfitting, creating extracted engine features into an HI value to acquire an HI curve representing the degradation trend of an engine, finally introducing an attention mechanism into an ESN network, processing different types of features in a self-adaptive mode, optimizing network parameters and finally acquiring an RUL value. And the residual service life prediction of the turbofan engine is realized. The residual service life is predicted by adopting a combined model of feature extraction and a network prediction structure, and the prediction precision is improved. The abstract drawing is as shown in figure 1.

Description

technical field [0001] The invention belongs to the technical field of remaining service life prediction of mechanical equipment, and in particular relates to a turbofan engine remaining service life prediction method based on an improved stacked sparse autoencoder and attention echo state network. Background technique [0002] The turbofan engine is the core of the aircraft. The health status analysis of the turbofan engine is very important for the assessment, safe use and maintenance strategy of the aircraft. The remaining useful life (RUL) is a measure of the health status of the turbofan engine. Accurately predicting the remaining service life can not only avoid safety accidents caused by untimely maintenance, but also reduce expensive costs caused by excessive maintenance. Due to the large number of measurement points, complex working conditions, and large amount of data, the prediction of the remaining service life of the turbofan engine faces great challenges in feat...

AI Technical Summary

Problems solved by technology

However, the degradation process of turbofan engines and other equipment is usually collected by multiple sensors. The data volume of such sensor data is huge and the effective information is difficult to extract. Therefore, how to design a combined structure composed of different models and which feature extraction method to use Extracting effective features, constructing the degradation trend of the engine, and for the constructed feature trend, which network to use for RUL prediction and balancing the internal relationship between the models, optimizing the function of the model and reducing the time complexity are the challenges faced by this method. challenge

Images