Enhanced Online Sequential Parallel Extreme Learning Machine and its Application in Remaining Useful Life Prediction of Integrated Modular Avionics

Abstract

Integrated modular avionics is one of the most advanced systems which has been widely applied in modern aircraft. The performance of integrated modular avionics deeply impacts flight mission. Remaining useful life prediction is the critical manner which can efficiently improve the safety and reliability of aircraft. Since integrated modular avionics is a real-time system, the prediction algorithm should have fast learning speed to satisfy the real-time requirement. In this paper, an enhanced online sequential method is proposed to predict the remaining useful life of integrated modular avionics. Firstly, this paper proposes an online sequential network which is based on the architecture of parallel layer network. Secondly, to enhance the learning capability, this paper adopts the extreme learning machine denosing autoencoder to determine the input weights of the network. Thirdly, an adaptive forgetting factor is added to further improve the performance of the proposed method. The effectiveness and the superiority of the proposed method are verified in comparison with three online sequential algorithms on the standard datasets. Finally, a degradation model is built to depict the deteriorated process of integrated modular avionics. The prediction results confirms that the proposed method can effectively address remaining useful life of integrated modular avionics.

Keywords

• Integrated modular avionics
• parallel layer network
• remaining useful life
• degradation model