Improved adaptive war strategy optimization algorithm assisted-adaptive multi-head graph attention mechanism network for remaining useful life of complex equipment

Abstract

The remaining useful life (RUL) of complex equipment is an important criterion to ensure stable operation. In recent years, deep learning-based methods for predicting the RUL of complex equipment have attracted wide attention. However, it is only able to obtain the potential information in the Euclidean space, which hinders their ability to capture the deeply degradation information. Thus, graph neural networks have gradually entered the researchers’ field of vision. Despite the fact that graph neural networks are able to accomplish the task of RUL for complex equipment, there are still limitations that restrict the prediction performance in practical engineering. To address this challenge, an improved adaptive war strategy optimization algorithm assisted-adaptive multi-head graph attention mechanism network (IWSO-LMGAT) is proposed. For one thing, a learnable attention mechanism is proposed to adjust the weights of different heads dynamical and improve the limitation of GAT in obtaining deep degradation information. In addition, since hyperparameters are essential elements affecting the predicted result, inspired by the “no-free lunch” principle, an improved mathematical expression is described to avoid the issue such as precocity, fall into local optimums for WSO so that the optimal hyperparameters of the LMGAT could be obtained. The effectiveness and advancement of IWSO-LMGAT are validated on the CMAPSS dataset, and experimental results show that the proposed method could provide competitive forecasted results compared to traditional methods, that is, R2 = 0.9939, RMSE = 4.3638, and MAPE = 0.0137; this illustrates the IWSO-LMGAT’s potential for the RUL prediction of complex equipment.