A novel bootstrap ensemble learning convolutional simple recurrent unit method for remaining useful life interval prediction of turbofan engines

Abstract

The deep neural network is widely applied in remaining useful life prediction because of its strong feature extraction ability. However, the prediction results of deep learning neural networks are often influenced by random noise and modeling parameters. Besides, the training process of the traditional neural network is time-consuming. In order to overcome these drawbacks, a novel bootstrap ensemble learning convolutional simple recurrent unit method is proposed for remaining useful life prediction. The simple recurrent unit is used to learn the time-series features of sensor data, which can effectively reduce the model parameters and boost the calculation speed. Moreover, the remaining useful life prediction uncertainty can be quantified with the prediction interval, which can be calculated by the ensemble learning convolutional simple recurrent unit model. The prediction performance of the ensemble learning convolutional simple recurrent unit model is demonstrated with the turbofan engine dataset. The experimental results show that the proposed ensemble learning convolutional simple recurrent unit model provides a prognosis framework with better prediction performance for quantifying RUL prediction uncertainty.

A hybrid remaining useful life prediction method for lithium-ion batteries based on transfer learning with CDRSN-BiGRU-AM

“…With the advantages such as long cycle life, high energy density, low pollution and recyclability, lithium-ion batteries (LIBs) are extensively used in electric vehicles, electric energy storage systems and other applications [1][2][3]. The life of a LIB is a determinant of the reliability of its operation.…”

“…It is not possible to obtain an accurate prediction in a short time. (2) The literature [23][24][25] To address these issues, a hybrid method for achieving accurate prediction of RUL for LIBs in a short time has been proposed. Firstly, the channel-wise deep residual shrinkage network (CDRSN) is used to automatically extract effective features from the original features, thus lowering the prediction cost and bias in the criteria of feature selection methods caused by manual feature extraction.…”

A deep learning based health indicator construction and fault prognosis with uncertainty quantification for rolling bearings

“…Meanwhile, resampling from the raw signal is the essential step of the bootstrap method [28]. Zhao et al [29] introduced a framework on the basis of bootstrap method to accomplish the interval prediction of turbofan engines. Huang et al [30] utilized a deep convolutional neural network (CNN) with the bootstrap method to realize the fault prognosis, and the validation was based on the rolling bearings.…”

A CNN‐BiLSTM‐Bootstrap integrated method for remaining useful life prediction of rolling bearings

“…Based on the integrated prediction method of bootstrap, Huang 35 embedded the network into the bootstrap framework and realized the quantification of RUL PI. Zhao 36 proposed a novel bootstrap ensemble learning convolutional simple recurrent unit method for RUL prediction. A single network model cannot achieve outstanding results between data feature extraction and information relevance.…”