A Novel Remaining Useful Life Prediction Method for Hydrogen Fuel Cells Based on the Gated Recurrent Unit Neural Network

The remaining useful life (RUL) prediction for hydrogen fuel cells is an important part of its prognostics and health management (PHM). Artificial neural networks (ANNs) are proven to be very effective in RUL prediction, as they do not need to understand the failure mechanisms behind hydrogen fuel cells. A novel RUL prediction method for hydrogen fuel cells based on the gated recurrent unit ANN is proposed in this paper. Firstly, the data were preprocessed to remove outliers and noises. Secondly, the performance of different neural networks is compared, including the back propagation neural network (BPNN), the long short-term memory (LSTM) network and the gated recurrent unit (GRU) network. According to our proposed method based on GRU, the root mean square error was 0.0026, the mean absolute percentage error was 0.0038 and the coefficient of determination was 0.9891 for the data from the challenge datasets provided by FCLAB Research Federation, when the prediction starting point was 650 h. Compared with the other RUL prediction methods based on the BPNN and the LSTM, our prediction method is better in both prediction accuracy and convergence rate.

Download Full-text

An Autoencoder Gated Recurrent Unit for Remaining Useful Life Prediction

Processes ◽

10.3390/pr8091155 ◽

2020 ◽

Vol 8 (9) ◽

pp. 1155

Author(s):

Yi-Wei Lu ◽

Chia-Yu Hsu ◽

Kuang-Chieh Huang

Keyword(s):

Neural Networks ◽

Recurrent Neural Networks ◽

Short Term Memory ◽

Development Trend ◽

Production Equipment ◽

Remaining Useful Life ◽

Sensor Data ◽

Smart Manufacturing ◽

Useful Life ◽

Gated Recurrent Unit

With the development of smart manufacturing, in order to detect abnormal conditions of the equipment, a large number of sensors have been used to record the variables associated with production equipment. This study focuses on the prediction of Remaining Useful Life (RUL). RUL prediction is part of predictive maintenance, which uses the development trend of the machine to predict when the machine will malfunction. High accuracy of RUL prediction not only reduces the consumption of manpower and materials, but also reduces the need for future maintenance. This study focuses on detecting faults as early as possible, before the machine needs to be replaced or repaired, to ensure the reliability of the system. It is difficult to extract meaningful features from sensor data directly. This study proposes a model based on an Autoencoder Gated Recurrent Unit (AE-GRU), in which the Autoencoder (AE) extracts the important features from the raw data and the Gated Recurrent Unit (GRU) selects the information from the sequences to forecast RUL. To evaluate the performance of the proposed AE-GRU model, an aircraft turbofan engine degradation simulation dataset provided by NASA was used and a comparison made of different recurrent neural networks. The results demonstrate that the AE-GRU is better than other recurrent neural networks, such as Long Short-Term Memory (LSTM) and GRU.

Download Full-text

A remaining useful life prediction method for bearing based on deep neural networks

Measurement ◽

10.1016/j.measurement.2020.108878 ◽

2021 ◽

Vol 172 ◽

pp. 108878

Author(s):

Hua Ding ◽

Liangliang Yang ◽

Zeyin Cheng ◽

Zhaojian Yang

Keyword(s):

Neural Networks ◽

Life Prediction ◽

Deep Neural Networks ◽

Prediction Method ◽

Remaining Useful Life ◽

Useful Life

Download Full-text

Remaining Useful Life Prediction from 3D Scan Data with Genetically Optimized Convolutional Neural Networks

10.20944/preprints202108.0272.v1 ◽

2021 ◽

Author(s):

Giovanni Diraco ◽

Pietro Siciliano ◽

Alessandro Leone

Keyword(s):

Neural Network ◽

Neural Networks ◽

Support Vector Regression ◽

Transfer Learning ◽

Convolutional Neural Networks ◽

Life Prediction ◽

Point Clouds ◽

Remaining Useful Life ◽

Support Vector ◽

Useful Life

In the current industrial landscape, increasingly pervaded by technological innovations, the adoption of optimized strategies for asset management is becoming a critical key success factor. Among the various strategies available, the “Prognostics and Health Management” strategy is able to support maintenance management decisions more accurately, through continuous monitoring of equipment health and “Remaining Useful Life” forecasting. In the present study, Convolutional Neural Network-based Deep Neural Network techniques are investigated for the Remaining Useful Life prediction of a punch tool, whose degradation is caused by working surface deformations during the machining process. Surface deformation is determined using a 3D scanning sensor capable of returning point clouds with micrometric accuracy during the operation of the punching machine, avoiding both downtime and human intervention. The 3D point clouds thus obtained are transformed into bidimensional image-type maps, i.e., maps of depths and normal vectors, to fully exploit the potential of convolutional neural networks for extracting features. Such maps are then processed by comparing 15 genetically optimized architectures with the transfer learning of 19 pre-trained models, using a classic machine learning approach, i.e., Support Vector Regression, as a benchmark. The achieved results clearly show that, in this specific case, optimized architectures provide performance far superior (MAPE=0.058) to that of transfer learning which, instead, remains at a lower or slightly higher level (MAPE=0.416) than Support Vector Regression (MAPE=0.857).

Download Full-text

Gated recurrent unit based recurrent neural network for remaining useful life prediction of nonlinear deterioration process

Reliability Engineering & System Safety ◽

10.1016/j.ress.2019.01.006 ◽

2019 ◽

Vol 185 ◽

pp. 372-382 ◽

Cited By ~ 41

Author(s):

Jinglong Chen ◽

Hongjie Jing ◽

Yuanhong Chang ◽

Qian Liu

Keyword(s):

Neural Network ◽

Recurrent Neural Network ◽

Life Prediction ◽

Remaining Useful Life ◽

Deterioration Process ◽

Useful Life ◽

Gated Recurrent Unit

Download Full-text

Remaining Useful Life Prediction from 3D Scan Data with Genetically Optimized Convolutional Neural Networks

Sensors ◽

10.3390/s21206772 ◽

2021 ◽

Vol 21 (20) ◽

pp. 6772

Author(s):

Giovanni Diraco ◽

Pietro Siciliano ◽

Alessandro Leone

Keyword(s):

Neural Network ◽

Neural Networks ◽

Support Vector Regression ◽

Transfer Learning ◽

Convolutional Neural Networks ◽

Life Prediction ◽

Point Clouds ◽

Remaining Useful Life ◽

Support Vector ◽

Useful Life

In the current industrial landscape, increasingly pervaded by technological innovations, the adoption of optimized strategies for asset management is becoming a critical key success factor. Among the various strategies available, the “Prognostics and Health Management” strategy is able to support maintenance management decisions more accurately, through continuous monitoring of equipment health and “Remaining Useful Life” forecasting. In the present study, convolutional neural network-based deep neural network techniques are investigated for the remaining useful life prediction of a punch tool, whose degradation is caused by working surface deformations during the machining process. Surface deformation is determined using a 3D scanning sensor capable of returning point clouds with micrometric accuracy during the operation of the punching machine, avoiding both downtime and human intervention. The 3D point clouds thus obtained are transformed into bidimensional image-type maps, i.e., maps of depths and normal vectors, to fully exploit the potential of convolutional neural networks for extracting features. Such maps are then processed by comparing 15 genetically optimized architectures with the transfer learning of 19 pretrained models, using a classic machine learning approach, i.e., support vector regression, as a benchmark. The achieved results clearly show that, in this specific case, optimized architectures provide performance far superior (MAPE = 0.058) to that of transfer learning, which, instead, remains at a lower or slightly higher level (MAPE = 0.416) than support vector regression (MAPE = 0.857).

Download Full-text