scholarly journals Remaining Useful Life Estimation Using Deep Convolutional Generative Adversarial Networks Based on an Autoencoder Scheme

2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Guisheng Hou ◽  
Shuo Xu ◽  
Nan Zhou ◽  
Lei Yang ◽  
Quanhao Fu
Keyword(s):  
Feature Extraction ◽  
Short Term Memory ◽  
Health Management ◽  
Remaining Useful Life ◽  
Fine Tuning ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Useful Life ◽  
Prediction Approach

Accurate predictions of remaining useful life (RUL) of important components play a crucial role in system reliability, which is the basis of prognostics and health management (PHM). This paper proposed an integrated deep learning approach for RUL prediction of a turbofan engine by integrating an autoencoder (AE) with a deep convolutional generative adversarial network (DCGAN). In the pretraining stage, the reconstructed data of the AE not only participate in its error reconstruction but also take part in the DCGAN parameter training as the generated data of the DCGAN. Through double-error reconstructions, the capability of feature extraction is enhanced, and high-level abstract information is obtained. In the fine-tuning stage, a long short-term memory (LSTM) network is used to extract the sequential information from the features to predict the RUL. The effectiveness of the proposed scheme is verified on the NASA commercial modular aero-propulsion system simulation (C-MAPSS) dataset. The superiority of the proposed method is demonstrated via excellent prediction performance and comparisons with other existing state-of-the-art prognostics. The results of this study suggest that the proposed data-driven prognostic method offers a new and promising prediction approach and an efficient feature extraction scheme.

scholarly journals Remaining useful life prediction with insufficient degradation data based on deep learning approach

2021 ◽  
Vol 23 (4) ◽  
pp. 745-756
Author(s):  
Yi Lyu ◽  
Yijie Jiang ◽  
Qichen Zhang ◽  
Ci Chen
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Time Window ◽  
Synthetic Data ◽  
Remaining Useful Life ◽  
Generative Adversarial Network ◽  
Data Set ◽  
Adversarial Network ◽  
Degradation Data ◽  
Useful Life

Remaining useful life (RUL) prediction plays a crucial role in decision-making in conditionbased maintenance for preventing catastrophic field failure. For degradation-failed products, the data of performance deterioration process are the key for lifetime estimation. Deep learning has been proved to have excellent performance in RUL prediction given that the degradation data are sufficiently large. However, in some applications, the degradation data are insufficient, under which how to improve the prediction accuracy is yet a challenging problem. To tackle such a challenge, we propose a novel deep learning-based RUL prediction framework by amplifying the degradation dataset. Specifically, we leverage the cycle-consistent generative adversarial network to generate the synthetic data, based on which the original degradation dataset is amplified so that the data characteristics hidden in the sample space could be captured. Moreover, the sliding time window strategy and deep bidirectional long short-term memory network are employed to complete the RUL prediction framework. We show the effectiveness of the proposed method by running it on the turbine engine data set from the National Aeronautics and Space Administration. The comparative experiments show that our method outperforms a case without the use of the synthetically generated data.

scholarly journals Developing Deep Survival Model for Remaining Useful Life Estimation Based on Convolutional and Long Short-Term Memory Neural Networks

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Chia-Hua Chu ◽  
Chia-Jung Lee ◽  
Hsiang-Yuan Yeh
Keyword(s):  
Neural Networks ◽  
Short Term Memory ◽  
Survival Model ◽  
Remaining Useful Life ◽  
Superior Performance ◽  
Short Term ◽  
Term Memory ◽  
Useful Life ◽  
Long Short Term Memory ◽  
Prediction Approach

The application of mechanical equipment in manufacturing is becoming more and more complicated with technology development and adoption. In order to keep the high reliability and stability of the production line, reducing the downtime to repair and the frequency of routine maintenance is necessary. Since machine and components’ degradations are inevitable, accurately estimating the remaining useful life of them is crucial. We propose an integrated deep learning approach with convolutional neural networks and long short-term memory networks to learn the latent features and estimate remaining useful life value with deep survival model based on the discrete Weibull distribution. We conduct the turbofan engine degradation simulation dataset from Commercial Modular Aero-Propulsion System Simulation dataset provided by NASA to validate our approach. The improved results have proven that our proposed model can capture the degradation trend of a fault and has superior performance under complex conditions compared with existing state-of-the-art methods. Our study provides an efficient feature extraction scheme and offers a promising prediction approach to make better maintenance strategies.

Remaining Useful Life Predictions for Turbofan Engine Degradation Using Online Long Short-Term Memory Network

2019 ◽  
Author(s):  
Pallabi Kakati ◽  
Devendra Dandotiya ◽  
Bhaskar Pal
Keyword(s):  
Neural Network ◽  
Time Domain ◽  
Short Term Memory ◽  
Markov Models ◽  
Health Management ◽  
Remaining Useful Life ◽  
Short Term ◽  
Term Memory ◽  
Useful Life ◽  
Long Short Term Memory

Abstract In any industrial system, accurate prediction of Remaining Useful Life (RUL) is important for Prognostics and Health Management (PHM), so as to detect breakdown of system well in advance and take proper measures. Different methods are available in the literature that have been proposed for prediction of RUL. Among these methods, the data driven method is accepted to be the most reliable by many researchers, due to the use of real time sensor based vibrational and/or pressure data. These data are acquired in time domain. Methods such as Recurrent Neural Networks (RNNs), Convolutional Neural Network (CNN), Hidden Markov Models (HMMs) are generally applied in this area. Nevertheless, all these methods have issues while dealing with dependencies in these data. In this context, Long Short-Term Memory (LSTM) neural network has been proposed to deal with these dependencies while predicting RUL of any system. The LSTM model has the advantage of retaining time domain information for a long duration of time. However, with the arrival of new data, the model needs to be updated. In this regard, a new online method based on LSTM network is proposed in this paper. The use of online technique offers us to retrain the model as new data arrives, which helps in improving the accuracy of the estimated RUL. To illustrate the application of the proposed online LSTM method, we have used the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) turbofan dataset. The results show an improved efficiency compared to the previously proposed methods for RUL estimation.

scholarly journals Generative Adversarial Network-based Missing Data Handling and Remaining Useful Life Estimation for Smart Train Control and Monitoring Systems

2020 ◽  
Vol 2020 ◽  
pp. 1-15
Author(s):  
Hyunsoo Lee ◽  
Seok-Youn Han ◽  
Kee-Jun Park
Keyword(s):  
Missing Values ◽  
Remaining Useful Life ◽  
Current Status ◽  
Generative Adversarial Network ◽  
Train Control ◽  
Adversarial Network ◽  
Maintenance Systems ◽  
Useful Life ◽  
Control And Monitoring System ◽  
Railway Maintenance

As railway is considered one of the most significant transports, sudden malfunction of train components or delayed maintenance may considerably disrupt societal activities. To prevent this issue, various railway maintenance frameworks, from “periodic time-based and distance-based traditional maintenance frameworks” to “monitoring/conditional-based maintenance systems,” have been proposed and developed. However, these maintenance frameworks depend on the current status and situations of trains and cars. To overcome these issues, several predictive frameworks have been proposed. This study proposes a new and effective remaining useful life (RUL) estimation framework using big data from a train control and monitoring system (TCMS). TCMS data is classified into two types: operation data and alarm data. Alarm or RUL information is extracted from the alarm data. Subsequently, a deep learning model achieves the mapping relationship between operation data and the extracted RUL. However, a number of TCMS data have missing values due to malfunction of embedded sensors and/or low life of monitoring modules. This issue is addressed in the proposed generative adversarial network (GAN) framework. Both deep neural network (DNN) models for a generator and a predictor estimate missing values and predict train fault, simultaneously. To prove the effectiveness of the proposed GAN-based predictive maintenance framework, TCMS data-based case studies and comparisons with other methods were carried out.

scholarly journals Health Indicators Construction and Remaining Useful Life Estimation for Concrete Structures Using Deep Neural Networks

2021 ◽  
Vol 11 (9) ◽  
pp. 4113
Author(s):  
Viet Tra ◽  
Tuan-Khai Nguyen ◽  
Cheol-Hong Kim ◽  
Jong-Myon Kim
Keyword(s):  
Concrete Structure ◽  
Short Term Memory ◽  
Health Management ◽  
Health Indicators ◽  
Remaining Useful Life ◽  
Training Data ◽  
Statistical Parameters ◽  
Average Prediction Error ◽  
Degradation Data ◽  
Useful Life

Remaining useful life (RUL) prognosis is one of the most important techniques in concrete structure health management. This technique evaluates the concrete structure strength through determining the advent of failure, which is very helpful to reduce maintenance costs and extend structure life. Degradation information with the capability of reflecting structure health can be considered as a principal factor to achieve better prognosis performance. In traditional data-driven RUL prognosis, there are drawbacks in which features are manually extracted and threshold is defined to mark the specimen’s breakdown. To overcome these limitations, this paper presents an innovative SAE-DNN structure capable of automatic health indicator (HI) construction from raw signals. HI curves constructed by SAE-DNN have much better fitness metrics than HI curves constructed from statistical parameters such as RMS, Kurtosis, Sknewness, etc. In the next stage, HI curves constructed from training degradation data are then used to train a long short-term memory recurrent neural network (LSTM-RNN). The LSTM-RNN is utilized as a RUL predictor since its special gates allow it to learn long-term dependencies even when the training data is limited. Model construction, verification, and comparison are performed on experimental reinforced concrete (RC) beam data. Experimental results indicates that LSTM-RNN generally estimates more accurate RULs of concrete beams than GRU-RNN and simple RNN with the average prediction error cycles was less than half compared to those of the simple RNN.

scholarly journals Unsupervised Domain Adaptation for Facial Expression Recognition Using Generative Adversarial Networks

2018 ◽  
Vol 2018 ◽  
pp. 1-10 ◽  
Author(s):  
Xiaoqing Wang ◽  
Xiangjun Wang ◽  
Yubo Ni
Keyword(s):  
Facial Expression ◽  
Facial Expression Recognition ◽  
Domain Adaptation ◽  
Recognition Task ◽  
Fine Tuning ◽  
Generative Adversarial Networks ◽  
Expression Recognition ◽  
Generative Adversarial Network ◽  
Unsupervised Domain Adaptation ◽  
Adversarial Network

In the facial expression recognition task, a good-performing convolutional neural network (CNN) model trained on one dataset (source dataset) usually performs poorly on another dataset (target dataset). This is because the feature distribution of the same emotion varies in different datasets. To improve the cross-dataset accuracy of the CNN model, we introduce an unsupervised domain adaptation method, which is especially suitable for unlabelled small target dataset. In order to solve the problem of lack of samples from the target dataset, we train a generative adversarial network (GAN) on the target dataset and use the GAN generated samples to fine-tune the model pretrained on the source dataset. In the process of fine-tuning, we give the unlabelled GAN generated samples distributed pseudolabels dynamically according to the current prediction probabilities. Our method can be easily applied to any existing convolutional neural networks (CNN). We demonstrate the effectiveness of our method on four facial expression recognition datasets with two CNN structures and obtain inspiring results.

scholarly journals Realistic Handwriting Generation using Generative Adversarial Networks (Rnn)

2020 ◽  
Vol 9 (1) ◽  
pp. 2049-2052
Keyword(s):  
Short Term Memory ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Cursive Handwriting ◽  
Long Short Term Memory ◽  
High Level ◽  
Online Handwriting ◽  
Handwriting Generation

Generating handwritings of different kinds is quite a challenging task, an area in which not much work has been done yet. Though there has been substantial research done in the area of text recognition, the opposite of handwriting generation. Handwriting generation can prove to be extremely useful for children from blind schools where their speech can get converted into text and be used to generate handwritings of different kinds for them. Handwriting generation also has an important role in field of captcha generation. Our study exhibits in what way recurrent neural networks (RNN) of the type Long Short Term Memory (LSTM) could be used in order to create a composite sequence with structure covering a long range. We propose to use that the Generative Adversarial Network algorithm can be used to generate more realistic handwriting styles with better accuracy than other algorithms. Here, we will be trying to predict one point of data at a time. Our approach is shownfor text, where the type of data is discrete. It can also be used for online handwriting, that is real-valued data. It will then be further drawn out to handwriting generation. The created network will be conditioning its predictions based on a sequence of text. We will be using the resulting system to generate highly realistic cursive handwriting in a wide variety of styles. Experiments that have been carried out on online handwriting databases that are public predict that the method that has been proposed can be used to achieve satisfactory performance, the resultant writing samples achieved a high level of similarity with original samples of handwriting.

Sign in / Sign up

Export Citation Format

Share Document