scholarly journals Transfer Learning with Deep Recurrent Neural Networks for Remaining Useful Life Estimation

2018 ◽  
Vol 8 (12) ◽  
pp. 2416 ◽  
Author(s):  
Ansi Zhang ◽  
Honglei Wang ◽  
Shaobo Li ◽  
Yuxin Cui ◽  
Zhonghao Liu ◽  
...  
Keyword(s):  
Neural Networks ◽  
Transfer Learning ◽  
Recurrent Neural Networks ◽  
Prediction Models ◽  
Learning Algorithm ◽  
Remaining Useful Life ◽  
Operating Conditions ◽  
Training Data ◽  
Good Prediction ◽  
Useful Life

Prognostics, such as remaining useful life (RUL) prediction, is a crucial task in condition-based maintenance. A major challenge in data-driven prognostics is the difficulty of obtaining a sufficient number of samples of failure progression. However, for traditional machine learning methods and deep neural networks, enough training data is a prerequisite to train good prediction models. In this work, we proposed a transfer learning algorithm based on Bi-directional Long Short-Term Memory (BLSTM) recurrent neural networks for RUL estimation, in which the models can be first trained on different but related datasets and then fine-tuned by the target dataset. Extensive experimental results show that transfer learning can in general improve the prediction models on the dataset with a small number of samples. There is one exception that when transferring from multi-type operating conditions to single operating conditions, transfer learning led to a worse result.

scholarly journals An Autoencoder Gated Recurrent Unit for Remaining Useful Life Prediction

Processes ◽  
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.

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

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).

scholarly journals Penerapan Metode K-Nearest Neighbors (kNN) pada Bearing

2021 ◽  
Vol 1 (1) ◽  
pp. 10-18
Author(s):  
Anggi Priliani Yulianto ◽  
Sutawanir Darwis
Keyword(s):  
Machine Learning ◽  
Nearest Neighbor ◽  
Learning Algorithm ◽  
Real Data ◽  
Remaining Useful Life ◽  
Operating Conditions ◽  
Training Data ◽  
K Nearest Neighbor ◽  
K Nearest Neighbors ◽  
K Value

Abstract. Monitoring the condition of the engine is a top priority to avoid damage. To know the condition of the bearing, it is important to know the remaining useful life of the machine. In the IEEE PHM 2012 Prognostic Challenge platform provides real data related to accelerated bearing degradation carried out under constant operating conditions and online controlled variables of temperature and vibration (with horizontal and vertical accelerometers). In this platform, the data used is bearing2_3 data in the horizontal direction which has a duration of about 2 hours, calculated RMS every 1/10 second (2560 data). In this study machine learning based modeling will be done using the k-nearest neighbor (kNN) method to determine the prediction of RMS bearings. The kNN method is based on the classification of objects based on training data that is the closest distance to the object. kNN is a nonparametric machine learning algorithm which is a model that does not assume distribution. The advantage is that the class decision line produced by the model can be very flexible and very nonlinear. The smallest MSE value was obtained at k = 16 with MSE value = 0.157579. After getting the optimum k value, proceed with predicting a RMS of 97 lags and identifying bearing performance in several phases. Abstrak. Pemantauan kondisi mesin menjadi prioritas utama untuk menghindari adanya kerusakan. Untuk mengetahui kondisi bantalan, penting untuk mengetahui sisa masa manfaat dari mesin tersebut. Dalam platfrom IEEE PHM 2012 Prognostic Challenge ini menyediakan data nyata terkait dengan degradasi bantalan yang dipercepat yang dilakukan di bawah kondisi operasi konstan dan variabel yang dikendalikan secara online berupa suhu dan getaran (dengan akselerometer horizontal dan vertikal). Dalam platform ini, data yang digunakan adalah data bearing2_3 pada arah horizontal yang berdurasi sekitar 2 jam ini dihitung RMS setiap 1/10 detik (2560 data). Dalam penelitian ini akan dilakukan pemodelan berbasis machine learning menggunakan metode k-nearest neighbor (kNN) untuk mengetahui prediksi RMS bearing. Metode kNN didasarkan pada klasifikasi terhadap objek berdasarkan data pelatihan yang jaraknya paling dekat dengan objek tersebut. kNN merupakan salah satu algoritma pembelajaran mesin yang bersifat nonparametrik yakni model yang tidak mengasumsikan distribusi. Kelebihannya adalah garis keputusan kelas yang dihasilkan model tersebut bisa jadi sangat fleksibel dan sangat nonlinier. Nilai MSE terkecil diperoleh pada k = 16 dengan nilai MSE = 0,157579. Setelah mendapatkan nilai k optimum, dilanjutkan dengan memprediksi RMS sebanyak 97-lag serta mengidentifikasi performance kinerja bearing dalam beberapa fase.

scholarly journals Predicting Remaining Useful Life using Time Series Embeddings based on Recurrent Neural Networks

2020 ◽  
Vol 9 (1) ◽  
Author(s):  
Narendhar Gugulothu ◽  
Vishnu TV ◽  
Pankaj Malhotra ◽  
Lovekesh Vig ◽  
Puneet Agarwal ◽  
...  
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Recurrent Neural Networks ◽  
Missing Values ◽  
Multivariate Time Series ◽  
Remaining Useful Life ◽  
Sensor Data ◽  
Novel Approach ◽  
Useful Life ◽  
Robust To Noise

We consider the problem of estimating the remaining useful life (RUL) of a system or a machine from sensor data. Many approaches for RUL estimation based on sensor data make assumptions about how machines degrade. Additionally, sensor data from machines is noisy and often suffers from missing values in many practical settings. We propose Embed-RUL: a novel approach for RUL estimation from sensor data that does not rely on any degradation-trend assumptions, is robust to noise, and handles missing values. Embed-RUL utilizes a sequence-to-sequence model based on Recurrent Neural Networks (RNNs) to generate embeddings for multivariate time series subsequences. The embeddings for normal and degraded machines tend to be different, and are therefore found to be useful for RUL estimation. We show that the embeddings capture the overall pattern in the time series while filtering out the noise, so that the embeddings of two machines with similar operational behavior are close to each other, even when their sensor readings have significant and varying levels of noise content. We perform experiments on publicly available turbofan engine dataset and a proprietary real-world dataset, and demonstrate that Embed-RUL outperforms the previously reported state-of-the-art (Malhotra, TV, et al., 2016) on several metrics.

Sign in / Sign up

Export Citation Format

Share Document