A knowledge-driven method for IGBT remaining useful life prediction using bidirectional learning and physics-enhanced pathformer networks

Remaining useful life prediction for multi-sensor systems using a novel end-to-end deep-learning method

Probabilistic remaining useful life prediction without lifetime labels: A Bayesian deep learning and stochastic process fusion method

Due to the strict requirements of satellite systems, accurate remaining useful life (RUL) prediction of the key components is very important to the reliability and security of satellite systems. Otherwise, a failure could lead to catastrophic consequences and enormous economic losses. Because of the complex structure of the satellite and its complex space environment, the factors that affect the satellite systems status are numerous. Moreover, as a result of the healthy historical data of key components in satellite are too few, which makes the traditional methods based on analysis model are not suitable for RUL prediction of key components in satellite. In this paper, in order to solve the RUL prediction problem of Lithium-ion batteries (LIBs) in satellite with incomplete healthy historical data, we propose an efficient RUL prediction method for key components of satellite, which is called Residual Remaining Useful Life Prediction Method (RRULPM), based on the study of Multivariate State Estimation Technique (MSET). The RRULPM is make up of degradation model based on MSET state estimation and criteria of failure based on historical degradation value, which is developed by improving MSET and combining the residuals with life cycle damage (LCD) prediction creatively when lacking healthy historical data. Experimental results demonstrate that the RRULPM is excellent to achieve the RUL prediction problems of LIBs through the actual in orbit telemetry data. Unlike previous RUL prediction methods, RRULPM provides good feasibility and effectiveness. This research can serve as guidance for prognostics and health management (PHM) of key components in satellite.

Predicting accurate remaining useful life (RUL) is quite necessary in many industrial cases. Recently, data-driven method has been widely used for RUL prediction because of its promising performance and ease of use. However, one practical challenging issue of the data-driven method is lack of labeled data. One way for dealing with this issue is domain adaptation. With domain adaptation technique, a RUL prediction model is built using labeled data of source domain and then the trained model is used to predict RUL of target domain where labeled data is unavailable. In this paper, we propose our method for RUL prediction through domain adaptation. Another practical issue of RUL prediction is that a single RUL prediction value may not be enough for successful maintenance of target systems. In other words, we need to know how uncertain RUL prediction is. In this paper, we study Monte Carlo (MC) dropout-based uncertainty metric for realizing better RUL prediction result. Through experiment, we first show that our domain adaptation technique shows reasonable performance. We also show that MC dropout-based approach generates the uncertainty metric only meaningful for source domain.

Organic electrochemical transistors (OECTs) show abundant potential in biosensors, artificial neuromorphic systems, brain-machine interfaces, etc With the fast development of novel functional materials and new device structures, OECTs with high transconductance (gm > mS) and good cycling stabilities (> 10,000 cycles) have been developed. While stability characterization is always time-consuming, to accelerate the development and commercialization of OECTs, tools for stability prediction are urgently needed. In this paper, OECTs with good cycling stabilities are realized by minimizing the gate voltage amplitude during cycling, while a remaining useful life (RUL) prediction framework for OECTs is proposed. Specifically, OECTs based on p(g2T-T) show tremendously enhanced stability which exhibits only 46.1% on-current (ION) and 33.2% peak gm decreases after 80,000 cycles (53 min). Then, RUL prediction is proposed based on the run-to-failure (RtF) aging tests (cycling stability test of OECTs). By selecting two aging parameters (ION and peak gm) as health indicators (HI), a novel multi-scale feature fusion (MFF) method for RUL prediction is proposed, which consists of a long short-term memory (LSTM) neural network based multi-scale feature generator (MFG) module for feature extraction and an attention-based feature fusion (AFF) module for feature fusion. Consequently, richer effective information is utilized to improve the prediction performance, where the experimental results show the superiority of the proposed framework on multiple OECTs in RUL prediction tasks. Therefore, by introducing such a powerful framework for the evaluation of the lifetime of OECTs, further optimization of materials, devices, and integrated systems relevant to OECTs will be stimulated. Moreover, this tool can also be extended to other relevant bioelectronics.

Remaining useful life (RUL) prediction is crucial in the field of engineering, which can reduce the frequency of accidents and the maintenance cost of machinery. With the increasing complexity of rotating machinery, the data analysis methods based on deep learning have become the mainstream methods of prediction work. However, most of the current RUL prediction methods only use single-sensor data as input, which cannot effectively use multi-sensor data. In addition, as an advanced deep learning prediction method, temporal convolutional network (TCN) only uses the past time information of vibration data to determine the current health status of bearings, while ignoring the importance of future time information of vibration data. To solve the above problems, a bearing RUL prediction method based on multi-sensor data fusion and bidirectional-temporal attention convolutional network (Bi-TACN) is proposed in this paper. In multi-sensor data fusion, multi-sensor data are combined into multi-channel data, and a channel-weighted attention is designed to emphasize the importance of each sensor data. Compared with traditional multi-sensor data fusion, the proposed fusion method allows deep prediction networks to learn more useful feature information from multi-sensor data. Then, Bi-TACN is developed to predict the RUL of bearings. Bi-TACN is mainly composed of the forward TCN block and the backward TCN block, both of which can learn the past and future time information of multi-sensor data simultaneously. Moreover, a temporal attention mechanism is embedded in Bi-TACN to adaptively calibrate the weights of the two TCN blocks, so as to achieve dynamic feature fusion of past and future time information. RUL prediction experiments are carried out through Xi’an Jiao tong University bearing dataset and PHM 2012 bearing dataset respectively. Compared with the advanced prediction methods, the proposed method can accurately predict the RUL of more types of bearings and has low prediction errors.

The remaining useful life (RUL) prediction plays an increasingly important role in predictive maintenance. With the development of big data and the Internet‐of‐Things (IoT), deep learning (DL) techniques have been widely adopted for RUL prediction. Addressing the limitation of the current methods for data under multiple operating conditions, this paper proposes a three‐stage feature selection approach for DL‐based RUL prediction models. The k‐medoids cluster is initially used to sort raw data based on different operating conditions. In the first stage of feature selection, an operational‐based normalisation approach is applied to reconstruct the data. Afterwards, Spearman's rank and pair‐wise Pearson correlation coefficients are used to eliminate irrelevant and redundant features in the second and third stages, respectively. A case study using NASA's Commercial Modular Aero‐Propulsion System Simulation (C‐MAPSS) dataset is presented to quantitatively evaluate the influence of the proposed feature selection method using the Recurrent Neural Network (RNN) and its’ variants, enhanced by an optimised activation function and optimiser. The results confirm that the proposed method can improve the stability of DL models and achieve about a 7.3% average improvement in the RUL prediction for popular and state‐of‐the‐art DL models.

Aiming at the difficulty of mining fault prognosis starting points and constructing prognostic models for remaining useful life (RUL) prediction of rolling bearings, a RUL prediction method is proposed based on health indicator (HI) extraction and trajectory-enhanced particle filter (TE-PF). By extracting a HI that can accurately track the trending of bearing degradation and combining it with the early fault enhancement technology, early abnormal sample nodes can be mined to provide more samples with fault information for the construction and training of subsequent prediction models. Aiming at the problem that traditional degradation rate models based on PF are vulnerable to HI mutations, a TE-PF prediction method is proposed based on comprehensive utilization of historical degradation information to timely modify prediction model parameters. Results from a rolling bearing prognostic study show that prediction starting points can be accurately detected and a reasonable prediction model can be conveniently constructed by the RUL prediction method based on HI amplitude abnormal detection and TE-PF. Furthermore, aiming at the RUL prediction problem under the condition of HI mutation, RUL prediction with probability and statistics characteristics under a confidence interval can be obtained based on the method proposed.

Remaining useful life (RUL) prediction is one of the main tasks of prognostics and health management (PHM). This paper proposes a novel method for RUL prediction, Attention_mechanism and Skip_connection are introduced into bidirectional long short-term memory autoencoder (BiLSTM-AS). In the previous RUL prediction scheme based on BiRNN autoencoder, during the encoding process, in the process of embedding vector generation, the multi-dimensional sensor data of each timestep contributes equally, the embedding vector is only used in the first step of decoding. To overcome the above shortcomings, the BiLSTM-AS model is proposed. This model introduces attention mechanism based on the BiLSTM autoencoder, assigns weights to each timestep information and highlights the key timestep information contribution; to relieve the decoding burden of embedding vector, skip connection is introduced in the decoding process. This method evaluated on the datasets of C-MAPSS and compared with the latest prediction methods, the comparison shows that our results are competitive. Subsequently, experiments are carried out on the monitoring data of train wheelset experimental datasets, and the RUL prediction results are obtained, indicating that the model has good generalization capability.

Fusing Coupled Degradation Mechanisms with Machine Learning: A Multi-fidelity Framework for Lithium-ion Battery Lifespan Prediction

The study of intelligent operation and maintenance methods for turbofan engines is of great importance for improving the reliability of turbofan engines. Given the harsh operating conditions and complex structure of the turbofan engine, it is extremely difficult to establish an accurate physical model for remaining useful life (RUL) prediction. The traditional operation and maintenance method based on the physical model has several limitations in the application of turbofan engines, while the data-driven method offers a new solution. Compared with traditional machine learning models, deep learning models possess more powerful nonlinear expression capabilities and feature extraction capabilities. Therefore, this study focuses on studying the RUL prediction algorithm for turbofan engines based on the fused deep learning models. In this article, a multimodal deep learning approach based on a 1DCNN (1D convolutional neural network) + attention enhanced Bi-LSTM (bidirectional long short-term memory) network is proposed to predict the RUL by mining the temporal information of data. Furthermore, a DDResNet (dilated deep residual network) is also introduced to the 1DCNN submodel to leverage its hidden pattern mining capability due to its advance in preventing performance degradation across layers. Subsequently, the output of these two submodels is weighted fused to obtain the final RUL prediction. The merits of the proposed method are demonstrated by comparing it with existing methods for RUL prediction using the C-MAPSS (commercial modular aero-propulsion system simulation) dataset.

Remaining useful life (RUL) prediction of machinery plays a significant role for predictive maintenance, thus attracting more and more attentions in recent years. Stochastic process model-based methods are widely used in the RUL prediction of machinery. One of the major issues in the stochastic process model-based methods is that how to deal with the unit-to-unit variability during the RUL prediction process. Traditional methods generally handle this issue by introducing a unit-to-unit variability parameter into the model expression and estimate the parameter using the maximum likelihood estimation (MLE) algorithm. There exist two major limitations in the traditional methods. 1) The degradation processes are assumed to be dependent on only the age, which restricts their implementation in the cases of the state-dependent degradation processes. 2) They do not discuss the influence of the unit-to-unit variability in the RUL prediction processes systematically. To deal with these two limitations, a new RUL prediction method based on age- and state-dependent stochastic process models is proposed in this paper. In the proposed method, a generalized expression of the age- and stage-dependent stochastic process models is generated. An enhanced MLE algorithm is developed to estimate the model parameters according to the measurements of the available training units. And the unit-to-unit variability parameter is updated according to the real-time measurements of the testing unit. The effectiveness of the proposed method is demonstrated using a numerical simulation dataset of fatigue crack-growth.

Remaining useful life (RUL) prediction of bearings has extraordinary significance for prognostics and health management (PHM) of rotating machinery. RUL prediction approaches based on deep learning have been dedicated to finding a nonlinear mapping relationship between non-stationary monitoring data and RUL. However, most existing approaches pay little attention to the degradation trend of diverse health stages of bearing and lack the discriminative power of crucial degradation features, resulting in the loss of some important information associated with RUL. To address this challenge, this article proposes a novel RUL prediction framework based on degradation-trend-aware deep neural network with attention mechanism (DTADAN). Firstly, the multi-direction features with evident degradation trend are extracted via the analysis of bearing vibration signal from both time domain and time-frequency domain. Next, the deep neural network architecture with attention mechanism is utilized to adaptively learn the critical degradation features beneficial for RUL prediction. Distinct from the existing approaches, the proposed framework is able to dynamically extract key degradation features of the bearing including degradation trend information and effectively fuse multi-direction information to improve RUL prediction accuracy. The performance of the proposed approach is evaluated via case studies on XJTU-SY bearing dataset and PRONOSTIA bearing dataset. Compared with other state-of-the-art approaches, the proposed framework has better predictive accuracy and robustness. Additionally, interpretable analysis is provided to reveal the process of model learning and data characteristics, and the analysis results are helpful in guiding model learning.

The operating conditions of rolling bearings are complex and variable, and their vibration monitoring signals are filled with strong noise interference, resulting in a low accuracy in remaining useful life (RUL) prediction. For this issue, this paper proposes a denoising method with vibration fault signals modeling, and a novel RUL prediction method with Gate-convolutional neural networks (CNN) and Conv-Transformer encoder. Firstly, the theoretical fault signal is obtained through the vibration fault signal model, and the quality of the extracted features is improved by the wavelet threshold denoising algorithm in the process of feature extraction and selection. Moreover, the CNN is combined with the gating mechanism to construct a feature extractor with the feature evaluation function, and the convolution layers are introduced into the transformer to expand the encoder’s ability to explore local information in temporal data. By using fixed-time step temporal features as the input to the prediction module and minimizing the Huber function as the optimization objective, the relationship between temporal features and RUL is obtained. The comparison with the existing state-of-the-art RUL methods illustrates that the combination of gate control and convolutional structure proposed in this paper can not only reduce the prediction error of the model but also improve its generalization ability and robustness.

Remaining useful life (RUL) prediction is crucial for the predictive maintenance and health management of mechanical transmission systems. Although data-driven RUL prediction methods have advanced significantly, three key challenges remain: (i) constructing a physically interpretable HI that is invariant to operating conditions yet sensitive to incipient degradation; (ii) achieving adaptive time to start prediction (TSP) detection that accommodates non-stationarity and controls false and missed alarms; (iii) accurate and generalizable RUL prediction under cross-domain scenarios. To address these issues, a method combining unsupervised anomaly detection and deep feature transfer for TSP determination and RUL prediction is proposed. A residual health indicator is constructed from an expected trajectory learned by Gaussian process regression (GPR) on the healthy segment and a Mahalanobis distance (MD) deviation measure. For the first time extreme value theory is used to create dynamic thresholds for performance degradation analysis and TSP determination. During the RUL prediction phase, transfer component analysis mitigates feature distribution discrepancies between source and target domains. A dual long short-term memory (dual-LSTM) network with L2 regularization is then employed for RUL prediction across two transfer tasks. Experimental validation on a public benchmark dataset and a laboratory run-to-failure bearing dataset demonstrates the superior predictive accuracy and generalization capability of the proposed approach compared to existing methods.