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

The remaining useful life (RUL) of bearings based on deep learning methods has been increasingly used. However, there are still two obstacles in deep learning RUL prediction: (1) the training process of the deep learning model requires enough data, but run-to-failure data are limited in the actual industry; (2) the mutual dependence between RUL predictions at different time instants are commonly ignored in existing RUL prediction methods. To overcome these problems, a RUL prediction method combining the data augmentation strategy and Wiener–LSTM network is proposed. First, the Sobol sampling strategy is implemented to augment run-to-failure data based on the degradation model. Then, the Wiener–LSTM model is developed for the RUL prediction of bearings. Different from the existing LSTM-based bearing RUL methods, the Wiener–LSTM model utilizes the Wiener process to represent the mutual dependence between the predicted RUL results at different time instants and embeds the Wiener process into the LSTM to control the uncertainty of the result. A joint optimization strategy is applied in the construction of the loss function. The efficacy and superiority of the proposed method are verified on a rolling bearing dataset obtained from the PRONOSTIA platform. Compared with the conventional bearing RUL prediction methods, the proposed method can effectively augment the bearing run-to-failure data and, thus, improve the prediction results. Meanwhile, fluctuations of the bearing RUL prediction result are significantly suppressed by the proposed method, and the prediction errors of the proposed method are much lower than other comparative methods.

Remaining useful life (RUL) prediction using deep learning networks primarily produces point estimates of RUL, but capturing the inherent uncertainty in RUL prediction is difficult. The use of the stochastic process approach can reflect the uncertainty in RUL predictions. However, the amount of data generated during equipment operation cannot be effectively utilized. This paper aims to propose an adaptive RUL prediction method tailored for extensive datasets and prediction uncertainty, effectively harnessing the strengths of deep learning methods in managing massive data and stochastic process techniques in quantifying uncertainties. RUL prediction method, based on stacked autoencoder (SAE) combined with Generalized Wiener Process, employs SAE to extract profound underlying features from the monitoring signals. Principal component analysis (PCA) is then used to select highly trending features as inputs. The output of PCA accurately reflects health status. A Generalized Wiener Process is used to construct a model for the evolution of the health indicators. The estimation values for the model parameters are determined using the Maximum Likelihood Estimation method. Furthermore, an adaptive update is performed based on Bayesian theory. Utilizing the sense of the first hitting time concept, the Probability Density Function for RUL prediction is derived accurately. Finally, the effectiveness and superiority of the proposed method is verified using numerical simulations and experimental studies of bearing degradation data. The method improves the life prediction accuracy while reducing the prediction uncertainty.

As the foundation and kernel point of prognostics and health management (PHM) technique, the prediction of remaining useful life (RUL) raises numerous concerns. Bearing is one of the momentous parts that determine the state of health and life of the wind turbines, high-speed trains, and rotating machines. With increasing application of bearing in the equipment, the research on RUL prediction of bearing has gradually become one of the issues concerned by people, the research on the RUL prediction methods has made some progress at home and abroad. This paper aims to summarize the research status of RUL prediction methods of the bearings in recently years. Furthermore, the RUL prediction methods of bearings are introduced, which includes RUL prediction methods based on statistical data-driven and RUL prediction methods based on machine learning (ML), and summarizes the research results of RUL prediction. Finally, the research on the RUL prediction method of bearing was prospected.

Remaining useful life prediction with spatio-temporal graph transform and weakly supervised adversarial network: An application in power components

Remaining useful life (RUL) prediction plays a core role in industrial prognostics and health management (PHM), requiring data-driven models with higher predictive capability for accurate long time series prediction. Developing reliable deep learning-based models based on multi-sensor monitoring data is fundamental for accurately predicting vibration trends during bearing operation and is crucial for bearing fault diagnosis and RUL prediction. In this work, a method for constructing a health index based on vibration signal is developed to describe the performance features of rolling bearings, which mainly includes feature extraction, sensitive feature index selection, dimensionality reduction, and normalization methods. In addition, a new RUL prediction method, TCN–Transformer, is developed which can efficiently learn and integrate local and global features of vibration signals, addressing the long time series prediction problem in RUL prediction. The TCN extracts local features, while the Transformer learns global features, both of which are seamlessly integrated through a specially designed feature fusion attention module. Both the health indicator (HI) constructed from extracted time domain and frequency domain feature parameters and the RUL prediction method were rigorously validated using the IEEE PHM 2012 Data Challenge dataset for rolling bearing prognostics. By employing the proposed HI construction method, the average comprehensive bearing performance index, used to evaluate RUL prediction accuracy, is improved by 8.69% across the entire dataset compared to the original feature-based composite index. The proposed RUL prediction model can more accurately predict the RUL of rolling bearings under different conditions, reducing the RMSE and MAE by 14.62% and 9.26%, respectively, and improving the SCORE by 13.04%. These results underscore the efficacy and superiority of our approach in RUL prediction of rotating machinery across varying conditions.

Remaining useful life (RUL) prediction is critical for health management of industrial equipment. It has been widely noted that degradation modeling is a core step for RUL prediction where the Brownian motion (BM)-based models attract much attention. However, the existing BM-based degradation models still have some impractical assumptions, where the increments of a BM are independent and stationary. To extend the application of the degradation models, a bifractional Brownian motion (biFBM)-based degradation model is developed in this article. The biFBM is a process with dependent and nonstationary increments, which includes the BM and fractional Brownian motion (FBM) as special cases. For the proposed degradation model, the estimation of parameters and degradation states as well as the prediction of RUL is further considered. To address the non-Markovian degradation processes, an improved particle filter is designed for degradation state estimation and RUL prediction. The proposed degradation model and RUL prediction method are validated by case studies of turbine engines and a blast furnace wall.

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

A deep learning approach for supercapacitor remaining useful life prediction using pre-classifying strategy

Journal bearings are the key components of the nuclear circulating water pump (NCWP), and accurate remaining useful life (RUL) prediction is of great significance for improving the reliability, safety, and maintenance planning of NCWP. However, it is difficult to quantify the uncertainty of bearing RUL based on the current deep learning (DL) model, resulting in a lack of credibility and effective convincing for RUL predicted by the model. Meanwhile, all existing hybrid models are basically simple combinations, and they cannot solve the uncertainty quantification problem of RUL predicted by DL. Hence, the bearing RUL prediction method based on a dynamic interactive hybrid model is proposed. Firstly, a degradation model based on a nonlinear enhanced generalized Wiener process (EGWP) is proposed, which combines gated neural networks and time-varying drift coefficients to describe the nonlinear degradation process of bearing. Then, a corrective gated recurrent unit (CGRU) network is designed to learn and predict real-time degradation increments, and the parameters of the degradation model are dynamically updated through the history and prediction of degradation increments. Finally, the bearing RUL prediction is given by the CGRU network, and the probability density function (PDF) of RUL is given by the proposed hybrid model. The performance of the proposed method is evaluated using the PHM 2012 bearing dataset and the NCWP journal bearing dataset. The results show that our proposed method can effectively predict bearing RUL and its uncertainty.

This study addresses the challenges in bearing remaining useful life (RUL) prediction, including small sample size and incomplete labels. A novel RUL prediction method is proposed. The method is based on adaptive degradation point detection and a hybrid deep learning framework. First, to determine the initial degradation time, the original vibration signals are combined with a physical bearing model. The Aquila Optimizer optimization algorithm is used to quantify the real-time crack values. An improved adaptive dynamic 3 σ criterion is applied together with the real-time crack values to identify the first prediction time. Second, to reduce the need for manually defined labels in RUL prediction, a feature model combining Gaussian mixture model and fuzzy entropy is developed. This model constructs an unsupervised health indicators (HI). Finally, a convolutional neural network-Bidirectional GRU-Attention model is proposed to predict the HI. The model integrates time-series modeling with an attention mechanism. The bearing HI is predicted sequentially. When the predicted HI exceeds the life threshold, the RUL is calculated. Experimental results on multiple datasets and comparisons with other methods show that the proposed method achieves the highest prediction accuracy, exceeding 93.59%. The results demonstrate that the method is reliable and practical for bearing RUL prediction.

Remaining useful life (RUL) prediction plays an important role in prognostics and health management (PHM) and can significantly enhance equipment reliability and safety in various engineering applications. Accurate RUL prediction enables proactive maintenance planning, helping prevent potential hazards and economic losses caused by equipment failures. Recently, while deep learning-based methods have swept the RUL prediction field, most existing methods still have difficulties in simultaneously extracting multiscale global and local degradation feature information from raw multi-sensor monitoring data. To address these issues, we propose a novel multiscale global and local self-attention-based network (MGLSN) for RUL prediction. MGLSN consists of global and local feature extraction subnetworks based on self-attention, which work in parallel to simultaneously extract the global and local degradation features of equipment and can adaptively focus on more important parts. While the global network captures long-term dependencies between time steps, the local network focuses on modeling local temporal dynamics. The design of parallel feature extraction can avoid the mutual influence of information from global and local aspects. Moreover, MGLSN adopts a multiscale feature extraction design (multiscale self-attention and convolution) to capture the global and local degradation patterns at different scales, which can be combined to better reflect the degradation trend. Experiments on the widely used Commercial Modular Aero-Propulsion System Simulation (CMAPSS), New CMAPSS (N-CMAPSS), and International Conference on Prognostics and Health Management 2008 challenge datasets provided by NASA show that MGLSN significantly outperforms state-of-the-art RUL prediction methods and has great application prospects in the field of PHM.

With increasing amounts of data being generated by businesses and researchers, there is a need for fast, accurate and robust algorithms for data analysis. Improvements in database's technology, computing performance and artificial intelligence have contributed to the development of intelligent data analysis. The primary aim of data mining is knowledge discovery, i.e. patterns in the data that lead to better understanding of the data generating process and to useful predictions. The knowledge that becomes available through data mining enables an asset owner to make important decisions about life cycle costs in advance. In maintenance field, CMMS (Computer maintenance management system) and CM (Condition Monitoring) are the most popular software available in the industries. Since first one stores all historical data, maintenance actions, events and ma nufacturer recommendations, second one collects and stores all critical physical parameters (vibration, temperature.) to be monitored in a regular time basis. However, converting these data into useful information is a challenge. The degradation process of a system may be affected by many unknown factors, such as unidentified fault modes, unmeasured operational conditions, engineering variance, environmental conditions, etc. These unknown factors not only complicate the degradation behaviors of the system, but also make it difficult to collect quality data. Due to lack of knowledge and incomplete measurements, certain important con text information (e.g. fault modes, operational conditions) of the collected data will be missing. Therefore, historical data of the system with a large variety of degradation patterns will be mixed together. With such data, learning a global model for Remaining Useful Life (RUL) prediction becomes extremely hard since the end user does not have enough and good-quality data to model properly the system. This has led us to look for advanced RUL prediction techniques beyond the traditional RUL prediction models. The degradation process for many engineering systems, especially mechanical systems, is irreversible unless the condition is recovered by effective maintenance actions. The irreversible degradation process does not necessarily imply that the observed features will exhibit a monotonic progression pattern during degradation. Such progression pattern is sometimes hard to model using parametric methods. Considering a degradation process involving no or limited maintenance, the process may compose of a sequence of irreversible stages (either discrete or continuous) from new to be worn out, which can be implicitly expressed by the trajectory of the measured condition data or features. Therefore, the RUL of the system can be estimated if its future degradation trend can be projected from those historical instances. In this paper, a novel RUL prediction method inspired by feature maps and SVM classifiers is proposed. The historical instances of a system with life-time condition data are used to create a classification by SVM hyper planes. For a test instance of the same system, whose RUL is going to be estimated, degradation speed is evaluated by computing the minimal distance defined based on the degradation trajectories, i.e. the approach of the system to the hyper plane that segregates good and bad condition data at a different time horizon. Therefore, the final RUL of a specific component can be estimated, and global RUL information can then be obtained by aggregating the multiple RUL estimations using a density estimation method. Proposed model develops an effective RUL prediction method that addresses multiple challenges in complex system prognostics, where many parameters are unknown. Similarities between degradation trajectories can be checked in order to enrich existing methodologies in prognostic's applications. Existing CM data for bearings will be used to verify the model.

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.

Res-HSA: Residual hybrid network with self-attention mechanism for RUL prediction of rotating machinery