A Neural Network-Based Joint Prognostic Model for Data Fusion and Remaining Useful Life Prediction

Local-Global Correlation Fusion-Based Graph Neural Network for Remaining Useful Life Prediction

Remaining useful life (RUL) prediction is an essential component for prognostics and health management of a system. Due to the powerful ability of nonlinear modeling, deep learning (DL) models have emerged as leading solutions by capturing temporal dependencies within time series sensory data. However, in RUL prediction tasks, data are typically collected from multiple sensors, introducing spatial dependencies in the form of sensor correlations. Existing methods are limited in effectively modeling and capturing the spatial dependencies, restricting their performance to learn representative features for RUL prediction. To overcome the limitations, we propose a novel LOcal-GlObal correlation fusion-based framework (LOGO). Our approach combines both local and global information to model sensor correlations effectively. From a local perspective, we account for local correlations that represent dynamic changes of sensor relationships in local ranges. Simultaneously, from a global perspective, we capture global correlations that depict relatively stable relations between sensors. An adaptive fusion mechanism is proposed to automatically fuse the correlations from different perspectives. Subsequently, we define sequential micrographs for each sample to effectively capture the fused correlations. Graph neural network (GNN) is introduced to capture the spatial dependencies within each micrograph, and the temporal dependencies between these sequential micrographs are then captured. This approach allows us to effectively model and capture the dependency information within the data for accurate RUL prediction. Extensive experiments have been conducted, verifying the effectiveness of our method.

A Hybrid Data Preprocessing-Based Hierarchical Attention BiLSTM Network for Remaining Useful Life Prediction of Spacecraft Lithium-Ion Batteries

As a crucial energy storage for the spacecraft power system, lithium-ion batteries degradation mechanisms are complex and involved with external environmental perturbations. Hence, effective remaining useful life (RUL) prediction and model reliability assessment confronts considerable obstacles. This article develops a new RUL prediction method for spacecraft lithium-ion batteries, where a hybrid data preprocessing-based deep learning model is proposed. First, to improve the correlation between battery capacity and features, the empirically selected high-dimensional features are linearized by using the Box-Cox transformation and then denoised via the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) method. Second, the principal component analysis (PCA) algorithm is employed to perform feature dimensionality reduction, and the output of PCA is further processed by the sliding window technique. Third, a multiscale hierarchical attention bi-directional long short-term memory (MHA-BiLSTM) model is constructed to estimate the capacity in future cycles. Specifically, the MHA-BiLSTM model can predict the RUL of lithium-ion batteries by considering the correlation and significance of each cycle's information during the degradation process on different scales. Finally, the proposed method is validated based on multiple types of experiments under two lithium-ion battery datasets, demonstrating its superior performance in terms of feature extraction and multidimensional time series prediction.

Interactive Prognosis Framework Between Deep Learning and a Stochastic Process Model for Remaining Useful Life Prediction

Uncertainty quantification of the remaining useful life (RUL) for degraded systems under the big data era has been a hot topic in recent years. A general idea is to execute two separate steps: deep-learning-based health indicator (HI) construction and stochastic process-based degradation modeling. However, there exists a critical matching defect between the constructed HI and a degradation model, which seriously affects the RUL prediction accuracy. Toward this end, this article proposes an interactive prognosis framework between deep learning and a stochastic process model for the RUL prediction. First, we resort to stacked contractive autoencoders to fuse multiple sensor information of historical systems for constructing the HI in a typical unsupervised manner. Then, considering the nonlinear characteristic of the constructed HI, an exponential-like degradation model is introduced to construct its degradation evolving model, and theoretical expressions of the prediction results are derived under the concept of the first hitting time. Furthermore, we design an optimization objective function by integrating the HI construction and degradation modeling for the RUL prediction. To minimize the designed objective function of the proposed interactive prognosis framework, a gradient descent algorithm is employed to update the model parameters. Based on the well-trained interactive prognosis model, we can obtain the HI of a field system from stacked contractive autoencoders with sensor data and the probability density function (pdf) of the predicted RUL on the basis of the estimated parameters. Finally, the effectiveness and superiority of the proposed interactive prognosis method are verified by two case studies associated with turbofan engines.

An Adaptation-Aware Interactive Learning Approach for Multiple Operational Condition-Based Degradation Modeling

Although degradation modeling has been widely applied to use multiple sensor signals to monitor the degradation process and predict the remaining useful lifetime (RUL) of operating machinery units, three challenging issues remain. One challenge is that units in engineering cases usually work under multiple operational conditions, causing the distribution of sensor signals to vary over conditions. It remains unexplored to characterize time-varying conditions as a distribution shift problem. The second challenge is that sensor signal fusion and degradation status modeling are separated into two independent steps in most of the existing methods, which ignores the intrinsic correlation between the two parts. The last challenge is how to find an accurate health index (HI) of units using previous knowledge of degradation. To tackle these issues, this article proposes an adaptation-aware interactive learning (AAIL) approach for degradation modeling. First, a condition-invariant HI is developed to handle time-varying operation conditions. Second, an interactive framework based on the fusion and degradation model is constructed, which naturally integrates a supervised learner and an unsupervised learner. To estimate the model parameters of AAIL, we propose an interactive training algorithm that shares learned degradation and fusion information during the model training process. A case study that uses the degradation data set of aircraft engines demonstrates that the proposed AAIL outperforms related benchmark methods.

Physics-Informed Neural Networks With Weighted Losses by Uncertainty Evaluation for Accurate and Stable Prediction of Manufacturing Systems

The state prediction of key components in manufacturing systems tends to be risk-sensitive tasks, where prediction accuracy and stability are the two key indicators. The physics-informed neural networks (PINNs), which integrate the advantages of both data-driven models and physics models, are deemed as an effective approach and research trends for stable prediction; however, the potential advantages of PINN are limited for the situations with inaccurate physics models or noisy data, where the balancing of the weights of the data-driven model and physics model is very important for improving the performance of PINN, and it is also a challenge urgently to be addressed. This article proposed a kind of PINN with weighted losses (PNNN-WLs) by uncertainty evaluation for accurate and stable prediction of manufacturing systems, where a novel weight allocation strategy based on uncertainty evaluation by quantifying the variance of prediction errors is proposed, and an improved PINN framework is established for accurate and stable prediction. The proposed approach is verified with open datasets on tool wear prediction, and experimental results show that the prediction accuracy and stability could be obviously improved over existing methods.

Online Piecewise Convex-Optimization Interpretable Weight Learning for Machine Life Cycle Performance Assessment

Machine life cycle performance assessment is of great significance to use a health index to inform the time of incipient fault initiation in a normal stage and realize fault identification and fault trending in a performance degradation stage. However, most existing works consider using unexplainable model parameters and historical data to build models and infer their off-line parameters for machine life cycle performance assessment. To overcome these limitations, an online piecewise convex-optimization interpretable weight learning framework without needing any historical abnormal and faulty data is proposed in this article to generate a piecewise health index to practically implement machine life cycle performance assessment. Firstly, based on a separation criterion, the first submodel in the proposed framework is built to detect the time of incipient fault initiation. Here, the piecewise health index generated by the first submodel is continuously updated by on-line monitoring data to timely detect the occurrence of any abnormal health conditions. Secondly, once the time of incipient fault initiation is informed, online updated model weights are highly correlated with fault characteristic frequencies and informative frequency bands for immediate fault identification. Simultaneously, the second submodel integrated with monotonicity and fitness properties in the proposed framework is triggered to generate the piecewise health index to realize overall monotonic fault trending. The significance of this article is that only online monitoring data are used to continuously update interpretable model weights as fault frequencies and informative frequency bands to generate the proposed piecewise health index so as to practically realize machine life cycle performance assessment. Two run-to-failure cases are studied to show the effectiveness and superiority of the proposed framework.

A decoupled Bayesian method for snake robot control in unstructured environment

This paper presents a method which avoids the common practice of using a complex coupled snake robot model and performing kinematic analysis for control in cluttered environments. Instead, we introduce a completely decoupled dynamical Bayesian formulation with respect to interacted snake robot links and environmental objects, which requires much lower complexity for efficient and robust control. When a snake robot does not interact with obstacles, it runs by a simple serpenoid controller. However, when it exhibits interaction with environments, defined as close proximity or collision with targets and/or obstacles, we extend the conventional Bayesian framework by modeling such interactions in terms of stimuli. The proposed 'multi-neural-stimulus function' represents the cumulative effect of both external environmental influences and internal constraints of the snake robot. It implicitly handles the 'unexpected collision' problem and thus solve the difficult data association and shape adjustment problems for snake robot control in an innovative way. Preliminary experimental results have demonstrated promising performance of the proposed method comparing with the state-of-the-art.

A Gated Multiscale Multitask Learning Model Using Time-Frequency Representation for Health Assessment and Remaining Useful Life Prediction

Health assessment and remaining useful life prediction are usually seen as separate tasks in industrial systems. Some multitask models use common features to handle these tasks synchronously, but they lack the usage of the representation in different scales and time-frequency domain. A lack of balance also exists among these scales. Therefore, a gated multiscale multitask learning model known as GMM-Net is proposed in this paper. By using the time-frequency representation, GMM-Net can obtain features of different scales via different kernels and compose the features by a gating network. A detailed loss function whose weight can be searched in a smaller scale is designed. The model is tested with different weights in the total loss function, and an optimal weight is found. Using this optimal weight, it is observed that the proposed method converges to a smaller loss and has a smaller model size than long short-term memory (LSTM) and gated recurrent unit (GRU) with less training time. The experiment results demonstrate the effectiveness of the proposed method.

A Two-Stage Transfer Regression Convolutional Neural Network for Bearing Remaining Useful Life Prediction

Recently, deep learning techniques have been successfully used for bearing remaining useful life (RUL) prediction. However, the degradation pattern of bearings can be much different from each other, which leads to the trained model usually not being able to work well for RUL prediction of a new bearing. As a method that can adapt a model trained on source datasets to a different but relative unlabeled target dataset, transfer learning shows the potential to solve this problem. Therefore, we propose a two-stage transfer regression (TR)-based bearing RUL prediction method. Firstly, the incipient fault point (IFP) is detected by a convolutional neural network (CNN) classifier to identity the start time of degradation stage and label the training samples. Then, a transfer regression CNN with multiloss is constructed for RUL prediction, including regression loss, classification loss, maximum mean discrepancy (MMD) and regularization loss, which can not only extract fault information from fault classification loss for RUL prediction, but also minimize the probability distribution distance, thus helping the method to be trained in a domain-invariant way via the transfer regression algorithm. Finally, real data collected from run-to-failure bearing experiments are analyzed by the TR-based CNN method. The results and comparisons with state-of-the-art methods demonstrate the superiority and reliable performance of the proposed method for bearing RUL prediction.

A Shape-Constrained Neural Data Fusion Network for Health Index Construction and Residual Life Prediction

With the rapid development of sensor technologies, multisensor signals are now readily available for health condition monitoring and remaining useful life (RUL) prediction. To fully utilize these signals for a better health condition assessment and RUL prediction, health indices are often constructed through various data fusion techniques. Nevertheless, most of the existing methods fuse signals linearly, which may not be sufficient to characterize the health status for RUL prediction. To address this issue and improve the predictability, this article proposes a novel nonlinear data fusion approach, namely, a shape-constrained neural data fusion network for health index construction. Especially, a neural network-based structure is employed, and a novel loss function is formulated by simultaneously considering the monotonicity and curvature of the constructed health index and its variability at the failure time. A tailored adaptive moment estimation algorithm (Adam) is proposed for model parameter estimation. The effectiveness of the proposed method is demonstrated and compared through a case study using the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) data set.