Machine learning based online fault prognostics for nonstationary industrial process via degradation feature extraction and temporal smoothness analysis

Fault degradation prognostic, which estimates the time before a failure occurs and process breakdowns, has been recognized as a key component in maintenance strategies nowadays. Fault degradation processes are, in general,slowly varying and can be modeled by autoregressive models. However, industrial processes always show typical nonstationary nature, which may bring two challenges: how to capture fault degradation information and how to model nonstationary processes. To address the critical issues, a novel fault degradation modeling and online fault prognostic strategy is developed in this paper. First, a fault degradation-oriented slow feature analysis(FDSFA) algorithm is proposed to extract fault degradation directions along which candidate fault degradation features are extracted. The trend ability assessment is then applied to select major fault degradation features. Second, a key fault degradation factor(KFDF) is calculated to characterize the fault degradation tendency by combining major fault degradation features and their stability weighting factors. After that, a time-varying regression model with temporal smoothness regularization is established considering nonstationary characteristics. On the basis of updating strategy, an online fault prognostic model is further developed by analyzing and modeling the prediction errors. The performance of the proposed method is illustrated with a real industrial process.

A dive into spectral inference networks: improved algorithms for self-supervised learning of continuous spectral representations

We propose a self-supervising learning framework for finding the dominant eigenfunction-eigenvalue pairs of linear and self-adjoint operators.We represent target eigenfunctions with coordinate-based neural networks and employ the Fourier positional encodings to enable the approximation of high-frequency modes.We formulate a self-supervised training objective for spectral learning and propose a novel regularization mechanism to ensure that the network finds the exact eigenfunctions instead of a space spanned by the eigenfunctions.Furthermore,we investigate the effect of weight normalization as a mechanism to alleviate the risk of recovering linear dependent modes,allowing us to accurately recover a large number of eigenpairs.The effectiveness of our methods is demonstrated across a collection of representative benchmarks including both local and non-local diffusion operators,as well as high-dimensional time-series data from a video sequence.Our results indicate that the present algorithm can outperform competing approaches in terms of both approximation accuracy and computational cost.

Introducing driving-force information increases the predictability of the North Atlantic Oscillation

The North Atlantic Oscillation(NAO)is the most prominent mode of atmospheric variability in the Northern Hemisphere.Because of the close relationship between the NAO and regional climate in Eurasia,North Atlantic,and North America,improving the prediction skill for the NAO has attracted much attention.Previous studies that focused on the predictability of the NAO were often based upon simulations by climate models.In this study,the authors took advantage of Slow Feature Analysis to extract information on the driving forces from daily NAO index and introduced it into phase-space reconstruction.By computing the largest Lyapunov exponent,the authors found that the predictability of daily NAO index shows a significant increase when its driving force signal is considered.Furthermore,the authors conducted a short-term prediction for the NAO by using a global prediction model for chaotic time series that incorporated the driving-force information.Results showed that the prediction skill for the NAO can be largely increased.In addition,results from wavelet analysis suggested that the driving-force signal of the NAO is associated with three basic drivers:the annual cycle(1.02 yr),the quasi-biennial oscillation(QBO)(2.44 yr);and the solar cycle(11.6 yr),which indicates the critical roles of the QBO and solar activities in the predictability of the NAO.