Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Data Mining Practical Machine Learning Tools and Techniques

A new Ensemble Empirical Mode Decomposition (EEMD) is presented. This new approach consists of sifting an ensemble of white noise-added signal (data) and treats the mean as the final true result. Finite, not infinitesimal, amplitude white noise is necessary to force the ensemble to exhaust all possible solutions in the sifting process, thus making the different scale signals to collate in the proper intrinsic mode functions (IMF) dictated by the dyadic filter banks. As EEMD is a time–space analysis method, the added white noise is averaged out with sufficient number of trials; the only persistent part that survives the averaging process is the component of the signal (original data), which is then treated as the true and more physical meaningful answer. The effect of the added white noise is to provide a uniform reference frame in the time–frequency space; therefore, the added noise collates the portion of the signal of comparable scale in one IMF. With this ensemble mean, one can separate scales naturall...

/pdf/ensemble-empirical-mode-decomposition-a-noise-assisted-data-4htvj7tcuy.pdf

Ensemble empirical mode decomposition: a noise-assisted data analysis method

Deep learning and its applications to machine health monitoring

A review on empirical mode decomposition in fault diagnosis of rotating machinery

Online joint replacement-order optimization driven by a nonlinear ensemble remaining useful life prediction method

Enhanced variable reluctance energy harvesting for self-powered monitoring

Based on machine learning techniques, this paper presents a novel intelligent fault diagnosis method, which is an integrated framework concerning reconstruction independent component analysis (RICA) and multiclass relevance vector machine (MRVM). In this method, the RICA is first used to automatically extract features from raw vibration signals. Then, the learned features are used as the input data of MRVM for the classification of different health conditions of machines. The proposed method is applied to the fault diagnosis of locomotive rolling bearings. According to the diagnosis results, it is verified that the proposed method is able to reliably classify different health conditions. By comparing with diagnosis method based on time-domain statistical analysis and wavelet transformation, the proposed method shows its superiority in automatic features extraction from raw signals.

Reconstruction independent component analysis-based methods for intelligent fault diagnosis

In this paper, a key performance indicator (KPI) related multiplicative fault diagnosis scheme is proposed for static industrial processes. This scheme is developed for an alternative algorithm to the standard partial least squares (PLS) based process monitoring, where no design parameter like “latent variable number” is involved. Based on both normal and faulty data sets, the multiplicative fault information is firstly estimated. With this knowledge, the most critical low-level control loop/component is further identified. Different from the existing data-driven additive fault diagnosis approaches, this scheme aims to handle the second order statistics, which is of fatal importance for KPI-related fault diagnosis. Finally, an academic example is investigated to illustrate the functionality of this scheme.

A KPI-related multiplicative fault diagnosis scheme for industrial processes

Since fault diagnosis has entered the big data era, deep learning has been more and more widely studied to diagnose faults of rolling element bearings Generally, existing methods require labeled data for training before they can be used to recognize faults However, in real scenarios, massive data are usually unlabeled data rather than labeled ones, because labeling data is always a tough issue and consumes much human labor In order to fully take advantage of the massive unlabeled data, this paper proposes a vibration indicator-based graph convolutional neural network (VI-GCN) for fault diagnosis The VI-GCN is applied to a benchmark dataset of bearing faults Experimental results indicate that it is promising for bearing fault diagnosis when there are few labeled data

https://iopscience.iop.org/article/10.1088/1757-899X/1043/5/052026/pdf

Yaguo Lei

Papers

Online joint replacement-order optimization driven by a nonlinear ensemble remaining useful life prediction method

Enhanced variable reluctance energy harvesting for self-powered monitoring

Reconstruction independent component analysis-based methods for intelligent fault diagnosis

A KPI-related multiplicative fault diagnosis scheme for industrial processes

Vibration indicator-based graph convolutional network for semi-supervised bearing fault diagnosis