Multi-scale and multi-layer perceptron hybrid method for bearings fault diagnosis

Discriminative and regularized echo state network for time series classification

The receptive field (RF), which determines the region of time series to be ``seen'' and used, is critical to improve the performance for time series classification (TSC). However, the variation of signal scales across and within time series data, makes it challenging to decide on proper RF sizes for TSC. In this paper, we propose a dynamic sparse network (DSN) with sparse connections for TSC, which can learn to cover various RF without cumbersome hyper-parameters tuning. The kernels in each sparse layer are sparse and can be explored under the constraint regions by dynamic sparse training, which makes it possible to reduce the resource cost. The experimental results show that the proposed DSN model can achieve state-of-art performance on both univariate and multivariate TSC datasets with less than 50\% computational cost compared with recent baseline methods, opening the path towards more accurate resource-aware methods for time series analyses. Our code is publicly available at: https://github.com/QiaoXiao7282/DSN.

Dynamic Sparse Network for Time Series Classification: Learning What to "see"

Vibration signals contain abundant information that reflects the health status of wind turbine high-speed shaft bearings ((HSSBs). Accurate health assessment and remaining useful life (RUL) prediction are the keys to the scientific maintenance of wind turbines. In this paper, a method based on the combination of a comprehensive evaluation function and a self-organizing feature map (SOM) network is proposed to construct a health indicator (HI) curve to characterizes the health state of HSSBs. Considering the difficulty in obtaining life cycle data of similar equipment in a short time, the exponential degradation model is selected as the degradation trajectory of HSSBs on the basis of the constructed HI curve, the Bayesian update model, and the expectation–maximization (EM) algorithm are used to predict the RUL of HSSBs. First, the time domain, frequency domain, and time–frequency domain degradation features of HSSBs are extracted. Second, a comprehensive evaluation function is constructed and used to select the degradation features with good performance. Third, the SOM network is used to fuse the selected degradation features to construct a one-dimensional HI curve. Finally, the exponential degradation model is selected as the degradation trajectory of HSSBs, and the Bayesian update and EM algorithm are used to predict the RUL of the HSSB. The monitoring data of a wind turbine HSSB in actual operation is used to validate the model. The HI curve constructed by the method in this paper can better reflect the degradation process of HSSBs. In terms of life prediction, the method in this paper has better prediction accuracy than the SVR model.

https://www.mdpi.com/1996-1073/14/15/4612/pdf

Health Assessment and Remaining Useful Life Prediction of Wind Turbine High-Speed Shaft Bearings

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causes the COVID-19 disease in humans, which has reached the scale of a global pandemic. Changes in the composition of the genome of the virus, in the form of mutations, can alter its ability to infect host cells. These modified forms of the virus are known as variants. The spike region of the SARS-CoV-2 genome has a crown-like structure — where “coronavirus” gets its name. In SARS-CoV-2, it has been noted that mutations happen disproportionately many in the spike region, making this region important for distinguishing different variants.Since amino acids (of the spike protein sequence) are not in a numerical form, they are of no direct use to machine learning algorithms. Thus we use various embedding techniques to make such spike sequence data amenable to machine learning approaches. However, there is ongoing research to find better solutions to study these variants using classification. This paper presents a transformation for spike sequences, called Spike2Signal, to allow the classification of different variants of SARS-CoV-2 using deep learning algorithms. Spike2Signal converts spike sequences into a signal-like representation to allow the classification by state-of-the-art time-series classifiers. Further, we transform this Spike2Signal representation into an image (Spike2Image) to allow the usage of state-of-the-art image classifiers and compare these results with those obtained purely with Spike2Signal. In a wider comparison with existing feature engineering-based methods, we show that the Spike2Signal representation allows to outperform all baselines in predictive power. 

Spike2Signal: Classifying Coronavirus Spike Sequences with Deep Learning

Multi-scale signed recurrence plot based time series classification using inception architectural networks

Conflicting evidence affects the final target recognition results. Thus, managing conflicting evidence efficiently can help to improve the belief degree of the true target. In current research, the existing approaches based on belief entropy use belief entropy itself to measure evidence conflict. However, it is not convincing to characterize the evidence conflict only through belief entropy itself. To solve this problem, we comprehensively consider the influences of the belief entropy itself and mutual belief entropy on conflict measurement, and propose a novel approach based on an improved belief entropy and entropy distance. The improved belief entropy based on pignistic probability transformation function is named pignistic probability transformation (PPT) entropy that measures the conflict between evidences from the perspective of self-belief entropy. Compared with the state-of-the-art belief entropy, it can measure the uncertainty of evidence more accurately, and make full use of the intersection information of evidence to estimate the degree of evidence conflict more reasonably. Entropy distance is a new distance measurement method and is used to measure the conflict between evidences from the perspective of mutual belief entropy. Two measures are mutually complementary in a sense. The results of numerical examples and target recognition applications demonstrate that our proposed approach has a faster convergence speed, and a higher belief degree of the true target compared with the existing methods.

Conflict Management for Target Recognition Based on PPT Entropy and Entropy Distance

Recently, some researchers adopted the convolutional neural network (CNN) for time series classification (TSC) and have achieved better performance than most hand-crafted methods in the University of California, Riverside (UCR) archive. The secret to the success of the CNN is weight sharing, which is robust to the global translation of the time series. However, global translation invariance is not the only case considered for TSC. Temporal distortion is another common phenomenon besides global translation in time series. The scale and phase changes due to temporal distortion bring significant challenges to TSC, which is out of the scope of conventional CNNs. In this paper, a CNN architecture with an elastic matching mechanism, which is named Elastic Matching CNN (short for EM-CNN), is proposed to address this challenge. Compared with the conventional CNN, EM-CNN allows local time shifting between the time series and convolutional kernels, and a matching matrix is exploited to learn the nonlinear alignment between time series and convolutional kernels of the CNN. Several EM-CNN models are proposed in this paper based on diverse CNN models. The results for 85 UCR datasets demonstrate that the elastic matching mechanism effectively improves CNN performance.

https://www.mdpi.com/1999-4893/14/7/192/pdf

Convolutional Neural Network with an Elastic Matching Mechanism for Time Series Classification

Wavelet transform is a well-known multi-resolution tool to analyze the time series in the time-frequency domain. Wavelet basis is diverse but predefined by manual without taking the data into the consideration. Hence, it is a great challenge to select an appropriate wavelet basis to separate the low and high frequency components for the task on the hand. Inspired by the lifting scheme in the second-generation wavelet, the updater and predictor are learned directly from the time series to separate the low and high frequency components of the time series. An adaptive multi-scale wavelet neural network (AMSW-NN) is proposed for time series classification in this paper. First, candidate frequency decompositions are obtained by a multi-scale convolutional neural network in conjunction with a depthwise convolutional neural network. Then, a selector is used to choose the optimal frequency decomposition from the candidates. At last, the optimal frequency decomposition is fed to a classification network to predict the label. A comprehensive experiment is performed on the UCR archive. The results demonstrate that, compared with the classical wavelet transform, AMSW-NN could improve the performance based on different classification networks.

https://www.mdpi.com/2078-2489/12/6/252/pdf

Shilin Zhou

Papers

Multi-scale signed recurrence plot based time series classification using inception architectural networks

Conflict Management for Target Recognition Based on PPT Entropy and Entropy Distance

Convolutional Neural Network with an Elastic Matching Mechanism for Time Series Classification

Adaptive Multi-Scale Wavelet Neural Network for Time Series Classification