Research on Feature Extraction and Classification Method of Vibration Signal of Escalator Sprocket Bearing

In order to improve the accuracy of escalator sprocket bearing fault diagnosis,the problem of the feature extraction method of bearing vibration signal is addressed.In this paper,empirical mode is used to decompose the original signal,and the optimal modal component among the multiple modal components is obtained after the optimization decomposition is selected by the envelope spectrum method,and the multi-angle feature measure is introduced to extract the fault characteristic value.According to the vibration characteristics of the bearing vibration signal data,a bearing signal feature group that is more inclined to the fault feature category information is established,which avoids the absolute problem of extracting a single metric feature.The fuzzy C-means clustering algorithm is used to cluster the sample data with similar characteristics into the same cluster area,which effectively solves the problem that a single measurement analysis cannot characterize the complex internal characteristics ofthe bearing vibration signal.

SENSORING DROPLET SPRAY TRANSFER IN MIG WELDING BASED ON ARC SPECTRUM SIGNAL

The method to detect droplet transfer by means of arc spectrum, while the experiment sets, testing principle and data processing procedure,are presented. The experiment and analysis results show that arc spectrum signal can be utilized to detect and measure the transfer procedure, the transfer modes and the transfer parameters. The arc spectrum signal enjoys excellent quality with high signal amplitude. Each transfer mode has its specific typical signal mode, and the pulse outline corresponds to an integrated transferring procedure of one droplet. All these features of arc spectrum signal can be easily applied hi the control of transfer procedure,the identification and stabilization of transfer mode and the measurement of transfer parameters.

Simulation and feature analysis for gas emboli Doppler ultrasound signals

The purpose of this study is to establish the simulation model of the gas emboli by analyzing reasons for features of gas emboli Doppler ultrasound signals. It is useful for the further classification of the solid emboli and gas emboli. First, the model of the radiation force and the drag force is used to calculate forces acting on the gas emboli. Second, the acceleration of the gas emboli is calculated in both the radial direction and the axial direction of the vessel, which is used to calculate the trajectory of the gas emboli in the vessel. Finally, the computer simulation model is established for the gas emboli. Doppler ultrasound signals of the gas emboli and the solid emboli are generated in the simulation experiment. Experimental results show that compared with the solid emboli, the gas emboli acted by the radiation force and the drag force will result in the frequency-domain broaden in the Doppler spectrogram. When the gas emboli circulate from the low speed area to the high speed one and then from the high speed area back to the low speed one, a ＂V＂ shape will be shown in the spectrogram of gas emboli signals. When the gas emboli circulate from the low speed area to the high speed one or from the high speed area to the low speed one, a diagonal shape will be shown for gas emboli signals. It is also shown that features of simulated gas emboli signals match with those of gas emboli signals sampled from clinic. All demonstrate that the simulation method of the gas emboli is reasonable.

Generalized labeled multi-Bernoulli filter with signal features of unknown emitters

A novel algorithm that combines the generalized labeled multi-Bernoulli(GLMB) filter with signal features of the unknown emitter is proposed in this paper. In complex electromagnetic environments, emitter features(EFs) are often unknown and time-varying. Aiming at the unknown feature problem, we propose a method for identifying EFs based on dynamic clustering of data fields. Because EFs are time-varying and the probability distribution is unknown, an improved fuzzy C-means algorithm is proposed to calculate the correlation coefficients between the target and measurements, to approximate the EF likelihood function. On this basis, the EF likelihood function is integrated into the recursive GLMB filter process to obtain the new prediction and update equations.Simulation results show that the proposed method can improve the tracking performance of multiple targets,especially in heavy clutter environments.

Individual Identification of Electronic Equipment Based on Electromagnetic Fingerprint Characteristics

With the rapid development of communication and computer,the individual identification technology of communication equipment has been brought to many application scenarios.The identification of the same type of electronic equipment is of considerable significance,whether it is the identification of friend or foe in military applications,identity determination,radio spectrum management in civil applications,equipment fault diagnosis,and so on.Because of the limited-expression ability of the traditional electromagnetic signal representation methods in the face of complex signals,a new method of individual identification of the same equipment of communication equipment based on deep learning is proposed.The contents of this paper include the following aspects:(1)Considering the shortcomings of deep learning in processing small sample data,this paper provides a universal and robust feature template for signal data.This paper constructs a relatively complete signal template library from multiple perspectives,such as time domain and transform domain features,combined with high-order statistical analysis.Based on the inspiration of the image texture feature,characteristics of amplitude histogram of signal and the signal amplitude co-occurrence matrix(SACM)are proposed in this paper.These signal features can be used as a signal fingerprint template for individual identification.(2)Considering the limitation of the recognition rate of a single classifier,using the integrated classifier has achieved better generalization ability.The final average accuracy of 5 NRF24LE1 modules is up to 98%and solved the problem of individual identification of the same equipment of communication equipment under the condition of the small sample,low signal-to-noise ratio.

The Algorithm of Balanced Orthogonal Multiwavelets and Its Application in Denoising

In order to extract fault features of a weak signal from the strong noise and maintain signal smoothness, a new method of denoising based on the algorithm of balanced orthogonal multiwavelets is proposed. Multiwavelets have several scaling functions and wavelet functions, and possess excellent properties that a scalar wavelet cannot satisfy simultaneously, and match the different characteristics of signals. Moreover, the balanced orthogonal multiwavelets can avoid the Gibbs phenomena and their processes have the advantages in denoising. Therefore, the denoising based on the algorithm of balanced orthogonal multiwavelets is introduced into the signal process. The algorithm of bal- anced orthogonal multiwavelet and the implementation steps of this denoising are described. The experimental compar- ison of the denoising effect between this algorithm and the traditional multiwavelet algorithm was done. The experi- ments indieate that this method is effective and feasible to extract the fault feature submerged in heavy noise.

An approach for automatic sleep stage scoring and apnea-hypopnea detection

In this article we present an application of data mining to the medical domain sleep research, an approach for automatic sleep stage scoring and apnea-hypopnea detec- tion. By several combined techniques （Fourier and wavelet transform, derivative dynamic time warping, and waveform recognition）, our approach extracts meaningful features （fre- quencies and special patterns like k-complexes and sleep spindles） from physiological recordings containing EEG, ECG, EOG and EMG data. Based on these pieces of in- formation, an ensemble of decision trees is constructed us- ing the principle of bagging, which classifies sleep epochs in their sleep stages according to the rules by Rechtschaf- fen and Kales and annotates occurrences of apnea-hypopnea （total or partial cessation of respiration）. After that, case- based reasoning is applied in order to improve quality. We tested and evaluated our approach on several large public databases from PhysioBank, which showed an overall accu- racy of 95.2% for sleep stage scoring and 94.5% for classify- ing minutes as apneic or non-apneic.