基于小波时频图和卷积神经网络的断路器故障诊断分析

高压断路器操动机构振动信号为非平稳性信号,蕴含着丰富的操动机构工作状态的信息,对操动机构工作状态的检验辨识具有重大意义。提出一种基于小波时频图和卷积神经网络的断路器故障诊断方法。对操动机构振动信号进行连续小波变换生成时频图(CWT),并对时频图进行统一压缩预处理;将预处理后的时频图作为特征图输入卷积神经网络AlexNet模型;通过对网络参数的调整,逐步改进网络模型,有监督地实现对操动机构故障状态的辨识诊断。结果表明,该方法能够有效地运用于断路器操动机构故障辨识诊断,与小波频带能量-RBF、小波频带能量-SVM的故障识别相比,故障识别准确率最高。     

基于优化遗传算法改进的小波网络预测锰系磷化膜的耐蚀性

针对小波网络训练速率较慢、结构不易确定等问题,结合实验选取的因素(包括输入参数和输出结果),通过仿真确定了小波网络的结构为3-7-1。接着,利用优化遗传算法对小波网络进行改进,修正其初始权值和因子。通过仿真证实了改进的小波网络具备更强的寻优能力和更快的收敛速率。最后,利用改进的小波网络预测锰系磷化膜的耐蚀性。结果表明:改进的小波网络可以更好地拟合样本数据,能够进行较准确的预测。     

A novel adaptive convolutional neural network for fault diagnosis of hydraulic piston pump with acoustic images

As an essential part of hydraulic transmission systems, hydraulic piston pumps have a significant role in many state-of-the-art industries. Thus, it is important to implement accurate and effective fault diagnosis of hydraulic piston pumps. Owing to the heavy reliance of shallow machine learning models on the expertise and experience of engineers, fault diagnosis based on deep models has attracted significant attention from academia and industry. To construct a deep model with good performance, it is necessary and challenging to tune the hyperparameters (HPs). Since many existing methods focus on manual tuning and use common search algorithms, it is meaningful to explore more intelligent algorithms that can automatically optimize the HPs. In this paper, Bayesian optimization (BO) is employed for adaptive HP learning, and an improved convolutional neural network (CNN) is established for fault feature extraction and classification in a hydraulic piston pump. First, acoustic signals are transformed into time–frequency distributions by a continuous wavelet transform. Second, a preliminary CNN model is built by setting initial HPs. The range of each HP to be optimized is identified. Third, BO is employed to select the optimal combination of HPs. An improved model called CNN-BO is constructed. Finally, the diagnostic efficiency of CNN-BO is analyzed using a confusion matrix and t-distributed stochastic neighbor embedding. The classification performance of different models is compared. It is found that CNN-BO has a higher accuracy and better robustness in fault diagnosis for a hydraulic piston pump. This research will provide a basis for ensuring the reliability and safety of the hydraulic pump.     

ADVANCES IN HIGH-RESOLUTION MALDI MASS SPECTROMETRY FOR NEUROBIOLOGY

Research in the field of neurobiology and neurochemistry has seen a rapid expansion in the last several years due to advances in technologies and instrumentation, facilitating the detection of biomolecules critical to the complex signaling of neurons. Part of this growth has been due to the development and implementation of high-resolution Fourier transform (FT) mass spectrometry (MS), as is offered by FT ion cyclotron resonance (FTICR) and Orbitrap mass analyzers, which improves the accuracy of measurements and helps resolve the complex biological mixtures often analyzed in the nervous system. The coupling of matrix-assisted laser desorption/ionization (MALDI) with high-resolution MS has drastically expanded the information that can be obtained with these complex samples. This review discusses notable technical developments in MALDI-FTICR and MALDI-Orbitrap platforms and their applications toward molecules in the nervous system, including sequence elucidation and profiling with de novo sequencing, analysis of post-translational modifications, in situ analysis, key advances in sample preparation and handling, quantitation, and imaging. Notable novel applications are also discussed to highlight key developments critical to advancing our understanding of neurobiology and providing insight into the exciting future of this field. © 2020 John Wiley & Sons Ltd. Mass Spec Rev     

Fourier transform ion cyclotron resonance mass spectrometry at the true cyclotron frequency

Ion cyclotron resonance (ICR) cells provide stability and coherence of ion oscillations in crossed electric and magnetic fields over extended periods of time. Using the Fourier transform enables precise measurements of ion oscillation frequencies. These precisely measured frequencies are converted into highly accurate mass-to-charge ratios of the analyte ions by calibration procedures. In terms of resolution and mass accuracy, Fourier transform ICR mass spectrometry (FT-ICR MS) offers the highest performance of any MS technology. This is reflected in its wide range of applications. However, in the most challenging MS application, for example, imaging, enhancements in the mass accuracy of fluctuating ion fluxes are required to continue advancing the field. One approach is to shift the ion signal power into the peak corresponding to the true cyclotron frequency instead of the reduced cyclotron frequency peak. The benefits of measuring the true cyclotron frequency include increased tolerance to electric fields within the ICR cell, which enhances frequency measurement precision. As a result, many attempts to implement this mode of FT-ICR MS operation have occurred. Examples of true cyclotron frequency measurements include detection of magnetron inter-harmonics of the reduced cyclotron frequency (i.e., the sidebands), trapping field-free (i.e., screened) ICR cells, and hyperbolic ICR cells with quadrupolar ion detection. More recently, ICR cells with spatially distributed ion clouds have demonstrated attractive performance characteristics for true cyclotron frequency ion detection. Here, we review the corresponding developments in FT-ICR MS over the past 40 years.     

Unconstrained Hand Dorsal Veins Image Database and Recognition System

Hand veins can be used effectively in biometric recognition since they are internal organs that, in contrast to fingerprints, are robust under external environment effects such as dirt and paper cuts. Moreover, they form a complex rich shape that is unique, even in identical twins, and allows a high degree of freedom. However, most currently employed hand-based biometric systems rely on hand-touch devices to capture images with the desired quality. Since the start of the COVID-19 pandemic, most hand-based biometric systems have become undesirable due to their possible impact on the spread of the pandemic. Consequently, new contactless hand-based biometric recognition systems and databases are desired to keep up with the rising hygiene awareness. One contribution of this research is the creation of a database for hand dorsal veins images obtained contact-free with a variation in capturing distance and rotation angle. This database consists of 1548 images collected from 86 participants whose ages ranged from 19 to 84 years. For the other research contribution, a novel geometrical feature extraction method has been developed based on the Curvelet Transform. This method is useful for extracting robust rotation invariance features from vein images. The database attributes and the veins recognition results are analyzed to demonstrate their efficacy.     

Multi-objective iterative optimization algorithm based optimal wavelet filter selection for multi-fault diagnosis of rolling element bearings

Rolling element bearings (REBs) play an essential role in modern machinery and their condition monitoring is significant in predictive maintenance. Due to the harsh operating conditions, multi-fault may co-exist in one bearing and vibration signal always exhibits low signal-to-noise ratio (SNR), which causes difficulties in detecting fault. In the previous studies, maximum correlated kurtosis deconvolution (MCKD) has been validated as an efficient method to extract fault feature in the fault signals. Nonetheless, there are still some challenges when MCKD is applied to fault detection owing to the rigorous requirements of multiple input parameters. To overcome limitation, a multi-objective iterative optimization algorithm (MOIOA) for multi-fault diagnosis is proposed. In this method, correlated kurtosis (CK) is taken as a criterion to select optimal Morlet wavelet filter using the whale optimization algorithm (WOA). Meanwhile, to further eliminate the effect of the inaccurate period on CK, the update process of period is incorporated. After that, the simulated and experimental signals are utilized to testify the validity and superiority of the MOIOA for multiple faults detection by the comparison with MCKD. The results indicate that MOIOA is efficient to extract weak fault features even with heavy noise and harmonic interferences.     

Principle of a two-output-difference interferometer for removing the most important interference distortions

This paper presents a two-output-difference interferometer for removing the most important interference distortions caused by nonlinear detectors. These distortions can be removed not only because the resulting interferogram is composed of the difference between the signals of the two detectors, but also because the modulated signals at each output have the same amplitude and opposite phases. Due to the use of two corner-cube mirrors fixed as a single moving element, the tilt and shearing problem will disappear. The effect of the corner-cube mirror deviation angle and the plane mirror tilt angle are investigated in detail, and the formulas of their tolerance are derived by means of modulation depth and phase error. The advantage of the interferometer enables it to be suitable for Fourier transform spectrometers.     

基于十字形阵列和2D-MUSIC算法的Lamb波检测

采用由压电传感器组成的十字形阵列进行Lamb波信号的激励和接收，提出一种二维多重信号分类（2D-MUSIC）方法对铝板中的缺陷进行定位检测。选用合适的频率激励产生单一模态信号，可避免多模态的影响，降低Lamb波的频散；利用2D-MUSIC算法对接收信号进行分段处理，并结合反射信号和二维导向矢量对铝板中的缺陷进行定位。结果表明，提出的2D-MUSIC算法对铝板中的缺陷定位比传统MUSIC算法更精准。     

Proposed network structures and combined adaptive algorithms for electrocardiogram signal denoising

An electrocardiogram (ECG) signal is a record of the electrical activities of heart muscle and is used clinically to diagnose heart diseases. An ECG signal should be presented as clear as possible to support accurate decisions made by doctors. This article proposes different combinations of combined adaptive algorithms to derive different noise-cancelling structures to remove (denoise) different kinds of noise from ECG signals. The algorithms are applied to the following types of noise: power line interference, baseline wander, electrode motion artifact, and muscle artifacts. Moreover, the results of the suggested models and algorithms are compared with those of conventional denoising tools such as the discrete wavelet transform, an adaptive filter, and a multilayer neural network (NN) to ensure the superiority of the proposed combined structures and algorithms. Furthermore, the hybrid concept is based on dual, triple, and quadruple combinations of well-known algorithms that derive adaptive filters, such as the least mean squares, normalized least mean squares and recursive least squares algorithms. The combinations are formulated based on partial update, variable step-size (VSS), and second iterative VSS algorithms, which are considered in different combinations. In addition, biased NN and unbiased linear neural network (ULNN) structures are considered. The performance of the different structures and related algorithms are evaluated by measuring the post-signal-to-noise ratio, mean square error, and percentage root mean square difference.