基于VMD-MPE-KPCA特征提取与MRVM相混合的滚动轴承故障诊断方法

针对滚动轴承振动信号在强噪声环境下出现非线性、非平稳、强干扰特性,进而导致故障特征难以提取及故障诊断准确率低的问题,提出变分模态分解(VMD)-多尺度排列熵(MPE)-核主元分析(KPCA)特征提取与多分类相关向量机(MRVM)相混合的滚动轴承故障诊断方法.该方法首先通过VMD-MPE进行滚动轴承振动信号的高维故障特征提取,其次对提取的故障特征进行KPCA可视化降维,最后将降维后的故障特征输入可实现不同样本概率输出的MRVM进行滚动轴承故障诊断.通过美国西储大学的滚动轴承故障数据集对该方法的有效性进行验证,结果表明提出的VMD-MPE-KPCA特征提取与MRVM相混合的滚动轴承故障诊断方法能够有效提取和识别滚动轴承故障特征,所提出的混合智能故障诊断方法与相关文献报道的故障诊断方法相比较,故障识别准确率达到了99.18%.     

Experimental Study of Discriminative Adaptive Training and MLLR for Automatic Pronunciation Evaluation

A stronger canonical model was developed to improve the performance of automatic pronunciation evaluations.Three different strategies were investigated with speaker adaptive training to normalize variations among speakers,minimum phone error training to identify easily confused phones and maximum likelihood linear regression(MLLR) adaptation to compensate for accent variations between native and non-native speakers.The three schemes were combined to improve the correlation coefficient between machine scores and human scores from 0.651 to 0.679 on the sentence level and from 0.788 to 0.822 on the speaker level.     

Eye‐safe UV stand‐off Raman spectroscopy for the ranged detection of explosives in the field

Increasing worldwide terrorist attacks involving explosives presents a growing need for a rapid and ranged explosive detection method that can safely be deployed in the field. Stand‐off Raman spectroscopy shows great promise; however, the radiant exposures of lasers required for adequate signal generation are often much greater than what is safe for the eye or the skin, restricting use of the technique to unpopulated areas. Here, by determining the safe exposure levels for lasers typically used in Raman spectroscopy, optimal parameter values are identified, which produce the largest possible detection range using power densities that do not exceed the eye‐safe limit. It is shown that safe ultraviolet pulse energies can be more than three orders of magnitude greater than equivalent safe visible pulse energies. Coupling this to the 16‐fold increase in Raman signal obtained in the ultraviolet at 266 nm over that at 532 nm results in a 131 times larger detection range for the eye‐safe 266‐nm system over an equivalent eye‐safe 532‐nm laser system. For the Raman system described here, this translates to a maximum range of 42 m for detecting Teflon with a 266‐nm laser emitting a 100‐mm diameter beam of 23.5‐mJ nanosecond pulses. Copyright © 2015 John Wiley & Sons, Ltd.     

A Rolling Bearing Fault Classification Scheme Based on k-Optimized Adaptive Local Iterative Filtering and Improved Multiscale Permutation Entropy

The health condition of the rolling bearing seriously affects the operation of the whole mechanical system. When the rolling bearing parts fail, the time series collected in the field generally shows strong nonlinearity and non-stationarity. To obtain the faulty characteristics of mechanical equipment accurately, a rolling bearing fault detection technique based on k-optimized adaptive local iterative filtering (ALIF), improved multiscale permutation entropy (improved MPE), and BP neural network was proposed. In the ALIF algorithm, a k-optimized ALIF method based on permutation entropy (PE) is presented to select the number of ALIF decomposition layers adaptively. The completely average coarse-graining method was proposed to excavate more hidden information. The performance analysis of the simulation signal shows that the improved MPE can more accurately dig out the depth information of the time series, and the entropy value obtained is more consistent and stable. In the research application, rolling bearing time series are decomposed by k-optimized ALIF to obtain a certain number of intrinsic mode functions (IMFs). Then the improved MPE value of effective IMF is calculated and input into backpropagation (BP) neural network as the feature vector for automatic fault identification. The comparative analysis of simulation signals shows that this method can extract fault information effectively. At the same time, the experimental part shows that this scheme not only effectively extracts the fault features, but also realizes the classification and identification of different fault modes and faults of different degrees, which has a certain application prospect in the research and application direction of rolling bearing fault identification.     

A method of acceleration for a class of multiplicative programming problems with exponent

Multiplicative programming problems with exponent (MPE) have many practical applications in various fields. In this paper, a method for accelerating global optimization is proposed for a class of multiplicative programming problems with exponent under multiplicative constraints using a suitable deleting technique. This technique offers the possibility of cutting away a large part of the currently investigated region in which the globally optimal solution of the MPE does not exist. The deleting technique can accelerate the convergence of the proposed global optimization algorithm. Two numerical examples are given to illustrate the feasibility of the deleting technique.     

改进变分模态分解-多尺度排列熵结合广义回归神经网络的高压直流输电线路故障辨识

针对现有的高压直流(high voltage direct current, HVDC)输电线路故障识别方法识别准确率低,且无法同时准确识别低阻和高阻故障的问题,提出一种改进变分模态分解(variational mode decomposition, VMD)-多尺度排列熵(multi-scale permutation entropy, MPE)结合广义回归神经网络(general regression neural network, GRNN)的HVDC输电线路故障辨识方法。首先,采用鲸鱼算法改进后的VMD对故障电流信号进行分解,并选择合适的本征模态函数(intrinsic mode function, IMF)分量计算多尺度排列熵和IMF能量和比值提取故障特征组成故障特征向量;其次,将特征向量输入到GRNN网络中进行训练与测试,利用GRNN网络对小样本数据的高分类能力识别不同类型的故障。实验结果表明,所提出的方法对HVDC输电线路不同类型故障辨识准确率高,无论发生低阻或高阻故障都能够准确辨识,耐受过渡电阻能力强,在小样本故障辨识方面性能突出,可靠性高。     

An intelligent maximum permissible exposure meter for safety assessments of laser radiation

There is frequently a need to make laser power or energy density measurements when determining whether radiation from a laser system exceeds the Maximum Permissible Exposure (MPE) as defined in BS EN 60825. This can be achieved using standard commercially available laser power or energy measurement equipment, but some of these have shortcomings when used in this application. Calculations must be performed by the user to compare the measured value to the MPE. The measurement and calculation procedure appears complex to the nonexpert who may be performing the assessment. A novel approach is described which uses purpose designed hardware and software to simplify the process. The hardware is optimized for measuring the relatively low powers associated with MPEs. The software runs on a Psion Series 3a palmtop computer. This reduces the cost and size of the system yet allows graphical and numerical presentation of data. Data output to other software running on PCs is also possible, enabling the instrument to be used as part of a quality system. Throughout the measurement process the opportunity for user error has been minimized by the hardware and software design.     

体育硕士专业学位研究生实践教学改革思考

从体育硕士专业学位研究生人才培养需求出发,探讨体育硕士实践教学中存在的问题,提出了实践教学改革的现实路径.     

支持ULE/MPE的IP over DVB-S接收系统在Linux下的设计与实现

IP over DVB-S是基于卫星实现IP数据广播的关键技术,在远程教育等领域广泛应用.ULE封装协议相比传统MPE协议更加简练、高效,对IP网络支持更好.设计了IP over DVB-S接收系统,并对其在Linux中实现时的关键技术予以介绍.该系统具有兼容ULE / MPE两种封装方式、支持IPv4/IPv6双协议的特点,在实际环境中进行了部署.     

Coal and Rock Hardness Identification Based on EEMD and Multi-Scale Permutation Entropy

This study offers an efficient hardness identification approach to address the problem of poor real-time performance and accuracy in coal and rock hardness detection. To begin, Ensemble Empirical Mode Decomposition (EEMD) was performed on the current signal of the cutting motor to obtain a number of Intrinsic Mode Functions (IMFs). Further, the target signal was selected among the IMFs to reconstruct the current signal according to the energy density and correlation coefficient criteria. After that, the Multi-scale Permutation Entropy (MPE) of the reconstructed signal was trained by the Adaboost improved Back Propagation (BP) neural network, in order to establish the hardness recognition model. Finally, the cutting arm’s swing speed and the cutting head’s rotation speed were adjusted based on the coal and rock hardness. The simulation results indicated that using the energy density and correlation criterion to reconstruct the signal can successfully filter out noise interference. Compared to the BP model, the relative root-mean-square error of the Adaboost-BP model decreased by 0.0633, and the prediction results were more accurate. Additionally, the speed control strategy based on coal and rock hardness can ensure the efficient cutting of the roadheader.