Neural network classification of hyperspectral images on the basis of the Hilbert–Huang transform

The method of image classification with its preliminary transformation to principal components and with the use of the Hilbert–Huang transform is studied by an example of neural network classification of a hyperspectral image. The efficiency of the method is demonstrated through comparisons with traditional methods of neural network classification with the use of spectral components and principal components without involving spatial information as features. Radial-basis and complex neural networks are used for classification.     

The Fourier transform spectrometer of the Université Pierre et Marie Curie QualAir platform

A Bruker Optics IFS 125HR Fourier transform spectrometer (FTS) and the Laboratoire de Physique Mole?culaire pour l'Atmosphe?re et l'Astrophysique retrieval algorithm were adapted for ground based atmospheric measurements. As one of the major instruments of the experimental research platform QualAir, this FTS is dedicated to study the urban air composition of large megacity such as Paris. The precise concentration measurements of the most important atmospheric pollutants are a key to improve the understanding and modeling of urban air pollution processes. Located in the center of Paris, this remote sensing spectrometer enables to monitor many pollutants. Examples for NO(2) and CO are demonstrating the performances of this new experimental setup.     

Development of a radiative transfer model for the determination of toxic gases by Fourier transform–infrared spectroscopy with a support vector machine algorithm

Abstract

This report describes a radiative transfer model for Fourier transform-infrared (FT-IR) spectroscopy to create close-to-reality toxic gas spectra by reflecting the unique spectral responses of detectors and using the atmospheric radiative transfer code, MODTRAN. This system can be highly useful in overcoming the limitations for measuring toxic gases in open environments. The emulated gas spectra can be used to train support vector machine (SVM) for chemical gas detection. Its detection performance is evaluated with nerve agents (tabun, sarin, soman, and cyclosarin) and a simulant gas (sulfur hexafluoride) for indoor and outdoor experiments by using two off-the-shelf FT-IR gas detectors. The experimental results show that the proposed SVM algorithm successfully detected and classified targeted gases while reducing false negative and false positive detection rates.     

A signal decomposition or lowpass filtering with Hilbert transform?

Recently, Chen and Wang discovered an explicit formula that makes use of the Hilbert transform for accurate decomposition of a lower harmonic from a signal composition. This letter presents another proof with a new interpretation for the formula using the Bedrosian identity for overlapping signals. This new and simpler proof is based only on the Hilbert transform and does not involve presentation of the Fourier transform. As a result the discovered formula is introduced as a lowpass filter suitable for non-stationary signals.     

Non-stationary signal analysis based on general parameterized time–frequency transform and its application in the feature extraction of a rotary machine

With the development of large rotary machines for faster and more integrated performance, the condition monitoring and fault diagnosis for them are becoming more challenging. Since the time-frequency (TF) pattern of the vibration signal from the rotary machine often contains condition information and fault feature, the methods based on TF analysis have been widely-used to solve these two problems in the industrial community. This article introduces an effective non-stationary signal analysis method based on the general parameterized time–frequency transform (GPTFT). The GPTFT is achieved by inserting a rotation operator and a shift operator in the short-time Fourier transform. This method can produce a high-concentrated TF pattern with a general kernel. A multi-component instantaneous frequency (IF) extraction method is proposed based on it. The estimation for the IF of every component is accomplished by defining a spectrum concentration index (SCI). Moreover, such an IF estimation process is iteratively operated until all the components are extracted. The tests on three simulation examples and a real vibration signal demonstrate the effectiveness and superiority of our method.     

Gear fault identification based on Hilbert–Huang transform and SOM neural network

Gear vibration signals always display non-stationary behavior. HHT (Hilbert–Huang transform) is a method for adaptive analysis of non-linear and non-stationary signals, but it can only distinguish conspicuous faults. SOM (self-organizing feature map) neural network is a network learning with no instructors which has self-adaptive and self-learning features and can compensate for the disadvantage of HHT. This paper proposed a new gear fault identification method based on HHT and SOM neural network. Firstly, the frequency families of gear vibration signals were separated effectively by EMD (empirical mode decomposition). Then Hilbert spectrum and Hilbert marginal spectrum were obtained by Hilbert transform of IMFs (intrinsic mode functions). The amplitude changes of gear vibration signals along with time and frequency had been displayed respectively. After HHT, the energy percentage of the first six IMFs were chosen as input vectors of SOM neural network for fault classification. The analysis results showed that the fault features of these signals can be accurately extracted and distinguished with the proposed approach.     

Vacuum compatible sample positioning device for matrix assisted laser desorption∕ionization Fourier transform ion cyclotron resonance mass spectrometry imaging

The high mass accuracy and resolving power of Fourier transform ion cyclotron resonance mass spectrometers (FT-ICR MS) make them ideal mass detectors for mass spectrometry imaging (MSI), promising to provide unmatched molecular resolution capabilities. The intrinsic low tolerance of FT-ICR MS to RF interference, however, along with typically vertical positioning of the sample, and MSI acquisition speed requirements present numerous engineering challenges in creating robotics capable of achieving the spatial resolution to match. This work discusses a two-dimensional positioning stage designed to address these issues. The stage is capable of operating in ～1 × 10(-8) mbar vacuum. The range of motion is set to 100 mm × 100 mm to accommodate large samples, while the positioning accuracy is demonstrated to be less than 0.4 micron in both directions under vertical load over the entire range. This device was integrated into three different matrix assisted laser desorption∕ionization (MALDI) FT-ICR instruments and showed no detectable RF noise. The "oversampling" MALDI-MSI experiments, under which the sample is completely ablated at each position, followed by the target movement of the distance smaller than the laser beam, conducted on the custom-built 7T FT-ICR MS demonstrate the stability and positional accuracy of the stage robotics which delivers high spatial resolution mass spectral images at a fraction of the laser spot diameter.     

PATENT LAW of the People''''s Republic of China

Article 1. This Law is enacted to protect patent rights for inventions-creations, to encourage inventioncreation, to foster the spreading and application of inventions-creations, and to promote the development of science and technology, for meeting the needs of the construction of socialist modernization. Article 2. In this Law, "inventions-creations" mean inventions, utility models and designs.     

Editorial Advisory Board of Chinese Journal of Mechanical Engineering

Honorary Chairmen: Lei Tianjue Wang Buxuan Pan Jiluan Lu YongxiangChairman: Zhong QunpengVice Chairmen: Xu Binshi Song Tianhu Liu Fei Shi ZhipingMembers:     

Editorial Advisory Board of Chinese Journal of Mechanical Engineering

Honorary Chairmen:Lei Tianlue Cha云rma:Zhong QunPeng V奋ce Chairmen:Xu Binshi Song Members: Wang Buxuan Pan JIluan Lu YongXiang Tianhu Liu Fei Shi ZhiPing Albert 5 H Chang China Institute of TeChnoIOgy, Tajwan,China B ian Xiufeng Shandong University, Chin…     

Editorial Advisory Board of Chinese Journal of Mechanical Engineering

Honorary Chairmen:Wang Buxuan Pan JIluan Lu Yongxiang Cha获rman:Zhong QunPeng Viee·Chairmen:Xu Binshi Song Tianhu Liu Fei Shi ZhiPing Members: Albert 5 H Chang Vanung University， Taiwan，China B ian Xiufeng Shandong Univers你Ch加a Cao Jian Northwestern University， USA Chen Xinzeng Nj门gbo UniVersity，China Chen Xinzhao Hefei University of Teehnology， Ch的a Chen XuejunXi’an Jiaotong UniVers你China Chen Ying Zhejiang Unjversi祝China Chen Yubao The UniversjtyofMie…     

Editorial Advisory Board of Chinese Journal of Mechanical Engineering

Honorary Chairmen: Lei Tianjue Wang Buxuan Pan Jiluan Lu Yongxiang Chairma: Zhong Qunpeng Vice Chairmen: Xu Binshi Song Tianhu Liu Fei Shi Zhiping Members:     

Editorial Advisory Board of Chinese Journal of Mechanical Engineering

Honorary Chairmen:Wang Buxuan Pan Jiluan Lu Yongxiang Tom Bell Chairman:Zhong Qunpeng Vice-Chairmen:XuBinshi Song Tianhu Liu Fei ShiZhiping Members:     

Driving Characters of New Type Machine of Mixing forming

Beside the special series--wound mode of production from batch-type production to continuous production, the special driving fashion is included in this new type machine.[第一段]     

Experimental analysis of high temperature capacitance variance of MLCC

研究了多层片式瓷介电容器(MLCC)受高温时的容值变化。结合MLCC的特点,提出了其在引信中的使用方法,同时,讨论了温度稳定性对电子产品设计的影响。实验结果表明,低频MLCC的容值受温度影响较大。     

Inspection of fatigue defects in endurance testing of half-axles of maneuverable aircraft’s stabilizers by means of acoustic emission and tensometry

The results obtained by acoustic-emission (AE) testing and continuous tensometry in endurance testing of half-axles of maneuverable aircrafts stabilizers are described. In order to ensure the reliability of the tests, fractography of the fractures obtained is carried out along with metallographic studies of the materials structure in the zone of fracture nucleation and propagation.Translated from Defektoskopiya, Vol. 40, No. 9, 2004, pp. 3–10. Original Russian Text Copyright © 2004 by Sereznov, Maltsev, Stepanova, Kabanov, Chaplygin, Laznenko, Kareev, Kozhemyakin.     

Investigation of Electrical Characteristics of Thin Silicone–Carbon Coatings

The complex resistance of silicone–carbon films of thickness more than 3 m is measured on the basis of an analysis of the electrotechnical substitution circuit containing a capacitor and a resistor. It was found that the parameters of the equivalent circuit determined experimentally make it possible to estimate whether the film thickness is greater than 3 m or not, i.e., to measure the film thickness more than 3 m. In this case, at frequencies higher that 100 kHz only the capacitive component of the impedance can be measured, whereas the active component associated most likely with the presence of silicon carbide in the film material was detected at lower frequencies. It is shown that for carrying out similar experiments with thinner coatings it is necessary to use a probe covered by a dielectric material with the higher dielectric constant.