Search scope:
排序： Display mode:
Hui Liu, Zhihao Long, Zhu Duan, Huipeng Shi
Engineering 2020, Volume 6, Issue 8, Pages 944-956 doi: 10.1016/j.eng.2020.05.009
Particulate matter with an aerodynamic diameter no greater than 2.5 μm (PM2.5) concentration forecasting is desirable for air pollution early warning. This study proposes an improved hybrid model, named multi-feature clustering decomposition (MCD)–echo state network (ESN)–particle swarm optimization (PSO), for multi-step PM2.5 concentration forecasting. The proposed model includes decomposition and optimized forecasting components. In the decomposition component, an MCD method consisting of rough sets attribute reduction (RSAR), k-means clustering (KC), and the empirical wavelet transform (EWT) is proposed for feature selection and data classification. Within the MCD, the RSAR algorithm is adopted to select significant air pollutant variables, which are then clustered by the KC algorithm. The clustered results of the PM2.5 concentration series are decomposed into several sublayers by the EWT algorithm. In the optimized forecasting component, an ESN-based predictor is built for each decomposed sublayer to complete the multi-step forecasting computation. The PSO algorithm is utilized to optimize the initial parameters of the ESN-based predictor. Real PM2.5 concentration data from four cities located in different zones in China are utilized to verify the effectiveness of the proposed model. The experimental results indicate that the proposed forecasting model is suitable for the multi-step high-precision forecasting of PM2.5 concentrations and has better performance than the benchmark models.
Keywords： PM2.52.5浓度预测 PM2.52.5浓度聚类 经验小波分解 多步预测
A Method for License Plate Localization based on Texture and Wavelet Analysis
Huang Wei,Lu Xiaobo,Yu Yanxiang,Ling Xiaojing
Strategic Study of CAE 2004, Volume 6, Issue 3, Pages 19-24
This paper presents a method for vehicle license plate localization using texture and wavelet analysis. In view of the complex background and the small ratio of the license plate area to the whole picture, a method for finding a threshold for primitive classification is proposed. According to the distribution regularities of the characters in the license plate, a binary texture primitive analysis method is presented to extract the candidate license plate areas. A feature of the vertical strokes in the license plate is extracted using wavelet analysis. The feature of the vertical strokes, position feature and shape feature are quantificationally evaluated using membership degree, and a method for selecting the license plate area from the candidates by integrating all the features is described. A test shows that the proposed method offers a localization correctness rate of higher than 96% .
Keywords： texture wavelet analysis primitive license plate localization
Noise Reduction of Vibration Signal of Cyclic Machine Based on the EMD
Yang Jianwen,Jia Minping,Xu Feiyun,Hu Jianzhong
Strategic Study of CAE 2005, Volume 7, Issue 8, Pages 66-69
The filtering property of empirical mode decomposition is analyzed in the paper. Aimed at the low signal/noise ratio and non stationary feature of vibration signal of cyclic machine, EMD is introduced to the noise reduction of vibration signal and the useful signal is given prominence efficiently, which offers the more efficient foundation to monitor on line and fault diagnosis of cyclic machine. By the simulation and application, it shows that EMD is very useful in reducing noise and provides new means of vibration signal analyzing.
Keywords： fault diagnosis empirical mode decomposition cyclic machine filter
Wavelet Analysis of a Sort of Multidimension Stochastic System
Xia Xuewen
Strategic Study of CAE 2004, Volume 6, Issue 11, Pages 43-46
In this paper, a linear stochastic systeme 
is studied, using wavelet analysis and its average power, density degree and wavelet expansion and corelation of expansion coefficient are obtained.
Keywords： stochastic system density degree wavelet expansion average power corelation
Analysis on the Machined Surface Profile Error Using Fractals and Wavelet
Liao Xiaoyun,Tang Qian,Zhao Ying,Zheng Shize
Strategic Study of CAE 2002, Volume 4, Issue 5, Pages 75-78
An analysis method based on fractals and wavelet for machined surface profile error was presented. It can be employed to analyze the machined surface in details, and reconstruct the surface profile for doing some related work, such as performance-tolerance analysis and process quality control. The fractal dimension algorithms, the analysis and reconstruction algorithms of surface profile based on wavelets theories were developed. The given example showed that this method and related algorithms were very effective.
Keywords： machining machined error analysis fractal geometry wavelet analysis
Summary and Analysis on the Ecological Civilization Experiences Domestic and Abroad
Yue Bo,Wu Xiaohui,Huang Qifei,Zhang Linbo
Strategic Study of CAE 2015, Volume 17, Issue 8, Pages 151-158
Since the 1960s, facing to a serious threat of environmental pollution, ecological destruction, survival crisis, the Western countries has carried out a long-lasting work, such as the legal system establishment for ecological protection, environmental and economic policy setting up, the low-carbon green circular economy mode founding, ecological protection awareness training and industrial structure upgrading, etc., which have achieved remarkable progress. Since the middle and late 20th century, China has focused on the construction and protection of ecological environment. In the 18th National Congress of the Communist Party of China, ecological civilization construction has been brought into the “Five in One” overall plan of socialist construction with Chinese characteristics. Since then, the ecological civilization has risen from the academic level to the government’s policy agenda and national philosophy. In further promoting of ecological civilization construction, the following points should be important, which are to learn the ideological essence from ancient ecology, to comprehensively promote the institutional mechanism reform, to strengthen enforcement of the ecological and environmental protection law, to actively found the complex capital for ecological civilization construction, to vigorously promote industrial structure adjustment and upgrading, and to attach great importance to the people’s ecological civilization quality education.
Keywords： ecological civilization home and abroad experience summary suggestion prospect
Hui Liu, Rui Yang, Zhu Duan, Haiping Wu
Engineering 2021, Volume 7, Issue 12, Pages 1751-1765 doi: 10.1016/j.eng.2020.10.023
Dissolved oxygen (DO) is an important indicator of aquaculture, and its accurate forecasting can effectively improve the quality of aquatic products. In this paper, a new DO hybrid forecasting model is proposed that includes three stages: multi-factor analysis, adaptive decomposition, and an optimization-based ensemble. First, considering the complex factors affecting DO, the grey relational (GR) degree method is used to screen out the environmental factors most closely related to DO. The consideration of multiple factors makes model fusion more effective. Second, the series of DO, water temperature, salinity, and oxygen saturation are decomposed adaptively into sub-series by means of the empirical wavelet transform (EWT) method. Then, five benchmark models are utilized to forecast the sub-series of EWT decomposition. The ensemble weights of these five sub-forecasting models are calculated by particle swarm optimization and gravitational search algorithm (PSOGSA). Finally, a multi-factor ensemble model for DO is obtained by weighted allocation. The performance of the proposed model is verified by time-series data collected by the pacific islands ocean observing system (PacIOOS) from the WQB04 station at Hilo. The evaluation indicators involved in the experiment include the nash-sutcliffe efficiency (NSE), kling-gupta efficiency (KGE), mean absolute percent error (MAPE), standard deviation of error (SDE), and coefficient of determination (R2). Example analysis demonstrates that: ① the proposed model can obtain excellent DO forecasting results; ② the proposed model is superior to other comparison models; and ③ the forecasting model can be used to analyze the trend of DO and enable managers to make better management decisions.
Keywords： Dissolved oxygen concentrations forecasting Time-series multi-step forecasting Multi-factor analysis Empirical wavelet transform decomposition Multi-model optimization ensemble
Level-direction decomposition analysis with a focus on image watermarking framework Article
M. F. KAZEMI,M. A. POURMINA,A. H. MAZINAN
Frontiers of Information Technology & Electronic Engineering 2016, Volume 17, Issue 11, Pages 1199-1217 doi: 10.1631/FITEE.1500165
Keywords： Level-direction decomposition analysis Watermarking framework Contourlet embedding representation Scrambling module Simulated attacks
Long Zhenhai,Wang Xibin,Wang Haochen
Strategic Study of CAE 2004, Volume 6, Issue 10, Pages 28-31
Factorials experiment and velocity single-factor experiment are applied in the dry high-speed milling experiments of Martensitic stainless steel 2Crl3, which is used in aerospace industry. Based on the analysis of cutting regimes, influences on milling force, the spectrum analysis and wavelet analysis are applied on the random cutting force signals. This study shows that in high speed milling of Martensitic stainless process, the interaction of depth of cut and feed per tooth has significant effect on the cutting force; the interaction of feed per tooth and depth of cut introduces a lower frequency periodic signal; this low frequency signal coupled with high frequency signal could remarkably increase the amplitude of cutting force signals.
Keywords： difficult-to-cut materials high speed machining factorials design Meyer wavelet transform Mallat algorithm
Online Monitoring of Welding Status Based on a DBN Model During Laser Welding Article
Yanxi Zhang, Deyong You, Xiangdong Gao, Seiji Katayama
Engineering 2019, Volume 5, Issue 4, Pages 671-678 doi: 10.1016/j.eng.2019.01.016
In this research, an auxiliary illumination visual sensor system, an ultraviolet/visible (UVV) band visual sensor system (with a wavelength less than 780 nm), a spectrometer, and a photodiode are employed to capture insights into the high-power disc laser welding process. The features of the visible optical light signal and the reflected laser light signal are extracted by decomposing the original signal captured by the photodiode via the wavelet packet decomposition (WPD) method. The captured signals of the spectrometer mainly have a wavelength of 400–900 nm, and are divided into 25 sub-bands to extract the spectrum features by statistical methods. The features of the plume and spatters are acquired by images captured by the UVV visual sensor system, and the features of the keyhole are extracted from images captured by the auxiliary illumination visual sensor system. Based on these real-time quantized features of the welding process, a deep belief network (DBN) is established to monitor the welding status. A genetic algorithm is applied to optimize the parameters of the proposed DBN model. The established DBN model shows higher accuracy and robustness in monitoring welding status in comparison with a traditional back-propagation neural network (BPNN) model. The effectiveness and generalization ability of the proposed DBN are validated by three additional experiments with different welding parameters.
Keywords： Online monitoring Multiple sensors Wavelet packet decomposition Deep belief network
Three-dimensional localization of near-field and strictly noncircular sources using steering vector decomposition Research Article
Zheng LI, Jinqing SHEN, Xiaofei ZHANG,lizhengjsnj@163.com,zhangxiaofei@nuaa.edu.cn
Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 4, Pages 644-652 doi: 10.1631/FITEE.2100034
Keywords： Localization Centro-symmetric cross array Noncircular sources Near-field Steering vector decomposition
Lian Jijian,Tian Huijing,Qin Liang,Zhang Yongji
Strategic Study of CAE 2006, Volume 8, Issue 4, Pages 72-75
During running process, the effect of dynamic loads is quite complex. So determining dynamic characteristics of supporting structure are of great importance when making hydro plant's dynamic analysis. However, conventional testing measures often cause intensive destruction or are too complicated to implement. In order to solving above problems，this paper，basing on principle of dynamics, applies the test data to analyze the structure vibration and variability of loads during machine halting process，and further puts forward a new method to identify dynamic characteristics of hydro plants supporting structure using machine halting process. The test data comes from prototype observation in Lijiaxia's power house structure of two-row placed units. The method, combining unit test and structure test result, and fully using advantage of wavelet analysis, successfully overcomes poor factor like long variation time of loads，vibration fluctuation，etc.,when analyzing halting problem.
Keywords： supporting structure of power house machine halting process dynamic characteristics wavelet analysis
Application of Wavelet Transform to Acoustic Radiation and Scattering
Wen Lihua,Ren Xingmin
Strategic Study of CAE 2002, Volume 4, Issue 8, Pages 63-68
Traditional boundary element methods with a full matrix equation for acoustic problems, have been met by a challenge in large-scale scientific computation and numerical simulation in engineering. In this paper, the new wavelet approaches have been presented for solving acoustic radiation and scattering, and structural-acoustic coupling. The boundary quantities are expanded in terms of a basis of the orthogonal wavelets on the interval, and a wavelet spectral formulation for solving acoustic problems is derived. Then coupled wavelet spectral and finite element method is formulated for solving sound-structure interaction. The advantages of the new approaches include a highly sparse matrix system which can be solved rapidly by sparse solvers and accurate modeling of curve surface. In the new technique, the iterative technique of frequencies is established for evaluating frequency-response functions through expanding the integral kernel in Taylor series in integral equation. The new technique was employed to investigate the underwater acoustic radiation from a complicate structure which is composed of shells, stiffening ribs and plates. The comparisons of the results from the new technique with analytic solution show that it has high computational efficiency and good accuracy.
At the end of the paper, the prospects of the application of wavelet analysis to numerical computation in acoustic engineering are discussed.
Keywords： wavelet analysis acoustic radiation and scattering structural-acoustic coupling frequency iteration
Experiences and Lessons From the Construction of Erlang Shan Tunnel
Zheng Daofang
Strategic Study of CAE 2000, Volume 2, Issue 1, Pages 62-67
Erlangshan Mountain lies at the contiguous area of Tianquan county, Ya´an Prefecture, Sichuan Province and Luding County, Ganzi Zang Autonomous State. The Erlangshan mountainous area with complicated geology and dangerously steep mountains is characterized by harsh weather such as storm, heavy fog, snow, ice, strong wind and various frequently occuring natural disasters, such as landslide, rock falling and debris flow, and therefore the highway in this area is low in standard and poor in condition, resulting in serious traffic jam and frequent accidents, which threaten the safety of traffic. This paper describes the scheme study of disease countermeasures on the Erlangshan section of Sichuan - Tibet Highway and the project comparison of line alternatives, and presents the reasons of building a tunnel in the area, the tunnel alignment and the problems occurred in the construction. The dialectical relationships between a tunnel and its linking works, between a key project and an ordinary project are profoundly analyzed and the related experinences and lessons are also summarized, which will enlighten both the organizers and the designers on the construction of a project.
Keywords： Erlangshan tunnel construction experiences
Thermodynamic study for the separation of tritium by CECE method from heavy water
Zhu Zhenghe,Fu Yibei,Sun Ying,Wang Xiaolin,Luo Yangming,Luo Wenlang,Hu Sheng,Ruan Wen
Strategic Study of CAE 2008, Volume 10, Issue 5, Pages 19-24
The present work makes a contribution to thermodynamic study for the separation of tritium by CECE method from D2-heavy water involving tritium.The reversible decomposition voltages of H2O,HDO,D2O,DTO and T2O have been calculated and the difference of decomposition voltage for H2O andT2O is 0.047 V. Therefore,the electrolytic volt of heavy water must be less 0.047 V than that of H2O. The functional relations of vapor pressure and vaporization heat with temperature from 0~100 ℃ for these five kinds of hydrogen-isotope water are derived. The equilibrium constants for reaction (19-1) and reaction (19-2) are also evaluated and both are quite small. Therefore,it is impossible to realize the two reactions in static system,however,it is possible to realize them in flow system. The most disadvantage for CECE method is the rather poor selectivity,the exploration is try to under way.
Keywords： separation of tritium CECE method thermodynamic reversible decomposition voltage
Title Author Date Type Operation
A New Model Using Multiple Feature Clustering and Neural Networks for Forecasting Hourly PM2.5 Concentrations, and Its Applications in China
Hui Liu, Zhihao Long, Zhu Duan, Huipeng Shi
Journal Article
A Method for License Plate Localization based on Texture and Wavelet Analysis
Huang Wei,Lu Xiaobo,Yu Yanxiang,Ling Xiaojing
Journal Article
Noise Reduction of Vibration Signal of Cyclic Machine Based on the EMD
Yang Jianwen,Jia Minping,Xu Feiyun,Hu Jianzhong
Journal Article
Analysis on the Machined Surface Profile Error Using Fractals and Wavelet
Liao Xiaoyun,Tang Qian,Zhao Ying,Zheng Shize
Journal Article
Summary and Analysis on the Ecological Civilization Experiences Domestic and Abroad
Yue Bo,Wu Xiaohui,Huang Qifei,Zhang Linbo
Journal Article
A Hybrid Neural Network Model for Marine Dissolved Oxygen Concentrations Time-Series Forecasting Based on Multi-Factor Analysis and a Multi-Model Ensemble
Hui Liu, Rui Yang, Zhu Duan, Haiping Wu
Journal Article
Level-direction decomposition analysis with a focus on image watermarking framework
M. F. KAZEMI,M. A. POURMINA,A. H. MAZINAN
Journal Article
Study on the Nonlinear Characteristics of Cutting Forces in High-speed Face-milling of Difficult-to-cut Materials by AR Spectrum Analysis and Wavelet Analysis
Long Zhenhai,Wang Xibin,Wang Haochen
Journal Article
Online Monitoring of Welding Status Based on a DBN Model During Laser Welding
Yanxi Zhang, Deyong You, Xiangdong Gao, Seiji Katayama
Journal Article
Three-dimensional localization of near-field and strictly noncircular sources using steering vector decomposition
Zheng LI, Jinqing SHEN, Xiaofei ZHANG,lizhengjsnj@163.com,zhangxiaofei@nuaa.edu.cn
Journal Article
The Method to Identify Dynamic Characteristics of Hydro Plant's Supporting Structure Using Machine Halting Process
Lian Jijian,Tian Huijing,Qin Liang,Zhang Yongji
Journal Article
Application of Wavelet Transform to Acoustic Radiation and Scattering
Wen Lihua,Ren Xingmin
Journal Article
京公网安备 11010502051620号
