In order to improve measurement accuracy of moving target signals, an automatic target recognition model of moving target signals was established based on empirical mode decomposition(EMD) and support vector machine(S...In order to improve measurement accuracy of moving target signals, an automatic target recognition model of moving target signals was established based on empirical mode decomposition(EMD) and support vector machine(SVM). Automatic target recognition process on the nonlinear and non-stationary of Doppler signals of military target by using automatic target recognition model can be expressed as follows. Firstly, the nonlinearity and non-stationary of Doppler signals were decomposed into a set of intrinsic mode functions(IMFs) using EMD. After the Hilbert transform of IMF, the energy ratio of each IMF to the total IMFs can be extracted as the features of military target. Then, the SVM was trained through using the energy ratio to classify the military targets, and genetic algorithm(GA) was used to optimize SVM parameters in the solution space. The experimental results show that this algorithm can achieve the recognition accuracies of 86.15%, 87.93%, and 82.28% for tank, vehicle and soldier, respectively.展开更多
The stability and local bifurcation of a simply-supported flexible beam (Bernoulli- Euler type) carrying a moving mass and subjected to harmonic axial excitation are investigated. In the theoretical analysis, the pa...The stability and local bifurcation of a simply-supported flexible beam (Bernoulli- Euler type) carrying a moving mass and subjected to harmonic axial excitation are investigated. In the theoretical analysis, the partial differential equation of motion with the fifth-order nonlinear term is solved using the method of multiple scales (a perturbation technique). The stability and local bifurcation of the beam are analyzed for 1/2 sub harmonic resonance. The results show that some of the parameters, especially the velocity of moving mass and external excitation, affect the local bifurcation significantly. Therefore, these parameters play important roles in the system stability.展开更多
Considering the engineering background of some transportation system like maglev, vertical vibration of the simply supported beam is investigated. The length of the vehicle is assumed to be longer than the beam span. ...Considering the engineering background of some transportation system like maglev, vertical vibration of the simply supported beam is investigated. The length of the vehicle is assumed to be longer than the beam span. The model of moving distributed load with constant speed is established .The beam can be taken as Euler-Bernoulli beam model and the right side of the control equation is simplified by using a moving status function. Duhamel integral and mode superposition method is used to solve the dynamic behavior of the beam. In this aspect deflection and acceleration are included. The results of different parameters such as the span of beam, velocity of load and ratio vehicle-Beam masses are compared. All results show that the dynamic response of the beam is tied up with these factors: the frequency of the beam, the moving frequency of the load and the ratio of vehicle-beam mass.展开更多
In the present study, finite element dynamic analysis or time history analysis of two-span beams subjected to asynchronous multi-support motions is carried out by using the moving support finite element. The elemental...In the present study, finite element dynamic analysis or time history analysis of two-span beams subjected to asynchronous multi-support motions is carried out by using the moving support finite element. The elemental equation of the element is based on total displacements and is derived under the concept of the quasi-static displacement decomposition. The use of moving support element shows that the element is very simple and convenient to represent continuous beam moving, deforming and vibrating simultaneously due to support motions. The comparison between the numerical results and analytical solutions indicates that the FE result agrees with the analytical solution.展开更多
To locate and quantify local damage in a simply supported bridge, in this study, we derived a rotational-angle influence line equation of a simply supported beam model with local damage. Using the diagram multiplicati...To locate and quantify local damage in a simply supported bridge, in this study, we derived a rotational-angle influence line equation of a simply supported beam model with local damage. Using the diagram multiplication method, we introduce an analytical formula for a novel damage-identification indicator, namely the diff erence of rotational-angle influence linescurvature(DRAIL-C). If the initial stiff ness of the simply supported beam is known, the analytical formula can be effectively used to determine the extent of damage under certain circumstances. We determined the effectiveness and anti-noise performance of this new damage-identification method using numerical examples of a simply supported beam, a simply supported hollow-slab bridge, and a simply supported truss bridge. The results show that the DRAIL-C is directly proportional to the moving concentrated load and inversely proportional to the distance between the bridge support and the concentrated load and the distance between the damaged truss girder and the angle measuring points. The DRAIL-C indicator is more sensitive to the damage in a steel-truss-bridge bottom chord than it is to the other elements.展开更多
In this paper, a novel data mining method is introduced to solve the multi-objective optimization problems of process industry. A hyperrectangle association rule mining (HARM) algorithm based on support vector machi...In this paper, a novel data mining method is introduced to solve the multi-objective optimization problems of process industry. A hyperrectangle association rule mining (HARM) algorithm based on support vector machines (SVMs) is proposed. Hyperrectangles rules are constructed on the base of prototypes and support vectors (SVs) under some heuristic limitations. The proposed algorithm is applied to a simulated moving bed (SMB) paraxylene (PX) adsorption process. The relationships between the key process variables and some objective variables such as purity, recovery rate of PX are obtained. Using existing domain knowledge about PX adsorption process, most of the obtained association rules can be explained.展开更多
In compartment fires (houses, buildings, underground, warehouse, etc.), smokes are a major dan- ger during firemen intervention. Most of the time, they are at high temperature (>800?C) and they flow everywhere thro...In compartment fires (houses, buildings, underground, warehouse, etc.), smokes are a major dan- ger during firemen intervention. Most of the time, they are at high temperature (>800?C) and they flow everywhere through many kinds of ducts, which leads to the propagation of the combustion by the creation other fires in places which may be far away from the initial fire. In this paper, we present a new approach of the problem, which allows to better follow the fire behavior and especially to detect the dangers that may appear and endanger firefighters. This approach consists in a mathematical analysis based on the comparison of moving averages centered in the past, calculated on the temperature recordings of the smokes. As a consequence, this method may allow to improve decision support in real time and therefore to improve the security and the efficiency of firefighters in their operations against that kind of fires.展开更多
为提高光伏发电功率预测精度,提出一种基于外生因素及季节性的差分自回归移动平均SARIMAX(seasonal autoregressive integrated moving average with exogenous factors)并结合优化支持向量回归SVR(support vector regression)的光伏发...为提高光伏发电功率预测精度,提出一种基于外生因素及季节性的差分自回归移动平均SARIMAX(seasonal autoregressive integrated moving average with exogenous factors)并结合优化支持向量回归SVR(support vector regression)的光伏发电功率预测方法。首先,采用相关性特征法聚类气象条件中关键气象因子,以消除数据冗余并降低ARIMAX模型的复杂性;其次,在ARIMAX模型中引入季节性因素,构建SARIMAX模型来捕捉数据的季节性变化;最后,使用SARIMAX模型的拟合残差其作为SVR模型的输入,进一步拟合数据的非线性。通过仿真算例分析表明,所提方法可显著提高光伏发电功率预测精度。展开更多
基金Projects(61471370,61401479)supported by the National Natural Science Foundation of China
文摘In order to improve measurement accuracy of moving target signals, an automatic target recognition model of moving target signals was established based on empirical mode decomposition(EMD) and support vector machine(SVM). Automatic target recognition process on the nonlinear and non-stationary of Doppler signals of military target by using automatic target recognition model can be expressed as follows. Firstly, the nonlinearity and non-stationary of Doppler signals were decomposed into a set of intrinsic mode functions(IMFs) using EMD. After the Hilbert transform of IMF, the energy ratio of each IMF to the total IMFs can be extracted as the features of military target. Then, the SVM was trained through using the energy ratio to classify the military targets, and genetic algorithm(GA) was used to optimize SVM parameters in the solution space. The experimental results show that this algorithm can achieve the recognition accuracies of 86.15%, 87.93%, and 82.28% for tank, vehicle and soldier, respectively.
文摘The stability and local bifurcation of a simply-supported flexible beam (Bernoulli- Euler type) carrying a moving mass and subjected to harmonic axial excitation are investigated. In the theoretical analysis, the partial differential equation of motion with the fifth-order nonlinear term is solved using the method of multiple scales (a perturbation technique). The stability and local bifurcation of the beam are analyzed for 1/2 sub harmonic resonance. The results show that some of the parameters, especially the velocity of moving mass and external excitation, affect the local bifurcation significantly. Therefore, these parameters play important roles in the system stability.
文摘Considering the engineering background of some transportation system like maglev, vertical vibration of the simply supported beam is investigated. The length of the vehicle is assumed to be longer than the beam span. The model of moving distributed load with constant speed is established .The beam can be taken as Euler-Bernoulli beam model and the right side of the control equation is simplified by using a moving status function. Duhamel integral and mode superposition method is used to solve the dynamic behavior of the beam. In this aspect deflection and acceleration are included. The results of different parameters such as the span of beam, velocity of load and ratio vehicle-Beam masses are compared. All results show that the dynamic response of the beam is tied up with these factors: the frequency of the beam, the moving frequency of the load and the ratio of vehicle-beam mass.
文摘In the present study, finite element dynamic analysis or time history analysis of two-span beams subjected to asynchronous multi-support motions is carried out by using the moving support finite element. The elemental equation of the element is based on total displacements and is derived under the concept of the quasi-static displacement decomposition. The use of moving support element shows that the element is very simple and convenient to represent continuous beam moving, deforming and vibrating simultaneously due to support motions. The comparison between the numerical results and analytical solutions indicates that the FE result agrees with the analytical solution.
基金supported by the National Natural Science Foundation of China(Nos.51608245 and 51568041)Natural Science Foundation of Gansu Province(Nos.148RJZA026 and 2014GS02269)
文摘To locate and quantify local damage in a simply supported bridge, in this study, we derived a rotational-angle influence line equation of a simply supported beam model with local damage. Using the diagram multiplication method, we introduce an analytical formula for a novel damage-identification indicator, namely the diff erence of rotational-angle influence linescurvature(DRAIL-C). If the initial stiff ness of the simply supported beam is known, the analytical formula can be effectively used to determine the extent of damage under certain circumstances. We determined the effectiveness and anti-noise performance of this new damage-identification method using numerical examples of a simply supported beam, a simply supported hollow-slab bridge, and a simply supported truss bridge. The results show that the DRAIL-C is directly proportional to the moving concentrated load and inversely proportional to the distance between the bridge support and the concentrated load and the distance between the damaged truss girder and the angle measuring points. The DRAIL-C indicator is more sensitive to the damage in a steel-truss-bridge bottom chord than it is to the other elements.
基金Supported by the National Natural Science Foundation of China (No. 60421002)National Outstanding Youth Science Foundation of China (No. 60025308)the New Century 151 Talent Project of Zhejiang Province.
文摘In this paper, a novel data mining method is introduced to solve the multi-objective optimization problems of process industry. A hyperrectangle association rule mining (HARM) algorithm based on support vector machines (SVMs) is proposed. Hyperrectangles rules are constructed on the base of prototypes and support vectors (SVs) under some heuristic limitations. The proposed algorithm is applied to a simulated moving bed (SMB) paraxylene (PX) adsorption process. The relationships between the key process variables and some objective variables such as purity, recovery rate of PX are obtained. Using existing domain knowledge about PX adsorption process, most of the obtained association rules can be explained.
文摘In compartment fires (houses, buildings, underground, warehouse, etc.), smokes are a major dan- ger during firemen intervention. Most of the time, they are at high temperature (>800?C) and they flow everywhere through many kinds of ducts, which leads to the propagation of the combustion by the creation other fires in places which may be far away from the initial fire. In this paper, we present a new approach of the problem, which allows to better follow the fire behavior and especially to detect the dangers that may appear and endanger firefighters. This approach consists in a mathematical analysis based on the comparison of moving averages centered in the past, calculated on the temperature recordings of the smokes. As a consequence, this method may allow to improve decision support in real time and therefore to improve the security and the efficiency of firefighters in their operations against that kind of fires.
文摘为提高光伏发电功率预测精度,提出一种基于外生因素及季节性的差分自回归移动平均SARIMAX(seasonal autoregressive integrated moving average with exogenous factors)并结合优化支持向量回归SVR(support vector regression)的光伏发电功率预测方法。首先,采用相关性特征法聚类气象条件中关键气象因子,以消除数据冗余并降低ARIMAX模型的复杂性;其次,在ARIMAX模型中引入季节性因素,构建SARIMAX模型来捕捉数据的季节性变化;最后,使用SARIMAX模型的拟合残差其作为SVR模型的输入,进一步拟合数据的非线性。通过仿真算例分析表明,所提方法可显著提高光伏发电功率预测精度。