For the recognition of high-resolution range profile (HRRP) in radar, the weighted HRRP can reduce the instability of range cells caused by the attitude change of targets. A novel approach is proposed to optimize th...For the recognition of high-resolution range profile (HRRP) in radar, the weighted HRRP can reduce the instability of range cells caused by the attitude change of targets. A novel approach is proposed to optimize the weighted HRRP. In the approach, the separability of weighted HRRPs in different targets is measured by de- signing an objective function, and the weighted coefficients are computed by using the gradient descent method, thus enhancing the influence of stable range cells. Simulation results based on five aircraft models show that the approach can effectively optimize the weighted HRRP and improve the recognition accuracy.展开更多
A self-organizing radial basis function(RBF) neural network(SODM-RBFNN) was presented for predicting the production yields and operating optimization. Gradient descent algorithm was used to optimize the widths of RBF ...A self-organizing radial basis function(RBF) neural network(SODM-RBFNN) was presented for predicting the production yields and operating optimization. Gradient descent algorithm was used to optimize the widths of RBF neural network with the initial parameters obtained by k-means learning method. During the iteration procedure of the algorithm, the centers of the neural network were optimized by using the gradient method with these optimized width values. The computational efficiency was maintained by using the multi-threading technique. SODM-RBFNN consists of two RBF neural network models: one is a running model used to predict the product yields of fluid catalytic cracking unit(FCCU) and optimize its operating parameters; the other is a learning model applied to construct or correct a RBF neural network. The running model can be updated by the learning model according to an accuracy criterion. The simulation results of a five-lump kinetic model exhibit its accuracy and generalization capabilities, and practical application in FCCU illustrates its effectiveness.展开更多
A simplified approach is presented to analyze the single pile settlement in multilayered soil. First, a fictitious soil-pile model is employed to consider the effect of layered soil beneath pile toe on pile settlement...A simplified approach is presented to analyze the single pile settlement in multilayered soil. First, a fictitious soil-pile model is employed to consider the effect of layered soil beneath pile toe on pile settlement behavior. Two approximation methods are proposed to simplify the nonlinear load transfer function and simulate the nonlinear compression of fictitious soil-pile, respectively. On this basis, an efficient program is developed. The procedures for determining the main parameters of mathematical model are discussed. Comparisons with two well-documented field experimental pile loading tests are conducted to verify the rationality of the present method. Further studies are also made to evaluate the practicability of the proposed approach when a soft substratum exists, and the results suggest that the proposed method can provide a constructive means for assessing the settlement of a single pile for use in engineering design.展开更多
Falling film generation process in lithium bromide absorption refrigeration generation system is researched in thispaper. To describe the coupled heat and mass transfer of laminar falling film in vertical generation t...Falling film generation process in lithium bromide absorption refrigeration generation system is researched in thispaper. To describe the coupled heat and mass transfer of laminar falling film in vertical generation tube, a mathematicalmodel is developed, in which the effect of mass transfer on heat transfer is carefully evaluated. Moreover,an equation related Re number with solution volume flow was also obtained in given conditions. We carried outthe experiments with the mass fraction of the inlet solution LiBr being 49.5% and obtained an empirical correlationof heat transfer with the film Re number and heat flux in different volume flow. Specifically, when 5kW/m2<qw<25kW/m2 and Re<500 the heat transfer correlation is given as: h=14009.87qw0.0764Re-0.5391.展开更多
The forecasting of time-series data plays an important role in various domains. It is of significance in theory and application to improve prediction accuracy of the time-series data. With the progress in the study of...The forecasting of time-series data plays an important role in various domains. It is of significance in theory and application to improve prediction accuracy of the time-series data. With the progress in the study of time-series, time-series forecasting model becomes more complicated, and consequently great concern has been drawn to the techniques in designing the forecasting model. A modeling method which is easy to use by engineers and may generate good results is in urgent need. In this paper, a gradient-boost AR ensemble learning algorithm (AREL) is put forward. The effectiveness of AREL is assessed by theoretical analyses, and it is demonstrated that this method can build a strong predictive model by assembling a set of AR models. In order to avoid fitting exactly any single training example, an insensitive loss function is introduced in the AREL algorithm, and accordingly the influence of random noise is reduced. To further enhance the capability of AREL algorithm for non-stationary time-series, improve the robustness of algorithm, discourage overfitting, and reduce sensitivity of algorithm to parameter settings, a weighted kNN prediction method based on AREL algorithm is presented. The results of numerical testing on real data demonstrate that the proposed modeling method and prediction method are effective.展开更多
A crystal plasticity constitutive model of high-entropy alloys(HEAs)coupled with damage evolution equation at high temperature is developed.To simulate the degraded load-carrying capacity of HEAs caused by microdefect...A crystal plasticity constitutive model of high-entropy alloys(HEAs)coupled with damage evolution equation at high temperature is developed.To simulate the degraded load-carrying capacity of HEAs caused by microdefects,a phenomenological damage evolution equation is proposed based on the compression experiments at different temperatures.The established model is used to simulate the stress softening phenomenon of polycrystalline AlCrCuFeNi-based HEAs,which is highly dependent on the strain rate and temperature.Compared with the experimental data,the proposed model is able to accurately describe the stress-strain relationship of HEAs.展开更多
基金Supported by the Academician Foundation of the 14th Research Institute of China Electronics Technology Group Corporation(2008041001)~~
文摘For the recognition of high-resolution range profile (HRRP) in radar, the weighted HRRP can reduce the instability of range cells caused by the attitude change of targets. A novel approach is proposed to optimize the weighted HRRP. In the approach, the separability of weighted HRRPs in different targets is measured by de- signing an objective function, and the weighted coefficients are computed by using the gradient descent method, thus enhancing the influence of stable range cells. Simulation results based on five aircraft models show that the approach can effectively optimize the weighted HRRP and improve the recognition accuracy.
基金Projects(60974031,60704011,61174128)supported by the National Natural Science Foundation of China
文摘A self-organizing radial basis function(RBF) neural network(SODM-RBFNN) was presented for predicting the production yields and operating optimization. Gradient descent algorithm was used to optimize the widths of RBF neural network with the initial parameters obtained by k-means learning method. During the iteration procedure of the algorithm, the centers of the neural network were optimized by using the gradient method with these optimized width values. The computational efficiency was maintained by using the multi-threading technique. SODM-RBFNN consists of two RBF neural network models: one is a running model used to predict the product yields of fluid catalytic cracking unit(FCCU) and optimize its operating parameters; the other is a learning model applied to construct or correct a RBF neural network. The running model can be updated by the learning model according to an accuracy criterion. The simulation results of a five-lump kinetic model exhibit its accuracy and generalization capabilities, and practical application in FCCU illustrates its effectiveness.
基金Project(51378464) supported by the National Natural Science Foundation of China
文摘A simplified approach is presented to analyze the single pile settlement in multilayered soil. First, a fictitious soil-pile model is employed to consider the effect of layered soil beneath pile toe on pile settlement behavior. Two approximation methods are proposed to simplify the nonlinear load transfer function and simulate the nonlinear compression of fictitious soil-pile, respectively. On this basis, an efficient program is developed. The procedures for determining the main parameters of mathematical model are discussed. Comparisons with two well-documented field experimental pile loading tests are conducted to verify the rationality of the present method. Further studies are also made to evaluate the practicability of the proposed approach when a soft substratum exists, and the results suggest that the proposed method can provide a constructive means for assessing the settlement of a single pile for use in engineering design.
文摘Falling film generation process in lithium bromide absorption refrigeration generation system is researched in thispaper. To describe the coupled heat and mass transfer of laminar falling film in vertical generation tube, a mathematicalmodel is developed, in which the effect of mass transfer on heat transfer is carefully evaluated. Moreover,an equation related Re number with solution volume flow was also obtained in given conditions. We carried outthe experiments with the mass fraction of the inlet solution LiBr being 49.5% and obtained an empirical correlationof heat transfer with the film Re number and heat flux in different volume flow. Specifically, when 5kW/m2<qw<25kW/m2 and Re<500 the heat transfer correlation is given as: h=14009.87qw0.0764Re-0.5391.
基金supported by the National Natural Science Foundation of China (Grant No. 60974101)Program for New Century Talents of Education Ministry of China (Grant No. NCET-06-0828)
文摘The forecasting of time-series data plays an important role in various domains. It is of significance in theory and application to improve prediction accuracy of the time-series data. With the progress in the study of time-series, time-series forecasting model becomes more complicated, and consequently great concern has been drawn to the techniques in designing the forecasting model. A modeling method which is easy to use by engineers and may generate good results is in urgent need. In this paper, a gradient-boost AR ensemble learning algorithm (AREL) is put forward. The effectiveness of AREL is assessed by theoretical analyses, and it is demonstrated that this method can build a strong predictive model by assembling a set of AR models. In order to avoid fitting exactly any single training example, an insensitive loss function is introduced in the AREL algorithm, and accordingly the influence of random noise is reduced. To further enhance the capability of AREL algorithm for non-stationary time-series, improve the robustness of algorithm, discourage overfitting, and reduce sensitivity of algorithm to parameter settings, a weighted kNN prediction method based on AREL algorithm is presented. The results of numerical testing on real data demonstrate that the proposed modeling method and prediction method are effective.
基金the Shaanxi Science and Technology Innovation Team(Grant No.2022TD-05),Shaanxi“Sanqin Scholar”Innovation Team,and the Natural Science Basic Research Plan in Shaanxi Province of China(Grant No.2021JQ-077).
文摘A crystal plasticity constitutive model of high-entropy alloys(HEAs)coupled with damage evolution equation at high temperature is developed.To simulate the degraded load-carrying capacity of HEAs caused by microdefects,a phenomenological damage evolution equation is proposed based on the compression experiments at different temperatures.The established model is used to simulate the stress softening phenomenon of polycrystalline AlCrCuFeNi-based HEAs,which is highly dependent on the strain rate and temperature.Compared with the experimental data,the proposed model is able to accurately describe the stress-strain relationship of HEAs.