This paper presents a new approach to synthesize admittance function polynomials and coupling matrices for coupled resonator filters. The N + 2 transversal network method is applied to study a coupled resonator f...This paper presents a new approach to synthesize admittance function polynomials and coupling matrices for coupled resonator filters. The N + 2 transversal network method is applied to study a coupled resonator filter. This method allowed us to determine the polynomials of the reflection and transmission coefficients. A study is made for a 4 poles filter with 2 transmission zeros between the N + 2 transversal network method and the one found in the literature. A MATLAB code was designed for the numerical simulation of these coefficients for the 6, 8, and 10 pole filter with 4 transmission zeros.展开更多
High-speed trains often use temperature sensors to monitor the motion state of bearings.However,the temperature of bearings can be affected by factors such as weather and faults.Therefore,it is necessary to analyze in...High-speed trains often use temperature sensors to monitor the motion state of bearings.However,the temperature of bearings can be affected by factors such as weather and faults.Therefore,it is necessary to analyze in detail the relationship between the bearing temperature and influencing factors.In this study,a dynamics model of the axle box bearing of high-speed trains is established.The model can obtain the contact force between the rollers and raceway and its change law when the bearing contains outer-ring,inner-ring,and rolling-element faults.Based on the model,a thermal network method is introduced to study the temperature field distribution of the axle box bearings of high-speed trains.In this model,the heat generation,conduction,and dispersion of the isothermal nodes can be solved.The results show that the temperature of the contact point between the outer-ring raceway and rolling-elements is the highest.The relationships between the node temperature and the speed,fault type,and fault size are analyzed,finding that the higher the speed,the higher the node temperature.Under different fault types,the node temperature first increases and then decreases as the fault size increases.The effectiveness of the model is demonstrated using the actual temperature data of a high-speed train.This study proposes a thermal network model that can predict the temperature of each component of the bearings on a high-speed train under various speed and fault conditions.展开更多
Superconductive properties for oxides were predicted by artificial neural network (ANN) method with structural and chemical parameters as inputs. The predicted properties include superconductivity for oxides, distribu...Superconductive properties for oxides were predicted by artificial neural network (ANN) method with structural and chemical parameters as inputs. The predicted properties include superconductivity for oxides, distributed ranges of the superconductive transition temperature (Tc) for complex oxides, and Tc values for cuprate superconductors. The calculated results indicated that the adjusted ANN can be used to predict superconductive properties for unknown oxides.展开更多
Tsunami ran-up height is a significant parameter for dimensions of coastal structures. In the present study, tsunami run-up heights are estimated by three different Artificial Neural Network （ANN） models, i.e. Feed ...Tsunami ran-up height is a significant parameter for dimensions of coastal structures. In the present study, tsunami run-up heights are estimated by three different Artificial Neural Network （ANN） models, i.e. Feed Forward Back Propagation （FFBP）, Radial Basis Functions （RBF） and Generalized Regression Neural Network （GRNN）. As the input for the ANN configuration, the wave height （H） values are employed. It is shown that the tsunami ran-up height values are closely approximated with all of the applied ANN methods. The ANN estimations are slightly superior to those of the empirical equation. It can be seen that the ANN applications are especially significant in the absence of adequate number of laboratory experiments. The results also prove that the available experiment data set can be extended with ANN simulations. This may be helpful to decrease the burden of the experimental studies and to supply results for comparisons.展开更多
In this paper,an approach is developed to optimize the quality of the training samples in the conventional Artificial Neural Network(ANN)by incorporating expert knowledge in the means of constructing expert-rule sampl...In this paper,an approach is developed to optimize the quality of the training samples in the conventional Artificial Neural Network(ANN)by incorporating expert knowledge in the means of constructing expert-rule samples from rules in an expert system,and through training by using these samples,an ANN based on expert-knowledge is further developed.The method is introduced into the field of quantitative identification of potential seismic sources on the basis of the rules in an expert system.Then it is applied to the quantitative identification of the potential seismic sources in Beijing and its adjacent area.The result indicates that the expert rule based on ANN method can well incorporate and represent the expert knowledge in the rules in an expert system,and the quality of the samples and the efficiency of training and the accuracy of the result are optimized.展开更多
Because the main failure type of a dangerous rock mass is collapse, the treatment of such a mass should focus on controlling collapse failure. When treating dangerous rock masses, disturbing the mass （e. g. by blast...Because the main failure type of a dangerous rock mass is collapse, the treatment of such a mass should focus on controlling collapse failure. When treating dangerous rock masses, disturbing the mass （e. g. by blasting） needs to be avoided, as this new damage could cause collapse. So the self-bearing capacity of the mountain mass must be used to treat the dangerous rock mass. This article is based on a practical example of the control of a dangerous rock mass at Banyan Mountain, Huangshi, Hubei Province. On the basis of an analysis of damage mechanism and the stability of the dangerous rock mass, a flexible network reinforcement method was designed to prevent the collapse of the rock mass. The deformations of section Ⅱ w of the dangerous rock mass before and after the flexible network reinforcement were calculated using the two-dimensional finite element method. The results show that the maximum deformation reduced by 55 % after the application of the flexible network reinforcement, from 45.99 to 20.75 ram, which demonstrates that the flexible network method is effective, and can provide some scientific basis for the treatment of dangerous rock masses.展开更多
BACKGROUND The prevalence and severity of noncommunicable chronic diseases(NCDs)among Chinese residents have been increasing with mental health emerging as a critical challenge in disease management.AIM To examine the...BACKGROUND The prevalence and severity of noncommunicable chronic diseases(NCDs)among Chinese residents have been increasing with mental health emerging as a critical challenge in disease management.AIM To examine the interactions between depression,anxiety symptoms,and related factors,and to identify key factors in the Chinese population with NCDs.METHODS Data from the Psychology and Behavior Investigation of Chinese Residents were used in a cross-sectional survey of 6182 individuals with NCDs.This study measured depression and anxiety symptoms as well as their influencing factorsincluding social environments,individual behaviors and lifestyles,and subjective indicators.A network analysis approach was used for data assessment.RESULTS Network analysis demonstrated that several central factors(media exposure,family health,problematic internet use,suboptimal health status,intimate relationship violence,tired or little energy,and nervousness/anxious/on edge)and bridge factors(media exposure,problematic internet use,intimate partner violence,health literacy,and suboptimal health status)that significantly influenced the co-occurrence and interconnectedness of depression and anxiety symptoms.Additionally,gender,ethnicity,residency,and living status did not significantly influence the overall network strength.CONCLUSION Depression and anxiety are prevalent among the Chinese population with NCDs.Effective interventions should focus on managing key symptoms,promoting correct media use for health information,and fostering healthier family relationships.展开更多
This paper extends a method, called bilinear neural network method(BNNM), to solve exact solutions to nonlinear partial differential equation. New, test functions are constructed by using this method. These test funct...This paper extends a method, called bilinear neural network method(BNNM), to solve exact solutions to nonlinear partial differential equation. New, test functions are constructed by using this method. These test functions are composed of specific activation functions of single-layer model,specific activation functions of "2-2" model and arbitrary functions of "2-2-3" model. By means of the BNNM, nineteen sets of exact analytical solutions and twenty-four arbitrary function solutions of the dimensionally reduced p-gB KP equation are obtained via symbolic computation with the help of Maple. The fractal solitons waves are obtained by choosing appropriate values and the self-similar characteristics of these waves are observed by reducing the observation range and amplifying the partial picture. By giving a specific activation function in the single layer neural network model, exact periodic waves and breathers are obtained. Via various three-dimensional plots, contour plots and density plots,the evolution characteristic of these waves are exhibited.展开更多
The network method for modeling thermoacoustic engines is described. Some simulation results on acoustic fields and phases in engine, especially in the thermoacoustic stack are presented and analyzed. The effects of s...The network method for modeling thermoacoustic engines is described. Some simulation results on acoustic fields and phases in engine, especially in the thermoacoustic stack are presented and analyzed. The effects of some key factors on performance of stack and engine system are simulated and discussed. These effect factors include the spaces of plates of stack, the position of stack in engine system, the source parameter of stack, and the mean working pressure of the engine system.展开更多
The simulation for particle or soliton propagation based on linear or nonlinear Schrodinger equations on unbounded domains requires the computational domain to be bounded,and therefore,a special boundary treatment suc...The simulation for particle or soliton propagation based on linear or nonlinear Schrodinger equations on unbounded domains requires the computational domain to be bounded,and therefore,a special boundary treatment such as an absorbing boundary condition(ABC)or a perfectly matched layer(PML)is needed so that the reflections of outgoing waves at the boundary can be minimized in order to prevent the destruction of the simulation.This article presents a new artificial neural network(ANN)method for solving linear and nonlinear Schrodinger equations on unbounded domains.In particular,this method randomly selects training points only from the bounded computational space-time domain,and the loss function involves only the initial condition and the Schrodinger equation itself in the computational domainwithout any boundary conditions.Moreover,unlike standard ANNmethods that calculate gradients using expensive automatic differentiation,this method uses accurate finitedifference approximations for the physical gradients in the Schrodinger equation.In addition,a Metropolis-Hastings algorithm is implemented for preferentially selecting regions of high loss in the computational domain allowing for the use of fewer training points in each batch.As such,the present training method uses fewer training points and less computation time for convergence of the loss function as compared with the standard ANN methods.This new ANN method is illustrated using three examples.展开更多
We present VPVnet,a deep neural network method for the Stokes’equa-tions under reduced regularity.Different with recently proposed deep learning meth-ods[40,51]which are based on the original form of PDEs,VPVnet uses...We present VPVnet,a deep neural network method for the Stokes’equa-tions under reduced regularity.Different with recently proposed deep learning meth-ods[40,51]which are based on the original form of PDEs,VPVnet uses the least square functional of thefirst-order velocity-pressure-vorticity(VPV)formulation([30])as loss functions.As such,onlyfirst-order derivative is required in the loss functions,hence the method is applicable to a much larger class of problems,e.g.problems with non-smooth solutions.Despite that several methods have been proposed recently to reduce the regularity requirement by transforming the original problem into a corresponding variational form,while for the Stokes’equations,the choice of approximating spaces for the velocity and the pressure has to satisfy the LBB condition additionally.Here by making use of the VPV formulation,lower regularity requirement is achieved with no need for considering the LBB condition.Convergence and error estimates have been established for the proposed method.It is worth emphasizing that the VPVnet method is divergence-free and pressure-robust,while classical inf-sup stable mixedfinite elements for the Stokes’equations are not pressure-robust.Various numerical experiments including 2D and 3D lid-driven cavity test cases are conducted to demon-strate its efficiency and accuracy.展开更多
In this paper, we made a new breakthrough, which proposes a new recursion–transform（RT） method with potential parameters to evaluate the nodal potential in arbitrary resistor networks. For the first time, we found ...In this paper, we made a new breakthrough, which proposes a new recursion–transform（RT） method with potential parameters to evaluate the nodal potential in arbitrary resistor networks. For the first time, we found the exact potential formulae of arbitrary m × n cobweb and fan networks by the RT method, and the potential formulae of infinite and semi-infinite networks are derived. As applications, a series of interesting corollaries of potential formulae are given by using the general formula, the equivalent resistance formula is deduced by using the potential formula, and we find a new trigonometric identity by comparing two equivalence results with different forms.展开更多
A new analytical method using Back-Propagation (BP) artificial neural network and kinetic spectrophotometry for simultaneous determination of iron and magnesium in tap water, the Yellow River water and seawater is est...A new analytical method using Back-Propagation (BP) artificial neural network and kinetic spectrophotometry for simultaneous determination of iron and magnesium in tap water, the Yellow River water and seawater is established. By conditional experiments, the optimum analytical conditions and parameters are obtained. Levenberg-Marquart (L-M) algorithm is used for calculation in BP neural network. The topological structure of three-layer BP ANN network architecture is chosen as 15-16-2 (nodes). The initial value of gradient coefficient μ is fixed at 0.001 and the increase factor and reduction factor of μ take the default values of the system. The data are processed by computers with our own programs written in MATLAB 7.0. The relative standard deviation of the calculated results for iron and manganese is 2.30% and 2.67% respectively. The results of standard addition method show that for the tap water, the recoveries of iron and manganese are in the ranges of 98.0%-104.3% and 96.5%-104.5%, and the RSD is in the range of 0.23%-0.98%; for the Yellow River water (Lijin district of Shandong Province), the recoveries of iron and manganese are in the ranges of 96.0%-101.0% and 98.7%-104.2%, and the RSD is in the range of 0.13%-2.52%; for the seawater in Qingdao offshore, the recoveries of iron and manganese are in the ranges of 95.3%-104.8% and 95.3%-104.7%, and the RSD is in the range of 0.14%-2.66%. It is found that 21 common cations and anions do not interfere with the determination of iron and manganese under the optimum experimental conditions. This method exhibits good reproducibility and high accuracy in the determination of iron and manganese and can be used for the simultaneous determination of iron and manganese in tap water and natural water. By using the established ANN- catalytic spectrophotometric method, the iron and manganese concentrations of the surface seawater at 11 sites in Qingdao offshore are determined and the level distribution maps of iron and manganese are drawn.展开更多
BP neural networks is used to mid-term earthquake prediction in this paper. Some usual prediction parameters of seismology are used as the import units of neural networks. And the export units of neural networks is ca...BP neural networks is used to mid-term earthquake prediction in this paper. Some usual prediction parameters of seismology are used as the import units of neural networks. And the export units of neural networks is called as the character parameter W_0 describing enhancement of seismicity. We applied this method to space scanning of North China. The result shows that the mid-term anomalous zone of W_0-value usually appeared obviously around the future epicenter 1~3 years before earthquake. It is effective to mid-term prediction.展开更多
Aiming at the reliability analysis of small sample data or implicit structural function,a novel structural reliability analysis model based on support vector machine(SVM)and neural network direct integration method(DN...Aiming at the reliability analysis of small sample data or implicit structural function,a novel structural reliability analysis model based on support vector machine(SVM)and neural network direct integration method(DNN)is proposed.Firstly,SVM with good small sample learning ability is used to train small sample data,fit structural performance functions and establish regular integration regions.Secondly,DNN is approximated the integral function to achieve multiple integration in the integration region.Finally,structural reliability was obtained by DNN.Numerical examples are investigated to demonstrate the effectiveness of the present method,which provides a feasible way for the structural reliability analysis.展开更多
This paper presents an artificial neural network（ANN）-based response surface method that can be used to predict the failure probability of c-φslopes with spatially variable soil.In this method,the Latin hypercube s...This paper presents an artificial neural network（ANN）-based response surface method that can be used to predict the failure probability of c-φslopes with spatially variable soil.In this method,the Latin hypercube sampling technique is adopted to generate input datasets for establishing an ANN model;the random finite element method is then utilized to calculate the corresponding output datasets considering the spatial variability of soil properties;and finally,an ANN model is trained to construct the response surface of failure probability and obtain an approximate function that incorporates the relevant variables.The results of the illustrated example indicate that the proposed method provides credible and accurate estimations of failure probability.As a result,the obtained approximate function can be used as an alternative to the specific analysis process in c-φslope reliability analyses.展开更多
Feedforward multi layer neural networks have very strong mapping capability that is based on the non linearity of the activation function, however, the non linearity of the activation function can cause the multiple ...Feedforward multi layer neural networks have very strong mapping capability that is based on the non linearity of the activation function, however, the non linearity of the activation function can cause the multiple local minima on the learning error surfaces, which affect the learning rate and solving optimal weights. This paper proposes a learning method linearizing non linearity of the activation function and discusses its merits and demerits theoretically.展开更多
Fusion and fission are two important phenomena that have been experimentally observed in many real physical models.In this paper,we investigate the two phenomena in the(2+1)-dimensional Hirota-Satsuma-Ito equation via...Fusion and fission are two important phenomena that have been experimentally observed in many real physical models.In this paper,we investigate the two phenomena in the(2+1)-dimensional Hirota-Satsuma-Ito equation via the physics-informed neural networks(PINN)method.By choosing suitable physically constrained initial boundary conditions,the data-driven fusion and fission solutions are obtained for the first time.Dynamical behaviors and error analysis of these solutions are investigated via illustratively numerical figures,which show that good results are achieved.It is pointed out that the PINN method adopted here can be effectively used to construct the data-driven fusion and fission solutions for other nonlinear integrable equations.Based on the powerful predictive capability of the PINN method and wide applications of fusion and fission in many physical areas,it is hoped that the data-driven solutions obtained here will be helpful for experts to predict or explain related physical phenomena.展开更多
The identification of the influential nodes in a network is of great significance for understanding the features of the network and controlling the complexity of networks in society and in biology. In this paper, we ...The identification of the influential nodes in a network is of great significance for understanding the features of the network and controlling the complexity of networks in society and in biology. In this paper, we propose a novel centrality measure for a node by considering the importance of edges and compare the performance of this method with existing seven topological-based ranking methods on the Susceptible-Infected-Recovered （SIR） model. The simulation results for four different types of real networks show that the proposed method is robust and exhibits excellent performance in identifying the most influential nodes when spreading starting from both single origin and multipleorigins simultaneously.展开更多
In this paper,we propose a local fuzzy method based on the idea of ＂p-strong＂ community to detect the disjoint and overlapping communities in networks.In the method,a refined agglomeration rule is designed for agglo...In this paper,we propose a local fuzzy method based on the idea of ＂p-strong＂ community to detect the disjoint and overlapping communities in networks.In the method,a refined agglomeration rule is designed for agglomerating nodes into local communities,and the overlapping nodes are detected based on the idea of making each community strong.We propose a contribution coefficient bvcito measure the contribution of an overlapping node to each of its belonging communities,and the fuzzy coefficients of the overlapping node can be obtained by normalizing the bvci to all its belonging communities.The running time of our method is analyzed and varies linearly with network size.We investigate our method on the computergenerated networks and real networks.The testing results indicate that the accuracy of our method in detecting disjoint communities is higher than those of the existing local methods and our method is efficient for detecting the overlapping nodes with fuzzy coefficients.Furthermore,the local optimizing scheme used in our method allows us to partly solve the resolution problem of the global modularity.展开更多
文摘This paper presents a new approach to synthesize admittance function polynomials and coupling matrices for coupled resonator filters. The N + 2 transversal network method is applied to study a coupled resonator filter. This method allowed us to determine the polynomials of the reflection and transmission coefficients. A study is made for a 4 poles filter with 2 transmission zeros between the N + 2 transversal network method and the one found in the literature. A MATLAB code was designed for the numerical simulation of these coefficients for the 6, 8, and 10 pole filter with 4 transmission zeros.
基金National Key R&D Program(Grant No.2020YFB2007700),National Natural Science Foundation of China(Grant Nos.11790282,12032017,12002221 and 11872256)S&T Program of Hebei(Grant No.20310803D)+1 种基金Natural Science Foundation of Hebei Province(Grant No.A2020210028)State Foundation for Studying Abroad.
文摘High-speed trains often use temperature sensors to monitor the motion state of bearings.However,the temperature of bearings can be affected by factors such as weather and faults.Therefore,it is necessary to analyze in detail the relationship between the bearing temperature and influencing factors.In this study,a dynamics model of the axle box bearing of high-speed trains is established.The model can obtain the contact force between the rollers and raceway and its change law when the bearing contains outer-ring,inner-ring,and rolling-element faults.Based on the model,a thermal network method is introduced to study the temperature field distribution of the axle box bearings of high-speed trains.In this model,the heat generation,conduction,and dispersion of the isothermal nodes can be solved.The results show that the temperature of the contact point between the outer-ring raceway and rolling-elements is the highest.The relationships between the node temperature and the speed,fault type,and fault size are analyzed,finding that the higher the speed,the higher the node temperature.Under different fault types,the node temperature first increases and then decreases as the fault size increases.The effectiveness of the model is demonstrated using the actual temperature data of a high-speed train.This study proposes a thermal network model that can predict the temperature of each component of the bearings on a high-speed train under various speed and fault conditions.
文摘Superconductive properties for oxides were predicted by artificial neural network (ANN) method with structural and chemical parameters as inputs. The predicted properties include superconductivity for oxides, distributed ranges of the superconductive transition temperature (Tc) for complex oxides, and Tc values for cuprate superconductors. The calculated results indicated that the adjusted ANN can be used to predict superconductive properties for unknown oxides.
文摘Tsunami ran-up height is a significant parameter for dimensions of coastal structures. In the present study, tsunami run-up heights are estimated by three different Artificial Neural Network （ANN） models, i.e. Feed Forward Back Propagation （FFBP）, Radial Basis Functions （RBF） and Generalized Regression Neural Network （GRNN）. As the input for the ANN configuration, the wave height （H） values are employed. It is shown that the tsunami ran-up height values are closely approximated with all of the applied ANN methods. The ANN estimations are slightly superior to those of the empirical equation. It can be seen that the ANN applications are especially significant in the absence of adequate number of laboratory experiments. The results also prove that the available experiment data set can be extended with ANN simulations. This may be helpful to decrease the burden of the experimental studies and to supply results for comparisons.
文摘In this paper,an approach is developed to optimize the quality of the training samples in the conventional Artificial Neural Network(ANN)by incorporating expert knowledge in the means of constructing expert-rule samples from rules in an expert system,and through training by using these samples,an ANN based on expert-knowledge is further developed.The method is introduced into the field of quantitative identification of potential seismic sources on the basis of the rules in an expert system.Then it is applied to the quantitative identification of the potential seismic sources in Beijing and its adjacent area.The result indicates that the expert rule based on ANN method can well incorporate and represent the expert knowledge in the rules in an expert system,and the quality of the samples and the efficiency of training and the accuracy of the result are optimized.
文摘Because the main failure type of a dangerous rock mass is collapse, the treatment of such a mass should focus on controlling collapse failure. When treating dangerous rock masses, disturbing the mass （e. g. by blasting） needs to be avoided, as this new damage could cause collapse. So the self-bearing capacity of the mountain mass must be used to treat the dangerous rock mass. This article is based on a practical example of the control of a dangerous rock mass at Banyan Mountain, Huangshi, Hubei Province. On the basis of an analysis of damage mechanism and the stability of the dangerous rock mass, a flexible network reinforcement method was designed to prevent the collapse of the rock mass. The deformations of section Ⅱ w of the dangerous rock mass before and after the flexible network reinforcement were calculated using the two-dimensional finite element method. The results show that the maximum deformation reduced by 55 % after the application of the flexible network reinforcement, from 45.99 to 20.75 ram, which demonstrates that the flexible network method is effective, and can provide some scientific basis for the treatment of dangerous rock masses.
文摘BACKGROUND The prevalence and severity of noncommunicable chronic diseases(NCDs)among Chinese residents have been increasing with mental health emerging as a critical challenge in disease management.AIM To examine the interactions between depression,anxiety symptoms,and related factors,and to identify key factors in the Chinese population with NCDs.METHODS Data from the Psychology and Behavior Investigation of Chinese Residents were used in a cross-sectional survey of 6182 individuals with NCDs.This study measured depression and anxiety symptoms as well as their influencing factorsincluding social environments,individual behaviors and lifestyles,and subjective indicators.A network analysis approach was used for data assessment.RESULTS Network analysis demonstrated that several central factors(media exposure,family health,problematic internet use,suboptimal health status,intimate relationship violence,tired or little energy,and nervousness/anxious/on edge)and bridge factors(media exposure,problematic internet use,intimate partner violence,health literacy,and suboptimal health status)that significantly influenced the co-occurrence and interconnectedness of depression and anxiety symptoms.Additionally,gender,ethnicity,residency,and living status did not significantly influence the overall network strength.CONCLUSION Depression and anxiety are prevalent among the Chinese population with NCDs.Effective interventions should focus on managing key symptoms,promoting correct media use for health information,and fostering healthier family relationships.
基金supported by the National Natural Science Foundation of China under Grant Nos.11661060,11571008the Program for Young Talents of Science and Technology in Universities of Inner Mongolia Autonomous Region under Grant No.NJYT-20-A06the Natural Science Foundation of Inner Mongolia Autonomous Region of China under Grant No.2018LH01013。
文摘This paper extends a method, called bilinear neural network method(BNNM), to solve exact solutions to nonlinear partial differential equation. New, test functions are constructed by using this method. These test functions are composed of specific activation functions of single-layer model,specific activation functions of "2-2" model and arbitrary functions of "2-2-3" model. By means of the BNNM, nineteen sets of exact analytical solutions and twenty-four arbitrary function solutions of the dimensionally reduced p-gB KP equation are obtained via symbolic computation with the help of Maple. The fractal solitons waves are obtained by choosing appropriate values and the self-similar characteristics of these waves are observed by reducing the observation range and amplifying the partial picture. By giving a specific activation function in the single layer neural network model, exact periodic waves and breathers are obtained. Via various three-dimensional plots, contour plots and density plots,the evolution characteristic of these waves are exhibited.
基金This work was supported by the National Nature Science Foundation of China (No.59706003).
文摘The network method for modeling thermoacoustic engines is described. Some simulation results on acoustic fields and phases in engine, especially in the thermoacoustic stack are presented and analyzed. The effects of some key factors on performance of stack and engine system are simulated and discussed. These effect factors include the spaces of plates of stack, the position of stack in engine system, the source parameter of stack, and the mean working pressure of the engine system.
文摘The simulation for particle or soliton propagation based on linear or nonlinear Schrodinger equations on unbounded domains requires the computational domain to be bounded,and therefore,a special boundary treatment such as an absorbing boundary condition(ABC)or a perfectly matched layer(PML)is needed so that the reflections of outgoing waves at the boundary can be minimized in order to prevent the destruction of the simulation.This article presents a new artificial neural network(ANN)method for solving linear and nonlinear Schrodinger equations on unbounded domains.In particular,this method randomly selects training points only from the bounded computational space-time domain,and the loss function involves only the initial condition and the Schrodinger equation itself in the computational domainwithout any boundary conditions.Moreover,unlike standard ANNmethods that calculate gradients using expensive automatic differentiation,this method uses accurate finitedifference approximations for the physical gradients in the Schrodinger equation.In addition,a Metropolis-Hastings algorithm is implemented for preferentially selecting regions of high loss in the computational domain allowing for the use of fewer training points in each batch.As such,the present training method uses fewer training points and less computation time for convergence of the loss function as compared with the standard ANN methods.This new ANN method is illustrated using three examples.
基金supported by China National Natural Science Foundation(No.12001306)Guangdong Provincial Natural Science Foundation(No.2017A030310285)funded in part by Beijing Academy of Artificial Intelligence.
文摘We present VPVnet,a deep neural network method for the Stokes’equa-tions under reduced regularity.Different with recently proposed deep learning meth-ods[40,51]which are based on the original form of PDEs,VPVnet uses the least square functional of thefirst-order velocity-pressure-vorticity(VPV)formulation([30])as loss functions.As such,onlyfirst-order derivative is required in the loss functions,hence the method is applicable to a much larger class of problems,e.g.problems with non-smooth solutions.Despite that several methods have been proposed recently to reduce the regularity requirement by transforming the original problem into a corresponding variational form,while for the Stokes’equations,the choice of approximating spaces for the velocity and the pressure has to satisfy the LBB condition additionally.Here by making use of the VPV formulation,lower regularity requirement is achieved with no need for considering the LBB condition.Convergence and error estimates have been established for the proposed method.It is worth emphasizing that the VPVnet method is divergence-free and pressure-robust,while classical inf-sup stable mixedfinite elements for the Stokes’equations are not pressure-robust.Various numerical experiments including 2D and 3D lid-driven cavity test cases are conducted to demon-strate its efficiency and accuracy.
基金Project supported by the Natural Science Foundation of Jiangsu Province,China(Grant No.BK20161278)
文摘In this paper, we made a new breakthrough, which proposes a new recursion–transform（RT） method with potential parameters to evaluate the nodal potential in arbitrary resistor networks. For the first time, we found the exact potential formulae of arbitrary m × n cobweb and fan networks by the RT method, and the potential formulae of infinite and semi-infinite networks are derived. As applications, a series of interesting corollaries of potential formulae are given by using the general formula, the equivalent resistance formula is deduced by using the potential formula, and we find a new trigonometric identity by comparing two equivalence results with different forms.
文摘A new analytical method using Back-Propagation (BP) artificial neural network and kinetic spectrophotometry for simultaneous determination of iron and magnesium in tap water, the Yellow River water and seawater is established. By conditional experiments, the optimum analytical conditions and parameters are obtained. Levenberg-Marquart (L-M) algorithm is used for calculation in BP neural network. The topological structure of three-layer BP ANN network architecture is chosen as 15-16-2 (nodes). The initial value of gradient coefficient μ is fixed at 0.001 and the increase factor and reduction factor of μ take the default values of the system. The data are processed by computers with our own programs written in MATLAB 7.0. The relative standard deviation of the calculated results for iron and manganese is 2.30% and 2.67% respectively. The results of standard addition method show that for the tap water, the recoveries of iron and manganese are in the ranges of 98.0%-104.3% and 96.5%-104.5%, and the RSD is in the range of 0.23%-0.98%; for the Yellow River water (Lijin district of Shandong Province), the recoveries of iron and manganese are in the ranges of 96.0%-101.0% and 98.7%-104.2%, and the RSD is in the range of 0.13%-2.52%; for the seawater in Qingdao offshore, the recoveries of iron and manganese are in the ranges of 95.3%-104.8% and 95.3%-104.7%, and the RSD is in the range of 0.14%-2.66%. It is found that 21 common cations and anions do not interfere with the determination of iron and manganese under the optimum experimental conditions. This method exhibits good reproducibility and high accuracy in the determination of iron and manganese and can be used for the simultaneous determination of iron and manganese in tap water and natural water. By using the established ANN- catalytic spectrophotometric method, the iron and manganese concentrations of the surface seawater at 11 sites in Qingdao offshore are determined and the level distribution maps of iron and manganese are drawn.
文摘BP neural networks is used to mid-term earthquake prediction in this paper. Some usual prediction parameters of seismology are used as the import units of neural networks. And the export units of neural networks is called as the character parameter W_0 describing enhancement of seismicity. We applied this method to space scanning of North China. The result shows that the mid-term anomalous zone of W_0-value usually appeared obviously around the future epicenter 1~3 years before earthquake. It is effective to mid-term prediction.
基金National Natural Science Foundation of China(Nos.11262014,11962021 and 51965051)Inner Mongolia Natural Science Foundation,China(No.2019MS05064)+1 种基金Inner Mongolia Earthquake Administration Director Fund Project,China(No.2019YB06)Inner Mongolia University of Technology Foundation,China(No.2020015)。
文摘Aiming at the reliability analysis of small sample data or implicit structural function,a novel structural reliability analysis model based on support vector machine(SVM)and neural network direct integration method(DNN)is proposed.Firstly,SVM with good small sample learning ability is used to train small sample data,fit structural performance functions and establish regular integration regions.Secondly,DNN is approximated the integral function to achieve multiple integration in the integration region.Finally,structural reliability was obtained by DNN.Numerical examples are investigated to demonstrate the effectiveness of the present method,which provides a feasible way for the structural reliability analysis.
基金financially supported by the National Natural Science Foundation of China(Grant No.51278217)
文摘This paper presents an artificial neural network（ANN）-based response surface method that can be used to predict the failure probability of c-φslopes with spatially variable soil.In this method,the Latin hypercube sampling technique is adopted to generate input datasets for establishing an ANN model;the random finite element method is then utilized to calculate the corresponding output datasets considering the spatial variability of soil properties;and finally,an ANN model is trained to construct the response surface of failure probability and obtain an approximate function that incorporates the relevant variables.The results of the illustrated example indicate that the proposed method provides credible and accurate estimations of failure probability.As a result,the obtained approximate function can be used as an alternative to the specific analysis process in c-φslope reliability analyses.
文摘Feedforward multi layer neural networks have very strong mapping capability that is based on the non linearity of the activation function, however, the non linearity of the activation function can cause the multiple local minima on the learning error surfaces, which affect the learning rate and solving optimal weights. This paper proposes a learning method linearizing non linearity of the activation function and discusses its merits and demerits theoretically.
基金supported by the National Natural Science Foundation of China under grant Nos.12371250 and 12205154Jiangsu Provincial Natural Science Foundation under grant Nos.BK20221508 and BK20210380Jiangsu Qinglan High-level Talent Project and High-level Personnel Project under grant No.JSSCBS20210277.
文摘Fusion and fission are two important phenomena that have been experimentally observed in many real physical models.In this paper,we investigate the two phenomena in the(2+1)-dimensional Hirota-Satsuma-Ito equation via the physics-informed neural networks(PINN)method.By choosing suitable physically constrained initial boundary conditions,the data-driven fusion and fission solutions are obtained for the first time.Dynamical behaviors and error analysis of these solutions are investigated via illustratively numerical figures,which show that good results are achieved.It is pointed out that the PINN method adopted here can be effectively used to construct the data-driven fusion and fission solutions for other nonlinear integrable equations.Based on the powerful predictive capability of the PINN method and wide applications of fusion and fission in many physical areas,it is hoped that the data-driven solutions obtained here will be helpful for experts to predict or explain related physical phenomena.
基金Supported by the Research Foundation of Hubei Province Department of Education(Q20151505)the East China Jiaotong University Doctor Scientific Research Start Fund Project(26441021)
文摘The identification of the influential nodes in a network is of great significance for understanding the features of the network and controlling the complexity of networks in society and in biology. In this paper, we propose a novel centrality measure for a node by considering the importance of edges and compare the performance of this method with existing seven topological-based ranking methods on the Susceptible-Infected-Recovered （SIR） model. The simulation results for four different types of real networks show that the proposed method is robust and exhibits excellent performance in identifying the most influential nodes when spreading starting from both single origin and multipleorigins simultaneously.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.51278101 and 51578149)the Science and Technology Program of Ministry of Transport of China(Grant No.2015318J33080)+1 种基金the Jiangsu Provincial Post-doctoral Science Foundation,China(Grant No.1501046B)the Fundamental Research Funds for the Central Universities,China(Grant No.Y0201500219)
文摘In this paper,we propose a local fuzzy method based on the idea of ＂p-strong＂ community to detect the disjoint and overlapping communities in networks.In the method,a refined agglomeration rule is designed for agglomerating nodes into local communities,and the overlapping nodes are detected based on the idea of making each community strong.We propose a contribution coefficient bvcito measure the contribution of an overlapping node to each of its belonging communities,and the fuzzy coefficients of the overlapping node can be obtained by normalizing the bvci to all its belonging communities.The running time of our method is analyzed and varies linearly with network size.We investigate our method on the computergenerated networks and real networks.The testing results indicate that the accuracy of our method in detecting disjoint communities is higher than those of the existing local methods and our method is efficient for detecting the overlapping nodes with fuzzy coefficients.Furthermore,the local optimizing scheme used in our method allows us to partly solve the resolution problem of the global modularity.
