Purpose–The study aims to build a high-precision longitudinal dynamics model for heavy-haul trains and validate it with line test data,present an optimization method for multi-stage cyclic brakes based on the model a...Purpose–The study aims to build a high-precision longitudinal dynamics model for heavy-haul trains and validate it with line test data,present an optimization method for multi-stage cyclic brakes based on the model and conduct a multi-objective detailed evaluation of the driver’s manipulation during cyclic braking.Design/methodology/approach–The high-precision longitudinal train dynamics model was established and verified by the cyclic braking test data of the 20,000 t heavy-haul combination train on the long and steep downgrade.Then the genetic algorithm is employed for optimization subsequent to decoupling multiple cyclic braking procedures,with due consideration of driver operation rules.For evaluation,key manipulation assessments in the scenario are prioritized,supplemented by multi-objective evaluation requirements,and the computational model is employed for detailed evaluation analysis.Findings–Based on the model,experimental data reveal that the probability of longitudinal force error being less than 64.6 kN is approximately 68%,95%for less than 129.2 kN and 99.7%for less than 193.8 kN.Upon optimizing manipulations during the cyclic braking,the maximum reduction in coupler force spans from 21%∼23.9%.Andtheevaluation scoresimply that a proper elevationof the releasingspeed favorssafety.A high electric braking force,although beneficial to some extent for energy-saving,is detrimental to reducing coupler force.Originality/value–The results will provide a theoretical basis and practical guidance for further ensuring the safety and energy-efficient operation of heavy haul trains on long downhill sections and improving the operational quality of heavy-haul trains.展开更多
A new kind of one-dimensional multilayer phononie heterostructure is constructed to obtain a broad acoustic omnidirectional reflection （ODR） band. The heterostructure is formed by combining finite periodic phononic ...A new kind of one-dimensional multilayer phononie heterostructure is constructed to obtain a broad acoustic omnidirectional reflection （ODR） band. The heterostructure is formed by combining finite periodic phononic crystals （PnCs） and Fibonacci （or Thue-Morse） quasiperiodic PnCs. From the numerical results performed by the transfer matrix method, it is found that the ODR bands can be enlarged obviously by using the combination of periodic and quasi-periodic PnCs. Moreover, an application of particle swarm optimization in designing and optimizing acoustic ODR bands is reported. With regards to different thickness ratios and periodic numbers in the heterostructure, we give some optimization examples and finally achieve phononic heterostructure with a very broad ODR bandwidth. The result provides a new approach to achieve broad acoustic ODR bandwidth, and will be applied in design of omnidirectional acoustic mirrors.展开更多
This paper presents an analytical solution for one-dimensional consolidation of soft soil under some common types of cyclic loading such as trapezoidal cyclic loading, based on the assumptions proposed by Davis and Ra...This paper presents an analytical solution for one-dimensional consolidation of soft soil under some common types of cyclic loading such as trapezoidal cyclic loading, based on the assumptions proposed by Davis and Raymond （1965） that the decrease in permeability is proportional to the decrease in compressibility during the consolidation process of the soil and that the distribution of initial effective stress is constant with depth the solution obtained, some diagrams are prepared and the It is verified by the existing analytical solutions in special cases. Using telex ant consolidation behavior is investigated.展开更多
This paper presents a semi-analytical method to solve one dimensional consolidation problem by taking consideration of varied compressibility of soil under cyclic loading. In the method, soil stratum is divided equall...This paper presents a semi-analytical method to solve one dimensional consolidation problem by taking consideration of varied compressibility of soil under cyclic loading. In the method, soil stratum is divided equally into n layers while load and consolidation time are also divided into small parts and time intervals accordingly. The problem of one-dimensional consolidation of soil stratum under cyclic loading can then be dealt with at each time interval as one-dimensional linear consolidation of multi-layered soils under constant loading. The compression or rebounding of each soil layer can be judged by the effective stress of the layer. When the effective stress is larger than that in the last time interval, the soil layer is compressed, and when it is smaller, the soil layer rebounds. Thus, appropriate compressibility can be chosen and the consolidation of the layered system can be analyzed by the available analytical linear consolidation theory. Based on the semi-analytical method, a computer program was developed and the behavior of one-dimensional consolidation of soil with varied compressibility under cyclic loading was investigated, and compared with the available consolidation theory which takes no consideration of varied compressibility of soil under cyclic loading. The results showed that by taking the variable compressibility into account, the rate of consolidation of soil was greater than the one predicted by conventional consolidation theory.展开更多
In order to explore the potential of profit margin improvement,a novel three-scale integrated optimization model of furnace simulation,cyclic scheduling,and supply chain of ethylene plants is proposed and evaluated.A ...In order to explore the potential of profit margin improvement,a novel three-scale integrated optimization model of furnace simulation,cyclic scheduling,and supply chain of ethylene plants is proposed and evaluated.A decoupling strategy is proposed for the solution of the three-scale model,which uses our previously proposed reactor scale model for operation optimization and then transfers the obtained results as a parameter table in the joint MILP optimization of plant-supply chain scale for cyclic scheduling.This optimization framework simplifies the fundamental mixed-integer nonlinear programming(MINLP)into several sub-models,and improves the interpretability and extendibility.In the evaluation of an industrial case,a profit increase at a percentage of 3.25%is attained in optimization compared to the practical operations.Further sensitivity analysis is carried out for strategy evolving study when price policy,supply chain,and production requirement parameters are varied.These results could provide useful suggestions for petrochemical enterprises on thermal cracking production.展开更多
An analytical solution was presented to the unsaturated soil with a finite thickness under confinement in the lateral direction and sinusoidal cyclic loading in the vertical direction based on Fredlund's one-dimen...An analytical solution was presented to the unsaturated soil with a finite thickness under confinement in the lateral direction and sinusoidal cyclic loading in the vertical direction based on Fredlund's one-dimensional consolidation equation for unsaturated soil. The transfer relationship between the state vectors at the top surface and any depth was gained by applying the Laplace transform and Cayley-Hamilton mathematical methods to the governing equations of water and air, Darcy's law and Fick's law. The excess pore-air and pore-water pressures and settlement in the Laplace-transformed domain were obtained by using the Laplace transform with the initial and boundary conditions. The analytical solutions of the excess pore-air and pore-water pressures at any depth and settlement were obtained in the time domain by performing the inverse Laplace transforms. A typical example illustrates the consolidation characteristics of unsaturated soil under sinusoidal loading from analytical results. Finally, comparisons between the analytical solutions and results of the numerical method indicate that the analytical solution is correct.展开更多
In this paper, we discuss one-dimensional optimal system and the invariant solutions of Coupled Burgers’ equations. By using Wu-differential characteristic set algorithm with the aid of Mathematica software, the clas...In this paper, we discuss one-dimensional optimal system and the invariant solutions of Coupled Burgers’ equations. By using Wu-differential characteristic set algorithm with the aid of Mathematica software, the classical symmetries of the Coupled Burgers’ equations are calculated, and the one-dimensional optimal system of Lie algebra is constructed. And we obtain the invariant solution of the Coupled Burgers’ equations corresponding to one element in one dimensional optimal system by using the invariant method. The results generalize the exact solutions of the Coupled Burgers’ equations.展开更多
Based on the idea that modules are independent of machines, different combinations of modules and machines result in different configurations and the system performances differ under different configurations, a kind o...Based on the idea that modules are independent of machines, different combinations of modules and machines result in different configurations and the system performances differ under different configurations, a kind of cyclic reconfigurable flow shops are proposed for the new manufacturing paradigm-reconfigurable manufacturing system. The cyclic reconfigurable flow shop is modeled as a timed event graph. The optimal configuration is defined as the one under which the cyclic reconfigurable flow shop functions with the minimum cycle time and the minimum number of pallets. The optimal configuration, the minimum cycle time and the minimum number of pallets can be obtained in two steps.展开更多
Based on results of chaos characteristics comparing one-dimensional iterative chaotic self-map x = sin（2/x） with infinite collapses within the finite region[-1, 1] to some representative iterative chaotic maps with ...Based on results of chaos characteristics comparing one-dimensional iterative chaotic self-map x = sin（2/x） with infinite collapses within the finite region[-1, 1] to some representative iterative chaotic maps with finite collapses （e.g., Logistic map, Tent map, and Chebyshev map）, a new adaptive mutative scale chaos optimization algorithm （AMSCOA） is proposed by using the chaos model x = sin（2/x）. In the optimization algorithm, in order to ensure its advantage of speed convergence and high precision in the seeking optimization process, some measures are taken： 1） the searching space of optimized variables is reduced continuously due to adaptive mutative scale method and the searching precision is enhanced accordingly; 2） the most circle time is regarded as its control guideline. The calculation examples about three testing functions reveal that the adaptive mutative scale chaos optimization algorithm has both high searching speed and precision.展开更多
For training the present Neural Network(NN)models,the standard technique is to utilize decaying Learning Rates(LR).While the majority of these techniques commence with a large LR,they will decay multiple times over ti...For training the present Neural Network(NN)models,the standard technique is to utilize decaying Learning Rates(LR).While the majority of these techniques commence with a large LR,they will decay multiple times over time.Decaying has been proved to enhance generalization as well as optimization.Other parameters,such as the network’s size,the number of hidden layers,drop-outs to avoid overfitting,batch size,and so on,are solely based on heuristics.This work has proposed Adaptive Teaching Learning Based(ATLB)Heuristic to identify the optimal hyperparameters for diverse networks.Here we consider three architec-tures Recurrent Neural Networks(RNN),Long Short Term Memory(LSTM),Bidirectional Long Short Term Memory(BiLSTM)of Deep Neural Networks for classification.The evaluation of the proposed ATLB is done through the various learning rate schedulers Cyclical Learning Rate(CLR),Hyperbolic Tangent Decay(HTD),and Toggle between Hyperbolic Tangent Decay and Triangular mode with Restarts(T-HTR)techniques.Experimental results have shown the performance improvement on the 20Newsgroup,Reuters Newswire and IMDB dataset.展开更多
An analysis model to simplify the shearing and blanking process was developed. Based on the simplified model, the shearing process was simulated by FEM and analyzed for various clearances. An optimum clearance in the ...An analysis model to simplify the shearing and blanking process was developed. Based on the simplified model, the shearing process was simulated by FEM and analyzed for various clearances. An optimum clearance in the process was determined by new approach based on orientation of the maximum shearing stress on the characteristic line linking two blades, according to the law of crack propagation and experiments. The optimum clearance determined by this method can be used to dictate the range of reasonable clearance. By the new approach, the optimum clearance can be obtained conveniently and accurately even if there is some difference between the selected points, where the initial crack is assumed originated, and the actual one, where the initial crack occurs really.展开更多
Based on one-dimensional water quality model and nonlinear programming, the point source pollution reduction model with multi-objective optimization has been established. To achieve cost effective and best water quali...Based on one-dimensional water quality model and nonlinear programming, the point source pollution reduction model with multi-objective optimization has been established. To achieve cost effective and best water quality, for us to optimize the process, we set pollutant concentration and total amount control as constraints and put forward the optimal pollution reduction control strategy by simulating and optimizing water quality monitoring data from the target section. Integrated with scenario analysis, COD and ammonia nitrogen pollution optimization wasstudiedin objective function area from Mountain Maan of Acheng to Fuerjia Bridge along Ashe River. The results showed that COD and NH3-N contribution has been greatly reduced to AsheRiverby 49.6% and 32.7% respectively. Therefore, multi-objective optimization by nonlinear programming for water pollution control can make source sewage optimization fairly and reasonably, and the optimal strategies of pollution emission are presented.展开更多
Having realized various significant roles that higher-dimensional nonlinear partial differ-ential equations(NLPDEs)play in engineering,we analytically investigate in this paper,a higher-dimensional soliton equation,wi...Having realized various significant roles that higher-dimensional nonlinear partial differ-ential equations(NLPDEs)play in engineering,we analytically investigate in this paper,a higher-dimensional soliton equation,with applications particularly in ocean physics and mechatronics(electrical electronics and mechanical)engineering.Infinitesimal generators of Lie point symmetries of the equation are computed using Lie group analysis of differen-tial equations.In addition,we construct commutation as well as Lie adjoint representation tables for the nine-dimensional Lie algebra achieved.Further,a one-dimensional optimal system of Lie subalgebras is also presented for the soliton equation.This consequently enables us to generate abundant group-invariant solutions through the reduction of the understudy equation into various ordinary differential equations(ODEs).On solving the achieved nonlinear differential equations,we secure various solitonic solutions.In conse-quence,these solutions containing diverse mathematical functions furnish copious shapes of dynamical wave structures,ranging from periodic,kink and kink-shaped nanopteron,soliton(bright and dark)to breather waves with extensive wave collisions depicted.We physically interpreted the resulting soliton solutions by imploring graphical depictions in three dimensions,two dimensions and density plots.Moreover,the gained group-invariant solutions involved several arbitrary functions,thus exhibiting rich physical structures.We also implore the power series technique to solve part of the complicated differential equa-tions and give valid comments on their results.Later,we outline some applications of our results in ocean physics and mechatronics engineering.展开更多
In this paper, two different methods are used to study the cyclic structure solution and the optimal approximation of the quaternion Stein equation AXB - X = F . Firstly, the matrix equation equivalent to the ta...In this paper, two different methods are used to study the cyclic structure solution and the optimal approximation of the quaternion Stein equation AXB - X = F . Firstly, the matrix equation equivalent to the target structure matrix is constructed by using the complex decomposition of the quaternion matrix, to obtain the necessary and sufficient conditions for the existence of the cyclic solution of the equation and the expression of the general solution. Secondly, the Stein equation is converted into the Sylvester equation by adding the necessary parameters, and the condition for the existence of a cyclic solution and the expression of the equation’s solution are then obtained by using the real decomposition of the quaternion matrix and the Kronecker product of the matrix. At the same time, under the condition that the solution set is non-empty, the optimal approximation solution to the given quaternion circulant matrix is obtained by using the property of Frobenius norm property. Numerical examples are given to verify the correctness of the theoretical results and the feasibility of the proposed method. .展开更多
Let G be a simple graph. The cyclic bandwidth sum problem is to determine a labeling of graph G in a cycle such that the total length of edges is as small as possible. In this paper, some upper and lower bound...Let G be a simple graph. The cyclic bandwidth sum problem is to determine a labeling of graph G in a cycle such that the total length of edges is as small as possible. In this paper, some upper and lower bounds on cyclic bandwidth sum of graphs are studied.展开更多
A simple constitutive model,called semi-implicit model,for cyclic loading is proposed for steel materials used for structures such as building frames in civil engineering.The constitutive model is implemented in the E...A simple constitutive model,called semi-implicit model,for cyclic loading is proposed for steel materials used for structures such as building frames in civil engineering.The constitutive model is implemented in the E-Simulator,which is a software package for large-scale seismic response analysis.The constitutive relation is defined in an algorithmic manner based on the piecewise linear combined isotropic-kinematic hardening.Different rules are used for the first and subsequent loading states to incorporate characteristics such as yield plateau and Bauschinger effect of rolled mild steel materials.An optimization method is also presented for parameter identification from the results of cyclic and monotonic loading tests.Therefore,the proposed model is readily applicable to practical elastoplastic analysis of building frames.Accuracy of the model is demonstrated in an example of a cantilever subjected to various types of cyclic loading.展开更多
Temperature prediction plays an important role in ring die granulator control,which can influence the quantity and quality of production. Temperature prediction modeling is a complicated problem with its MIMO, nonline...Temperature prediction plays an important role in ring die granulator control,which can influence the quantity and quality of production. Temperature prediction modeling is a complicated problem with its MIMO, nonlinear, and large time-delay characteristics. Support vector machine( SVM) has been successfully based on small data. But its accuracy is not high,in contrast,if the number of data and dimension of feature increase,the training time of model will increase dramatically. In this paper,a linear SVM was applied combing with cyclic coordinate descent( CCD) to solving big data regression. It was mathematically strictly proved and validated by simulation. Meanwhile,real data were conducted to prove the linear SVM model's effect. Compared with other methods for big data in simulation, this algorithm has apparent advantage not only in fast modeling but also in high fitness.展开更多
Tian and Meng in [Y. Tian and J. Meng, λc -Optimally half vertex transitive graphs with regularity k, Information Processing Letters 109 (2009) 683 - 686] shown that a connected half vertex transitive graph with regu...Tian and Meng in [Y. Tian and J. Meng, λc -Optimally half vertex transitive graphs with regularity k, Information Processing Letters 109 (2009) 683 - 686] shown that a connected half vertex transitive graph with regularity k and girth g(G) ≥ 6 is cyclically optimal. In this paper, we show that a connected half vertex transitive graph G is super cyclically edge-connected if minimum degree δ(G) ≥ 6 and girth g(G) ≥ 6.展开更多
文摘Purpose–The study aims to build a high-precision longitudinal dynamics model for heavy-haul trains and validate it with line test data,present an optimization method for multi-stage cyclic brakes based on the model and conduct a multi-objective detailed evaluation of the driver’s manipulation during cyclic braking.Design/methodology/approach–The high-precision longitudinal train dynamics model was established and verified by the cyclic braking test data of the 20,000 t heavy-haul combination train on the long and steep downgrade.Then the genetic algorithm is employed for optimization subsequent to decoupling multiple cyclic braking procedures,with due consideration of driver operation rules.For evaluation,key manipulation assessments in the scenario are prioritized,supplemented by multi-objective evaluation requirements,and the computational model is employed for detailed evaluation analysis.Findings–Based on the model,experimental data reveal that the probability of longitudinal force error being less than 64.6 kN is approximately 68%,95%for less than 129.2 kN and 99.7%for less than 193.8 kN.Upon optimizing manipulations during the cyclic braking,the maximum reduction in coupler force spans from 21%∼23.9%.Andtheevaluation scoresimply that a proper elevationof the releasingspeed favorssafety.A high electric braking force,although beneficial to some extent for energy-saving,is detrimental to reducing coupler force.Originality/value–The results will provide a theoretical basis and practical guidance for further ensuring the safety and energy-efficient operation of heavy haul trains on long downhill sections and improving the operational quality of heavy-haul trains.
基金Supported by the National Natural Science Foundation of China under Grant Nos 11304286,11274279 and 11174255the Scientific Research Fund of Zhejiang Provincial Education Department under Grant No Y201226257
文摘A new kind of one-dimensional multilayer phononie heterostructure is constructed to obtain a broad acoustic omnidirectional reflection （ODR） band. The heterostructure is formed by combining finite periodic phononic crystals （PnCs） and Fibonacci （or Thue-Morse） quasiperiodic PnCs. From the numerical results performed by the transfer matrix method, it is found that the ODR bands can be enlarged obviously by using the combination of periodic and quasi-periodic PnCs. Moreover, an application of particle swarm optimization in designing and optimizing acoustic ODR bands is reported. With regards to different thickness ratios and periodic numbers in the heterostructure, we give some optimization examples and finally achieve phononic heterostructure with a very broad ODR bandwidth. The result provides a new approach to achieve broad acoustic ODR bandwidth, and will be applied in design of omnidirectional acoustic mirrors.
基金Projects supported by the National Research Foundation for theDoctoral Program of Higher Education of China (No. 20030335027)and the Natural Science Foundation of Zhejiang Province (No.Y104463), China
文摘This paper presents an analytical solution for one-dimensional consolidation of soft soil under some common types of cyclic loading such as trapezoidal cyclic loading, based on the assumptions proposed by Davis and Raymond （1965） that the decrease in permeability is proportional to the decrease in compressibility during the consolidation process of the soil and that the distribution of initial effective stress is constant with depth the solution obtained, some diagrams are prepared and the It is verified by the existing analytical solutions in special cases. Using telex ant consolidation behavior is investigated.
文摘This paper presents a semi-analytical method to solve one dimensional consolidation problem by taking consideration of varied compressibility of soil under cyclic loading. In the method, soil stratum is divided equally into n layers while load and consolidation time are also divided into small parts and time intervals accordingly. The problem of one-dimensional consolidation of soil stratum under cyclic loading can then be dealt with at each time interval as one-dimensional linear consolidation of multi-layered soils under constant loading. The compression or rebounding of each soil layer can be judged by the effective stress of the layer. When the effective stress is larger than that in the last time interval, the soil layer is compressed, and when it is smaller, the soil layer rebounds. Thus, appropriate compressibility can be chosen and the consolidation of the layered system can be analyzed by the available analytical linear consolidation theory. Based on the semi-analytical method, a computer program was developed and the behavior of one-dimensional consolidation of soil with varied compressibility under cyclic loading was investigated, and compared with the available consolidation theory which takes no consideration of varied compressibility of soil under cyclic loading. The results showed that by taking the variable compressibility into account, the rate of consolidation of soil was greater than the one predicted by conventional consolidation theory.
基金the National Natural Science Foundation of China for its financial support(U1462206,21991100,21991104)。
文摘In order to explore the potential of profit margin improvement,a novel three-scale integrated optimization model of furnace simulation,cyclic scheduling,and supply chain of ethylene plants is proposed and evaluated.A decoupling strategy is proposed for the solution of the three-scale model,which uses our previously proposed reactor scale model for operation optimization and then transfers the obtained results as a parameter table in the joint MILP optimization of plant-supply chain scale for cyclic scheduling.This optimization framework simplifies the fundamental mixed-integer nonlinear programming(MINLP)into several sub-models,and improves the interpretability and extendibility.In the evaluation of an industrial case,a profit increase at a percentage of 3.25%is attained in optimization compared to the practical operations.Further sensitivity analysis is carried out for strategy evolving study when price policy,supply chain,and production requirement parameters are varied.These results could provide useful suggestions for petrochemical enterprises on thermal cracking production.
基金Project(2010G016-B)supported by Science and Technology Research and Development of China
文摘An analytical solution was presented to the unsaturated soil with a finite thickness under confinement in the lateral direction and sinusoidal cyclic loading in the vertical direction based on Fredlund's one-dimensional consolidation equation for unsaturated soil. The transfer relationship between the state vectors at the top surface and any depth was gained by applying the Laplace transform and Cayley-Hamilton mathematical methods to the governing equations of water and air, Darcy's law and Fick's law. The excess pore-air and pore-water pressures and settlement in the Laplace-transformed domain were obtained by using the Laplace transform with the initial and boundary conditions. The analytical solutions of the excess pore-air and pore-water pressures at any depth and settlement were obtained in the time domain by performing the inverse Laplace transforms. A typical example illustrates the consolidation characteristics of unsaturated soil under sinusoidal loading from analytical results. Finally, comparisons between the analytical solutions and results of the numerical method indicate that the analytical solution is correct.
文摘In this paper, we discuss one-dimensional optimal system and the invariant solutions of Coupled Burgers’ equations. By using Wu-differential characteristic set algorithm with the aid of Mathematica software, the classical symmetries of the Coupled Burgers’ equations are calculated, and the one-dimensional optimal system of Lie algebra is constructed. And we obtain the invariant solution of the Coupled Burgers’ equations corresponding to one element in one dimensional optimal system by using the invariant method. The results generalize the exact solutions of the Coupled Burgers’ equations.
基金Supported by National Key Fundamental Research and Development Project of P. R. China (2002CB312200)
文摘Based on the idea that modules are independent of machines, different combinations of modules and machines result in different configurations and the system performances differ under different configurations, a kind of cyclic reconfigurable flow shops are proposed for the new manufacturing paradigm-reconfigurable manufacturing system. The cyclic reconfigurable flow shop is modeled as a timed event graph. The optimal configuration is defined as the one under which the cyclic reconfigurable flow shop functions with the minimum cycle time and the minimum number of pallets. The optimal configuration, the minimum cycle time and the minimum number of pallets can be obtained in two steps.
基金Hunan Provincial Natural Science Foundation of China (No. 06JJ50103)the National Natural Science Foundationof China (No. 60375001)
文摘Based on results of chaos characteristics comparing one-dimensional iterative chaotic self-map x = sin（2/x） with infinite collapses within the finite region[-1, 1] to some representative iterative chaotic maps with finite collapses （e.g., Logistic map, Tent map, and Chebyshev map）, a new adaptive mutative scale chaos optimization algorithm （AMSCOA） is proposed by using the chaos model x = sin（2/x）. In the optimization algorithm, in order to ensure its advantage of speed convergence and high precision in the seeking optimization process, some measures are taken： 1） the searching space of optimized variables is reduced continuously due to adaptive mutative scale method and the searching precision is enhanced accordingly; 2） the most circle time is regarded as its control guideline. The calculation examples about three testing functions reveal that the adaptive mutative scale chaos optimization algorithm has both high searching speed and precision.
文摘For training the present Neural Network(NN)models,the standard technique is to utilize decaying Learning Rates(LR).While the majority of these techniques commence with a large LR,they will decay multiple times over time.Decaying has been proved to enhance generalization as well as optimization.Other parameters,such as the network’s size,the number of hidden layers,drop-outs to avoid overfitting,batch size,and so on,are solely based on heuristics.This work has proposed Adaptive Teaching Learning Based(ATLB)Heuristic to identify the optimal hyperparameters for diverse networks.Here we consider three architec-tures Recurrent Neural Networks(RNN),Long Short Term Memory(LSTM),Bidirectional Long Short Term Memory(BiLSTM)of Deep Neural Networks for classification.The evaluation of the proposed ATLB is done through the various learning rate schedulers Cyclical Learning Rate(CLR),Hyperbolic Tangent Decay(HTD),and Toggle between Hyperbolic Tangent Decay and Triangular mode with Restarts(T-HTR)techniques.Experimental results have shown the performance improvement on the 20Newsgroup,Reuters Newswire and IMDB dataset.
基金Project( 5 992 2 0 )supportedbyNaturalScienceFoundationofHebeiProvince China
文摘An analysis model to simplify the shearing and blanking process was developed. Based on the simplified model, the shearing process was simulated by FEM and analyzed for various clearances. An optimum clearance in the process was determined by new approach based on orientation of the maximum shearing stress on the characteristic line linking two blades, according to the law of crack propagation and experiments. The optimum clearance determined by this method can be used to dictate the range of reasonable clearance. By the new approach, the optimum clearance can be obtained conveniently and accurately even if there is some difference between the selected points, where the initial crack is assumed originated, and the actual one, where the initial crack occurs really.
文摘Based on one-dimensional water quality model and nonlinear programming, the point source pollution reduction model with multi-objective optimization has been established. To achieve cost effective and best water quality, for us to optimize the process, we set pollutant concentration and total amount control as constraints and put forward the optimal pollution reduction control strategy by simulating and optimizing water quality monitoring data from the target section. Integrated with scenario analysis, COD and ammonia nitrogen pollution optimization wasstudiedin objective function area from Mountain Maan of Acheng to Fuerjia Bridge along Ashe River. The results showed that COD and NH3-N contribution has been greatly reduced to AsheRiverby 49.6% and 32.7% respectively. Therefore, multi-objective optimization by nonlinear programming for water pollution control can make source sewage optimization fairly and reasonably, and the optimal strategies of pollution emission are presented.
基金the North-West University,Mafikeng campus for its continued support.
文摘Having realized various significant roles that higher-dimensional nonlinear partial differ-ential equations(NLPDEs)play in engineering,we analytically investigate in this paper,a higher-dimensional soliton equation,with applications particularly in ocean physics and mechatronics(electrical electronics and mechanical)engineering.Infinitesimal generators of Lie point symmetries of the equation are computed using Lie group analysis of differen-tial equations.In addition,we construct commutation as well as Lie adjoint representation tables for the nine-dimensional Lie algebra achieved.Further,a one-dimensional optimal system of Lie subalgebras is also presented for the soliton equation.This consequently enables us to generate abundant group-invariant solutions through the reduction of the understudy equation into various ordinary differential equations(ODEs).On solving the achieved nonlinear differential equations,we secure various solitonic solutions.In conse-quence,these solutions containing diverse mathematical functions furnish copious shapes of dynamical wave structures,ranging from periodic,kink and kink-shaped nanopteron,soliton(bright and dark)to breather waves with extensive wave collisions depicted.We physically interpreted the resulting soliton solutions by imploring graphical depictions in three dimensions,two dimensions and density plots.Moreover,the gained group-invariant solutions involved several arbitrary functions,thus exhibiting rich physical structures.We also implore the power series technique to solve part of the complicated differential equa-tions and give valid comments on their results.Later,we outline some applications of our results in ocean physics and mechatronics engineering.
文摘In this paper, two different methods are used to study the cyclic structure solution and the optimal approximation of the quaternion Stein equation AXB - X = F . Firstly, the matrix equation equivalent to the target structure matrix is constructed by using the complex decomposition of the quaternion matrix, to obtain the necessary and sufficient conditions for the existence of the cyclic solution of the equation and the expression of the general solution. Secondly, the Stein equation is converted into the Sylvester equation by adding the necessary parameters, and the condition for the existence of a cyclic solution and the expression of the equation’s solution are then obtained by using the real decomposition of the quaternion matrix and the Kronecker product of the matrix. At the same time, under the condition that the solution set is non-empty, the optimal approximation solution to the given quaternion circulant matrix is obtained by using the property of Frobenius norm property. Numerical examples are given to verify the correctness of the theoretical results and the feasibility of the proposed method. .
文摘Let G be a simple graph. The cyclic bandwidth sum problem is to determine a labeling of graph G in a cycle such that the total length of edges is as small as possible. In this paper, some upper and lower bounds on cyclic bandwidth sum of graphs are studied.
文摘A simple constitutive model,called semi-implicit model,for cyclic loading is proposed for steel materials used for structures such as building frames in civil engineering.The constitutive model is implemented in the E-Simulator,which is a software package for large-scale seismic response analysis.The constitutive relation is defined in an algorithmic manner based on the piecewise linear combined isotropic-kinematic hardening.Different rules are used for the first and subsequent loading states to incorporate characteristics such as yield plateau and Bauschinger effect of rolled mild steel materials.An optimization method is also presented for parameter identification from the results of cyclic and monotonic loading tests.Therefore,the proposed model is readily applicable to practical elastoplastic analysis of building frames.Accuracy of the model is demonstrated in an example of a cantilever subjected to various types of cyclic loading.
基金Nantong Research Program of Application Foundation,China(No.BK2012030)Key Project of Science and Technology Commission of Shanghai Municipality,China(No.10JC1405000)
文摘Temperature prediction plays an important role in ring die granulator control,which can influence the quantity and quality of production. Temperature prediction modeling is a complicated problem with its MIMO, nonlinear, and large time-delay characteristics. Support vector machine( SVM) has been successfully based on small data. But its accuracy is not high,in contrast,if the number of data and dimension of feature increase,the training time of model will increase dramatically. In this paper,a linear SVM was applied combing with cyclic coordinate descent( CCD) to solving big data regression. It was mathematically strictly proved and validated by simulation. Meanwhile,real data were conducted to prove the linear SVM model's effect. Compared with other methods for big data in simulation, this algorithm has apparent advantage not only in fast modeling but also in high fitness.
基金Supported by National Natural Science Foundation of China （61273260）, Specialized Research Fund for the Doctoral Program of Higher Education of China （20121333120010）, Natural Scientific Research Foundation of the Higher Education Institutions of Hebei Province （2010t65）, the Major Program of the National Natural Science Foundation of China （61290322）, Foundation of Key Labora- tory of System Control and Information Processing, Ministry of Education （SCIP2012008）, and Science and Technology Research and Development Plan of Qinhuangdao City （2012021A041）
文摘Tian and Meng in [Y. Tian and J. Meng, λc -Optimally half vertex transitive graphs with regularity k, Information Processing Letters 109 (2009) 683 - 686] shown that a connected half vertex transitive graph with regularity k and girth g(G) ≥ 6 is cyclically optimal. In this paper, we show that a connected half vertex transitive graph G is super cyclically edge-connected if minimum degree δ(G) ≥ 6 and girth g(G) ≥ 6.
