To enhance the efficiency of stochastic vibration analysis for the Train-Track-Bridge(TTB)coupled system,this paper proposes a prediction method based on a Genetic Algorithm-optimized Backpropagation(GA-BP)neural netw...To enhance the efficiency of stochastic vibration analysis for the Train-Track-Bridge(TTB)coupled system,this paper proposes a prediction method based on a Genetic Algorithm-optimized Backpropagation(GA-BP)neural network.First,initial track irregularity samples and random parameter sets of the Vehicle-Bridge System(VBS)are generated using the stochastic harmonic function method.Then,the stochastic dynamic responses corresponding to the sample sets are calculated using a developed stochastic vibration analysis model of the TTB system.The track irregularity data and vehicle-bridge random parameters are used as input variables,while the corresponding stochastic responses serve as output variables for training the BP neural network to construct the prediction model.Subsequently,the Genetic Algorithm(GA)is applied to optimize the BP neural network by considering the randomness in excitation and parameters of the TTB system,improving model accuracy.After optimization,the trained GA-BP model enables rapid and accurate prediction of vehicle-bridge responses.To validate the proposed method,predictions of vehicle-bridge responses under varying train speeds are compared with numerical simulation results.The findings demonstrate that the proposed method offers notable advantages in predicting the stochastic vibration response of high-speed railway TTB coupled systems.展开更多
The analysis of interwell connectivity plays an important role in the formulation of oilfield development plans and the description of residual oil distribution. In fact, sandstone reservoirs in China's onshore oi...The analysis of interwell connectivity plays an important role in the formulation of oilfield development plans and the description of residual oil distribution. In fact, sandstone reservoirs in China's onshore oilfields generally have the characteristics of thin and many layers, so multi-layer joint production is usually adopted. It remains a challenge to ensure the accuracy of splitting and dynamic connectivity in each layer of the injection-production wells with limited field data. The three-dimensional well pattern of multi-layer reservoir and the relationship between injection-production wells can be equivalent to a directional heterogeneous graph. In this paper, an improved graph neural network is proposed to construct an interacting process mimics the real interwell flow regularity. In detail, this method is used to split injection and production rates by combining permeability, porosity and effective thickness, and to invert the dynamic connectivity in each layer of the injection-production wells by attention mechanism.Based on the material balance and physical information, the overall connectivity from the injection wells,through the water injection layers to the production layers and the output of final production wells is established. Meanwhile, the change of well pattern caused by perforation, plugging and switching of wells at different times is achieved by updated graph structure in spatial and temporal ways. The effectiveness of the method is verified by a combination of reservoir numerical simulation examples and field example. The method corresponds to the actual situation of the reservoir, has wide adaptability and low cost, has good practical value, and provides a reference for adjusting the injection-production relationship of the reservoir and the development of the remaining oil.展开更多
Artificial neural networks(ANNs)are one of the hottest topics in computer science and artificial intelligence due to their potential and advantages in analyzing real-world problems in various disciplines,including but...Artificial neural networks(ANNs)are one of the hottest topics in computer science and artificial intelligence due to their potential and advantages in analyzing real-world problems in various disciplines,including but not limited to physics,biology,chemistry,and engineering.However,ANNs lack several key characteristics of biological neural networks,such as sparsity,scale-freeness,and small-worldness.The concept of sparse and scale-free neural networks has been introduced to fill this gap.Network sparsity is implemented by removing weak weights between neurons during the learning process and replacing them with random weights.When the network is initialized,the neural network is fully connected,which means the number of weights is four times the number of neurons.In this study,considering that a biological neural network has some degree of initial sparsity,we design an ANN with a prescribed level of initial sparsity.The neural network is tested on handwritten digits,Arabic characters,CIFAR-10,and Reuters newswire topics.Simulations show that it is possible to reduce the number of weights by up to 50%without losing prediction accuracy.Moreover,in both cases,the testing time is dramatically reduced compared with fully connected ANNs.展开更多
A kind of second order algorithm--recursive approximate Newton algorithm was given by Karayiannis. The algorithm was simplified when it was formulated. Especially, the simplification to matrix Hessian was very reluct...A kind of second order algorithm--recursive approximate Newton algorithm was given by Karayiannis. The algorithm was simplified when it was formulated. Especially, the simplification to matrix Hessian was very reluctant, which led to the loss of valuable information and affected performance of the algorithm to certain extent. For multi layer feed forward neural networks, the second order back propagation recursive algorithm based generalized cost criteria was proposed. It is proved that it is equivalent to Newton recursive algorithm and has a second order convergent rate. The performance and application prospect are analyzed. Lots of simulation experiments indicate that the calculation of the new algorithm is almost equivalent to the recursive least square multiple algorithm. The algorithm and selection of networks parameters are significant and the performance is more excellent than BP algorithm and the second order learning algorithm that was given by Karayiannis.展开更多
This elucidation investigates the Hausdorff dimension of the output space of multi-layer neural networks. When the factor map from the covering space of the output space to the output space has a synchronizing word, t...This elucidation investigates the Hausdorff dimension of the output space of multi-layer neural networks. When the factor map from the covering space of the output space to the output space has a synchronizing word, the Hausdorff dimension of the output space relates to its topological entropy. This clarifies the geometrical structure of the output space in more details.展开更多
This paper presents a study on the improvement of MLNNs(multi-layer neural networks)performance by an activity function for multi logic training patterns.Our model network has L hidden layers of two inputs and three,f...This paper presents a study on the improvement of MLNNs(multi-layer neural networks)performance by an activity function for multi logic training patterns.Our model network has L hidden layers of two inputs and three,four to six output training using BP(backpropagation)neural network.We used logic functions of XOR(exclusive OR),OR,AND,NAND(not AND),NXOR(not exclusive OR)and NOR(not OR)as the multi logic teacher signals to evaluate the training performance of MLNNs by an activity function for information and data enlargement in signal processing(synaptic divergence state).We specifically used four activity functions from which we modified one and called it L&exp.function as it could give the highest training abilities compared to the original activity functions of Sigmoid,ReLU and Step during simulation and training in the network.And finally,we propose L&exp.function as being good for MLNNs and it may be applicable for signal processing of data and information enlargement because of its performance training characteristics with multiple training logic patterns hence can be adopted in machine deep learning.展开更多
A momentum BP neural network model （MBPNNM） was constructed to retrieve the water depth information for the South Channel of the Yangtze River Estuary using the relationship between the reflectance derived from Land...A momentum BP neural network model （MBPNNM） was constructed to retrieve the water depth information for the South Channel of the Yangtze River Estuary using the relationship between the reflectance derived from Landsat 7 satellite data and the water depth information. Results showed that MBPNNM, which exhibited a strong capability of nonlinear mapping, allowed the water depth information in the study area to be retrieved at a relatively high level of accuracy. Affected by the sediment concentration of water in the estuary, MBPNNM enabled the retrieval of water depth of less than 5 meters accurately. However, the accuracy was not ideal for the water depths of more than 10 meters.展开更多
The excessive staminate catkin thinning （emasculation） of proterandrous walnut is an important management measure for improving yield. To improve the excessive staminate catkin thinning efficiency, the model of quad...The excessive staminate catkin thinning （emasculation） of proterandrous walnut is an important management measure for improving yield. To improve the excessive staminate catkin thinning efficiency, the model of quadratic polynomial regression equation and BP artificial neural network was developed. The effects of ethephon, gibberel in and mepiquat on shedding rate of staminate catkin of pro-terandrous walnut were investigated by modeling field test. Based on the modeling test results, the excessive staminate catkin thinning model of quadratic polynomial regression equation and BP artificial neural network was established, and it was validated by field test next year. The test data were divided into training set, vali-dation set and test set. The total 20 sets of data obtained from the modeling field test were randomly divided into training set （17） and validation set （3） by central composite design （quadric rotational regression test design）, and the data obtained from the next-year field test were divided into the test set. The topological struc-ture of BP artificial neural network was 3-5-1. The results showed that the pre-diction errors of BP neural network for samples from the validation set were 1.355 0%, 0.429 1% and 0.353 8%, respectively; the difference between the predicted value by the BP neural network and validated value by field test was 2.04%, and the difference between the predicted value by the regression equation and validated value by field test was 3.12%; the prediction accuracy of BP neural network was over 1.0% higher than that of regression equation. The effective combination of quadratic polynomial stepwise regression and BP artificial neural network wil not only help to determine the effect of independent parameter but also improve the prediction accuracy.展开更多
To find a neural network model suitable to identify the concentration of mixed pernicious gases in pig house, the quantitative detection model of pernicious gases in pig house was set up based on BP （ Back propagatio...To find a neural network model suitable to identify the concentration of mixed pernicious gases in pig house, the quantitative detection model of pernicious gases in pig house was set up based on BP （ Back propagation） neural network. The BP neural network was trained separately by the three functions, trainbr, traingdm and trainlm, in order to identify the concentration of mixed pernicious gases composed of ammonia gas and hepatic gas. The neural network toolbox in MATLAB software was used to simulate the detection. The results showed that the neural network trained by trainbr function has high average identification accuracy and faster detection speed, and it is also insensitive to noise; therefore, it is suitable to identify the concentration of pemidous gases in pig house. These data provide a reference for intelligent monitoring of pemicious gases in pigsty.展开更多
Injection of water to enhance oil production is commonplace, and improvements in understanding the process are economically important. This study examines predictive models of the injection-to-production ratio. First...Injection of water to enhance oil production is commonplace, and improvements in understanding the process are economically important. This study examines predictive models of the injection-to-production ratio. Firstly, the error between the fitting and actual injection-production ratio is calculated with such methods as the injection-production ratio and water-oil ratio method, the material balance method, the multiple regression method, the gray theory GM (1,1) model and the back-propogation (BP) neural network method by computer applications in this paper. The relative average errors calculated are respectively 1.67%, 1.08%, 19.2%, 1.38% and 0.88%. Secondly, the reasons for the errors from different prediction methods are analyzed theoretically, indicating that the prediction precision of the BP neural network method is high, and that it has a better self-adaptability, so that it can reflect the internal relationship between the injection-production ratio and the influencing factors. Therefore, the BP neural network method is suitable to the prediction of injection-production ratio.展开更多
With Zengcheng City, Guangdong Province, as the object of study, 200 soil sampling points were col ected for the spatial interpolation prediction of soil properties by using Kriging method and BP neural network method...With Zengcheng City, Guangdong Province, as the object of study, 200 soil sampling points were col ected for the spatial interpolation prediction of soil properties by using Kriging method and BP neural network method. After comparing the interpolation results with the measured values, the root mean square error of the prediction data was obtained. The results showed that the interpolation accuracy of BP neural network was higher than that of Kriging method under the same cir-cumstances, and there was no smoothness in using BP neural network method when there were few sample points. In addition, with no requirement on the distri-bution of sample data, BP neural network method had stronger generalization ability than traditional interpolation method, which was an alternative interpolation method.展开更多
基金supported by the China State Railway Group Co.,Ltd.Science and Technology Research and Development Program Project(Grant No.L2024G007)the Natural Science Foundation of Hunan Province(Grant No.2024JJ5427)+1 种基金the National Natural Science Foundation of China(Grant No.52478321,52078485)the Science and Technology Research and Development Program Project of China Railway Group Limited(Grant No.2021-Special-08,2022-Key-06&2023-Key-22).
文摘To enhance the efficiency of stochastic vibration analysis for the Train-Track-Bridge(TTB)coupled system,this paper proposes a prediction method based on a Genetic Algorithm-optimized Backpropagation(GA-BP)neural network.First,initial track irregularity samples and random parameter sets of the Vehicle-Bridge System(VBS)are generated using the stochastic harmonic function method.Then,the stochastic dynamic responses corresponding to the sample sets are calculated using a developed stochastic vibration analysis model of the TTB system.The track irregularity data and vehicle-bridge random parameters are used as input variables,while the corresponding stochastic responses serve as output variables for training the BP neural network to construct the prediction model.Subsequently,the Genetic Algorithm(GA)is applied to optimize the BP neural network by considering the randomness in excitation and parameters of the TTB system,improving model accuracy.After optimization,the trained GA-BP model enables rapid and accurate prediction of vehicle-bridge responses.To validate the proposed method,predictions of vehicle-bridge responses under varying train speeds are compared with numerical simulation results.The findings demonstrate that the proposed method offers notable advantages in predicting the stochastic vibration response of high-speed railway TTB coupled systems.
基金the support of the National Nature Science Foundation of China(No.52074336)Emerging Big Data Projects of Sinopec Corporation(No.20210918084304712)。
文摘The analysis of interwell connectivity plays an important role in the formulation of oilfield development plans and the description of residual oil distribution. In fact, sandstone reservoirs in China's onshore oilfields generally have the characteristics of thin and many layers, so multi-layer joint production is usually adopted. It remains a challenge to ensure the accuracy of splitting and dynamic connectivity in each layer of the injection-production wells with limited field data. The three-dimensional well pattern of multi-layer reservoir and the relationship between injection-production wells can be equivalent to a directional heterogeneous graph. In this paper, an improved graph neural network is proposed to construct an interacting process mimics the real interwell flow regularity. In detail, this method is used to split injection and production rates by combining permeability, porosity and effective thickness, and to invert the dynamic connectivity in each layer of the injection-production wells by attention mechanism.Based on the material balance and physical information, the overall connectivity from the injection wells,through the water injection layers to the production layers and the output of final production wells is established. Meanwhile, the change of well pattern caused by perforation, plugging and switching of wells at different times is achieved by updated graph structure in spatial and temporal ways. The effectiveness of the method is verified by a combination of reservoir numerical simulation examples and field example. The method corresponds to the actual situation of the reservoir, has wide adaptability and low cost, has good practical value, and provides a reference for adjusting the injection-production relationship of the reservoir and the development of the remaining oil.
文摘Artificial neural networks(ANNs)are one of the hottest topics in computer science and artificial intelligence due to their potential and advantages in analyzing real-world problems in various disciplines,including but not limited to physics,biology,chemistry,and engineering.However,ANNs lack several key characteristics of biological neural networks,such as sparsity,scale-freeness,and small-worldness.The concept of sparse and scale-free neural networks has been introduced to fill this gap.Network sparsity is implemented by removing weak weights between neurons during the learning process and replacing them with random weights.When the network is initialized,the neural network is fully connected,which means the number of weights is four times the number of neurons.In this study,considering that a biological neural network has some degree of initial sparsity,we design an ANN with a prescribed level of initial sparsity.The neural network is tested on handwritten digits,Arabic characters,CIFAR-10,and Reuters newswire topics.Simulations show that it is possible to reduce the number of weights by up to 50%without losing prediction accuracy.Moreover,in both cases,the testing time is dramatically reduced compared with fully connected ANNs.
文摘A kind of second order algorithm--recursive approximate Newton algorithm was given by Karayiannis. The algorithm was simplified when it was formulated. Especially, the simplification to matrix Hessian was very reluctant, which led to the loss of valuable information and affected performance of the algorithm to certain extent. For multi layer feed forward neural networks, the second order back propagation recursive algorithm based generalized cost criteria was proposed. It is proved that it is equivalent to Newton recursive algorithm and has a second order convergent rate. The performance and application prospect are analyzed. Lots of simulation experiments indicate that the calculation of the new algorithm is almost equivalent to the recursive least square multiple algorithm. The algorithm and selection of networks parameters are significant and the performance is more excellent than BP algorithm and the second order learning algorithm that was given by Karayiannis.
文摘This elucidation investigates the Hausdorff dimension of the output space of multi-layer neural networks. When the factor map from the covering space of the output space to the output space has a synchronizing word, the Hausdorff dimension of the output space relates to its topological entropy. This clarifies the geometrical structure of the output space in more details.
文摘This paper presents a study on the improvement of MLNNs(multi-layer neural networks)performance by an activity function for multi logic training patterns.Our model network has L hidden layers of two inputs and three,four to six output training using BP(backpropagation)neural network.We used logic functions of XOR(exclusive OR),OR,AND,NAND(not AND),NXOR(not exclusive OR)and NOR(not OR)as the multi logic teacher signals to evaluate the training performance of MLNNs by an activity function for information and data enlargement in signal processing(synaptic divergence state).We specifically used four activity functions from which we modified one and called it L&exp.function as it could give the highest training abilities compared to the original activity functions of Sigmoid,ReLU and Step during simulation and training in the network.And finally,we propose L&exp.function as being good for MLNNs and it may be applicable for signal processing of data and information enlargement because of its performance training characteristics with multiple training logic patterns hence can be adopted in machine deep learning.
基金the Key Program of National Natural Science Foundation （Project No.50339010） the Huaihe Valley 0pen Fund Project （No.Hx2007）.
文摘A momentum BP neural network model （MBPNNM） was constructed to retrieve the water depth information for the South Channel of the Yangtze River Estuary using the relationship between the reflectance derived from Landsat 7 satellite data and the water depth information. Results showed that MBPNNM, which exhibited a strong capability of nonlinear mapping, allowed the water depth information in the study area to be retrieved at a relatively high level of accuracy. Affected by the sediment concentration of water in the estuary, MBPNNM enabled the retrieval of water depth of less than 5 meters accurately. However, the accuracy was not ideal for the water depths of more than 10 meters.
基金Supported by Key Science and Technology Program of Shanxi Province,China(002023)~~
文摘The excessive staminate catkin thinning （emasculation） of proterandrous walnut is an important management measure for improving yield. To improve the excessive staminate catkin thinning efficiency, the model of quadratic polynomial regression equation and BP artificial neural network was developed. The effects of ethephon, gibberel in and mepiquat on shedding rate of staminate catkin of pro-terandrous walnut were investigated by modeling field test. Based on the modeling test results, the excessive staminate catkin thinning model of quadratic polynomial regression equation and BP artificial neural network was established, and it was validated by field test next year. The test data were divided into training set, vali-dation set and test set. The total 20 sets of data obtained from the modeling field test were randomly divided into training set （17） and validation set （3） by central composite design （quadric rotational regression test design）, and the data obtained from the next-year field test were divided into the test set. The topological struc-ture of BP artificial neural network was 3-5-1. The results showed that the pre-diction errors of BP neural network for samples from the validation set were 1.355 0%, 0.429 1% and 0.353 8%, respectively; the difference between the predicted value by the BP neural network and validated value by field test was 2.04%, and the difference between the predicted value by the regression equation and validated value by field test was 3.12%; the prediction accuracy of BP neural network was over 1.0% higher than that of regression equation. The effective combination of quadratic polynomial stepwise regression and BP artificial neural network wil not only help to determine the effect of independent parameter but also improve the prediction accuracy.
文摘To find a neural network model suitable to identify the concentration of mixed pernicious gases in pig house, the quantitative detection model of pernicious gases in pig house was set up based on BP （ Back propagation） neural network. The BP neural network was trained separately by the three functions, trainbr, traingdm and trainlm, in order to identify the concentration of mixed pernicious gases composed of ammonia gas and hepatic gas. The neural network toolbox in MATLAB software was used to simulate the detection. The results showed that the neural network trained by trainbr function has high average identification accuracy and faster detection speed, and it is also insensitive to noise; therefore, it is suitable to identify the concentration of pemidous gases in pig house. These data provide a reference for intelligent monitoring of pemicious gases in pigsty.
文摘Injection of water to enhance oil production is commonplace, and improvements in understanding the process are economically important. This study examines predictive models of the injection-to-production ratio. Firstly, the error between the fitting and actual injection-production ratio is calculated with such methods as the injection-production ratio and water-oil ratio method, the material balance method, the multiple regression method, the gray theory GM (1,1) model and the back-propogation (BP) neural network method by computer applications in this paper. The relative average errors calculated are respectively 1.67%, 1.08%, 19.2%, 1.38% and 0.88%. Secondly, the reasons for the errors from different prediction methods are analyzed theoretically, indicating that the prediction precision of the BP neural network method is high, and that it has a better self-adaptability, so that it can reflect the internal relationship between the injection-production ratio and the influencing factors. Therefore, the BP neural network method is suitable to the prediction of injection-production ratio.
基金Supported by the National Natural Science Foundation of China(40971125)the Science and Technology Planning Project of Guangdong Province,China(2012A020200006,2012B091100220)~~
文摘With Zengcheng City, Guangdong Province, as the object of study, 200 soil sampling points were col ected for the spatial interpolation prediction of soil properties by using Kriging method and BP neural network method. After comparing the interpolation results with the measured values, the root mean square error of the prediction data was obtained. The results showed that the interpolation accuracy of BP neural network was higher than that of Kriging method under the same cir-cumstances, and there was no smoothness in using BP neural network method when there were few sample points. In addition, with no requirement on the distri-bution of sample data, BP neural network method had stronger generalization ability than traditional interpolation method, which was an alternative interpolation method.
