In the electroslag remelting(ESR)process,it mainly relies on thermal experiments or analysis via mechanistic models to realize the physical fields simulation of the electromagnetic field and temperature field coupled ...In the electroslag remelting(ESR)process,it mainly relies on thermal experiments or analysis via mechanistic models to realize the physical fields simulation of the electromagnetic field and temperature field coupled transfer,which has the limitations of high cost,a large amount of calculating data and high computing power requirements.A novel network based on physics-informed neural network(PINN)was designed to realize the fast and high-fidelity prediction of the distribution of electromagnetic field and temperature field in ESR process.The physical laws were combined with the deep learning network through PINN,and physical constraints were embedded to achieve effective solution of partial differential equations(PDEs).PINN was used to minimize the loss function consisting of data error,physical information error and boundary condition error.The physical laws and boundary condition constraints in the ESR process were considered to maintain high PDE solution accuracy under different spatial and temporal resolutions.Automatic differentiation(Autodiff)technique and gradient descent algorithm were used to optimize the network parameters.The experimental results show that compared with the mechanistic models,PINN can effectively replace thermal experiments to realize the physical field simulation of ESR process with only a few experimental data,which can avoid the disadvantages of pure data-driven network simulation that requires a large amount of training data.Moreover,the solution of PINN has good physical interpretability and reliability of simulation results.For simulating electromagnetic field and temperature field distribution,the training time of the network is only 140 and 203 s,and the regression indicators of root mean square error can reach 12.65 and 13.76,respectively.展开更多
Recent advances in deep learning have expanded new possibilities for fluid flow simulation in petroleum reservoirs.However,the predominant approach in existing research is to train neural networks using high-fidelity ...Recent advances in deep learning have expanded new possibilities for fluid flow simulation in petroleum reservoirs.However,the predominant approach in existing research is to train neural networks using high-fidelity numerical simulation data.This presents a significant challenge because the sole source of authentic wellbore production data for training is sparse.In response to this challenge,this work introduces a novel architecture called physics-informed neural network based on domain decomposition(PINN-DD),aiming to effectively utilize the sparse production data of wells for reservoir simulation with large-scale systems.To harness the capabilities of physics-informed neural networks(PINNs)in handling small-scale spatial-temporal domain while addressing the challenges of large-scale systems with sparse labeled data,the computational domain is divided into two distinct sub-domains:the well-containing and the well-free sub-domain.Moreover,the two sub-domains and the interface are rigorously constrained by the governing equations,data matching,and boundary conditions.The accuracy of the proposed method is evaluated on two problems,and its performance is compared against state-of-the-art PINNs through numerical analysis as a benchmark.The results demonstrate the superiority of PINN-DD in handling large-scale reservoir simulation with limited data and show its potential to outperform conventional PINNs in such scenarios.展开更多
In order to solve three kinds of fuzzy programm model, fuzzy chance-constrained programming mode ng models, i.e. fuzzy expected value and fuzzy dependent-chance programming model, a simultaneous perturbation stochast...In order to solve three kinds of fuzzy programm model, fuzzy chance-constrained programming mode ng models, i.e. fuzzy expected value and fuzzy dependent-chance programming model, a simultaneous perturbation stochastic approximation algorithm is proposed by integrating neural network with fuzzy simulation. At first, fuzzy simulation is used to generate a set of input-output data. Then a neural network is trained according to the set. Finally, the trained neural network is embedded in simultaneous perturbation stochastic approximation algorithm. Simultaneous perturbation stochastic approximation algorithm is used to search the optimal solution. Two numerical examples are presented to illustrate the effectiveness of the proposed algorithm.展开更多
Plastic injection molding is a very complex process and its process planning has a direct influence on product quality and production efficiency. This paper studied the optimization of injection molding process by com...Plastic injection molding is a very complex process and its process planning has a direct influence on product quality and production efficiency. This paper studied the optimization of injection molding process by combining the numerical simulation with back-propagation(BP) networks. The BP networks are trained by the results of numerical simulation. The trained BP networks may:(1) shorten time for process planning;(2) optimize process parameters;(3) be employed in on-line quality control;(4) be integrated with knowledge-based system(KBS) and case-based reasoning(CBR) to make intelligent process planning of injection molding.展开更多
Deep simulations have gained widespread attention owing to their excellent acceleration performances.However,these methods cannot provide effective collision detection and response strategies.We propose a deep interac...Deep simulations have gained widespread attention owing to their excellent acceleration performances.However,these methods cannot provide effective collision detection and response strategies.We propose a deep interac-tive physical simulation framework that can effectively address tool-object collisions.The framework can predict the dynamic information by considering the collision state.In particular,the graph neural network is chosen as the base model,and a collision-aware recursive regression module is introduced to update the network parameters recursively using interpenetration distances calculated from the vertex-face and edge-edge tests.Additionally,a novel self-supervised collision term is introduced to provide a more compact collision response.This study extensively evaluates the proposed method and shows that it effectively reduces interpenetration artifacts while ensuring high simulation efficiency.展开更多
A one-dimensional BOD-DO coupling model for water quality simulation is presented, which adopts Streeter-Phelps equations and the theory of back-propagation artificial neural network. The water quality data of Yangtze...A one-dimensional BOD-DO coupling model for water quality simulation is presented, which adopts Streeter-Phelps equations and the theory of back-propagation artificial neural network. The water quality data of Yangtze River in the Chongqing region in the year of 1989 are divided into 5 groups and used in the learning and testing courses of this model. The result shows that such model is feasible for water quality simulation and is more accurate than traditional models.展开更多
A large amount of data can partly assure good fitting quality for the trained neural networks.When the quantity of experimental or on-site monitoring data is commonly insufficient and the quality is difficult to contr...A large amount of data can partly assure good fitting quality for the trained neural networks.When the quantity of experimental or on-site monitoring data is commonly insufficient and the quality is difficult to control in engineering practice,numerical simulations can provide a large amount of controlled high quality data.Once the neural networks are trained by such data,they can be used for predicting the properties/responses of the engineering objects instantly,saving the further computing efforts of simulation tools.Correspondingly,a strategy for efficiently transferring the input and output data used and obtained in numerical simulations to neural networks is desirable for engineers and programmers.In this work,we proposed a simple image representation strategy of numerical simulations,where the input and output data are all represented by images.The temporal and spatial information is kept and the data are greatly compressed.In addition,the results are readable for not only computers but also human resources.Some examples are given,indicating the effectiveness of the proposed strategy.展开更多
Identification simulation for dynamical system which is based on genetic algorithm (GA) and recurrent multilayer neural network (RMNN) is presented. In order to reduce the inputs of the model, RMNN which can remember ...Identification simulation for dynamical system which is based on genetic algorithm (GA) and recurrent multilayer neural network (RMNN) is presented. In order to reduce the inputs of the model, RMNN which can remember and store some previous parameters is used for identifier. And for its high efficiency and optimization, genetic algorithm is introduced into training RMNN. Simulation results show the effectiveness of the proposed scheme. Under the same training algorithm, the identification performance of RMNN is superior to that of nonrecurrent multilayer neural network (NRMNN).展开更多
Dongguan is an important industrial city, located in the Pearl River Delta, South China. Recently, Dongguan city experienced a rapid urban growth with the locational advantage by transforming from traditional agricult...Dongguan is an important industrial city, located in the Pearl River Delta, South China. Recently, Dongguan city experienced a rapid urban growth with the locational advantage by transforming from traditional agricultural region to modern manufacturing metropolis. The urban transformation became the usual change in China under the background of urbanization which belongs to one trend of globalization in the 21st century. This paper tries to analyze urban growth simulation based on remotely sensed data of previous years and the related physical and socio-economic factors and predict future urban growth in 2024. The study examined and compared the land use/cover (LUC) changes over time based on produced maps of 2004, 2009, and 2014. The results showed that water and forest area decreased since the past years. In contrast, the urban land increased from 2004 to 2014, and this increasing trend will continue to the future years through the urbanization process. Having understood the spatiotemporal trends of urban growth, the study simulated the urban growth of Dongguan city for 2024 using neural network simulation technique. Further, the figure of merit (FoM) of simulated map of 2014 map was 8.86%, which can be accepted in the simulation and used in the prediction process. Based on the consideration of water body and forest, the newly growth area is located in the west, northeast, and southeast regions of Dongguan city. The finding can help us to understand which areas are going to be considered in the future urban planning and policy by the local government.展开更多
Compositional reservoir simulation is an important tool to model fluid flow in oil and gas reservoirs.Important investment decisions regarding oil recovery methods are based on simulation results,where hundred or even...Compositional reservoir simulation is an important tool to model fluid flow in oil and gas reservoirs.Important investment decisions regarding oil recovery methods are based on simulation results,where hundred or even thousand of different runs are performed.In this work,a new methodology using artificial intelligence to learn the thermodynamic equilibrium is proposed.This algorithm is used to replace the classical equilibrium workflow in reservoir simulation.The new method avoids the stability test for single-phase cells in most cases and provides an accurate two-phase flash initial estimate.The classical and the new workflow are compared for a gas-oil mixing case,showing a simulation time speed-up of approximately 50%.The new method can be used in compositional reservoir simulations.展开更多
This study introduces a hybrid Cuckoo Search-Deep Neural Network(CS-DNN)model for uncertainty quantification and composition optimization of Na_(1/2)Bi_(1/2)TiO_(3)(NBT)-based dielectric energy storage ceramics.Addres...This study introduces a hybrid Cuckoo Search-Deep Neural Network(CS-DNN)model for uncertainty quantification and composition optimization of Na_(1/2)Bi_(1/2)TiO_(3)(NBT)-based dielectric energy storage ceramics.Addressing the limitations of traditional ferroelectric materials—such as hysteresis loss and low breakdown strength under high electric fields—we fabricate(1−x)NBBT8-xBMT solid solutions via chemical modification and systematically investigate their temperature stability and composition-dependent energy storage performance through XRD,SEM,and electrical characterization.The key innovation lies in integrating the CS metaheuristic algorithm with a DNN,overcoming localminima in training and establishing a robust composition-property prediction framework.Our model accurately predicts room-temperature dielectric constant(ε_(r)),maximum dielectric constant(ε_(max)),dielectric loss(tanδ),discharge energy density(W_(rec)),and charge-discharge efficiency(η)from compositional inputs.A Monte Carlo-based uncertainty quantification framework,combined with the 3σ statistical criterion,demonstrates that CSDNN outperforms conventional DNN models in three critical aspects:Higher prediction accuracy(R^(2)=0.9717 vs.0.9382 for ε_(max));Tighter error distribution,satisfying the 99.7% confidence interval under the 3σprinciple;Enhanced robustness,maintaining stable predictions across a 25% composition span in generalization tests.While the model’s generalization is constrained by both the limited experimental dataset(n=45)and the underlying assumptions of MC-based data augmentation,the CS-DNN framework establishes a machine learning-guided paradigm for accelerated discovery of high-temperature dielectric capacitors through its unique capability in quantifying composition-level energy storage uncertainties.展开更多
The aim of the research was to create a prediction model for winter rapeseed yield.The constructed model enabled to perform simulation on 30 June,in the current year,immediately before harvesting.An artificial neural ...The aim of the research was to create a prediction model for winter rapeseed yield.The constructed model enabled to perform simulation on 30 June,in the current year,immediately before harvesting.An artificial neural network with multilayer perceptron(MLP) topology was used to build the predictive model.The model was created on the basis of meteorological data(air temperature and atmospheric precipitation) and mineral fertilization data.The data were collected in the period 2008–2017 from 291 productive fields located in Poland,in the southern part of the Opole region.The assessment of the forecast quality created on the basis of the neural model has been verified by defining forecast errors using relative approximation error(RAE),root mean square error(RMS),mean absolute error(MAE),and mean absolute percentage error(MAPE) metrics.An important feature of the created predictive model is the ability to forecast the current agrotechnical year based on current weather and fertilizing data.The lowest value of the MAPE error was obtained for a neural network model based on the MLP network of 21:21-13-6-1:1 structure,which was 9.43%.The performed sensitivity analysis of the network examined the factors that have the greatest impact on the yield of winter rape.The highest rank 1 was obtained by an independent variable with the average air temperature from 1 January to 15 April of 2017(designation by the T1-4_CY model).展开更多
In this paper, neural network control systems for decreasing the spatter of CO2 welding have been created. The Generalized inverse Learning Architecture(GILA), the SPecialized inverse Learning Architecture(SILA)-I &a...In this paper, neural network control systems for decreasing the spatter of CO2 welding have been created. The Generalized inverse Learning Architecture(GILA), the SPecialized inverse Learning Architecture(SILA)-I & H and the Error Back Propagating Model(EBPM) are adopted respectively to simulate the static and dynamic welding control processes. The results of simulation and experiment show that the SILA-I and EBPM have betted properties. The factors affecting the simulating results and the dynamic response quality have also been analyzed.展开更多
Nowadays, with regard to environmental issues, proper operation of wastewater treatment plants is of particular importance that in the case of inappropriate utilization, they will cause serious problems. Processes tha...Nowadays, with regard to environmental issues, proper operation of wastewater treatment plants is of particular importance that in the case of inappropriate utilization, they will cause serious problems. Processes that exist in environmental systems and environmental engineers are dealing with them mostly have two major characteristics: they are dependent on many variables;and there are complex relationships between its components which make them very difficult to analyze. Being familiar with characteristics of industrial town effluents from various wastewater treatment units, which have high qualitative and quantitative variations and more uncertainties compared to urban wastewaters, plays very effective role in governing them. In order to achieve a better and efficient control over the operation of an industrial wastewater treatment plant, powerful mathematical tool can be used that is based on recorded data from some basic parameters of wastewater during a period of treatment plant operation. In this study, the multilayer perceptron (MLP) feed forward neural network with a hidden layer and stop training method was used to predict quality parameters of the industrial effluent. Data of this study are related to the Fajr Industrial Wastewater Treatment Plant located in Mahshahr—Iran that qualitative and quantitative characteristics of its units were used for training, calibration and evaluation of the neural model. Also, Principal Component Analysis technique was applied to modify and improve performance of generated models of neural networks. The results of this model showed good accuracy of the model in estimating qualitative pro- file of wastewater. This model facilitates evaluating the performance of each treatment plant units through comparing the results of prediction model with the standard amount of output.展开更多
This research work investigated comparative studies of expert system design and control of crude oil distillation column (CODC) using artificial neural networks based Monte Carlo (ANNBMC) simulation of random processe...This research work investigated comparative studies of expert system design and control of crude oil distillation column (CODC) using artificial neural networks based Monte Carlo (ANNBMC) simulation of random processes and artificial neural networks (ANN) model which were validated using experimental data obtained from functioning crude oil distillation column of Port-Harcourt Refinery, Nigeria by MATLAB computer program. Ninety percent (90%) of the experimental data sets were used for training while ten percent (10%) were used for testing the networks. The maximum relative errors between the experimental and calculated data obtained from the output variables of the neural network for CODC design were 1.98 error % and 0.57 error % when ANN only and ANNBMC were used respectively while their respective values for the maximum relative error were 0.346 error % and 0.124 error % when they were used for the controller prediction. Larger number of iteration steps of below 2500 and 5000 were required to achieve convergence of less than 10-7?for the training error using ANNBMC for both the design of the CODC and controller respectively while less than 400 and 700 iteration steps were needed to achieve convergence of 10-4?using ANN only. The linear regression analysis performed revealed the minimum and maximum prediction accuracies to be 80.65% and 98.79%;and 98.38% and 99.98% when ANN and ANNBMC were used for the CODC design respectively. Also, the minimum and maximum prediction accuracies were 92.83% and 99.34%;and 98.89% and 99.71% when ANN and ANNBMC were used for the CODC controller respectively as both methodologies have excellent predictions. Hence, artificial neural networks based Monte Carlo simulation is an effective and better tool for the design and control of crude oil distillation column.展开更多
In the current study,an artificial neural network(ANN)and a numerical reservoir simulation(NRS)technique are used to analyse reservoir performance under waterflooding in the ZH86 block of the Zhaozhouqiao oilfield,Chi...In the current study,an artificial neural network(ANN)and a numerical reservoir simulation(NRS)technique are used to analyse reservoir performance under waterflooding in the ZH86 block of the Zhaozhouqiao oilfield,China.Using five input datasets extracted from the history-matched NRS model,an NRS-ANN hybrid is trained using a trial-and-error approach.NRS-ANN hybrid model#46(which has 5,10,10,6,6,and 1 neurons in the input layer,four hidden layers,and output layer,respectively)is found to produce the minimal root mean square error on the test dataset.On the validation data,the prediction performance of the selected NRS-ANN hybrid model achieves a minimal root mean square error of 0.0274 m^(3)/day and maximal coefficient of determination and coefficient of correlation values of about 0.9999.The correlation between the block liquid production rate(BLPR,m^(3)/day),block water production rate(BWPR,m^(3)/day),block water cut(BWCT,%),block water injection rate(BWIR,m^(3)/day),and block reservoir pressure(BRP,bar)as input variables and the simulated oil production rate(SOPRH)as the output variable is investigated.There is a positive correlation between SOPRH and BLPR,BWIR,and BWCT,and a negative correlation between SOPRH and BRP and BWPR.Segment B of ZH86 block experiences a 3.8%increase in BLPR,while segments A and C show declines of 1.3%and 1.6%,respectively.These variations in the liquid production rate correspond to changes in SOPRH of 4.3%,1.9%,and 9.7%for segments A,B,and C,respectively.The prediction performance of the NRS-ANN hybrid model is compared with that of a simple NRS model.The accuracy of the NRS-ANN hybrid model in predicting oil production is found to be 1125 times that of the NRS model.Based on these results,it is concluded that the proposed NRS-ANN hybrid provides an accurate and useful tool for analysing reservoir performance under the waterflooding oil recovery technique.展开更多
The present study proposes a sub-grid scale model for the one-dimensional Burgers turbulence based on the neuralnetwork and deep learning method.The filtered data of the direct numerical simulation is used to establis...The present study proposes a sub-grid scale model for the one-dimensional Burgers turbulence based on the neuralnetwork and deep learning method.The filtered data of the direct numerical simulation is used to establish thetraining data set,the validation data set,and the test data set.The artificial neural network(ANN)methodand Back Propagation method are employed to train parameters in the ANN.The developed ANN is applied toconstruct the sub-grid scale model for the large eddy simulation of the Burgers turbulence in the one-dimensionalspace.The proposed model well predicts the time correlation and the space correlation of the Burgers turbulence.展开更多
This paper proposes a novel method for solving the first-passage time probability problem of nonlinear stochastic dynamic systems.The safe domain boundary is exactly imposed into the radial basis function neural netwo...This paper proposes a novel method for solving the first-passage time probability problem of nonlinear stochastic dynamic systems.The safe domain boundary is exactly imposed into the radial basis function neural network(RBF-NN)architecture such that the solution is an admissible function of the boundary-value problem.In this way,the neural network solution can automatically satisfy the safe domain boundaries and no longer requires adding the corresponding loss terms,thus efficiently handling structure failure problems defined by various safe domain boundaries.The effectiveness of the proposed method is demonstrated through three nonlinear stochastic examples defined by different safe domains,and the results are validated against the extensive Monte Carlo simulations(MCSs).展开更多
Most previous research on areas with abundant rainfall shows that simulations using rainfall-runoff modes have a very high prediction accuracy and applicability when using a back-propagation(BP), feed-forward, multila...Most previous research on areas with abundant rainfall shows that simulations using rainfall-runoff modes have a very high prediction accuracy and applicability when using a back-propagation(BP), feed-forward, multilayer perceptron artificial neural network(ANN). However, in runoff areas with relatively low rainfall or a dry climate, more studies are needed. In these areas—of which oasis-plain areas are a particularly good example—the existence and development of runoff depends largely on that which is generated from alpine regions. Quantitative analysis of the uncertainty of runoff simulation under climate change is the key to improving the utilization and management of water resources in arid areas. Therefore, in this context, three kinds of BP feed-forward, three-layer ANNs with similar structure were chosen as models in this paper.Taking the oasis–plain region traverse by the Qira River Basin in Xinjiang, China, as the research area, the monthly accumulated runoff of the Qira River in the next month was simulated and predicted. The results showed that the training precision of a compact wavelet neural network is low; but from the forecasting results, it could be concluded that the training algorithm can better reflect the whole law of samples. The traditional artificial neural network(TANN) model and radial basis-function neural network(RBFNN) model showed higher accuracy in the training and prediction stage. However, the TANN model, more sensitive to the selection of input variables, requires a large number of numerical simulations to determine the appropriate input variables and the number of hidden-layer neurons. Hence, The RBFNN model is more suitable for the study of such problems. And it can be extended to other similar research arid-oasis areas on the southern edge of the Kunlun Mountains and provides a reference for sustainable water-resource management of arid-oasis areas.展开更多
The prediction of slope stability is considered as one of the critical concerns in geotechnical engineering.Conventional stochastic analysis with spatially variable slopes is time-consuming and highly computation-dema...The prediction of slope stability is considered as one of the critical concerns in geotechnical engineering.Conventional stochastic analysis with spatially variable slopes is time-consuming and highly computation-demanding.To assess the slope stability problems with a more desirable computational effort,many machine learning(ML)algorithms have been proposed.However,most ML-based techniques require that the training data must be in the same feature space and have the same distribution,and the model may need to be rebuilt when the spatial distribution changes.This paper presents a new ML-based algorithm,which combines the principal component analysis(PCA)-based neural network(NN)and transfer learning(TL)techniques(i.e.PCAeNNeTL)to conduct the stability analysis of slopes with different spatial distributions.The Monte Carlo coupled with finite element simulation is first conducted for data acquisition considering the spatial variability of cohesive strength or friction angle of soils from eight slopes with the same geometry.The PCA method is incorporated into the neural network algorithm(i.e.PCA-NN)to increase the computational efficiency by reducing the input variables.It is found that the PCA-NN algorithm performs well in improving the prediction of slope stability for a given slope in terms of the computational accuracy and computational effort when compared with the other two algorithms(i.e.NN and decision trees,DT).Furthermore,the PCAeNNeTL algorithm shows great potential in assessing the stability of slope even with fewer training data.展开更多
基金supported by National Natural Science Foundation of China(52274323 and 524743495)the Postdoctoral Fellowship Program of CPSF under Grant Number GZC20240231.
文摘In the electroslag remelting(ESR)process,it mainly relies on thermal experiments or analysis via mechanistic models to realize the physical fields simulation of the electromagnetic field and temperature field coupled transfer,which has the limitations of high cost,a large amount of calculating data and high computing power requirements.A novel network based on physics-informed neural network(PINN)was designed to realize the fast and high-fidelity prediction of the distribution of electromagnetic field and temperature field in ESR process.The physical laws were combined with the deep learning network through PINN,and physical constraints were embedded to achieve effective solution of partial differential equations(PDEs).PINN was used to minimize the loss function consisting of data error,physical information error and boundary condition error.The physical laws and boundary condition constraints in the ESR process were considered to maintain high PDE solution accuracy under different spatial and temporal resolutions.Automatic differentiation(Autodiff)technique and gradient descent algorithm were used to optimize the network parameters.The experimental results show that compared with the mechanistic models,PINN can effectively replace thermal experiments to realize the physical field simulation of ESR process with only a few experimental data,which can avoid the disadvantages of pure data-driven network simulation that requires a large amount of training data.Moreover,the solution of PINN has good physical interpretability and reliability of simulation results.For simulating electromagnetic field and temperature field distribution,the training time of the network is only 140 and 203 s,and the regression indicators of root mean square error can reach 12.65 and 13.76,respectively.
基金funded by the National Natural Science Foundation of China(Grant No.52274048)Beijing Natural Science Foundation(Grant No.3222037)+1 种基金the CNPC 14th Five-Year Perspective Fundamental Research Project(Grant No.2021DJ2104)the Science Foundation of China University of Petroleum-Beijing(No.2462021YXZZ010).
文摘Recent advances in deep learning have expanded new possibilities for fluid flow simulation in petroleum reservoirs.However,the predominant approach in existing research is to train neural networks using high-fidelity numerical simulation data.This presents a significant challenge because the sole source of authentic wellbore production data for training is sparse.In response to this challenge,this work introduces a novel architecture called physics-informed neural network based on domain decomposition(PINN-DD),aiming to effectively utilize the sparse production data of wells for reservoir simulation with large-scale systems.To harness the capabilities of physics-informed neural networks(PINNs)in handling small-scale spatial-temporal domain while addressing the challenges of large-scale systems with sparse labeled data,the computational domain is divided into two distinct sub-domains:the well-containing and the well-free sub-domain.Moreover,the two sub-domains and the interface are rigorously constrained by the governing equations,data matching,and boundary conditions.The accuracy of the proposed method is evaluated on two problems,and its performance is compared against state-of-the-art PINNs through numerical analysis as a benchmark.The results demonstrate the superiority of PINN-DD in handling large-scale reservoir simulation with limited data and show its potential to outperform conventional PINNs in such scenarios.
基金National Natural Science Foundation of China (No.70471049)China Postdoctoral Science Foundation (No. 20060400704)
文摘In order to solve three kinds of fuzzy programm model, fuzzy chance-constrained programming mode ng models, i.e. fuzzy expected value and fuzzy dependent-chance programming model, a simultaneous perturbation stochastic approximation algorithm is proposed by integrating neural network with fuzzy simulation. At first, fuzzy simulation is used to generate a set of input-output data. Then a neural network is trained according to the set. Finally, the trained neural network is embedded in simultaneous perturbation stochastic approximation algorithm. Simultaneous perturbation stochastic approximation algorithm is used to search the optimal solution. Two numerical examples are presented to illustrate the effectiveness of the proposed algorithm.
文摘Plastic injection molding is a very complex process and its process planning has a direct influence on product quality and production efficiency. This paper studied the optimization of injection molding process by combining the numerical simulation with back-propagation(BP) networks. The BP networks are trained by the results of numerical simulation. The trained BP networks may:(1) shorten time for process planning;(2) optimize process parameters;(3) be employed in on-line quality control;(4) be integrated with knowledge-based system(KBS) and case-based reasoning(CBR) to make intelligent process planning of injection molding.
基金This project was funded by Natural Science Foundation of Guangdong Province,No.2020B010165004。
文摘Deep simulations have gained widespread attention owing to their excellent acceleration performances.However,these methods cannot provide effective collision detection and response strategies.We propose a deep interac-tive physical simulation framework that can effectively address tool-object collisions.The framework can predict the dynamic information by considering the collision state.In particular,the graph neural network is chosen as the base model,and a collision-aware recursive regression module is introduced to update the network parameters recursively using interpenetration distances calculated from the vertex-face and edge-edge tests.Additionally,a novel self-supervised collision term is introduced to provide a more compact collision response.This study extensively evaluates the proposed method and shows that it effectively reduces interpenetration artifacts while ensuring high simulation efficiency.
基金Funded by the National Natural Science Foundation of China (No.59838300 No.59778021)
文摘A one-dimensional BOD-DO coupling model for water quality simulation is presented, which adopts Streeter-Phelps equations and the theory of back-propagation artificial neural network. The water quality data of Yangtze River in the Chongqing region in the year of 1989 are divided into 5 groups and used in the learning and testing courses of this model. The result shows that such model is feasible for water quality simulation and is more accurate than traditional models.
基金support from the National Natural Science Foundation of China(NSFC)(52178324).
文摘A large amount of data can partly assure good fitting quality for the trained neural networks.When the quantity of experimental or on-site monitoring data is commonly insufficient and the quality is difficult to control in engineering practice,numerical simulations can provide a large amount of controlled high quality data.Once the neural networks are trained by such data,they can be used for predicting the properties/responses of the engineering objects instantly,saving the further computing efforts of simulation tools.Correspondingly,a strategy for efficiently transferring the input and output data used and obtained in numerical simulations to neural networks is desirable for engineers and programmers.In this work,we proposed a simple image representation strategy of numerical simulations,where the input and output data are all represented by images.The temporal and spatial information is kept and the data are greatly compressed.In addition,the results are readable for not only computers but also human resources.Some examples are given,indicating the effectiveness of the proposed strategy.
文摘Identification simulation for dynamical system which is based on genetic algorithm (GA) and recurrent multilayer neural network (RMNN) is presented. In order to reduce the inputs of the model, RMNN which can remember and store some previous parameters is used for identifier. And for its high efficiency and optimization, genetic algorithm is introduced into training RMNN. Simulation results show the effectiveness of the proposed scheme. Under the same training algorithm, the identification performance of RMNN is superior to that of nonrecurrent multilayer neural network (NRMNN).
文摘Dongguan is an important industrial city, located in the Pearl River Delta, South China. Recently, Dongguan city experienced a rapid urban growth with the locational advantage by transforming from traditional agricultural region to modern manufacturing metropolis. The urban transformation became the usual change in China under the background of urbanization which belongs to one trend of globalization in the 21st century. This paper tries to analyze urban growth simulation based on remotely sensed data of previous years and the related physical and socio-economic factors and predict future urban growth in 2024. The study examined and compared the land use/cover (LUC) changes over time based on produced maps of 2004, 2009, and 2014. The results showed that water and forest area decreased since the past years. In contrast, the urban land increased from 2004 to 2014, and this increasing trend will continue to the future years through the urbanization process. Having understood the spatiotemporal trends of urban growth, the study simulated the urban growth of Dongguan city for 2024 using neural network simulation technique. Further, the figure of merit (FoM) of simulated map of 2014 map was 8.86%, which can be accepted in the simulation and used in the prediction process. Based on the consideration of water body and forest, the newly growth area is located in the west, northeast, and southeast regions of Dongguan city. The finding can help us to understand which areas are going to be considered in the future urban planning and policy by the local government.
文摘Compositional reservoir simulation is an important tool to model fluid flow in oil and gas reservoirs.Important investment decisions regarding oil recovery methods are based on simulation results,where hundred or even thousand of different runs are performed.In this work,a new methodology using artificial intelligence to learn the thermodynamic equilibrium is proposed.This algorithm is used to replace the classical equilibrium workflow in reservoir simulation.The new method avoids the stability test for single-phase cells in most cases and provides an accurate two-phase flash initial estimate.The classical and the new workflow are compared for a gas-oil mixing case,showing a simulation time speed-up of approximately 50%.The new method can be used in compositional reservoir simulations.
基金supported by the Postgraduate Education Reform and Quality Improvement Project of Henan Province(Grant Nos.YJS2023JD52 and YJS2025GZZ48)the Zhumadian 2023 Major Science and Technology Special Project(Grant No.ZMD SZDZX2023002)+1 种基金2025 Henan Province International Science and Technology Cooperation Project(Cultivation Project,No.252102521011)Research Merit-Based Funding Program for Overseas Educated Personnel in Henan Province(Letter of Henan Human Resources and Social Security Office[2025]No.37).
文摘This study introduces a hybrid Cuckoo Search-Deep Neural Network(CS-DNN)model for uncertainty quantification and composition optimization of Na_(1/2)Bi_(1/2)TiO_(3)(NBT)-based dielectric energy storage ceramics.Addressing the limitations of traditional ferroelectric materials—such as hysteresis loss and low breakdown strength under high electric fields—we fabricate(1−x)NBBT8-xBMT solid solutions via chemical modification and systematically investigate their temperature stability and composition-dependent energy storage performance through XRD,SEM,and electrical characterization.The key innovation lies in integrating the CS metaheuristic algorithm with a DNN,overcoming localminima in training and establishing a robust composition-property prediction framework.Our model accurately predicts room-temperature dielectric constant(ε_(r)),maximum dielectric constant(ε_(max)),dielectric loss(tanδ),discharge energy density(W_(rec)),and charge-discharge efficiency(η)from compositional inputs.A Monte Carlo-based uncertainty quantification framework,combined with the 3σ statistical criterion,demonstrates that CSDNN outperforms conventional DNN models in three critical aspects:Higher prediction accuracy(R^(2)=0.9717 vs.0.9382 for ε_(max));Tighter error distribution,satisfying the 99.7% confidence interval under the 3σprinciple;Enhanced robustness,maintaining stable predictions across a 25% composition span in generalization tests.While the model’s generalization is constrained by both the limited experimental dataset(n=45)and the underlying assumptions of MC-based data augmentation,the CS-DNN framework establishes a machine learning-guided paradigm for accelerated discovery of high-temperature dielectric capacitors through its unique capability in quantifying composition-level energy storage uncertainties.
文摘The aim of the research was to create a prediction model for winter rapeseed yield.The constructed model enabled to perform simulation on 30 June,in the current year,immediately before harvesting.An artificial neural network with multilayer perceptron(MLP) topology was used to build the predictive model.The model was created on the basis of meteorological data(air temperature and atmospheric precipitation) and mineral fertilization data.The data were collected in the period 2008–2017 from 291 productive fields located in Poland,in the southern part of the Opole region.The assessment of the forecast quality created on the basis of the neural model has been verified by defining forecast errors using relative approximation error(RAE),root mean square error(RMS),mean absolute error(MAE),and mean absolute percentage error(MAPE) metrics.An important feature of the created predictive model is the ability to forecast the current agrotechnical year based on current weather and fertilizing data.The lowest value of the MAPE error was obtained for a neural network model based on the MLP network of 21:21-13-6-1:1 structure,which was 9.43%.The performed sensitivity analysis of the network examined the factors that have the greatest impact on the yield of winter rape.The highest rank 1 was obtained by an independent variable with the average air temperature from 1 January to 15 April of 2017(designation by the T1-4_CY model).
文摘In this paper, neural network control systems for decreasing the spatter of CO2 welding have been created. The Generalized inverse Learning Architecture(GILA), the SPecialized inverse Learning Architecture(SILA)-I & H and the Error Back Propagating Model(EBPM) are adopted respectively to simulate the static and dynamic welding control processes. The results of simulation and experiment show that the SILA-I and EBPM have betted properties. The factors affecting the simulating results and the dynamic response quality have also been analyzed.
文摘Nowadays, with regard to environmental issues, proper operation of wastewater treatment plants is of particular importance that in the case of inappropriate utilization, they will cause serious problems. Processes that exist in environmental systems and environmental engineers are dealing with them mostly have two major characteristics: they are dependent on many variables;and there are complex relationships between its components which make them very difficult to analyze. Being familiar with characteristics of industrial town effluents from various wastewater treatment units, which have high qualitative and quantitative variations and more uncertainties compared to urban wastewaters, plays very effective role in governing them. In order to achieve a better and efficient control over the operation of an industrial wastewater treatment plant, powerful mathematical tool can be used that is based on recorded data from some basic parameters of wastewater during a period of treatment plant operation. In this study, the multilayer perceptron (MLP) feed forward neural network with a hidden layer and stop training method was used to predict quality parameters of the industrial effluent. Data of this study are related to the Fajr Industrial Wastewater Treatment Plant located in Mahshahr—Iran that qualitative and quantitative characteristics of its units were used for training, calibration and evaluation of the neural model. Also, Principal Component Analysis technique was applied to modify and improve performance of generated models of neural networks. The results of this model showed good accuracy of the model in estimating qualitative pro- file of wastewater. This model facilitates evaluating the performance of each treatment plant units through comparing the results of prediction model with the standard amount of output.
文摘This research work investigated comparative studies of expert system design and control of crude oil distillation column (CODC) using artificial neural networks based Monte Carlo (ANNBMC) simulation of random processes and artificial neural networks (ANN) model which were validated using experimental data obtained from functioning crude oil distillation column of Port-Harcourt Refinery, Nigeria by MATLAB computer program. Ninety percent (90%) of the experimental data sets were used for training while ten percent (10%) were used for testing the networks. The maximum relative errors between the experimental and calculated data obtained from the output variables of the neural network for CODC design were 1.98 error % and 0.57 error % when ANN only and ANNBMC were used respectively while their respective values for the maximum relative error were 0.346 error % and 0.124 error % when they were used for the controller prediction. Larger number of iteration steps of below 2500 and 5000 were required to achieve convergence of less than 10-7?for the training error using ANNBMC for both the design of the CODC and controller respectively while less than 400 and 700 iteration steps were needed to achieve convergence of 10-4?using ANN only. The linear regression analysis performed revealed the minimum and maximum prediction accuracies to be 80.65% and 98.79%;and 98.38% and 99.98% when ANN and ANNBMC were used for the CODC design respectively. Also, the minimum and maximum prediction accuracies were 92.83% and 99.34%;and 98.89% and 99.71% when ANN and ANNBMC were used for the CODC controller respectively as both methodologies have excellent predictions. Hence, artificial neural networks based Monte Carlo simulation is an effective and better tool for the design and control of crude oil distillation column.
基金Funding for this research was provided by the Department of Petroleum Engineering,China University of Geosciences,under the sponsorship of the China Scholarship Council (CSC)the National Natural Science Foundation of China through grant nos.41972326 and 51774258.
文摘In the current study,an artificial neural network(ANN)and a numerical reservoir simulation(NRS)technique are used to analyse reservoir performance under waterflooding in the ZH86 block of the Zhaozhouqiao oilfield,China.Using five input datasets extracted from the history-matched NRS model,an NRS-ANN hybrid is trained using a trial-and-error approach.NRS-ANN hybrid model#46(which has 5,10,10,6,6,and 1 neurons in the input layer,four hidden layers,and output layer,respectively)is found to produce the minimal root mean square error on the test dataset.On the validation data,the prediction performance of the selected NRS-ANN hybrid model achieves a minimal root mean square error of 0.0274 m^(3)/day and maximal coefficient of determination and coefficient of correlation values of about 0.9999.The correlation between the block liquid production rate(BLPR,m^(3)/day),block water production rate(BWPR,m^(3)/day),block water cut(BWCT,%),block water injection rate(BWIR,m^(3)/day),and block reservoir pressure(BRP,bar)as input variables and the simulated oil production rate(SOPRH)as the output variable is investigated.There is a positive correlation between SOPRH and BLPR,BWIR,and BWCT,and a negative correlation between SOPRH and BRP and BWPR.Segment B of ZH86 block experiences a 3.8%increase in BLPR,while segments A and C show declines of 1.3%and 1.6%,respectively.These variations in the liquid production rate correspond to changes in SOPRH of 4.3%,1.9%,and 9.7%for segments A,B,and C,respectively.The prediction performance of the NRS-ANN hybrid model is compared with that of a simple NRS model.The accuracy of the NRS-ANN hybrid model in predicting oil production is found to be 1125 times that of the NRS model.Based on these results,it is concluded that the proposed NRS-ANN hybrid provides an accurate and useful tool for analysing reservoir performance under the waterflooding oil recovery technique.
基金supported by the National Key R&D Program of China(Grant No.2022YFB3303500).
文摘The present study proposes a sub-grid scale model for the one-dimensional Burgers turbulence based on the neuralnetwork and deep learning method.The filtered data of the direct numerical simulation is used to establish thetraining data set,the validation data set,and the test data set.The artificial neural network(ANN)methodand Back Propagation method are employed to train parameters in the ANN.The developed ANN is applied toconstruct the sub-grid scale model for the large eddy simulation of the Burgers turbulence in the one-dimensionalspace.The proposed model well predicts the time correlation and the space correlation of the Burgers turbulence.
基金Project supported by the National Natural Science Foundation of China(Nos.11972070,12072118,and 12372029)the Natural Science Funds for Distinguished Young Scholars of the Fujian Province of China(No.2021J06024)。
文摘This paper proposes a novel method for solving the first-passage time probability problem of nonlinear stochastic dynamic systems.The safe domain boundary is exactly imposed into the radial basis function neural network(RBF-NN)architecture such that the solution is an admissible function of the boundary-value problem.In this way,the neural network solution can automatically satisfy the safe domain boundaries and no longer requires adding the corresponding loss terms,thus efficiently handling structure failure problems defined by various safe domain boundaries.The effectiveness of the proposed method is demonstrated through three nonlinear stochastic examples defined by different safe domains,and the results are validated against the extensive Monte Carlo simulations(MCSs).
基金financially supported by the regional collaborative innovation project for Xinjiang Uygur Autonomous Region (Shanghai cooperation organization science and technology partnership project) (2017E01029)the "Western Light" program of the Chinese Academy of Sciences (2017XBQNXZ-B-016)+1 种基金the National Natural Science Foundation of China (41601595, U1603343, 41471031)the State Key Laboratory of Desert and Oasis Ecology, Xinjiang Institute of Ecology and Geography, Chinese Academy of Sciences (G201802-08)
文摘Most previous research on areas with abundant rainfall shows that simulations using rainfall-runoff modes have a very high prediction accuracy and applicability when using a back-propagation(BP), feed-forward, multilayer perceptron artificial neural network(ANN). However, in runoff areas with relatively low rainfall or a dry climate, more studies are needed. In these areas—of which oasis-plain areas are a particularly good example—the existence and development of runoff depends largely on that which is generated from alpine regions. Quantitative analysis of the uncertainty of runoff simulation under climate change is the key to improving the utilization and management of water resources in arid areas. Therefore, in this context, three kinds of BP feed-forward, three-layer ANNs with similar structure were chosen as models in this paper.Taking the oasis–plain region traverse by the Qira River Basin in Xinjiang, China, as the research area, the monthly accumulated runoff of the Qira River in the next month was simulated and predicted. The results showed that the training precision of a compact wavelet neural network is low; but from the forecasting results, it could be concluded that the training algorithm can better reflect the whole law of samples. The traditional artificial neural network(TANN) model and radial basis-function neural network(RBFNN) model showed higher accuracy in the training and prediction stage. However, the TANN model, more sensitive to the selection of input variables, requires a large number of numerical simulations to determine the appropriate input variables and the number of hidden-layer neurons. Hence, The RBFNN model is more suitable for the study of such problems. And it can be extended to other similar research arid-oasis areas on the southern edge of the Kunlun Mountains and provides a reference for sustainable water-resource management of arid-oasis areas.
基金supported by the National Natural Science Foundation of China(Grant No.52008402)the Central South University autonomous exploration project(Grant No.2021zzts0790).
文摘The prediction of slope stability is considered as one of the critical concerns in geotechnical engineering.Conventional stochastic analysis with spatially variable slopes is time-consuming and highly computation-demanding.To assess the slope stability problems with a more desirable computational effort,many machine learning(ML)algorithms have been proposed.However,most ML-based techniques require that the training data must be in the same feature space and have the same distribution,and the model may need to be rebuilt when the spatial distribution changes.This paper presents a new ML-based algorithm,which combines the principal component analysis(PCA)-based neural network(NN)and transfer learning(TL)techniques(i.e.PCAeNNeTL)to conduct the stability analysis of slopes with different spatial distributions.The Monte Carlo coupled with finite element simulation is first conducted for data acquisition considering the spatial variability of cohesive strength or friction angle of soils from eight slopes with the same geometry.The PCA method is incorporated into the neural network algorithm(i.e.PCA-NN)to increase the computational efficiency by reducing the input variables.It is found that the PCA-NN algorithm performs well in improving the prediction of slope stability for a given slope in terms of the computational accuracy and computational effort when compared with the other two algorithms(i.e.NN and decision trees,DT).Furthermore,the PCAeNNeTL algorithm shows great potential in assessing the stability of slope even with fewer training data.
