With the advancement of Vehicle-to-Everything(V2X)technology,efficient resource allocation in dynamic vehicular networks has become a critical challenge for achieving optimal performance.Existing methods suffer from h...With the advancement of Vehicle-to-Everything(V2X)technology,efficient resource allocation in dynamic vehicular networks has become a critical challenge for achieving optimal performance.Existing methods suffer from high computational complexity and decision latency under high-density traffic and heterogeneous network conditions.To address these challenges,this study presents an innovative framework that combines Graph Neural Networks(GNNs)with a Double Deep Q-Network(DDQN),utilizing dynamic graph structures and reinforcement learning.An adaptive neighbor sampling mechanism is introduced to dynamically select the most relevant neighbors based on interference levels and network topology,thereby improving decision accuracy and efficiency.Meanwhile,the framework models communication links as nodes and interference relationships as edges,effectively capturing the direct impact of interference on resource allocation while reducing computational complexity and preserving critical interaction information.Employing an aggregation mechanism based on the Graph Attention Network(GAT),it dynamically adjusts the neighbor sampling scope and performs attention-weighted aggregation based on node importance,ensuring more efficient and adaptive resource management.This design ensures reliable Vehicle-to-Vehicle(V2V)communication while maintaining high Vehicle-to-Infrastructure(V2I)throughput.The framework retains the global feature learning capabilities of GNNs and supports distributed network deployment,allowing vehicles to extract low-dimensional graph embeddings from local observations for real-time resource decisions.Experimental results demonstrate that the proposed method significantly reduces computational overhead,mitigates latency,and improves resource utilization efficiency in vehicular networks under complex traffic scenarios.This research not only provides a novel solution to resource allocation challenges in V2X networks but also advances the application of DDQN in intelligent transportation systems,offering substantial theoretical significance and practical value.展开更多
A highly sensitive double artificial neural network （DANN） analysis with flow-injection chemiluminescence （FI-CL） has been developed to simultaneously determine the trace amounts of the gold and platinum in simula...A highly sensitive double artificial neural network （DANN） analysis with flow-injection chemiluminescence （FI-CL） has been developed to simultaneously determine the trace amounts of the gold and platinum in simulated mixed samples, without the boring process.展开更多
A model is developed for predicting the correlation between processing parameters and the technical target of double glow by applying artificial neural network (ANN). The input parameters of the neural network (NN) ar...A model is developed for predicting the correlation between processing parameters and the technical target of double glow by applying artificial neural network (ANN). The input parameters of the neural network (NN) are source voltage, workplace voltage, working pressure and distance between source electrode and workpiece. The output of the NN model is three important technical targets, namely the gross element content, the thickness of surface alloying layer and the absorption rate (the ratio of the mass loss of source materials to the increasing mass of workpiece) in the processing of double glow plasma surface alloying. The processing parameters and technical target are then used as a training set for an artificial neural network. The model is based on multiplayer feedforward neural network. A very good performance of the neural network is achieved and the calculated results are in good agreement with the experimental ones.展开更多
In cognitive radio networks(CoR),the performance of cooperative spectrum sensing is improved by reducing the overall error rate or maximizing the detection probability.Several optimization methods are usually used to ...In cognitive radio networks(CoR),the performance of cooperative spectrum sensing is improved by reducing the overall error rate or maximizing the detection probability.Several optimization methods are usually used to optimize the number of user-chosen for cooperation and the threshold selection.However,these methods do not take into account the effect of sample size and its effect on improving CoR performance.In general,a large sample size results in more reliable detection,but takes longer sensing time and increases complexity.Thus,the locally sensed sample size is an optimization problem.Therefore,optimizing the local sample size for each cognitive user helps to improve CoR performance.In this study,two new methods are proposed to find the optimum sample size to achieve objective-based improved(single/double)threshold energy detection,these methods are the optimum sample size N^(*)and neural networks(NN)optimization.Through the evaluation,it was found that the proposed methods outperform the traditional sample size selection in terms of the total error rate,detection probability,and throughput.展开更多
This paper expounds a data-fitting algorithm for the double-weight neural network,and presents a new algorithm for the system's power management on the base of that.The double-weight neural network learns knowledg...This paper expounds a data-fitting algorithm for the double-weight neural network,and presents a new algorithm for the system's power management on the base of that.The double-weight neural network learns knowledge from the past idle periods of the system,and predicts the lengths of the coming idle periods.As a result of that,the system can switch its running states and re- duce the power dissipation according to the predictive values.The results of the experiments prove that this algorithm shows a better performance in increasing the right rate of shutting down and reducing the power consumption than other traditional ones.展开更多
Cooling system design applicable to more than one photovoltaic(PV)unit may be challenging due to the arrangement and geometry of the modules.Different cooling techniques are provided in this study to regulate the temp...Cooling system design applicable to more than one photovoltaic(PV)unit may be challenging due to the arrangement and geometry of the modules.Different cooling techniques are provided in this study to regulate the temperature of conductive panels that are arranged perpendicular to each other.The model uses two vented cavity systems and one L-shaped channel with ternary nanofluid enhanced non-uniform magnetic field.Their cooling performances and comparative results between different systems are provided.The finite element method is used to conduct a numerical analysis for a range of values of the following:the strength of themagnetic field(Hartmann number(Ha)between 0 and 50),the inclination of the magnetic field(γbetween 0 and 90),and the loading of nanoparticles in the base fluid(ϕbetween 0 and 0.03),taking into account both uniformand non-uniformmagnetic fields.For the L-shaped channel and vented cavities,vortex size is controlled by imposing magnetic field and adjusting its strength.Whether uniform or non-uniform magnetic field is applied affects the cooling performances for different cooling configurations.Temperature drops of the horizontal panel with different magnetic field strengths by using channel cooling,vented cavity-1 and vented cavity-2 systems for uniformmagnetic are 11℃,21.5℃,and 3℃when the reference case of Ha=0 is considered for the same cooling systems.However,they become 9.5℃,13.5℃,and 12.5℃when nonuniform magnetic field is used.In the presence of uniform magnetic field effects and changing its magnitude,the use of cooling channel in vented cavity-1 and vented cavity-2 systems results in temperature drops of 4℃,10.8℃,and 3.8℃for vertical panels.On the other hand,when non-uniform magnetic field effects are present,they become 0.5℃,2.1℃,and 9℃.For L-channel cooling,the average Nu for the horizontal panel is more affected byγ,andNu rises asγrises.With increasing nanoparticle loading of ternary nanofluid,the average panel surface temperature shows a linear drop.For the horizontal panel,the temperature declines for nanofluid at the highest loading are 4℃,10℃,and 12℃as compared to using only base fluid.The values of 5℃,7℃,and 11℃are obtained for the vertical panel.Different cooling systems’performance is estimated using artificial neural networks.The method captures the combined impact of applying non-uniformmagnetic field and nanofluid together on the cooling performancewhile accounting for varied cooling strategies for both panels.展开更多
Peristaltic transport of non-Newtonian nanofluids with double diffusion is essential to biological engineering,microfluidics,and manufacturing processes.The authors tackle the key problem of Sisko nanofluids under dou...Peristaltic transport of non-Newtonian nanofluids with double diffusion is essential to biological engineering,microfluidics,and manufacturing processes.The authors tackle the key problem of Sisko nanofluids under double diffusion convection with thermal radiations and electroosmotic effects.Thestudy proposes a solution approach by using Morlet-Wavelet Neural Networks that can effectively solve this complex problem by their superior ability in the capture of nonlinear dynamics.These convergence analyses were calculated across fifty independent runs.Theil’s Inequality Coefficient and theMean Squared Error values range from 10^(-7) to 10^(-5) and 10^(-7) to 10^(-10),respectively.These values showed the proposed method is scientifically reliable and fast converging.Studies reveal that the intensity of the magnetic field causes a reduction in the flow velocity profile in the center of the channel.It is also evaluated that thermal radiations enhance the energy of the system,which promotes thermally induced diffusion and particle flow.The physical applications of this work pertain to improving fluid flow and heat transfer in engineering structures like converters or cooling devices or magnetic fluids in electronics,energy,and biomedical applications,where optimal control of fluid behavior is of paramount importance.展开更多
A parallel neural network-based controller （PNNC） is presented for the motion control of underwater vehicles in this paper. It consists of a real-time part, a self-learning part and a desired-state programmer, and i...A parallel neural network-based controller （PNNC） is presented for the motion control of underwater vehicles in this paper. It consists of a real-time part, a self-learning part and a desired-state programmer, and it is different from normal adaptive neural network controller in structure. Owing to the introduction of the self-learning part, on-line learning can be performed without sample data in several sample periods, resulting in high learning speed of the controller and good control performance. The desired-state programmer is utilized to obtain better learning samples of the neural network to keep the stability of the controller. The developed controller is applied to the 4-degree of freedom control of the AUV “IUV- IV” and is successful on the simulation platform. The control performance is also compared with that of neural network controller with different structures such as normal adaptive neural network and different learning methods. Current effects and surge velocity control are also included to demonstrate the controller＇ s performance. It is shown that the PNNC has a great possibility to solve the problems in the control system design of underwater vehicles.展开更多
On the basis of the gain-scheduled H∞ design strategy, a novel active fault-tolerant control scheme is proposed. Under the assumption that the effects of faults on the state-space matrices of systems can be of affine...On the basis of the gain-scheduled H∞ design strategy, a novel active fault-tolerant control scheme is proposed. Under the assumption that the effects of faults on the state-space matrices of systems can be of affine parameter dependence, a reconfigurable robust H∞ linear parameter varying controller is developed. The designed controller is a function of the fault effect factors that can be derived online by using a well-trained neural network. To demonstrate the effectiveness of the proposed method, a double inverted pendulum system, with a fault in the motor tachometer loop, is considered.展开更多
Seismic impedance inversion is an important technique for structure identification and reservoir prediction.Model-based and data-driven impedance inversion are the commonly used inversion methods.In practice,the geoph...Seismic impedance inversion is an important technique for structure identification and reservoir prediction.Model-based and data-driven impedance inversion are the commonly used inversion methods.In practice,the geophysical inversion problem is essentially an ill-posedness problem,which means that there are many solutions corresponding to the same seismic data.Therefore,regularization schemes,which can provide stable and unique inversion results to some extent,have been introduced into the objective function as constrain terms.Among them,given a low-frequency initial impedance model is the most commonly used regularization method,which can provide a smooth and stable solution.However,this model-based inversion method relies heavily on the initial model and the inversion result is band limited to the effective frequency bandwidth of seismic data,which cannot effectively improve the seismic vertical resolution and is difficult to be applied to complex structural regions.Therefore,we propose a data-driven approach for high-resolution impedance inversion based on the bidirectional long short-term memory recurrent neural network,which regards seismic data as time-series rather than image-like patches.Compared with the model-based inversion method,the data-driven approach provides higher resolution inversion results,which demonstrates the effectiveness of the data-driven method for recovering the high-frequency components.However,judging from the inversion results for characterization the spatial distribution of thin-layer sands,the accuracy of high-frequency components is difficult to guarantee.Therefore,we add the model constraint to the objective function to overcome the shortages of relying only on the data-driven schemes.First,constructing the supervisor1 based on the bidirectional long short-term memory recurrent neural network,which provides the predicted impedance with higher resolution.Then,convolution constraint as supervisor2 is introduced into the objective function to guarantee the reliability and accuracy of the inversion results,which makes the synthetic seismic data obtained from the inversion result consistent with the input data.Finally,we test the proposed scheme based on the synthetic and field seismic data.Compared to model-based and purely data-driven impedance inversion methods,the proposed approach provides more accurate and reliable inversion results while with higher vertical resolution and better spatial continuity.The inversion results accurately characterize the spatial distribution relationship of thin sands.The model tests demonstrate that the model-constrained and data-driven impedance inversion scheme can effectively improve the thin-layer structure characterization based on the seismic data.Moreover,tests on the oil field data indicate the practicality and adaptability of the proposed method.展开更多
Purpose–The wavelet neural network(WNN)has the drawbacks of slow convergence speed and easy falling into local optima in data prediction.Although the artificial bee colony(ABC)algorithm has strong global optimization...Purpose–The wavelet neural network(WNN)has the drawbacks of slow convergence speed and easy falling into local optima in data prediction.Although the artificial bee colony(ABC)algorithm has strong global optimization ability and fast convergence speed,it also has the drawbacks of slow speed while finding the optimal solution and weak optimization ability in the later stage.Design/methodology/approach–This article uses an ABC algorithm to optimize the WNN and establishes an ABC-WNN analysis model.Based on the example of the Jinan Yuhan underground tunnel project,the deformation of the surrounding rock of the double-arch tunnel crossing the fault fracture zone is predicted and analyzed,and the analysis results are compared with the actual detection amount.Findings–The comparison results show that the predicted values of the ABC-WNN model have a high degree of fitting with the actual engineering data,with a maximum relative error of only 4.73%.On this basis,the results show that the statistical features of ABC-WNN are the lowest,with the errors at 0.566 and 0.573,compared with the single back propagation(BP)neural network model and WNN model.Therefore,it can be derived that the ABC-WNN model has higher prediction accuracy,better computational stability and faster convergence speed for deformation.Originality/value–This article uses firstly the ABC-WNN for the deformation analysis of double-arch tunnels.This attempt laid the foundation for artificial intelligence prediction in deformation analysis of multiarch tunnels and small clearance tunnels.It can provide a new and effective way for deformation prediction in similar projects.展开更多
Online estimation of the double nugget diameters was performed by means of a back propagation neural network.The double nugget diameters were obtained using actual welding experiment and numerical simulation,according...Online estimation of the double nugget diameters was performed by means of a back propagation neural network.The double nugget diameters were obtained using actual welding experiment and numerical simulation,according to different characteristics of aluminum nugget and steel nugget.The input of the neural network was some key characteristic parameters extracted from dynamic power signal,which were peak point,knee point and their variation rate over time,as well as heat energy delivered into the welding system.The architecture of the neural network was confirmed by confirming the number of neurons in hidden layer through a series of calculations.The key parameters of the neural network were obtained by means of training 81 arrays of data set.Then,the neural network was used to test the remaining 20 arrays of verifying data set,and the results showed that both of the mean errors for the two nugget diameters were below 3%.In addition,corresponding analyses showed that the accuracy of two nugget diameters was higher than that of tensile-shear strength.展开更多
Constructing metamodel with global high-fidelity in design space is significant in engineering design. In this paper, a double-stage metamodel （DSM） which integrates advantages of both interpolation metamodel and re...Constructing metamodel with global high-fidelity in design space is significant in engineering design. In this paper, a double-stage metamodel （DSM） which integrates advantages of both interpolation metamodel and regression metamodel is constructed. It takes regression model as the first stage to fit overall distribution of the original model, and then interpolation model of regression model approximation error is used as the second stage to improve accuracy. Under the same conditions and with the same samples, DSM expresses higher fidelity and represents physical characteristics of original model better. Besides, in order to validate DSM characteristics, three examples including Ackley function, airfoil aerodynamic analysis and wing aerodynamic analysis are investigated, In the end, airfoil and wing aerodynamic design optimizations using genetic algorithm are presented to verify the engineering applicability of DSM.展开更多
Aiming at the dimension disaster problem, poor model generalization ability and deadlock problem in special obstacles environment caused by the increase of state information in the local path planning process of mobil...Aiming at the dimension disaster problem, poor model generalization ability and deadlock problem in special obstacles environment caused by the increase of state information in the local path planning process of mobile robot, this paper proposed a Double BP Q-learning algorithm based on the fusion of Double Q-learning algorithm and BP neural network. In order to solve the dimensional disaster problem, two BP neural network fitting value functions with the same network structure were used to replace the two <i>Q</i> value tables in Double Q-Learning algorithm to solve the problem that the <i>Q</i> value table cannot store excessive state information. By adding the mechanism of priority experience replay and using the parameter transfer to initialize the model parameters in different environments, it could accelerate the convergence rate of the algorithm, improve the learning efficiency and the generalization ability of the model. By designing specific action selection strategy in special environment, the deadlock state could be avoided and the mobile robot could reach the target point. Finally, the designed Double BP Q-learning algorithm was simulated and verified, and the probability of mobile robot reaching the target point in the parameter update process was compared with the Double Q-learning algorithm under the same condition of the planned path length. The results showed that the model trained by the improved Double BP Q-learning algorithm had a higher success rate in finding the optimal or sub-optimal path in the dense discrete environment, besides, it had stronger model generalization ability, fewer redundant sections, and could reach the target point without entering the deadlock zone in the special obstacles environment.展开更多
Computational fluid dynamics（CFD） can give a lot of potentially very useful information for hydraulic optimization design of pumps, however, it cannot directly state what kind of modification should be made to impro...Computational fluid dynamics（CFD） can give a lot of potentially very useful information for hydraulic optimization design of pumps, however, it cannot directly state what kind of modification should be made to improve such hydrodynamic performance. In this paper, a more convenient and effective approach is proposed by combined using of CFD, multi-objective genetic algorithm（MOGA） and artificial neural networks（ANN） for a double-channel pump＇s impeller, with maximum head and efficiency set as optimization objectives, four key geometrical parameters including inlet diameter, outlet diameter, exit width and midline wrap angle chosen as optimization parameters. Firstly, a multi-fidelity fitness assignment system in which fitness of impellers serving as training and comparison samples for ANN is evaluated by CFD, meanwhile fitness of impellers generated by MOGA is evaluated by ANN, is established and dramatically reduces the computational expense. Then, a modified MOGA optimization process, in which selection is performed independently in two sub-populations according to two optimization objectives, crossover and mutation is performed afterword in the merged population, is developed to ensure the global optimal solution to be found. Finally, Pareto optimal frontier is found after 500 steps of iterations, and two optimal design schemes are chosen according to the design requirements. The preliminary and optimal design schemes are compared, and the comparing results show that hydraulic performances of both pumps 1 and 2 are improved, with the head and efficiency of pump 1 increased by 5.7% and 5.2%, respectively in the design working conditions, meanwhile shaft power decreased in all working conditions, the head and efficiency of pump 2 increased by 11.7% and 5.9%, respectively while shaft power increased by 5.5%. Inner flow field analyses also show that the backflow phenomenon significantly diminishes at the entrance of the optimal impellers 1 and 2, both the area of vortex and intensity of vortex decreases in the whole flow channel. This paper provides a promising tool to solve the hydraulic optimization problem of pumps＇ impellers.展开更多
Double parallel forward neural network （DPFNN） model is a mixture structure of single-layer perception and single-hidden-layer forward neural network （SLFN）. In this paper, by making use of the idea of online sequ...Double parallel forward neural network （DPFNN） model is a mixture structure of single-layer perception and single-hidden-layer forward neural network （SLFN）. In this paper, by making use of the idea of online sequential extreme learning machine （OS-ELM） on DPFNN, we derive the online sequential double parallel extreme learning machine algorithm （OS-DPELM）. Compared to other similar algorithms, our algorithms can achieve approximate learning performance with fewer numbers of hidden units, as well as the parameters to be determined. The experimental results show that the proposed algorithm has good generalization performance for real world classification problems, and thus can be a necessary and beneficial complement to OS-ELM.展开更多
The elevated-temperature deformation behavior of Ti2AlNb superalloy was observed by isothermal compression experiments in a wide range of temperatures(950–1200°C)and strain rates(0.001–10 s^(-1)).The flow behav...The elevated-temperature deformation behavior of Ti2AlNb superalloy was observed by isothermal compression experiments in a wide range of temperatures(950–1200°C)and strain rates(0.001–10 s^(-1)).The flow behavior is nonlinear,strongly coupled,and multivariable.The constitutive models,namely the double multivariate nonlinear regression model,artificial neural network model,and modified artificial neural network model with an explicit expression,were applied to describe the Ti2AlNb superalloy plastic deformation behavior.The comparative predictability of those constitutive models was further evaluated by considering the correlation coefficient and average absolute relative error.The comparative results show that the modified artificial network model can describe the flow stress of Ti2AlNb superalloy more accurately than the other developed constitutive models.The explicit expression obtained from the modified artificial neural network model can be directly used for finite element simulation.The modified artificial neural network model solves the problems that the double multivariate nonlinear regression model cannot describe the nonlinear,strongly coupled,and multivariable flow behavior of Ti2AlNb superalloy accurately,and the artificial neural network model cannot be embedded into the finite element software directly.However,the modified artificial neural network model is mainly dependent on the quantity of high-quality experimental data and characteristic variables,and the modified artificial neural network model has not physical meanings.Besides,the processing maps were applied to obtain the optimum processing parameters.展开更多
Physical neural networks are artificial neural networks that mimic synapses and neurons using physical systems or materials.These networks harness the distinctive characteristics of physical systems to carry out compu...Physical neural networks are artificial neural networks that mimic synapses and neurons using physical systems or materials.These networks harness the distinctive characteristics of physical systems to carry out computations effectively,potentially surpassing the constraints of conventional digital neural networks.A recent advancement known as“physical self-learning”aims to achieve learning through intrinsic physical processes rather than relying on external computations.This article offers a comprehensive review of the progress made in implementing physical self-learning across various physical systems.Prevailing learning strategies that contribute to the realization of physical self-learning are discussed.Despite challenges in understanding the fundamental mechanism of learning,this work highlights the progress towards constructing intelligent hardware from the ground up,incorporating embedded self-organizing and self-adaptive dynamics in physical systems.展开更多
基金Project ZR2023MF111 supported by Shandong Provincial Natural Science Foundation。
文摘With the advancement of Vehicle-to-Everything(V2X)technology,efficient resource allocation in dynamic vehicular networks has become a critical challenge for achieving optimal performance.Existing methods suffer from high computational complexity and decision latency under high-density traffic and heterogeneous network conditions.To address these challenges,this study presents an innovative framework that combines Graph Neural Networks(GNNs)with a Double Deep Q-Network(DDQN),utilizing dynamic graph structures and reinforcement learning.An adaptive neighbor sampling mechanism is introduced to dynamically select the most relevant neighbors based on interference levels and network topology,thereby improving decision accuracy and efficiency.Meanwhile,the framework models communication links as nodes and interference relationships as edges,effectively capturing the direct impact of interference on resource allocation while reducing computational complexity and preserving critical interaction information.Employing an aggregation mechanism based on the Graph Attention Network(GAT),it dynamically adjusts the neighbor sampling scope and performs attention-weighted aggregation based on node importance,ensuring more efficient and adaptive resource management.This design ensures reliable Vehicle-to-Vehicle(V2V)communication while maintaining high Vehicle-to-Infrastructure(V2I)throughput.The framework retains the global feature learning capabilities of GNNs and supports distributed network deployment,allowing vehicles to extract low-dimensional graph embeddings from local observations for real-time resource decisions.Experimental results demonstrate that the proposed method significantly reduces computational overhead,mitigates latency,and improves resource utilization efficiency in vehicular networks under complex traffic scenarios.This research not only provides a novel solution to resource allocation challenges in V2X networks but also advances the application of DDQN in intelligent transportation systems,offering substantial theoretical significance and practical value.
文摘A highly sensitive double artificial neural network （DANN） analysis with flow-injection chemiluminescence （FI-CL） has been developed to simultaneously determine the trace amounts of the gold and platinum in simulated mixed samples, without the boring process.
文摘A model is developed for predicting the correlation between processing parameters and the technical target of double glow by applying artificial neural network (ANN). The input parameters of the neural network (NN) are source voltage, workplace voltage, working pressure and distance between source electrode and workpiece. The output of the NN model is three important technical targets, namely the gross element content, the thickness of surface alloying layer and the absorption rate (the ratio of the mass loss of source materials to the increasing mass of workpiece) in the processing of double glow plasma surface alloying. The processing parameters and technical target are then used as a training set for an artificial neural network. The model is based on multiplayer feedforward neural network. A very good performance of the neural network is achieved and the calculated results are in good agreement with the experimental ones.
基金This research was funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project Number(PNURSP2022R97),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘In cognitive radio networks(CoR),the performance of cooperative spectrum sensing is improved by reducing the overall error rate or maximizing the detection probability.Several optimization methods are usually used to optimize the number of user-chosen for cooperation and the threshold selection.However,these methods do not take into account the effect of sample size and its effect on improving CoR performance.In general,a large sample size results in more reliable detection,but takes longer sensing time and increases complexity.Thus,the locally sensed sample size is an optimization problem.Therefore,optimizing the local sample size for each cognitive user helps to improve CoR performance.In this study,two new methods are proposed to find the optimum sample size to achieve objective-based improved(single/double)threshold energy detection,these methods are the optimum sample size N^(*)and neural networks(NN)optimization.Through the evaluation,it was found that the proposed methods outperform the traditional sample size selection in terms of the total error rate,detection probability,and throughput.
文摘This paper expounds a data-fitting algorithm for the double-weight neural network,and presents a new algorithm for the system's power management on the base of that.The double-weight neural network learns knowledge from the past idle periods of the system,and predicts the lengths of the coming idle periods.As a result of that,the system can switch its running states and re- duce the power dissipation according to the predictive values.The results of the experiments prove that this algorithm shows a better performance in increasing the right rate of shutting down and reducing the power consumption than other traditional ones.
基金funded by the Deanship of Scientific Research and Libraries,Princess Nourah bint Abdulrahman University,through the Program of Research Project Funding after Publication,grant No.(RPFAP-88-1445).
文摘Cooling system design applicable to more than one photovoltaic(PV)unit may be challenging due to the arrangement and geometry of the modules.Different cooling techniques are provided in this study to regulate the temperature of conductive panels that are arranged perpendicular to each other.The model uses two vented cavity systems and one L-shaped channel with ternary nanofluid enhanced non-uniform magnetic field.Their cooling performances and comparative results between different systems are provided.The finite element method is used to conduct a numerical analysis for a range of values of the following:the strength of themagnetic field(Hartmann number(Ha)between 0 and 50),the inclination of the magnetic field(γbetween 0 and 90),and the loading of nanoparticles in the base fluid(ϕbetween 0 and 0.03),taking into account both uniformand non-uniformmagnetic fields.For the L-shaped channel and vented cavities,vortex size is controlled by imposing magnetic field and adjusting its strength.Whether uniform or non-uniform magnetic field is applied affects the cooling performances for different cooling configurations.Temperature drops of the horizontal panel with different magnetic field strengths by using channel cooling,vented cavity-1 and vented cavity-2 systems for uniformmagnetic are 11℃,21.5℃,and 3℃when the reference case of Ha=0 is considered for the same cooling systems.However,they become 9.5℃,13.5℃,and 12.5℃when nonuniform magnetic field is used.In the presence of uniform magnetic field effects and changing its magnitude,the use of cooling channel in vented cavity-1 and vented cavity-2 systems results in temperature drops of 4℃,10.8℃,and 3.8℃for vertical panels.On the other hand,when non-uniform magnetic field effects are present,they become 0.5℃,2.1℃,and 9℃.For L-channel cooling,the average Nu for the horizontal panel is more affected byγ,andNu rises asγrises.With increasing nanoparticle loading of ternary nanofluid,the average panel surface temperature shows a linear drop.For the horizontal panel,the temperature declines for nanofluid at the highest loading are 4℃,10℃,and 12℃as compared to using only base fluid.The values of 5℃,7℃,and 11℃are obtained for the vertical panel.Different cooling systems’performance is estimated using artificial neural networks.The method captures the combined impact of applying non-uniformmagnetic field and nanofluid together on the cooling performancewhile accounting for varied cooling strategies for both panels.
文摘Peristaltic transport of non-Newtonian nanofluids with double diffusion is essential to biological engineering,microfluidics,and manufacturing processes.The authors tackle the key problem of Sisko nanofluids under double diffusion convection with thermal radiations and electroosmotic effects.Thestudy proposes a solution approach by using Morlet-Wavelet Neural Networks that can effectively solve this complex problem by their superior ability in the capture of nonlinear dynamics.These convergence analyses were calculated across fifty independent runs.Theil’s Inequality Coefficient and theMean Squared Error values range from 10^(-7) to 10^(-5) and 10^(-7) to 10^(-10),respectively.These values showed the proposed method is scientifically reliable and fast converging.Studies reveal that the intensity of the magnetic field causes a reduction in the flow velocity profile in the center of the channel.It is also evaluated that thermal radiations enhance the energy of the system,which promotes thermally induced diffusion and particle flow.The physical applications of this work pertain to improving fluid flow and heat transfer in engineering structures like converters or cooling devices or magnetic fluids in electronics,energy,and biomedical applications,where optimal control of fluid behavior is of paramount importance.
文摘A parallel neural network-based controller （PNNC） is presented for the motion control of underwater vehicles in this paper. It consists of a real-time part, a self-learning part and a desired-state programmer, and it is different from normal adaptive neural network controller in structure. Owing to the introduction of the self-learning part, on-line learning can be performed without sample data in several sample periods, resulting in high learning speed of the controller and good control performance. The desired-state programmer is utilized to obtain better learning samples of the neural network to keep the stability of the controller. The developed controller is applied to the 4-degree of freedom control of the AUV “IUV- IV” and is successful on the simulation platform. The control performance is also compared with that of neural network controller with different structures such as normal adaptive neural network and different learning methods. Current effects and surge velocity control are also included to demonstrate the controller＇ s performance. It is shown that the PNNC has a great possibility to solve the problems in the control system design of underwater vehicles.
文摘On the basis of the gain-scheduled H∞ design strategy, a novel active fault-tolerant control scheme is proposed. Under the assumption that the effects of faults on the state-space matrices of systems can be of affine parameter dependence, a reconfigurable robust H∞ linear parameter varying controller is developed. The designed controller is a function of the fault effect factors that can be derived online by using a well-trained neural network. To demonstrate the effectiveness of the proposed method, a double inverted pendulum system, with a fault in the motor tachometer loop, is considered.
基金funded by R&D Department of China National Petroleum Corporation(2022DQ0604-04)the Strategic Cooperation Technology Projects of CNPC and CUPB(ZLZX2020-03)the Science Research and Technology Development of PetroChina(2021DJ1206).
文摘Seismic impedance inversion is an important technique for structure identification and reservoir prediction.Model-based and data-driven impedance inversion are the commonly used inversion methods.In practice,the geophysical inversion problem is essentially an ill-posedness problem,which means that there are many solutions corresponding to the same seismic data.Therefore,regularization schemes,which can provide stable and unique inversion results to some extent,have been introduced into the objective function as constrain terms.Among them,given a low-frequency initial impedance model is the most commonly used regularization method,which can provide a smooth and stable solution.However,this model-based inversion method relies heavily on the initial model and the inversion result is band limited to the effective frequency bandwidth of seismic data,which cannot effectively improve the seismic vertical resolution and is difficult to be applied to complex structural regions.Therefore,we propose a data-driven approach for high-resolution impedance inversion based on the bidirectional long short-term memory recurrent neural network,which regards seismic data as time-series rather than image-like patches.Compared with the model-based inversion method,the data-driven approach provides higher resolution inversion results,which demonstrates the effectiveness of the data-driven method for recovering the high-frequency components.However,judging from the inversion results for characterization the spatial distribution of thin-layer sands,the accuracy of high-frequency components is difficult to guarantee.Therefore,we add the model constraint to the objective function to overcome the shortages of relying only on the data-driven schemes.First,constructing the supervisor1 based on the bidirectional long short-term memory recurrent neural network,which provides the predicted impedance with higher resolution.Then,convolution constraint as supervisor2 is introduced into the objective function to guarantee the reliability and accuracy of the inversion results,which makes the synthetic seismic data obtained from the inversion result consistent with the input data.Finally,we test the proposed scheme based on the synthetic and field seismic data.Compared to model-based and purely data-driven impedance inversion methods,the proposed approach provides more accurate and reliable inversion results while with higher vertical resolution and better spatial continuity.The inversion results accurately characterize the spatial distribution relationship of thin sands.The model tests demonstrate that the model-constrained and data-driven impedance inversion scheme can effectively improve the thin-layer structure characterization based on the seismic data.Moreover,tests on the oil field data indicate the practicality and adaptability of the proposed method.
基金funded by the Natural Science Foundation of Hebei Province(No:E2020210068)Project of Science and Technology Research and Development Program of China National Railway Group Co.,Ltd.(No:N2020G009).
文摘Purpose–The wavelet neural network(WNN)has the drawbacks of slow convergence speed and easy falling into local optima in data prediction.Although the artificial bee colony(ABC)algorithm has strong global optimization ability and fast convergence speed,it also has the drawbacks of slow speed while finding the optimal solution and weak optimization ability in the later stage.Design/methodology/approach–This article uses an ABC algorithm to optimize the WNN and establishes an ABC-WNN analysis model.Based on the example of the Jinan Yuhan underground tunnel project,the deformation of the surrounding rock of the double-arch tunnel crossing the fault fracture zone is predicted and analyzed,and the analysis results are compared with the actual detection amount.Findings–The comparison results show that the predicted values of the ABC-WNN model have a high degree of fitting with the actual engineering data,with a maximum relative error of only 4.73%.On this basis,the results show that the statistical features of ABC-WNN are the lowest,with the errors at 0.566 and 0.573,compared with the single back propagation(BP)neural network model and WNN model.Therefore,it can be derived that the ABC-WNN model has higher prediction accuracy,better computational stability and faster convergence speed for deformation.Originality/value–This article uses firstly the ABC-WNN for the deformation analysis of double-arch tunnels.This attempt laid the foundation for artificial intelligence prediction in deformation analysis of multiarch tunnels and small clearance tunnels.It can provide a new and effective way for deformation prediction in similar projects.
基金supported by the National Natural Science Foundation of China(No.51605103).
文摘Online estimation of the double nugget diameters was performed by means of a back propagation neural network.The double nugget diameters were obtained using actual welding experiment and numerical simulation,according to different characteristics of aluminum nugget and steel nugget.The input of the neural network was some key characteristic parameters extracted from dynamic power signal,which were peak point,knee point and their variation rate over time,as well as heat energy delivered into the welding system.The architecture of the neural network was confirmed by confirming the number of neurons in hidden layer through a series of calculations.The key parameters of the neural network were obtained by means of training 81 arrays of data set.Then,the neural network was used to test the remaining 20 arrays of verifying data set,and the results showed that both of the mean errors for the two nugget diameters were below 3%.In addition,corresponding analyses showed that the accuracy of two nugget diameters was higher than that of tensile-shear strength.
文摘Constructing metamodel with global high-fidelity in design space is significant in engineering design. In this paper, a double-stage metamodel （DSM） which integrates advantages of both interpolation metamodel and regression metamodel is constructed. It takes regression model as the first stage to fit overall distribution of the original model, and then interpolation model of regression model approximation error is used as the second stage to improve accuracy. Under the same conditions and with the same samples, DSM expresses higher fidelity and represents physical characteristics of original model better. Besides, in order to validate DSM characteristics, three examples including Ackley function, airfoil aerodynamic analysis and wing aerodynamic analysis are investigated, In the end, airfoil and wing aerodynamic design optimizations using genetic algorithm are presented to verify the engineering applicability of DSM.
文摘Aiming at the dimension disaster problem, poor model generalization ability and deadlock problem in special obstacles environment caused by the increase of state information in the local path planning process of mobile robot, this paper proposed a Double BP Q-learning algorithm based on the fusion of Double Q-learning algorithm and BP neural network. In order to solve the dimensional disaster problem, two BP neural network fitting value functions with the same network structure were used to replace the two <i>Q</i> value tables in Double Q-Learning algorithm to solve the problem that the <i>Q</i> value table cannot store excessive state information. By adding the mechanism of priority experience replay and using the parameter transfer to initialize the model parameters in different environments, it could accelerate the convergence rate of the algorithm, improve the learning efficiency and the generalization ability of the model. By designing specific action selection strategy in special environment, the deadlock state could be avoided and the mobile robot could reach the target point. Finally, the designed Double BP Q-learning algorithm was simulated and verified, and the probability of mobile robot reaching the target point in the parameter update process was compared with the Double Q-learning algorithm under the same condition of the planned path length. The results showed that the model trained by the improved Double BP Q-learning algorithm had a higher success rate in finding the optimal or sub-optimal path in the dense discrete environment, besides, it had stronger model generalization ability, fewer redundant sections, and could reach the target point without entering the deadlock zone in the special obstacles environment.
基金Supported by National Natural Science Foundation of China(Grant No.51109094)Priority Academic Program Development of Jiangsu Higher Education Institutions of China
文摘Computational fluid dynamics（CFD） can give a lot of potentially very useful information for hydraulic optimization design of pumps, however, it cannot directly state what kind of modification should be made to improve such hydrodynamic performance. In this paper, a more convenient and effective approach is proposed by combined using of CFD, multi-objective genetic algorithm（MOGA） and artificial neural networks（ANN） for a double-channel pump＇s impeller, with maximum head and efficiency set as optimization objectives, four key geometrical parameters including inlet diameter, outlet diameter, exit width and midline wrap angle chosen as optimization parameters. Firstly, a multi-fidelity fitness assignment system in which fitness of impellers serving as training and comparison samples for ANN is evaluated by CFD, meanwhile fitness of impellers generated by MOGA is evaluated by ANN, is established and dramatically reduces the computational expense. Then, a modified MOGA optimization process, in which selection is performed independently in two sub-populations according to two optimization objectives, crossover and mutation is performed afterword in the merged population, is developed to ensure the global optimal solution to be found. Finally, Pareto optimal frontier is found after 500 steps of iterations, and two optimal design schemes are chosen according to the design requirements. The preliminary and optimal design schemes are compared, and the comparing results show that hydraulic performances of both pumps 1 and 2 are improved, with the head and efficiency of pump 1 increased by 5.7% and 5.2%, respectively in the design working conditions, meanwhile shaft power decreased in all working conditions, the head and efficiency of pump 2 increased by 11.7% and 5.9%, respectively while shaft power increased by 5.5%. Inner flow field analyses also show that the backflow phenomenon significantly diminishes at the entrance of the optimal impellers 1 and 2, both the area of vortex and intensity of vortex decreases in the whole flow channel. This paper provides a promising tool to solve the hydraulic optimization problem of pumps＇ impellers.
基金Supported by the National Natural Science Foundation of China(Grant Nos.1140107661473328+1 种基金1117136761473059)
文摘Double parallel forward neural network （DPFNN） model is a mixture structure of single-layer perception and single-hidden-layer forward neural network （SLFN）. In this paper, by making use of the idea of online sequential extreme learning machine （OS-ELM） on DPFNN, we derive the online sequential double parallel extreme learning machine algorithm （OS-DPELM）. Compared to other similar algorithms, our algorithms can achieve approximate learning performance with fewer numbers of hidden units, as well as the parameters to be determined. The experimental results show that the proposed algorithm has good generalization performance for real world classification problems, and thus can be a necessary and beneficial complement to OS-ELM.
基金China National Science and Technology Major Project(Grant No.2017-VI-0004-0075).
文摘The elevated-temperature deformation behavior of Ti2AlNb superalloy was observed by isothermal compression experiments in a wide range of temperatures(950–1200°C)and strain rates(0.001–10 s^(-1)).The flow behavior is nonlinear,strongly coupled,and multivariable.The constitutive models,namely the double multivariate nonlinear regression model,artificial neural network model,and modified artificial neural network model with an explicit expression,were applied to describe the Ti2AlNb superalloy plastic deformation behavior.The comparative predictability of those constitutive models was further evaluated by considering the correlation coefficient and average absolute relative error.The comparative results show that the modified artificial network model can describe the flow stress of Ti2AlNb superalloy more accurately than the other developed constitutive models.The explicit expression obtained from the modified artificial neural network model can be directly used for finite element simulation.The modified artificial neural network model solves the problems that the double multivariate nonlinear regression model cannot describe the nonlinear,strongly coupled,and multivariable flow behavior of Ti2AlNb superalloy accurately,and the artificial neural network model cannot be embedded into the finite element software directly.However,the modified artificial neural network model is mainly dependent on the quantity of high-quality experimental data and characteristic variables,and the modified artificial neural network model has not physical meanings.Besides,the processing maps were applied to obtain the optimum processing parameters.
基金supported by the National Key Research and Development Program of China(Grant Nos.2022YFA1403300,and 2020YFA0309100)the National Natural Science Foundation of China(Grant Nos.12204107,and 12074073)+2 种基金Shanghai Municipal Science and Technology Major Project(Grant No.2019SHZDZX01)Shanghai Pujiang Program(Grant No.21PJ1401500)Shanghai Science and Technology Committee(Grant Nos.21JC1406200,and 20JC1415900)。
文摘Physical neural networks are artificial neural networks that mimic synapses and neurons using physical systems or materials.These networks harness the distinctive characteristics of physical systems to carry out computations effectively,potentially surpassing the constraints of conventional digital neural networks.A recent advancement known as“physical self-learning”aims to achieve learning through intrinsic physical processes rather than relying on external computations.This article offers a comprehensive review of the progress made in implementing physical self-learning across various physical systems.Prevailing learning strategies that contribute to the realization of physical self-learning are discussed.Despite challenges in understanding the fundamental mechanism of learning,this work highlights the progress towards constructing intelligent hardware from the ground up,incorporating embedded self-organizing and self-adaptive dynamics in physical systems.
