The lack of interpretability of the neural network algorithm has become the bottleneck of its wide application.We propose a general mathematical framework,which couples the complex structure of the system with the non...The lack of interpretability of the neural network algorithm has become the bottleneck of its wide application.We propose a general mathematical framework,which couples the complex structure of the system with the nonlinear activation function to explore the decoupled dimension reduction method of high-dime sional system and reveal the calculation mechanism of the neural network.We apply our framework to some network models and a real system of the whole neuron map of Caenorhabditis elegans.Result shows that a simple linear mapping relationship exists between network structure and network behavior in the neural network with highdimensional and nonlinear characteristics.Our simulation and theoretical results fully demonstrate this interesting phenomenon.Our new interpretation mechanism provides not only the potential mathematical calculation principle of neural network but also an effective way to accurately match and predict human brain or animal activities,which can further expand and enrich the interpretable mechanism of artificial neural network in the future.展开更多
System reliability can produce a strong influence on the performance of the heat exchanger network(HEN).In this paper,an optimization method with system reliability analysis for flexible HEN by genetic/simulated annea...System reliability can produce a strong influence on the performance of the heat exchanger network(HEN).In this paper,an optimization method with system reliability analysis for flexible HEN by genetic/simulated annealing algorithms(GA/SA) is presented.Initial flexible arrangements of HEN is received by pseudo-temperature enthalpy diagram.For determining system reliability of HEN,the connections of heat exchangers(HEXs) and independent subsystems in the HEN are analyzed by the connection sequence matrix(CSM),and the system reliability is measured by the independent subsystem including maximum number of HEXs in the HEN.As for the HEN that did not meet system reliability,HEN decoupling is applied and the independent subsystems in the HEN are changed by removing decoupling HEX,and thus the system reliability is elevated.After that,heat duty redistribution based on the relevant elements of the heat load loops and HEX areas are optimized in GA/SA.Then,the favorable network configuration,which matches both the most economical cost and system reliability criterion,is located.Moreover,particular features belonging to suitable decoupling HEX are extracted from calculations.Corresponding numerical example is presented to verify that the proposed strategy is effective to formulate optimal flexible HEN with system reliability measurement.展开更多
Medical image fusion technology is crucial for improving the detection accuracy and treatment efficiency of diseases,but existing fusion methods have problems such as blurred texture details,low contrast,and inability...Medical image fusion technology is crucial for improving the detection accuracy and treatment efficiency of diseases,but existing fusion methods have problems such as blurred texture details,low contrast,and inability to fully extract fused image information.Therefore,a multimodal medical image fusion method based on mask optimization and parallel attention mechanism was proposed to address the aforementioned issues.Firstly,it converted the entire image into a binary mask,and constructed a contour feature map to maximize the contour feature information of the image and a triple path network for image texture detail feature extraction and optimization.Secondly,a contrast enhancement module and a detail preservation module were proposed to enhance the overall brightness and texture details of the image.Afterwards,a parallel attention mechanism was constructed using channel features and spatial feature changes to fuse images and enhance the salient information of the fused images.Finally,a decoupling network composed of residual networks was set up to optimize the information between the fused image and the source image so as to reduce information loss in the fused image.Compared with nine high-level methods proposed in recent years,the seven objective evaluation indicators of our method have improved by 6%−31%,indicating that this method can obtain fusion results with clearer texture details,higher contrast,and smaller pixel differences between the fused image and the source image.It is superior to other comparison algorithms in both subjective and objective indicators.展开更多
Passive detection of moving target is an important part of intelligent surveillance. Satellite has the potential to play a key role in many applications of space-air-ground integrated networks(SAGIN). In this paper, w...Passive detection of moving target is an important part of intelligent surveillance. Satellite has the potential to play a key role in many applications of space-air-ground integrated networks(SAGIN). In this paper, we propose a novel intelligent passive detection method for aerial target based on reservoir computing networks. Specifically, delayed feedback networks are utilized to refine the direct signals from the satellite in the reference channels. In addition, the satellite direct wave interference in the monitoring channels adopts adaptive interference suppression using the minimum mean square error filter. Furthermore, we employ decoupling echo state networks to predict the clutter interference in the monitoring channels and construct the detection statistics accordingly. Finally, a multilayer perceptron is adopted to detect the echo signal after interference suppression. Extensive simulations is conducted to evaluate the performance of our proposed method. Results show that the detection probability is almost 100% when the signal-to-interference ratio of echo signal is-36 dB, which demonstrates that our proposed method achieves efficient passive detection for aerial targets in typical SAGIN scenarios.展开更多
The control objective of the forced-circulation evaporation process of alumina production is not only to avoid large fluctuations of the level, but also to ensure the product density to track its setpoint quickly. Due...The control objective of the forced-circulation evaporation process of alumina production is not only to avoid large fluctuations of the level, but also to ensure the product density to track its setpoint quickly. Due to the existence of strong coupling between the level loop and the product density loop, and high nonlinearities in the process, the conventional control strategy cannot achieve satisfactory control performance, and thus the production demand cannot be met. In this paper, an intelligent decoupling PID controller including conventional PID controllers, a decoupling compensator and a neural feedforward compensator is proposed. The parameters of such controller are determined by generalized predictive control law. Real-time experiment results show that the proposed method can decouple the loops effectively and thus improve the evaporation efficiency.展开更多
Enforcing initial and boundary conditions(I/BCs)poses challenges in physics-informed neural networks(PINNs).Several PINN studies have gained significant achievements in developing techniques for imposing BCs in static...Enforcing initial and boundary conditions(I/BCs)poses challenges in physics-informed neural networks(PINNs).Several PINN studies have gained significant achievements in developing techniques for imposing BCs in static problems;however,the simultaneous enforcement of I/BCs in dynamic problems remains challenging.To overcome this limitation,a novel approach called decoupled physics-informed neural network(d PINN)is proposed in this work.The d PINN operates based on the core idea of converting a partial differential equation(PDE)to a system of ordinary differential equations(ODEs)via the space-time decoupled formulation.To this end,the latent solution is expressed in the form of a linear combination of approximation functions and coefficients,where approximation functions are admissible and coefficients are unknowns of time that must be solved.Subsequently,the system of ODEs is obtained by implementing the weighted-residual form of the original PDE over the spatial domain.A multi-network structure is used to parameterize the set of coefficient functions,and the loss function of d PINN is established based on minimizing the residuals of the gained ODEs.In this scheme,the decoupled formulation leads to the independent handling of I/BCs.Accordingly,the BCs are automatically satisfied based on suitable selections of admissible functions.Meanwhile,the original ICs are replaced by the Galerkin form of the ICs concerning unknown coefficients,and the neural network(NN)outputs are modified to satisfy the gained ICs.Several benchmark problems involving different types of PDEs and I/BCs are used to demonstrate the superior performance of d PINN compared with regular PINN in terms of solution accuracy and computational cost.展开更多
基金This work was supported by the National Natural Science Foundation of China(Grant Nos.72071153,71631001,and 71771186)the Natural Science Foundation of Shaanxi Province(Project No.2020JM-486)the Fund of the Key Laboratory of Equipment Integrated Support Technology(Project No.6142003190102).
文摘The lack of interpretability of the neural network algorithm has become the bottleneck of its wide application.We propose a general mathematical framework,which couples the complex structure of the system with the nonlinear activation function to explore the decoupled dimension reduction method of high-dime sional system and reveal the calculation mechanism of the neural network.We apply our framework to some network models and a real system of the whole neuron map of Caenorhabditis elegans.Result shows that a simple linear mapping relationship exists between network structure and network behavior in the neural network with highdimensional and nonlinear characteristics.Our simulation and theoretical results fully demonstrate this interesting phenomenon.Our new interpretation mechanism provides not only the potential mathematical calculation principle of neural network but also an effective way to accurately match and predict human brain or animal activities,which can further expand and enrich the interpretable mechanism of artificial neural network in the future.
文摘System reliability can produce a strong influence on the performance of the heat exchanger network(HEN).In this paper,an optimization method with system reliability analysis for flexible HEN by genetic/simulated annealing algorithms(GA/SA) is presented.Initial flexible arrangements of HEN is received by pseudo-temperature enthalpy diagram.For determining system reliability of HEN,the connections of heat exchangers(HEXs) and independent subsystems in the HEN are analyzed by the connection sequence matrix(CSM),and the system reliability is measured by the independent subsystem including maximum number of HEXs in the HEN.As for the HEN that did not meet system reliability,HEN decoupling is applied and the independent subsystems in the HEN are changed by removing decoupling HEX,and thus the system reliability is elevated.After that,heat duty redistribution based on the relevant elements of the heat load loops and HEX areas are optimized in GA/SA.Then,the favorable network configuration,which matches both the most economical cost and system reliability criterion,is located.Moreover,particular features belonging to suitable decoupling HEX are extracted from calculations.Corresponding numerical example is presented to verify that the proposed strategy is effective to formulate optimal flexible HEN with system reliability measurement.
基金supported by Gansu Natural Science Foundation Programme(No.24JRRA231)National Natural Science Foundation of China(No.62061023)Gansu Provincial Education,Science and Technology Innovation and Industry(No.2021CYZC-04)。
文摘Medical image fusion technology is crucial for improving the detection accuracy and treatment efficiency of diseases,but existing fusion methods have problems such as blurred texture details,low contrast,and inability to fully extract fused image information.Therefore,a multimodal medical image fusion method based on mask optimization and parallel attention mechanism was proposed to address the aforementioned issues.Firstly,it converted the entire image into a binary mask,and constructed a contour feature map to maximize the contour feature information of the image and a triple path network for image texture detail feature extraction and optimization.Secondly,a contrast enhancement module and a detail preservation module were proposed to enhance the overall brightness and texture details of the image.Afterwards,a parallel attention mechanism was constructed using channel features and spatial feature changes to fuse images and enhance the salient information of the fused images.Finally,a decoupling network composed of residual networks was set up to optimize the information between the fused image and the source image so as to reduce information loss in the fused image.Compared with nine high-level methods proposed in recent years,the seven objective evaluation indicators of our method have improved by 6%−31%,indicating that this method can obtain fusion results with clearer texture details,higher contrast,and smaller pixel differences between the fused image and the source image.It is superior to other comparison algorithms in both subjective and objective indicators.
基金supported by the National Natural Science Foundation of China under Grant 62071364in part by the Aeronautical Science Foundation of China under Grant 2020Z073081001+2 种基金in part by the Fundamental Research Funds for the Central Universities under Grant JB210104in part by the Shaanxi Provincial Key Research and Development Program under Grant 2019GY-043in part by the 111 Project under Grant B08038。
文摘Passive detection of moving target is an important part of intelligent surveillance. Satellite has the potential to play a key role in many applications of space-air-ground integrated networks(SAGIN). In this paper, we propose a novel intelligent passive detection method for aerial target based on reservoir computing networks. Specifically, delayed feedback networks are utilized to refine the direct signals from the satellite in the reference channels. In addition, the satellite direct wave interference in the monitoring channels adopts adaptive interference suppression using the minimum mean square error filter. Furthermore, we employ decoupling echo state networks to predict the clutter interference in the monitoring channels and construct the detection statistics accordingly. Finally, a multilayer perceptron is adopted to detect the echo signal after interference suppression. Extensive simulations is conducted to evaluate the performance of our proposed method. Results show that the detection probability is almost 100% when the signal-to-interference ratio of echo signal is-36 dB, which demonstrates that our proposed method achieves efficient passive detection for aerial targets in typical SAGIN scenarios.
基金Supported by the National Natural Science Foundation of China(61473063)the National Key Technology R&D Program(2012BAJ26B01)+2 种基金the China Postdoctoral Science Foundation(2014M552040,2014M561250,2015M571328)the Special Fund for Agroscientific Research in the Public Interest(201503136)the Key Scientific and Technological Project of Liaoning Province(201500834)
文摘The control objective of the forced-circulation evaporation process of alumina production is not only to avoid large fluctuations of the level, but also to ensure the product density to track its setpoint quickly. Due to the existence of strong coupling between the level loop and the product density loop, and high nonlinearities in the process, the conventional control strategy cannot achieve satisfactory control performance, and thus the production demand cannot be met. In this paper, an intelligent decoupling PID controller including conventional PID controllers, a decoupling compensator and a neural feedforward compensator is proposed. The parameters of such controller are determined by generalized predictive control law. Real-time experiment results show that the proposed method can decouple the loops effectively and thus improve the evaporation efficiency.
基金Project supported by the Basic Science Research Program through the National Research Foundation(NRF)of Korea funded by the Ministry of Science and ICT(No.RS-2024-00337001)。
文摘Enforcing initial and boundary conditions(I/BCs)poses challenges in physics-informed neural networks(PINNs).Several PINN studies have gained significant achievements in developing techniques for imposing BCs in static problems;however,the simultaneous enforcement of I/BCs in dynamic problems remains challenging.To overcome this limitation,a novel approach called decoupled physics-informed neural network(d PINN)is proposed in this work.The d PINN operates based on the core idea of converting a partial differential equation(PDE)to a system of ordinary differential equations(ODEs)via the space-time decoupled formulation.To this end,the latent solution is expressed in the form of a linear combination of approximation functions and coefficients,where approximation functions are admissible and coefficients are unknowns of time that must be solved.Subsequently,the system of ODEs is obtained by implementing the weighted-residual form of the original PDE over the spatial domain.A multi-network structure is used to parameterize the set of coefficient functions,and the loss function of d PINN is established based on minimizing the residuals of the gained ODEs.In this scheme,the decoupled formulation leads to the independent handling of I/BCs.Accordingly,the BCs are automatically satisfied based on suitable selections of admissible functions.Meanwhile,the original ICs are replaced by the Galerkin form of the ICs concerning unknown coefficients,and the neural network(NN)outputs are modified to satisfy the gained ICs.Several benchmark problems involving different types of PDEs and I/BCs are used to demonstrate the superior performance of d PINN compared with regular PINN in terms of solution accuracy and computational cost.
