The integration of artificial intelligence(AI)with satellite technology is ushering in a new era of space exploration,with small satellites playing a pivotal role in advancing this field.However,the deployment of mach...The integration of artificial intelligence(AI)with satellite technology is ushering in a new era of space exploration,with small satellites playing a pivotal role in advancing this field.However,the deployment of machine learning(ML)models in space faces distinct challenges,such as single event upsets(SEUs),which are triggered by space radiation and can corrupt the outputs of neural networks.To defend against this threat,we investigate laser-based fault injection techniques on 55-nm SRAM cells,aiming to explore the impact of SEUs on neural network performance.In this paper,we propose a novel solution in the form of Bin-DNCNN,a binary neural network(BNN)-based model that significantly enhances robustness to radiation-induced faults.We conduct experiments to evaluate the denoising effectiveness of different neural network architectures,comparing their resilience to weight errors before and after fault injections.Our experimental results demonstrate that binary neural networks(BNNs)exhibit superior robustness to weight errors compared to traditional deep neural networks(DNNs),making them a promising candidate for spaceborne AI applications.展开更多
Photonic computing has emerged as a promising technology for the ever-increasing computational demands of machine learning and artificial intelligence.Due to the advantages in computing speed,integrated photonic chips...Photonic computing has emerged as a promising technology for the ever-increasing computational demands of machine learning and artificial intelligence.Due to the advantages in computing speed,integrated photonic chips have attracted wide research attention on performing convolutional neural network algorithm.Programmable photonic chips are vital for achieving practical applications of photonic computing.Herein,a programmable photonic chip based on ultrafast laser-induced phase change is fabricated for photonic computing.Through designing the ultrafast laser pulses,the Sb film integrated into photonic waveguides can be reversibly switched between crystalline and amorphous phase,resulting in a large contrast in refractive index and extinction coefficient.As a consequence,the light transmission of waveguides can be switched between write and erase states.To determine the phase change time,the transient laser-induced phase change dynamics of Sb film are revealed at atomic scale,and the time-resolved transient reflectivity is measured.Based on the integrated photonic chip,photonic convolutional neural networks are built to implement machine learning algorithm,and images recognition task is achieved.This work paves a route for fabricating programmable photonic chips by designed ultrafast laser,which will facilitate the application of photonic computing in artificial intelligence.展开更多
Track reconstruction algorithms are critical for polarization measurements.Convolutional neural networks(CNNs)are a promising alternative to traditional moment-based track reconstruction approaches.However,the hexagon...Track reconstruction algorithms are critical for polarization measurements.Convolutional neural networks(CNNs)are a promising alternative to traditional moment-based track reconstruction approaches.However,the hexagonal grid track images obtained using gas pixel detectors(GPDs)for better anisotropy do not match the classical rectangle-based CNN,and converting the track images from hexagonal to square results in a loss of information.We developed a new hexagonal CNN algorithm for track reconstruction and polarization estimation in X-ray polarimeters,which was used to extract the emission angles and absorption points from photoelectron track images and predict the uncer-tainty of the predicted emission angles.The simulated data from the PolarLight test were used to train and test the hexagonal CNN models.For individual energies,the hexagonal CNN algorithm produced 15%-30%improvements in the modulation factor compared to the moment analysis method for 100%polarized data,and its performance was comparable to that of the rectangle-based CNN algorithm that was recently developed by the Imaging X-ray Polarimetry Explorer team,but at a lower computational and storage cost for preprocessing.展开更多
Physics informed neural networks(PINNs)are a deep learning approach designed to solve partial differential equations(PDEs).Accurately learning the initial conditions is crucial when employing PINNs to solve PDEs.Howev...Physics informed neural networks(PINNs)are a deep learning approach designed to solve partial differential equations(PDEs).Accurately learning the initial conditions is crucial when employing PINNs to solve PDEs.However,simply adjusting weights and imposing hard constraints may not always lead to better learning of the initial conditions;sometimes it even makes it difficult for the neural networks to converge.To enhance the accuracy of PINNs in learning the initial conditions,this paper proposes a novel strategy named causally enhanced initial conditions(CEICs).This strategy works by embedding a new loss in the loss function:the loss is constructed by the derivative of the initial condition and the derivative of the neural network at the initial condition.Furthermore,to respect the causality in learning the derivative,a novel causality coefficient is introduced for the training when selecting multiple derivatives.Additionally,because CEICs can provide more accurate pseudo-labels in the first subdomain,they are compatible with the temporal-marching strategy.Experimental results demonstrate that CEICs outperform hard constraints and improve the overall accuracy of pre-training PINNs.For the 1D-Korteweg–de Vries,reaction and convection equations,the CEIC method proposed in this paper reduces the relative error by at least 60%compared to the previous methods.展开更多
The single event effects(SEEs)evaluations caused by atmospheric neutrons were conducted on three different convolutional neural network(CNN)models(Yolov3,MNIST,and ResNet50)in the atmospheric neutron irradiation spect...The single event effects(SEEs)evaluations caused by atmospheric neutrons were conducted on three different convolutional neural network(CNN)models(Yolov3,MNIST,and ResNet50)in the atmospheric neutron irradiation spectrometer(ANIS)at the China Spallation Neutron Source(CSNS).The Yolov3 and MNIST models were implemented on the XILINX28-nm system-on-chip(So C).Meanwhile,the Yolov3 and ResNet50 models were deployed on the XILINX 16-nm Fin FET Ultra Scale+MPSoC.The atmospheric neutron SEEs on the tested CNN systems were comprehensively evaluated from six aspects,including chip type,network architecture,deployment methods,inference time,datasets,and the position of the anchor boxes.The various types of SEE soft errors,SEE cross-sections,and their distribution were analyzed to explore the radiation sensitivities and rules of 28-nm and 16-nm SoC.The current research can provide the technology support of radiation-resistant design of CNN system for developing and applying high-reliability,long-lifespan domestic artificial intelligence chips.展开更多
This paper proposes a concurrent neural network model to mitigate non-linear distortion in power amplifiers using a basis function generation approach.The model is designed using polynomial expansion and comprises a f...This paper proposes a concurrent neural network model to mitigate non-linear distortion in power amplifiers using a basis function generation approach.The model is designed using polynomial expansion and comprises a feedforward neural network(FNN)and a convolutional neural network(CNN).The proposed model takes the basic elements that form the bases as input,defined by the generalized memory polynomial(GMP)and dynamic deviation reduction(DDR)models.The FNN generates the basis function and its output represents the basis values,while the CNN generates weights for the corresponding bases.Through the concurrent training of FNN and CNN,the hidden layer coefficients are updated,and the complex multiplication of their outputs yields the trained in-phase/quadrature(I/Q)signals.The proposed model was trained and tested using 300 MHz and 400 MHz broadband data in an orthogonal frequency division multiplexing(OFDM)communication system.The results show that the model achieves an adjacent channel power ratio(ACPR)of less than-48 d B within a 100 MHz integral bandwidth for both the training and test datasets.展开更多
To address the problems of low accuracy by the CONWEP model and poor efficiency by the Coupled Eulerian-Lagrangian(CEL)method in predicting close-range air blast loads of cylindrical charges,a neural network-based sim...To address the problems of low accuracy by the CONWEP model and poor efficiency by the Coupled Eulerian-Lagrangian(CEL)method in predicting close-range air blast loads of cylindrical charges,a neural network-based simulation(NNS)method with higher accuracy and better efficiency was proposed.The NNS method consisted of three main steps.First,the parameters of blast loads,including the peak pressures and impulses of cylindrical charges with different aspect ratios(L/D)at different stand-off distances and incident angles were obtained by two-dimensional numerical simulations.Subsequently,incident shape factors of cylindrical charges with arbitrary aspect ratios were predicted by a neural network.Finally,reflected shape factors were derived and implemented into the subroutine of the ABAQUS code to modify the CONWEP model,including modifications of impulse and overpressure.The reliability of the proposed NNS method was verified by related experimental results.Remarkable accuracy improvement was acquired by the proposed NNS method compared with the unmodified CONWEP model.Moreover,huge efficiency superiority was obtained by the proposed NNS method compared with the CEL method.The proposed NNS method showed good accuracy when the scaled distance was greater than 0.2 m/kg^(1/3).It should be noted that there is no need to generate a new dataset again since the blast loads satisfy the similarity law,and the proposed NNS method can be directly used to simulate the blast loads generated by different cylindrical charges.The proposed NNS method with high efficiency and accuracy can be used as an effective method to analyze the dynamic response of structures under blast loads,and it has significant application prospects in designing protective structures.展开更多
The ammunition loading system manipulator is susceptible to gear failure due to high-frequency,heavyload reciprocating motions and the absence of protective gear components.After a fault occurs,the distribution of fau...The ammunition loading system manipulator is susceptible to gear failure due to high-frequency,heavyload reciprocating motions and the absence of protective gear components.After a fault occurs,the distribution of fault characteristics under different loads is markedly inconsistent,and data is hard to label,which makes it difficult for the traditional diagnosis method based on single-condition training to generalize to different conditions.To address these issues,the paper proposes a novel transfer discriminant neural network(TDNN)for gear fault diagnosis.Specifically,an optimized joint distribution adaptive mechanism(OJDA)is designed to solve the distribution alignment problem between two domains.To improve the classification effect within the domain and the feature recognition capability for a few labeled data,metric learning is introduced to distinguish features from different fault categories.In addition,TDNN adopts a new pseudo-label training strategy to achieve label replacement by comparing the maximum probability of the pseudo-label with the test result.The proposed TDNN is verified in the experimental data set of the artillery manipulator device,and the diagnosis can achieve 99.5%,significantly outperforming other traditional adaptation methods.展开更多
The high thermal conductivity of the nanoparticles in hybrid nanofluids results in enhanced thermal conductivity associated with their base fluids.Enhanced heat transfer is a result of this high thermal conductivity,w...The high thermal conductivity of the nanoparticles in hybrid nanofluids results in enhanced thermal conductivity associated with their base fluids.Enhanced heat transfer is a result of this high thermal conductivity,which has significant applications in heat exchangers and engineering devices.To optimize heat transfer,a liquid film of Cu and TiO_(2)hybrid nanofluid behind a stretching sheet in a variable porous medium is being considered due to its importance.The nature of the fluid is considered time-dependent and the thickness of the liquid film is measured variable adjustable with the variable porous space and favorable for the uniform flow of the liquid film.The solution of the problem is acquired using the homotopy analysis method HAM,and the artificial neural network ANN is applied to obtain detailed information in the form of error estimation and validations using the fitting curve analysis.HAM data is utilized to train the ANN in this study,which uses Cu and TiO_(2)hybrid nanofluids in a variable porous space for unsteady thin film flow,and it is used to train the ANN.The results indicate that Cu and TiO_(2)play a greater role in boosting the rate.展开更多
Optical neural networks have significant advantages in terms of power consumption,parallelism,and high computing speed,which has intrigued extensive attention in both academic and engineering communities.It has been c...Optical neural networks have significant advantages in terms of power consumption,parallelism,and high computing speed,which has intrigued extensive attention in both academic and engineering communities.It has been considered as one of the powerful tools in promoting the fields of imaging processing and object recognition.However,the existing optical system architecture cannot be reconstructed to the realization of multi-functional artificial intelligence systems simultaneously.To push the development of this issue,we propose the pluggable diffractive neural networks(P-DNN),a general paradigm resorting to the cascaded metasurfaces,which can be applied to recognize various tasks by switching internal plug-ins.As the proof-of-principle,the recognition functions of six types of handwritten digits and six types of fashions are numerical simulated and experimental demonstrated at near-infrared regimes.Encouragingly,the proposed paradigm not only improves the flexibility of the optical neural networks but paves the new route for achieving high-speed,low-power and versatile artificial intelligence systems.展开更多
To reduce CO_(2) emissions in response to global climate change,shale reservoirs could be ideal candidates for long-term carbon geo-sequestration involving multi-scale transport processes.However,most current CO_(2) s...To reduce CO_(2) emissions in response to global climate change,shale reservoirs could be ideal candidates for long-term carbon geo-sequestration involving multi-scale transport processes.However,most current CO_(2) sequestration models do not adequately consider multiple transport mechanisms.Moreover,the evaluation of CO_(2) storage processes usually involves laborious and time-consuming numerical simulations unsuitable for practical prediction and decision-making.In this paper,an integrated model involving gas diffusion,adsorption,dissolution,slip flow,and Darcy flow is proposed to accurately characterize CO_(2) storage in depleted shale reservoirs,supporting the establishment of a training database.On this basis,a hybrid physics-informed data-driven neural network(HPDNN)is developed as a deep learning surrogate for prediction and inversion.By incorporating multiple sources of scientific knowledge,the HPDNN can be configured with limited simulation resources,significantly accelerating the forward and inversion processes.Furthermore,the HPDNN can more intelligently predict injection performance,precisely perform reservoir parameter inversion,and reasonably evaluate the CO_(2) storage capacity under complicated scenarios.The validation and test results demonstrate that the HPDNN can ensure high accuracy and strong robustness across an extensive applicability range when dealing with field data with multiple noise sources.This study has tremendous potential to replace traditional modeling tools for predicting and making decisions about CO_(2) storage projects in depleted shale reservoirs.展开更多
As the main link of ground engineering,crude oil gathering and transportation systems require huge energy consumption and complex structures.It is necessary to establish an energy efficiency evaluation system for crud...As the main link of ground engineering,crude oil gathering and transportation systems require huge energy consumption and complex structures.It is necessary to establish an energy efficiency evaluation system for crude oil gathering and transportation systems and identify the energy efficiency gaps.In this paper,the energy efficiency evaluation system of the crude oil gathering and transportation system in an oilfield in western China is established.Combined with the big data analysis method,the GA-BP neural network is used to establish the energy efficiency index prediction model for crude oil gathering and transportation systems.The comprehensive energy consumption,gas consumption,power consumption,energy utilization rate,heat utilization rate,and power utilization rate of crude oil gathering and transportation systems are predicted.Considering the efficiency and unit consumption index of the crude oil gathering and transportation system,the energy efficiency evaluation system of the crude oil gathering and transportation system is established based on a game theory combined weighting method and TOPSIS evaluation method,and the subjective weight is determined by the triangular fuzzy analytic hierarchy process.The entropy weight method determines the objective weight,and the combined weight of game theory combines subjectivity with objectivity to comprehensively evaluate the comprehensive energy efficiency of crude oil gathering and transportation systems and their subsystems.Finally,the weak links in energy utilization are identified,and energy conservation and consumption reduction are improved.The above research provides technical support for the green,efficient and intelligent development of crude oil gathering and transportation systems.展开更多
This paper investigates interception missiles’trajectory tracking guidance problem under wind field and external disturbances in the boost phase.Indeed,the velocity control in such trajectory tracking guidance system...This paper investigates interception missiles’trajectory tracking guidance problem under wind field and external disturbances in the boost phase.Indeed,the velocity control in such trajectory tracking guidance systems of missiles is challenging.As our contribution,the velocity control channel is designed to deal with the intractable velocity problem and improve tracking accuracy.The global prescribed performance function,which guarantees the tracking error within the set range and the global convergence of the tracking guidance system,is first proposed based on the traditional PPF.Then,a tracking guidance strategy is derived using the integral sliding mode control techniques to make the sliding manifold and tracking errors converge to zero and avoid singularities.Meanwhile,an improved switching control law is introduced into the designed tracking guidance algorithm to deal with the chattering problem.A back propagation neural network(BPNN)extended state observer(BPNNESO)is employed in the inner loop to identify disturbances.The obtained results indicate that the proposed tracking guidance approach achieves the trajectory tracking guidance objective without and with disturbances and outperforms the existing tracking guidance schemes with the lowest tracking errors,convergence times,and overshoots.展开更多
The power module of the Insulated Gate Bipolar Transistor(IGBT)is the core component of the traction transmission system of high-speed trains.The module's junction temperature is a critical factor in determining d...The power module of the Insulated Gate Bipolar Transistor(IGBT)is the core component of the traction transmission system of high-speed trains.The module's junction temperature is a critical factor in determining device reliability.Existing temperature monitoring methods based on the electro-thermal coupling model have limitations,such as ignoring device interactions and high computational complexity.To address these issues,an analysis of the parameters influencing IGBT failure is conducted,and a temperature monitoring method based on the Macro-Micro Attention Long Short-Term Memory(MMALSTM)recursive neural network is proposed,which takes the forward voltage drop and collector current as features.Compared with the traditional electricalthermal coupling model method,it requires fewer monitoring parameters and eliminates the complex loss calculation and equivalent thermal resistance network establishment process.The simulation model of a highspeed train traction system has been established to explore the accuracy and efficiency of MMALSTM-based prediction methods for IGBT power module junction temperature.The simulation outcomes,which deviate only 3.2% from the theoretical calculation results of the electric-thermal coupling model,confirm the reliability of this approach for predicting the temperature of IGBT power modules.展开更多
In a very recent study,Prof.Lingling Huang and co-workers proposed and demonstrated reconfigurable optical neural networks based on cascaded metasurfaces.By fixing one metasurface and switching the other pluggable met...In a very recent study,Prof.Lingling Huang and co-workers proposed and demonstrated reconfigurable optical neural networks based on cascaded metasurfaces.By fixing one metasurface and switching the other pluggable metasurfaces,the neural networks,which operate at near-infrared wavelengths,can perform distinct recognition tasks for handwritten digits and fashion products.This innovative device opens up an avenue for all-optical,high-speed,low-power,and multifunctional artificial intelligence systems.展开更多
The shale gas development process is complex in terms of its flow mechanisms and the accuracy of the production forecasting is influenced by geological parameters and engineering parameters.Therefore,to quantitatively...The shale gas development process is complex in terms of its flow mechanisms and the accuracy of the production forecasting is influenced by geological parameters and engineering parameters.Therefore,to quantitatively evaluate the relative importance of model parameters on the production forecasting performance,sensitivity analysis of parameters is required.The parameters are ranked according to the sensitivity coefficients for the subsequent optimization scheme design.A data-driven global sensitivity analysis(GSA)method using convolutional neural networks(CNN)is proposed to identify the influencing parameters in shale gas production.The CNN is trained on a large dataset,validated against numerical simulations,and utilized as a surrogate model for efficient sensitivity analysis.Our approach integrates CNN with the Sobol'global sensitivity analysis method,presenting three key scenarios for sensitivity analysis:analysis of the production stage as a whole,analysis by fixed time intervals,and analysis by declining rate.The findings underscore the predominant influence of reservoir thickness and well length on shale gas production.Furthermore,the temporal sensitivity analysis reveals the dynamic shifts in parameter importance across the distinct production stages.展开更多
Beams typically do not travel through the magnet centers because of errors in storage rings.The beam deviating from the quadrupole centers is affected by additional dipole fields due to magnetic field feed-down.Beam-b...Beams typically do not travel through the magnet centers because of errors in storage rings.The beam deviating from the quadrupole centers is affected by additional dipole fields due to magnetic field feed-down.Beam-based alignment(BBA)is often performed to determine a golden orbit where the beam circulates around the quadrupole center axes.For storage rings with many quadrupoles,the conventional BBA procedure is time-consuming,particularly in the commissioning phase,because of the necessary iterative process.In addition,the conventional BBA method can be affected by strong coupling and the nonlinearity of the storage ring optics.In this study,a novel method based on a neural network was proposed to determine the golden orbit in a much shorter time with reasonable accuracy.This golden orbit can be used directly for operation or adopted as a starting point for conventional BBA.The method was demonstrated in the HLS-II storage ring for the first time through simulations and online experiments.The results of the experiments showed that the golden orbit obtained using this new method was consistent with that obtained using the conventional BBA.The development of this new method and the corresponding experiments are reported in this paper.展开更多
This letter proposes a sliced-gated-convolutional neural network with belief propagation(SGCNN-BP) architecture for decoding long codes under correlated noise. The basic idea of SGCNNBP is using Neural Networks(NN) to...This letter proposes a sliced-gated-convolutional neural network with belief propagation(SGCNN-BP) architecture for decoding long codes under correlated noise. The basic idea of SGCNNBP is using Neural Networks(NN) to transform the correlated noise into white noise, setting up the optimal condition for a standard BP decoder that takes the output from the NN. A gate-controlled neuron is used to regulate information flow and an optional operation—slicing is adopted to reduce parameters and lower training complexity. Simulation results show that SGCNN-BP has much better performance(with the largest gap being 5dB improvement) than a single BP decoder and achieves a nearly 1dB improvement compared to Fully Convolutional Networks(FCN).展开更多
High-resolution flow field data has important applications in meteorology,aerospace engineering,high-energy physics and other fields.Experiments and numerical simulations are two main ways to obtain high-resolution fl...High-resolution flow field data has important applications in meteorology,aerospace engineering,high-energy physics and other fields.Experiments and numerical simulations are two main ways to obtain high-resolution flow field data,while the high experiment cost and computing resources for simulation hinder the specificanalysis of flow field evolution.With the development of deep learning technology,convolutional neural networks areused to achieve high-resolution reconstruction of the flow field.In this paper,an ordinary convolutional neuralnetwork and a multi-time-path convolutional neural network are established for the ablative Rayleigh-Taylorinstability.These two methods can reconstruct the high-resolution flow field in just a few seconds,and further greatlyenrich the application of high-resolution reconstruction technology in fluid instability.Compared with the ordinaryconvolutional neural network,the multi-time-path convolutional neural network model has smaller error and canrestore more details of the flow field.The influence of low-resolution flow field data obtained by the two poolingmethods on the convolutional neural networks model is also discussed.展开更多
A neural network model with a classical annotation method has been used on the EXL-50tokamak to predict impending disruption.However,the results revealed issues of overfitting and overconfidence in predictions caused ...A neural network model with a classical annotation method has been used on the EXL-50tokamak to predict impending disruption.However,the results revealed issues of overfitting and overconfidence in predictions caused by inaccurate labeling.To mitigate these issues,an improved training framework has been proposed.In this approach,soft labels from previous training serve as teachers to supervise the further learning process;this has lead to a significant improvement in predictive model performance.Notably,this enhancement is primarily attributed to the coupling effect of the soft labels and correction mechanism.This improved training framework introduces an instance-specific label smoothing method,which reflects a more nuanced model assessment on the likelihood of a disruption.It presents a possible solution to effectively address the challenges associated with accurate labeling across different machines.展开更多
文摘The integration of artificial intelligence(AI)with satellite technology is ushering in a new era of space exploration,with small satellites playing a pivotal role in advancing this field.However,the deployment of machine learning(ML)models in space faces distinct challenges,such as single event upsets(SEUs),which are triggered by space radiation and can corrupt the outputs of neural networks.To defend against this threat,we investigate laser-based fault injection techniques on 55-nm SRAM cells,aiming to explore the impact of SEUs on neural network performance.In this paper,we propose a novel solution in the form of Bin-DNCNN,a binary neural network(BNN)-based model that significantly enhances robustness to radiation-induced faults.We conduct experiments to evaluate the denoising effectiveness of different neural network architectures,comparing their resilience to weight errors before and after fault injections.Our experimental results demonstrate that binary neural networks(BNNs)exhibit superior robustness to weight errors compared to traditional deep neural networks(DNNs),making them a promising candidate for spaceborne AI applications.
基金supported by the National Key R&D Program of China(2024YFB4609801)the National Natural Science Foundation of China(52075289)the Tsinghua-Jiangyin Innovation Special Fund(TJISF,2023JYTH0104).
文摘Photonic computing has emerged as a promising technology for the ever-increasing computational demands of machine learning and artificial intelligence.Due to the advantages in computing speed,integrated photonic chips have attracted wide research attention on performing convolutional neural network algorithm.Programmable photonic chips are vital for achieving practical applications of photonic computing.Herein,a programmable photonic chip based on ultrafast laser-induced phase change is fabricated for photonic computing.Through designing the ultrafast laser pulses,the Sb film integrated into photonic waveguides can be reversibly switched between crystalline and amorphous phase,resulting in a large contrast in refractive index and extinction coefficient.As a consequence,the light transmission of waveguides can be switched between write and erase states.To determine the phase change time,the transient laser-induced phase change dynamics of Sb film are revealed at atomic scale,and the time-resolved transient reflectivity is measured.Based on the integrated photonic chip,photonic convolutional neural networks are built to implement machine learning algorithm,and images recognition task is achieved.This work paves a route for fabricating programmable photonic chips by designed ultrafast laser,which will facilitate the application of photonic computing in artificial intelligence.
基金supported by the National Natural Science Foundation of China(No.12025301)the Tsinghua University Initiative Scientific Research Program.
文摘Track reconstruction algorithms are critical for polarization measurements.Convolutional neural networks(CNNs)are a promising alternative to traditional moment-based track reconstruction approaches.However,the hexagonal grid track images obtained using gas pixel detectors(GPDs)for better anisotropy do not match the classical rectangle-based CNN,and converting the track images from hexagonal to square results in a loss of information.We developed a new hexagonal CNN algorithm for track reconstruction and polarization estimation in X-ray polarimeters,which was used to extract the emission angles and absorption points from photoelectron track images and predict the uncer-tainty of the predicted emission angles.The simulated data from the PolarLight test were used to train and test the hexagonal CNN models.For individual energies,the hexagonal CNN algorithm produced 15%-30%improvements in the modulation factor compared to the moment analysis method for 100%polarized data,and its performance was comparable to that of the rectangle-based CNN algorithm that was recently developed by the Imaging X-ray Polarimetry Explorer team,but at a lower computational and storage cost for preprocessing.
基金supported by the National Natural Science Foundation of China(Grant Nos.1217211 and 12372244).
文摘Physics informed neural networks(PINNs)are a deep learning approach designed to solve partial differential equations(PDEs).Accurately learning the initial conditions is crucial when employing PINNs to solve PDEs.However,simply adjusting weights and imposing hard constraints may not always lead to better learning of the initial conditions;sometimes it even makes it difficult for the neural networks to converge.To enhance the accuracy of PINNs in learning the initial conditions,this paper proposes a novel strategy named causally enhanced initial conditions(CEICs).This strategy works by embedding a new loss in the loss function:the loss is constructed by the derivative of the initial condition and the derivative of the neural network at the initial condition.Furthermore,to respect the causality in learning the derivative,a novel causality coefficient is introduced for the training when selecting multiple derivatives.Additionally,because CEICs can provide more accurate pseudo-labels in the first subdomain,they are compatible with the temporal-marching strategy.Experimental results demonstrate that CEICs outperform hard constraints and improve the overall accuracy of pre-training PINNs.For the 1D-Korteweg–de Vries,reaction and convection equations,the CEIC method proposed in this paper reduces the relative error by at least 60%compared to the previous methods.
基金Project supported by the National Natural Science Foundation of China(Grant No.12305303)the Natural Science Foundation of Hunan Province of China(Grant Nos.2023JJ40520,2024JJ2044,and 2021JJ40444)+3 种基金the Science and Technology Innovation Program of Hunan Province,China(Grant No.2020RC3054)the Postgraduate Scientific Research Innovation Project of Hunan Province,China(Grant No.CX20240831)the Natural Science Basic Research Plan in the Shaanxi Province of China(Grant No.2023-JC-QN0015)the Doctoral Research Fund of University of South China(Grant No.200XQD033)。
文摘The single event effects(SEEs)evaluations caused by atmospheric neutrons were conducted on three different convolutional neural network(CNN)models(Yolov3,MNIST,and ResNet50)in the atmospheric neutron irradiation spectrometer(ANIS)at the China Spallation Neutron Source(CSNS).The Yolov3 and MNIST models were implemented on the XILINX28-nm system-on-chip(So C).Meanwhile,the Yolov3 and ResNet50 models were deployed on the XILINX 16-nm Fin FET Ultra Scale+MPSoC.The atmospheric neutron SEEs on the tested CNN systems were comprehensively evaluated from six aspects,including chip type,network architecture,deployment methods,inference time,datasets,and the position of the anchor boxes.The various types of SEE soft errors,SEE cross-sections,and their distribution were analyzed to explore the radiation sensitivities and rules of 28-nm and 16-nm SoC.The current research can provide the technology support of radiation-resistant design of CNN system for developing and applying high-reliability,long-lifespan domestic artificial intelligence chips.
基金supported by ZTE Industry-University-Institute Cooperation Funds under Grant No.HC-CN-20220722010。
文摘This paper proposes a concurrent neural network model to mitigate non-linear distortion in power amplifiers using a basis function generation approach.The model is designed using polynomial expansion and comprises a feedforward neural network(FNN)and a convolutional neural network(CNN).The proposed model takes the basic elements that form the bases as input,defined by the generalized memory polynomial(GMP)and dynamic deviation reduction(DDR)models.The FNN generates the basis function and its output represents the basis values,while the CNN generates weights for the corresponding bases.Through the concurrent training of FNN and CNN,the hidden layer coefficients are updated,and the complex multiplication of their outputs yields the trained in-phase/quadrature(I/Q)signals.The proposed model was trained and tested using 300 MHz and 400 MHz broadband data in an orthogonal frequency division multiplexing(OFDM)communication system.The results show that the model achieves an adjacent channel power ratio(ACPR)of less than-48 d B within a 100 MHz integral bandwidth for both the training and test datasets.
基金financially supported by the National Natural Science Foundation of China(Grant Nos.52271317 and 52071149)the Fundamental Research Funds for the Central Universities(HUST:2019kfy XJJS007)。
文摘To address the problems of low accuracy by the CONWEP model and poor efficiency by the Coupled Eulerian-Lagrangian(CEL)method in predicting close-range air blast loads of cylindrical charges,a neural network-based simulation(NNS)method with higher accuracy and better efficiency was proposed.The NNS method consisted of three main steps.First,the parameters of blast loads,including the peak pressures and impulses of cylindrical charges with different aspect ratios(L/D)at different stand-off distances and incident angles were obtained by two-dimensional numerical simulations.Subsequently,incident shape factors of cylindrical charges with arbitrary aspect ratios were predicted by a neural network.Finally,reflected shape factors were derived and implemented into the subroutine of the ABAQUS code to modify the CONWEP model,including modifications of impulse and overpressure.The reliability of the proposed NNS method was verified by related experimental results.Remarkable accuracy improvement was acquired by the proposed NNS method compared with the unmodified CONWEP model.Moreover,huge efficiency superiority was obtained by the proposed NNS method compared with the CEL method.The proposed NNS method showed good accuracy when the scaled distance was greater than 0.2 m/kg^(1/3).It should be noted that there is no need to generate a new dataset again since the blast loads satisfy the similarity law,and the proposed NNS method can be directly used to simulate the blast loads generated by different cylindrical charges.The proposed NNS method with high efficiency and accuracy can be used as an effective method to analyze the dynamic response of structures under blast loads,and it has significant application prospects in designing protective structures.
文摘The ammunition loading system manipulator is susceptible to gear failure due to high-frequency,heavyload reciprocating motions and the absence of protective gear components.After a fault occurs,the distribution of fault characteristics under different loads is markedly inconsistent,and data is hard to label,which makes it difficult for the traditional diagnosis method based on single-condition training to generalize to different conditions.To address these issues,the paper proposes a novel transfer discriminant neural network(TDNN)for gear fault diagnosis.Specifically,an optimized joint distribution adaptive mechanism(OJDA)is designed to solve the distribution alignment problem between two domains.To improve the classification effect within the domain and the feature recognition capability for a few labeled data,metric learning is introduced to distinguish features from different fault categories.In addition,TDNN adopts a new pseudo-label training strategy to achieve label replacement by comparing the maximum probability of the pseudo-label with the test result.The proposed TDNN is verified in the experimental data set of the artillery manipulator device,and the diagnosis can achieve 99.5%,significantly outperforming other traditional adaptation methods.
文摘The high thermal conductivity of the nanoparticles in hybrid nanofluids results in enhanced thermal conductivity associated with their base fluids.Enhanced heat transfer is a result of this high thermal conductivity,which has significant applications in heat exchangers and engineering devices.To optimize heat transfer,a liquid film of Cu and TiO_(2)hybrid nanofluid behind a stretching sheet in a variable porous medium is being considered due to its importance.The nature of the fluid is considered time-dependent and the thickness of the liquid film is measured variable adjustable with the variable porous space and favorable for the uniform flow of the liquid film.The solution of the problem is acquired using the homotopy analysis method HAM,and the artificial neural network ANN is applied to obtain detailed information in the form of error estimation and validations using the fitting curve analysis.HAM data is utilized to train the ANN in this study,which uses Cu and TiO_(2)hybrid nanofluids in a variable porous space for unsteady thin film flow,and it is used to train the ANN.The results indicate that Cu and TiO_(2)play a greater role in boosting the rate.
基金The authors acknowledge the funding provided by the National Key R&D Program of China(2021YFA1401200)Beijing Outstanding Young Scientist Program(BJJWZYJH01201910007022)+2 种基金National Natural Science Foundation of China(No.U21A20140,No.92050117,No.62005017)programBeijing Municipal Science&Technology Commission,Administrative Commission of Zhongguancun Science Park(No.Z211100004821009)This work was supported by the Synergetic Extreme Condition User Facility(SECUF).
文摘Optical neural networks have significant advantages in terms of power consumption,parallelism,and high computing speed,which has intrigued extensive attention in both academic and engineering communities.It has been considered as one of the powerful tools in promoting the fields of imaging processing and object recognition.However,the existing optical system architecture cannot be reconstructed to the realization of multi-functional artificial intelligence systems simultaneously.To push the development of this issue,we propose the pluggable diffractive neural networks(P-DNN),a general paradigm resorting to the cascaded metasurfaces,which can be applied to recognize various tasks by switching internal plug-ins.As the proof-of-principle,the recognition functions of six types of handwritten digits and six types of fashions are numerical simulated and experimental demonstrated at near-infrared regimes.Encouragingly,the proposed paradigm not only improves the flexibility of the optical neural networks but paves the new route for achieving high-speed,low-power and versatile artificial intelligence systems.
基金This work is funded by National Natural Science Foundation of China(Nos.42202292,42141011)the Program for Jilin University(JLU)Science and Technology Innovative Research Team(No.2019TD-35).The authors would also like to thank the reviewers and editors whose critical comments are very helpful in preparing this article.
文摘To reduce CO_(2) emissions in response to global climate change,shale reservoirs could be ideal candidates for long-term carbon geo-sequestration involving multi-scale transport processes.However,most current CO_(2) sequestration models do not adequately consider multiple transport mechanisms.Moreover,the evaluation of CO_(2) storage processes usually involves laborious and time-consuming numerical simulations unsuitable for practical prediction and decision-making.In this paper,an integrated model involving gas diffusion,adsorption,dissolution,slip flow,and Darcy flow is proposed to accurately characterize CO_(2) storage in depleted shale reservoirs,supporting the establishment of a training database.On this basis,a hybrid physics-informed data-driven neural network(HPDNN)is developed as a deep learning surrogate for prediction and inversion.By incorporating multiple sources of scientific knowledge,the HPDNN can be configured with limited simulation resources,significantly accelerating the forward and inversion processes.Furthermore,the HPDNN can more intelligently predict injection performance,precisely perform reservoir parameter inversion,and reasonably evaluate the CO_(2) storage capacity under complicated scenarios.The validation and test results demonstrate that the HPDNN can ensure high accuracy and strong robustness across an extensive applicability range when dealing with field data with multiple noise sources.This study has tremendous potential to replace traditional modeling tools for predicting and making decisions about CO_(2) storage projects in depleted shale reservoirs.
基金This work was financially supported by the National Natural Science Foundation of China(52074089 and 52104064)Natural Science Foundation of Heilongjiang Province of China(LH2019E019).
文摘As the main link of ground engineering,crude oil gathering and transportation systems require huge energy consumption and complex structures.It is necessary to establish an energy efficiency evaluation system for crude oil gathering and transportation systems and identify the energy efficiency gaps.In this paper,the energy efficiency evaluation system of the crude oil gathering and transportation system in an oilfield in western China is established.Combined with the big data analysis method,the GA-BP neural network is used to establish the energy efficiency index prediction model for crude oil gathering and transportation systems.The comprehensive energy consumption,gas consumption,power consumption,energy utilization rate,heat utilization rate,and power utilization rate of crude oil gathering and transportation systems are predicted.Considering the efficiency and unit consumption index of the crude oil gathering and transportation system,the energy efficiency evaluation system of the crude oil gathering and transportation system is established based on a game theory combined weighting method and TOPSIS evaluation method,and the subjective weight is determined by the triangular fuzzy analytic hierarchy process.The entropy weight method determines the objective weight,and the combined weight of game theory combines subjectivity with objectivity to comprehensively evaluate the comprehensive energy efficiency of crude oil gathering and transportation systems and their subsystems.Finally,the weak links in energy utilization are identified,and energy conservation and consumption reduction are improved.The above research provides technical support for the green,efficient and intelligent development of crude oil gathering and transportation systems.
基金the National Natural Science Foundation of China(Grant No.12072090).
文摘This paper investigates interception missiles’trajectory tracking guidance problem under wind field and external disturbances in the boost phase.Indeed,the velocity control in such trajectory tracking guidance systems of missiles is challenging.As our contribution,the velocity control channel is designed to deal with the intractable velocity problem and improve tracking accuracy.The global prescribed performance function,which guarantees the tracking error within the set range and the global convergence of the tracking guidance system,is first proposed based on the traditional PPF.Then,a tracking guidance strategy is derived using the integral sliding mode control techniques to make the sliding manifold and tracking errors converge to zero and avoid singularities.Meanwhile,an improved switching control law is introduced into the designed tracking guidance algorithm to deal with the chattering problem.A back propagation neural network(BPNN)extended state observer(BPNNESO)is employed in the inner loop to identify disturbances.The obtained results indicate that the proposed tracking guidance approach achieves the trajectory tracking guidance objective without and with disturbances and outperforms the existing tracking guidance schemes with the lowest tracking errors,convergence times,and overshoots.
基金supported by the Science and Technology Project of the Headquarters of the State Grid Corporation of China(52199922001U).
文摘The power module of the Insulated Gate Bipolar Transistor(IGBT)is the core component of the traction transmission system of high-speed trains.The module's junction temperature is a critical factor in determining device reliability.Existing temperature monitoring methods based on the electro-thermal coupling model have limitations,such as ignoring device interactions and high computational complexity.To address these issues,an analysis of the parameters influencing IGBT failure is conducted,and a temperature monitoring method based on the Macro-Micro Attention Long Short-Term Memory(MMALSTM)recursive neural network is proposed,which takes the forward voltage drop and collector current as features.Compared with the traditional electricalthermal coupling model method,it requires fewer monitoring parameters and eliminates the complex loss calculation and equivalent thermal resistance network establishment process.The simulation model of a highspeed train traction system has been established to explore the accuracy and efficiency of MMALSTM-based prediction methods for IGBT power module junction temperature.The simulation outcomes,which deviate only 3.2% from the theoretical calculation results of the electric-thermal coupling model,confirm the reliability of this approach for predicting the temperature of IGBT power modules.
基金support of the National Science Foundation(ECCS-1916839 and DMR-2202268).
文摘In a very recent study,Prof.Lingling Huang and co-workers proposed and demonstrated reconfigurable optical neural networks based on cascaded metasurfaces.By fixing one metasurface and switching the other pluggable metasurfaces,the neural networks,which operate at near-infrared wavelengths,can perform distinct recognition tasks for handwritten digits and fashion products.This innovative device opens up an avenue for all-optical,high-speed,low-power,and multifunctional artificial intelligence systems.
基金supported by the National Natural Science Foundation of China (Nos.52274048 and 52374017)Beijing Natural Science Foundation (No.3222037)the CNPC 14th five-year perspective fundamental research project (No.2021DJ2104)。
文摘The shale gas development process is complex in terms of its flow mechanisms and the accuracy of the production forecasting is influenced by geological parameters and engineering parameters.Therefore,to quantitatively evaluate the relative importance of model parameters on the production forecasting performance,sensitivity analysis of parameters is required.The parameters are ranked according to the sensitivity coefficients for the subsequent optimization scheme design.A data-driven global sensitivity analysis(GSA)method using convolutional neural networks(CNN)is proposed to identify the influencing parameters in shale gas production.The CNN is trained on a large dataset,validated against numerical simulations,and utilized as a surrogate model for efficient sensitivity analysis.Our approach integrates CNN with the Sobol'global sensitivity analysis method,presenting three key scenarios for sensitivity analysis:analysis of the production stage as a whole,analysis by fixed time intervals,and analysis by declining rate.The findings underscore the predominant influence of reservoir thickness and well length on shale gas production.Furthermore,the temporal sensitivity analysis reveals the dynamic shifts in parameter importance across the distinct production stages.
基金supported by the National Natural Science Foundation of China(No.11975227)。
文摘Beams typically do not travel through the magnet centers because of errors in storage rings.The beam deviating from the quadrupole centers is affected by additional dipole fields due to magnetic field feed-down.Beam-based alignment(BBA)is often performed to determine a golden orbit where the beam circulates around the quadrupole center axes.For storage rings with many quadrupoles,the conventional BBA procedure is time-consuming,particularly in the commissioning phase,because of the necessary iterative process.In addition,the conventional BBA method can be affected by strong coupling and the nonlinearity of the storage ring optics.In this study,a novel method based on a neural network was proposed to determine the golden orbit in a much shorter time with reasonable accuracy.This golden orbit can be used directly for operation or adopted as a starting point for conventional BBA.The method was demonstrated in the HLS-II storage ring for the first time through simulations and online experiments.The results of the experiments showed that the golden orbit obtained using this new method was consistent with that obtained using the conventional BBA.The development of this new method and the corresponding experiments are reported in this paper.
基金supported by Beijing Natural Science Foundation (L202003)。
文摘This letter proposes a sliced-gated-convolutional neural network with belief propagation(SGCNN-BP) architecture for decoding long codes under correlated noise. The basic idea of SGCNNBP is using Neural Networks(NN) to transform the correlated noise into white noise, setting up the optimal condition for a standard BP decoder that takes the output from the NN. A gate-controlled neuron is used to regulate information flow and an optional operation—slicing is adopted to reduce parameters and lower training complexity. Simulation results show that SGCNN-BP has much better performance(with the largest gap being 5dB improvement) than a single BP decoder and achieves a nearly 1dB improvement compared to Fully Convolutional Networks(FCN).
基金National Natural Science Foundation of China(1180500311947102+4 种基金12004005)Natural Science Foundation of Anhui Province(2008085MA162008085QA26)University Synergy Innovation Program of Anhui Province(GXXT-2022-039)State Key Laboratory of Advanced Electromagnetic Technology(Grant No.AET 2024KF006)。
文摘High-resolution flow field data has important applications in meteorology,aerospace engineering,high-energy physics and other fields.Experiments and numerical simulations are two main ways to obtain high-resolution flow field data,while the high experiment cost and computing resources for simulation hinder the specificanalysis of flow field evolution.With the development of deep learning technology,convolutional neural networks areused to achieve high-resolution reconstruction of the flow field.In this paper,an ordinary convolutional neuralnetwork and a multi-time-path convolutional neural network are established for the ablative Rayleigh-Taylorinstability.These two methods can reconstruct the high-resolution flow field in just a few seconds,and further greatlyenrich the application of high-resolution reconstruction technology in fluid instability.Compared with the ordinaryconvolutional neural network,the multi-time-path convolutional neural network model has smaller error and canrestore more details of the flow field.The influence of low-resolution flow field data obtained by the two poolingmethods on the convolutional neural networks model is also discussed.
基金supported by National Natural Science Foundation of China(Nos.12175277 and 11975271)the National Key R&D Program of China(No.2022YFE 03050003)。
文摘A neural network model with a classical annotation method has been used on the EXL-50tokamak to predict impending disruption.However,the results revealed issues of overfitting and overconfidence in predictions caused by inaccurate labeling.To mitigate these issues,an improved training framework has been proposed.In this approach,soft labels from previous training serve as teachers to supervise the further learning process;this has lead to a significant improvement in predictive model performance.Notably,this enhancement is primarily attributed to the coupling effect of the soft labels and correction mechanism.This improved training framework introduces an instance-specific label smoothing method,which reflects a more nuanced model assessment on the likelihood of a disruption.It presents a possible solution to effectively address the challenges associated with accurate labeling across different machines.
