Shape Memory Polymers(SMPs)need to be given a temporary shape in advance to realize the shape memory process,but the manual shaping process is cumbersome and has low precision.Here,we propose a universal applicable me...Shape Memory Polymers(SMPs)need to be given a temporary shape in advance to realize the shape memory process,but the manual shaping process is cumbersome and has low precision.Here,we propose a universal applicable method for 4D printing self-folding SMPs by pre-stretching extruded filaments during 3D printing,the temporary shape of the SMPs were designed and fixed during 3D printing.Prepared samples can automatically perform shape memory process under stimulation without manual temporary shape programming process.Furthermore,using carbon ink as a photothermal conversion agent enables the 4D printing SMPs to have thermal and light response characteristics.In addition,some bionic applications of self-folding SMPs were demonstrated,such as self-morphing grasper,DNA double helix structures,programmable sequential switching mimosa,self-folding box and human hand.The combination of SMP and 3D printing fully takes advantage of 4D printing technology,and the self-folding SMPs show great potential applications in the fields of tissue engineering scaffold,self-folding robots,self-assembly system and so on.展开更多
To solve the problems of deformation,micro-cracks,and residual tensile stress in laser cladding coatings,the technique of laser cladding with Fe-based memory alloy can be considered.However,the process of in-situ synt...To solve the problems of deformation,micro-cracks,and residual tensile stress in laser cladding coatings,the technique of laser cladding with Fe-based memory alloy can be considered.However,the process of in-situ synthesis of Fe-based memory alloy coatings is extremely complex.At present,there is no clear guidance scheme for its preparation process,which limits its promotion and application to some extent.Therefore,in this study,response surface methodology(RSM)was used to model the response surface between the target values and the cladding process parameters.The NSGA-2 algorithm was employed to optimize the process parameters.The results indicate that the composite optimization method consisting of RSM and the NSGA-2 algorithm can establish a more accurate model,with an error of less than 4.5%between the predicted and actual values.Based on this established model,the optimal scheme for process parameters corresponding to different target results can be rapidly obtained.The prepared coating exhibits a uniform structure,with no defects such as pores,cracks,and deformation.The surface roughness and microhardness of the coating are enhanced,the shaping quality of the coating is effectively improved,and the electrochemical corrosion performance of the coating in 3.5%NaCl solution is obviously better than that of the substrate,providing an important guide for engineering applications.展开更多
We examined the effects of simulated rainfall and increasing N supply of different levels on CO2 pulse emission from typical Inner Mongolian steppe soil using the static opaque chamber technique, respectively in a dry...We examined the effects of simulated rainfall and increasing N supply of different levels on CO2 pulse emission from typical Inner Mongolian steppe soil using the static opaque chamber technique, respectively in a dry June and a rainy August. The treatments included NH4NO3 additions at rates of 0, 5, 10, and 20 g N/（m2.year） with or without water. Immediately after the experimental simulated rainfall events, the CO2 effluxes in the watering plots without N addition （WCK） increased greatly and reached the maximum value at 2 hr. However, the efflux level reverted to the background level within 48 hr. The cumulative CO2 effluxes in the soil ranged from 5.60 to 6.49 g C/m2 over 48 hr after a single water application, thus showing an increase of approximately 148.64% and 48.36% in the efftuxes during both observation periods. By contrast, the addition of different N levels without water addition did not result in a significant change in soil respiration in the short term. Two-way ANOVA showed that the effects of the interaction between water and N addition were insignificant in short-term soil COz efftuxes in the soil. The cumulative soil CO2 fluxes of different treatments over 48 hr accounted for approximately 5.34% to 6.91% and 2.36% to 2.93% of annual C emission in both experimental periods. These results stress the need for improving the sampling frequency after rainfall in future studies to ensure more accurate evaluation of the grassland C emission contribution.展开更多
Previous research suggests that emotional stimuli capture attention and guide behavior often automatically. The present study investigated the relationship between emotion-driven attention capture and motor response i...Previous research suggests that emotional stimuli capture attention and guide behavior often automatically. The present study investigated the relationship between emotion-driven attention capture and motor response inhibition to emotional words in the stop-signal task. By experimental variations of the onset of motor response inhibition across the time-course of emotional word processing, we show that processing of emotional information significantly interferes with motor response inhibition in an early time-window, previously related to automatic emotion-driven attention capture. Second, we found that stopping reduced memory recall for unpleasant words during a subsequent surprise free recall task supporting assumptions of a link between mechanisms of motor response inhibition and memory functions. Together, our results provide behavioral evidence for dual competition models of emotion and cognition. This study provides an important link between research focusing on different sub-processes of emotion processing (from perception to action and from action to memory).展开更多
Accurately predicting motion responses is a crucial component of the design process for floating offshore structures.This study introduces a hybrid model that integrates a convolutional neural network(CNN),a bidirecti...Accurately predicting motion responses is a crucial component of the design process for floating offshore structures.This study introduces a hybrid model that integrates a convolutional neural network(CNN),a bidirectional long short-term memory(BiLSTM)neural network,and an attention mechanism for forecasting the short-term motion responses of a semisubmersible.First,the motions are processed through the CNN for feature extraction.The extracted features are subsequently utilized by the BiLSTM network to forecast future motions.To enhance the predictive capability of the neural networks,an attention mechanism is integrated.In addition to the hybrid model,the BiLSTM is independently employed to forecast the motion responses of the semi-submersible,serving as benchmark results for comparison.Furthermore,both the 1D and 2D convolutions are conducted to check the influence of the convolutional dimensionality on the predicted results.The results demonstrate that the hybrid 1D CNN-BiLSTM network with an attention mechanism outperforms all other models in accurately predicting motion responses.展开更多
Solar flares are violent solar outbursts which have a great influence on the space environment surrounding Earth,potentially causing disruption of the ionosphere and interference with the geomagnetic field,thus causin...Solar flares are violent solar outbursts which have a great influence on the space environment surrounding Earth,potentially causing disruption of the ionosphere and interference with the geomagnetic field,thus causing magnetic storms.Consequently,it is very important to accurately predict the time period of solar flares.This paper proposes a flare prediction model,based on physical images of active solar regions.We employ X-ray flux curves recorded directly by the Geostationary Operational Environmental Satellite,used as input data for the model,allowing us to largely avoid the influence of accidental errors,effectively improving the model prediction efficiency.A model based on the X-ray flux curve can predict whether there will be a flare event within 24 hours.The reverse can also be verified by the peak of the X-ray flux curve to see if a flare has occurred within the past 24 hours.The True Positive Rate and False Positive Rate of the prediction model,based on physical images of active regions are 0.6070 and 0.2410 respectively,and the accuracy and True Skill Statistics are 0.7590 and 0.5556.Our model can effectively improve prediction efficiency compared with models based on the physical parameters of active regions or magnetic field records,providing a simple method for solar flare prediction.展开更多
Deep learning plays a vital role in real-life applications, for example object identification, human face recognition, speech recognition, biometrics identification, and short and long-term forecasting of data. The ma...Deep learning plays a vital role in real-life applications, for example object identification, human face recognition, speech recognition, biometrics identification, and short and long-term forecasting of data. The main objective of our work is to predict the market performance of the Dhaka Stock Exchange (DSE) on day closing price using different Deep Learning techniques. In this study, we have used the LSTM (Long Short-Term Memory) network to forecast the data of DSE for the convenience of shareholders. We have enforced LSTM networks to train data as well as forecast the future time series that has differentiated with test data. We have computed the Root Mean Square Error (RMSE) value to scrutinize the error between the forecasted value and test data that diminished the error by updating the LSTM networks. As a consequence of the renovation of the network, the LSTM network provides tremendous performance which outperformed the existing works to predict stock market prices.展开更多
Shape memory alloys(SMAs)are smart materials with superelasticity originating from a reversible stressinduced martensitic transformation(MT)accompanied by a significant electrical resistance change.However,the stress-...Shape memory alloys(SMAs)are smart materials with superelasticity originating from a reversible stressinduced martensitic transformation(MT)accompanied by a significant electrical resistance change.However,the stress-strain and resistance-stress relationships of typical NiTi wires are non-linear due to the stress plateau during the stress-induced MT.This limits the usage of these materials as pressure sensors.Herein,we propose a high-strength flexible sensor based on superelastic NiTi wires that achieves near-linear mechanical and electrical responses through a low-cost double-braided strategy.This microarchitectured strategy reduces or even eliminates stress plateau and it is demonstrated that the phase transformation of microfilaments can be controlled:regions with localized stress undergo the MT first,which is successively followed by the rest of the microfilament.This structure-dependent MT characteristic exhibits slim-hysteresis superelasticity and tunable low stiffness,and the braided wire shows improved flexibility.The double-braided NiTi microfilaments exhibit stable electrical properties and repeatability under approximately 600 MPa(8%strain)and can maintain stability over a wide temperature range(303-403 K).Moreover,a cross-grid flexible woven sensor array textile based on microfilaments is further developed to detect pressure distribution.This work provides insight into the design and application of SMAs in the field of flexible and functional fiber.展开更多
Control crosslink network and chain connectivity are essential to develop shape memory polymers(SMPs)with high shape memory capabilities,adjustable response temperature,and satisfying mechanistical properties.In this ...Control crosslink network and chain connectivity are essential to develop shape memory polymers(SMPs)with high shape memory capabilities,adjustable response temperature,and satisfying mechanistical properties.In this study,novel poly(ε-caprolactone)(PCL)-poly(2-vinyl)ethylene glycol(PVEG)copolymers bearing multi-pendant vinyl groups is synthesized by branched-selective allylic etherification polymerization of vinylethylene carbonate(VEC)with linear and tetra-arm PCLs under a synergistic catalysis of palladium complex and boron reagent.Facile thiol-ene photo-click reaction of PCL-PVEG copolymers with multifunctional thiols can rapidly access a serious crosslinked SMPs with high shape memory performance.The thermal properties,mechanical properties and response temperature of the obtained SMPs are tunable by the variation of PCL prepolymers,vinyl contents and functionality of thiols.Moreover,high elastic modulus in the rubbery plateau region can be maintained effectively owing to high-density topological networks of the PCL materials.In addition,the utility of the present SMPs is further demonstrated by the post-functionalization via thiol-ene photo-click chemistry.展开更多
The remaining useful life prediction of rolling bearing is vital in safety and reliability guarantee.In engineering scenarios,only a small amount of bearing performance degradation data can be obtained through acceler...The remaining useful life prediction of rolling bearing is vital in safety and reliability guarantee.In engineering scenarios,only a small amount of bearing performance degradation data can be obtained through accelerated life testing.In the absence of lifetime data,the hidden long-term correlation between performance degradation data is challenging to mine effectively,which is the main factor that restricts the prediction precision and engineering application of the residual life prediction method.To address this problem,a novel method based on the multi-layer perception neural network and bidirectional long short-term memory network is proposed.Firstly,a nonlinear health indicator(HI)calculation method based on kernel principal component analysis(KPCA)and exponential weighted moving average(EWMA)is designed.Then,using the raw vibration data and HI,a multi-layer perceptron(MLP)neural network is trained to further calculate the HI of the online bearing in real time.Furthermore,The bidirectional long short-term memory model(BiLSTM)optimized by particle swarm optimization(PSO)is used to mine the time series features of HI and predict the remaining service life.Performance verification experiments and comparative experiments are carried out on the XJTU-SY bearing open dataset.The research results indicate that this method has an excellent ability to predict future HI and remaining life.展开更多
A hysteric model is represented to describe the dependence of restoring force on deformation of pseudoelastic SMA.The dynamic response of the system is investigated by means of mathematical models.The result shows th...A hysteric model is represented to describe the dependence of restoring force on deformation of pseudoelastic SMA.The dynamic response of the system is investigated by means of mathematical models.The result shows that this kind of vibration absorbing system can suppress vibration with large amplitude effectively.Furthermore,the vibration absorbing system can work in optimum state by adjusting temperature and using piezoelectric sensors and actuators.展开更多
Triply periodic minimal surfaces(TPMS)are structures with smooth surfaces and excellent energy absorption properties.Combining new functional materials,such as shape memory alloys,with TPMS structures provides a novel...Triply periodic minimal surfaces(TPMS)are structures with smooth surfaces and excellent energy absorption properties.Combining new functional materials,such as shape memory alloys,with TPMS structures provides a novel and promising research field.In this study,three TPMS structures(Gyroid,Diamond,and Primitive)of Cu-11.85Al-3.2Mn-0.1Ti alloy were printed by laser powder bed fusion,which is favorable for the fabrication of complex structures.The manufacturing fidelity,mechanical response,and superelastic properties of the three structures were investigated.Stress distributions in the three structures during compression were analyzed by finite element(FE)simulation.The three structures were equipped with high-quality,glossy surfaces and uniform pores.However,due to powder adhesion and forming steps,there were volumetric errors and dimensional deviations between the samples and the CAD models.The errors were within 1.6%for the Gyroid and Diamond structures.The dimensional deviations at the nodes in the three structures were less than 0.09 mm.The microstructures of all structures wereβ1´martensite,consistent with the cubic sample.Experimental results of compression showed that the structures underwent a layer-by-layer compression failure mode,and the Primitive structures exhibited a more pronounced oscillatory process.The Diamond structures showed the highest first fracture stress and strain of 164.67 MPa and 13.89%,respectively.It also possessed the lowest yield strength(61.97 MPa)and the best energy absorption properties(7.6 MJ/m3).Through the deformation analysis,the Gyroid and Diamond structures were found to fracture at a 45°direction,while the Primitive structures fractured horizontally.These findings were consistent with the results obtained from the FE simulation,which showed equivalent stress distributions.After applying various pre-strains,the Diamond structures displayed the highest superelastic strain of up to 3.53%.The superelastic recovery of all samples ranged from 63.5%to 71.5%.展开更多
Complicated loads encountered by floating offshore wind turbines(FOWTs)in real sea conditions are crucial for future optimization of design,but obtaining data on them directly poses a challenge.To address this issue,w...Complicated loads encountered by floating offshore wind turbines(FOWTs)in real sea conditions are crucial for future optimization of design,but obtaining data on them directly poses a challenge.To address this issue,we applied machine learning techniques to obtain hydrodynamic and aerodynamic loads of FOWTs by measuring platform motion responses and wave-elevation sequences.First,a computational fluid dynamics(CFD)simulation model of the floating platform was established based on the dynamic fluid body interaction technique and overset grid technology.Then,a long short-term memory(LSTM)neural network model was constructed and trained to learn the nonlinear relationship between the waves,platform-motion inputs,and hydrodynamic-load outputs.The optimal model was determined after analyzing the sensitivity of parameters such as sample characteristics,network layers,and neuron numbers.Subsequently,the effectiveness of the hydrodynamic load model was validated under different simulation conditions,and the aerodynamic load calculation was completed based on the D'Alembert principle.Finally,we built a hybrid-scale FOWT model,based on the software in the loop strategy,in which the wind turbine was replaced by an actuation system.Model tests were carried out in a wave basin and the results demonstrated that the root mean square errors of the hydrodynamic and aerodynamic load measurements were 4.20%and 10.68%,respectively.展开更多
Intelligent maintenance of roads and highways requires accurate deterioration evaluation and performance prediction of asphalt pavement.To this end,we develop a time series long short-term memory(LSTM)model to predict...Intelligent maintenance of roads and highways requires accurate deterioration evaluation and performance prediction of asphalt pavement.To this end,we develop a time series long short-term memory(LSTM)model to predict key performance indicators(PIs)of pavement,namely the international roughness index(IRI)and rutting depth(RD).Subsequently,we propose a comprehensive performance indicator for the pavement quality index(PQI),which leverages the highway performance assessment standard method,entropy weight method,and fuzzy comprehensive evaluation method.This indicator can evaluate the overall performance condition of the pavement.The data used for the model development and analysis are extracted from tests on two full-scale accelerated test tracks,called MnRoad and RIOHTrack.Six variables are used as predictors,including temperature,precipitation,total traffic volume,asphalt surface layer thickness,pavement age,and maintenance condition.Furthermore,wavelet denoising is performed to analyze the impact of missing or abnormal data on the LSTM model accuracy.In comparison to a traditional autoregressive integrated moving average(ARIMAX)model,the proposed LSTM model performs better in terms of PI prediction and resiliency to noise.Finally,the overall prediction accuracy of our proposed performance indicator PQI is 93.8%.展开更多
This research focuses on solving the fault detection and health monitoring of high-power thyristor converter.In terms of the critical role of thyristor converter in nuclear fusion system,a method based on long short-t...This research focuses on solving the fault detection and health monitoring of high-power thyristor converter.In terms of the critical role of thyristor converter in nuclear fusion system,a method based on long short-term memory(LSTM)neural network model is proposed to monitor the operational state of the converter and accurately detect faults as they occur.By sampling and processing a large number of thyristor converter operation data,the LSTM model is trained to identify and detect abnormal state,and the power supply health status is monitored.Compared with traditional methods,LSTM model shows higher accuracy and abnormal state detection ability.The experimental results show that this method can effectively improve the reliability and safety of the thyristor converter,and provide a strong guarantee for the stable operation of the nuclear fusion reactor.展开更多
A Long Short-Term Memory(LSTM) Recurrent Neural Network(RNN) has driven tremendous improvements on an acoustic model based on Gaussian Mixture Model(GMM). However, these models based on a hybrid method require a force...A Long Short-Term Memory(LSTM) Recurrent Neural Network(RNN) has driven tremendous improvements on an acoustic model based on Gaussian Mixture Model(GMM). However, these models based on a hybrid method require a forced aligned Hidden Markov Model(HMM) state sequence obtained from the GMM-based acoustic model. Therefore, it requires a long computation time for training both the GMM-based acoustic model and a deep learning-based acoustic model. In order to solve this problem, an acoustic model using CTC algorithm is proposed. CTC algorithm does not require the GMM-based acoustic model because it does not use the forced aligned HMM state sequence. However, previous works on a LSTM RNN-based acoustic model using CTC used a small-scale training corpus. In this paper, the LSTM RNN-based acoustic model using CTC is trained on a large-scale training corpus and its performance is evaluated. The implemented acoustic model has a performance of 6.18% and 15.01% in terms of Word Error Rate(WER) for clean speech and noisy speech, respectively. This is similar to a performance of the acoustic model based on the hybrid method.展开更多
A correct and timely fault diagnosis is important for improving the safety and reliability of chemical processes. With the advancement of big data technology, data-driven fault diagnosis methods are being extensively ...A correct and timely fault diagnosis is important for improving the safety and reliability of chemical processes. With the advancement of big data technology, data-driven fault diagnosis methods are being extensively used and still have considerable potential. In recent years, methods based on deep neural networks have made significant breakthroughs, and fault diagnosis methods for industrial processes based on deep learning have attracted considerable research attention. Therefore, we propose a fusion deeplearning algorithm based on a fully convolutional neural network(FCN) to extract features and build models to correctly diagnose all types of faults. We use long short-term memory(LSTM) units to expand our proposed FCN so that our proposed deep learning model can better extract the time-domain features of chemical process data. We also introduce the attention mechanism into the model, aimed at highlighting the importance of features, which is significant for the fault diagnosis of chemical processes with many features. When applied to the benchmark Tennessee Eastman process, our proposed model exhibits impressive performance, demonstrating the effectiveness of the attention-based LSTM FCN in chemical process fault diagnosis.展开更多
The present study established a rat model of vascular dementia induced by chronic cerebral hypoperfusion through permanent ligation of bilateral common carotid arteries.At 60 days after modeling,escape latency and swi...The present study established a rat model of vascular dementia induced by chronic cerebral hypoperfusion through permanent ligation of bilateral common carotid arteries.At 60 days after modeling,escape latency and swimming path length during hidden-platform acquisition training in Morris water maze significantly increased in the model group.In addition,the number of accurate crossings over the original platform significantly decreased,hippocampal CA1 synaptophysin and growth-associated protein 43 expression significantly decreased,cAMP response element-binding protein expression remained unchanged,and phosphorylated cAMP response element-binding protein expression significantly decreased.Results suggested that abnormal expression of hippocampal synaptic structural protein and cAMP response element-binding protein phosphorylation played a role in cognitive impairment following chronic cerebral hypoperfusion.展开更多
To explore new operational forecasting methods of waves,a forecasting model for wave heights at three stations in the Bohai Sea has been developed.This model is based on long short-term memory(LSTM)neural network with...To explore new operational forecasting methods of waves,a forecasting model for wave heights at three stations in the Bohai Sea has been developed.This model is based on long short-term memory(LSTM)neural network with sea surface wind and wave heights as training samples.The prediction performance of the model is evaluated,and the error analysis shows that when using the same set of numerically predicted sea surface wind as input,the prediction error produced by the proposed LSTM model at Sta.N01 is 20%,18%and 23%lower than the conventional numerical wave models in terms of the total root mean square error(RMSE),scatter index(SI)and mean absolute error(MAE),respectively.Particularly,for significant wave height in the range of 3–5 m,the prediction accuracy of the LSTM model is improved the most remarkably,with RMSE,SI and MAE all decreasing by 24%.It is also evident that the numbers of hidden neurons,the numbers of buoys used and the time length of training samples all have impact on the prediction accuracy.However,the prediction does not necessary improve with the increase of number of hidden neurons or number of buoys used.The experiment trained by data with the longest time length is found to perform the best overall compared to other experiments with a shorter time length for training.Overall,long short-term memory neural network was proved to be a very promising method for future development and applications in wave forecasting.展开更多
基金supported by the National Natural Science Foundation of China(52175271,52021003,52375287)Science and Technology Development Plan Project of Jilin Province(20210509047RQ,20230508041RC).
文摘Shape Memory Polymers(SMPs)need to be given a temporary shape in advance to realize the shape memory process,but the manual shaping process is cumbersome and has low precision.Here,we propose a universal applicable method for 4D printing self-folding SMPs by pre-stretching extruded filaments during 3D printing,the temporary shape of the SMPs were designed and fixed during 3D printing.Prepared samples can automatically perform shape memory process under stimulation without manual temporary shape programming process.Furthermore,using carbon ink as a photothermal conversion agent enables the 4D printing SMPs to have thermal and light response characteristics.In addition,some bionic applications of self-folding SMPs were demonstrated,such as self-morphing grasper,DNA double helix structures,programmable sequential switching mimosa,self-folding box and human hand.The combination of SMP and 3D printing fully takes advantage of 4D printing technology,and the self-folding SMPs show great potential applications in the fields of tissue engineering scaffold,self-folding robots,self-assembly system and so on.
基金financial supports from the National Natural Science Foundation of China-Youth Project(51801076)the Provincial Colleges and Universities Natural Science Research Project of Jiangsu Province(18KJB430009)+1 种基金the Postdoctoral Research Support Project of Jiangsu Province(1601055C)the Senior Talents Research Startup of Jiangsu University(14JDG126)。
文摘To solve the problems of deformation,micro-cracks,and residual tensile stress in laser cladding coatings,the technique of laser cladding with Fe-based memory alloy can be considered.However,the process of in-situ synthesis of Fe-based memory alloy coatings is extremely complex.At present,there is no clear guidance scheme for its preparation process,which limits its promotion and application to some extent.Therefore,in this study,response surface methodology(RSM)was used to model the response surface between the target values and the cladding process parameters.The NSGA-2 algorithm was employed to optimize the process parameters.The results indicate that the composite optimization method consisting of RSM and the NSGA-2 algorithm can establish a more accurate model,with an error of less than 4.5%between the predicted and actual values.Based on this established model,the optimal scheme for process parameters corresponding to different target results can be rapidly obtained.The prepared coating exhibits a uniform structure,with no defects such as pores,cracks,and deformation.The surface roughness and microhardness of the coating are enhanced,the shaping quality of the coating is effectively improved,and the electrochemical corrosion performance of the coating in 3.5%NaCl solution is obviously better than that of the substrate,providing an important guide for engineering applications.
基金supported by the Knowledge Innovation Program of the Chinese Academy of Sciences(No.KZCX2-EW-302)the National Natural Science Foundation of China(No.41330528,41373084,and 41203054)the Special Fund for Agro-scientific Research in the Public Interest(No.201203012)
文摘We examined the effects of simulated rainfall and increasing N supply of different levels on CO2 pulse emission from typical Inner Mongolian steppe soil using the static opaque chamber technique, respectively in a dry June and a rainy August. The treatments included NH4NO3 additions at rates of 0, 5, 10, and 20 g N/（m2.year） with or without water. Immediately after the experimental simulated rainfall events, the CO2 effluxes in the watering plots without N addition （WCK） increased greatly and reached the maximum value at 2 hr. However, the efflux level reverted to the background level within 48 hr. The cumulative CO2 effluxes in the soil ranged from 5.60 to 6.49 g C/m2 over 48 hr after a single water application, thus showing an increase of approximately 148.64% and 48.36% in the efftuxes during both observation periods. By contrast, the addition of different N levels without water addition did not result in a significant change in soil respiration in the short term. Two-way ANOVA showed that the effects of the interaction between water and N addition were insignificant in short-term soil COz efftuxes in the soil. The cumulative soil CO2 fluxes of different treatments over 48 hr accounted for approximately 5.34% to 6.91% and 2.36% to 2.93% of annual C emission in both experimental periods. These results stress the need for improving the sampling frequency after rainfall in future studies to ensure more accurate evaluation of the grassland C emission contribution.
文摘Previous research suggests that emotional stimuli capture attention and guide behavior often automatically. The present study investigated the relationship between emotion-driven attention capture and motor response inhibition to emotional words in the stop-signal task. By experimental variations of the onset of motor response inhibition across the time-course of emotional word processing, we show that processing of emotional information significantly interferes with motor response inhibition in an early time-window, previously related to automatic emotion-driven attention capture. Second, we found that stopping reduced memory recall for unpleasant words during a subsequent surprise free recall task supporting assumptions of a link between mechanisms of motor response inhibition and memory functions. Together, our results provide behavioral evidence for dual competition models of emotion and cognition. This study provides an important link between research focusing on different sub-processes of emotion processing (from perception to action and from action to memory).
基金the National Natural Science Foundation of China (Grant No. 52301322)the Jiangsu Provincial Natural Science Foundation (Grant No. BK20220653)+1 种基金the National Science Fund for Distinguished Young Scholars (Grant No. 52025112)the Key Projects of the National Natural Science Foundation of China (Grant No. 52331011)
文摘Accurately predicting motion responses is a crucial component of the design process for floating offshore structures.This study introduces a hybrid model that integrates a convolutional neural network(CNN),a bidirectional long short-term memory(BiLSTM)neural network,and an attention mechanism for forecasting the short-term motion responses of a semisubmersible.First,the motions are processed through the CNN for feature extraction.The extracted features are subsequently utilized by the BiLSTM network to forecast future motions.To enhance the predictive capability of the neural networks,an attention mechanism is integrated.In addition to the hybrid model,the BiLSTM is independently employed to forecast the motion responses of the semi-submersible,serving as benchmark results for comparison.Furthermore,both the 1D and 2D convolutions are conducted to check the influence of the convolutional dimensionality on the predicted results.The results demonstrate that the hybrid 1D CNN-BiLSTM network with an attention mechanism outperforms all other models in accurately predicting motion responses.
基金partially supported by the National Key R&D Program of China (2022YFE0133700)the National Natural Science Foundation of China(12273007)+4 种基金the Guizhou Provincial Excellent Young Science and Technology Talent Program (YQK[2023]006)the National SKA Program of China (2020SKA0110300)the National Natural Science Foundation of China(11963003)the Guizhou Provincial Basic Research Program (Natural Science)(ZK[2022]143)the Cultivation project of Guizhou University ([2020]76).
文摘Solar flares are violent solar outbursts which have a great influence on the space environment surrounding Earth,potentially causing disruption of the ionosphere and interference with the geomagnetic field,thus causing magnetic storms.Consequently,it is very important to accurately predict the time period of solar flares.This paper proposes a flare prediction model,based on physical images of active solar regions.We employ X-ray flux curves recorded directly by the Geostationary Operational Environmental Satellite,used as input data for the model,allowing us to largely avoid the influence of accidental errors,effectively improving the model prediction efficiency.A model based on the X-ray flux curve can predict whether there will be a flare event within 24 hours.The reverse can also be verified by the peak of the X-ray flux curve to see if a flare has occurred within the past 24 hours.The True Positive Rate and False Positive Rate of the prediction model,based on physical images of active regions are 0.6070 and 0.2410 respectively,and the accuracy and True Skill Statistics are 0.7590 and 0.5556.Our model can effectively improve prediction efficiency compared with models based on the physical parameters of active regions or magnetic field records,providing a simple method for solar flare prediction.
文摘Deep learning plays a vital role in real-life applications, for example object identification, human face recognition, speech recognition, biometrics identification, and short and long-term forecasting of data. The main objective of our work is to predict the market performance of the Dhaka Stock Exchange (DSE) on day closing price using different Deep Learning techniques. In this study, we have used the LSTM (Long Short-Term Memory) network to forecast the data of DSE for the convenience of shareholders. We have enforced LSTM networks to train data as well as forecast the future time series that has differentiated with test data. We have computed the Root Mean Square Error (RMSE) value to scrutinize the error between the forecasted value and test data that diminished the error by updating the LSTM networks. As a consequence of the renovation of the network, the LSTM network provides tremendous performance which outperformed the existing works to predict stock market prices.
基金supported by the National Natural Science Foundation of China(Nos.52031005,52201224)the Natural Science Foundation of Shanghai(No.24ZR1438200)+1 种基金the Shanghai Academy of Spaceflight Technology Joint Research Fund(No.USCAST2023-19)the Equipment Development Depart-ment Huiyan Action.
文摘Shape memory alloys(SMAs)are smart materials with superelasticity originating from a reversible stressinduced martensitic transformation(MT)accompanied by a significant electrical resistance change.However,the stress-strain and resistance-stress relationships of typical NiTi wires are non-linear due to the stress plateau during the stress-induced MT.This limits the usage of these materials as pressure sensors.Herein,we propose a high-strength flexible sensor based on superelastic NiTi wires that achieves near-linear mechanical and electrical responses through a low-cost double-braided strategy.This microarchitectured strategy reduces or even eliminates stress plateau and it is demonstrated that the phase transformation of microfilaments can be controlled:regions with localized stress undergo the MT first,which is successively followed by the rest of the microfilament.This structure-dependent MT characteristic exhibits slim-hysteresis superelasticity and tunable low stiffness,and the braided wire shows improved flexibility.The double-braided NiTi microfilaments exhibit stable electrical properties and repeatability under approximately 600 MPa(8%strain)and can maintain stability over a wide temperature range(303-403 K).Moreover,a cross-grid flexible woven sensor array textile based on microfilaments is further developed to detect pressure distribution.This work provides insight into the design and application of SMAs in the field of flexible and functional fiber.
基金financially supported by the National Natural Science Foundation of China(No.22171182)Sichuan Tianfu Emei Plan.
文摘Control crosslink network and chain connectivity are essential to develop shape memory polymers(SMPs)with high shape memory capabilities,adjustable response temperature,and satisfying mechanistical properties.In this study,novel poly(ε-caprolactone)(PCL)-poly(2-vinyl)ethylene glycol(PVEG)copolymers bearing multi-pendant vinyl groups is synthesized by branched-selective allylic etherification polymerization of vinylethylene carbonate(VEC)with linear and tetra-arm PCLs under a synergistic catalysis of palladium complex and boron reagent.Facile thiol-ene photo-click reaction of PCL-PVEG copolymers with multifunctional thiols can rapidly access a serious crosslinked SMPs with high shape memory performance.The thermal properties,mechanical properties and response temperature of the obtained SMPs are tunable by the variation of PCL prepolymers,vinyl contents and functionality of thiols.Moreover,high elastic modulus in the rubbery plateau region can be maintained effectively owing to high-density topological networks of the PCL materials.In addition,the utility of the present SMPs is further demonstrated by the post-functionalization via thiol-ene photo-click chemistry.
基金supported by the National Key Research and Development Project(Grant Number 2023YFB3709601)the National Natural Science Foundation of China(Grant Numbers 62373215,62373219,62073193)+2 种基金the Key Research and Development Plan of Shandong Province(Grant Numbers 2021CXGC010204,2022CXGC020902)the Fundamental Research Funds of Shandong University(Grant Number 2021JCG008)the Natural Science Foundation of Shandong Province(Grant Number ZR2023MF100).
文摘The remaining useful life prediction of rolling bearing is vital in safety and reliability guarantee.In engineering scenarios,only a small amount of bearing performance degradation data can be obtained through accelerated life testing.In the absence of lifetime data,the hidden long-term correlation between performance degradation data is challenging to mine effectively,which is the main factor that restricts the prediction precision and engineering application of the residual life prediction method.To address this problem,a novel method based on the multi-layer perception neural network and bidirectional long short-term memory network is proposed.Firstly,a nonlinear health indicator(HI)calculation method based on kernel principal component analysis(KPCA)and exponential weighted moving average(EWMA)is designed.Then,using the raw vibration data and HI,a multi-layer perceptron(MLP)neural network is trained to further calculate the HI of the online bearing in real time.Furthermore,The bidirectional long short-term memory model(BiLSTM)optimized by particle swarm optimization(PSO)is used to mine the time series features of HI and predict the remaining service life.Performance verification experiments and comparative experiments are carried out on the XJTU-SY bearing open dataset.The research results indicate that this method has an excellent ability to predict future HI and remaining life.
基金This project is supported by National Natural Science Foundation of China and the 21st Century Youth Foundation of Tianjin
文摘A hysteric model is represented to describe the dependence of restoring force on deformation of pseudoelastic SMA.The dynamic response of the system is investigated by means of mathematical models.The result shows that this kind of vibration absorbing system can suppress vibration with large amplitude effectively.Furthermore,the vibration absorbing system can work in optimum state by adjusting temperature and using piezoelectric sensors and actuators.
基金Supported by National Natural Science Foundation of China(Grant Nos.52275333,52375335,and U22A202494)the Stabilization Support Project of AVIC Manufacturing Technology Institute(Grant No.KZ571801)+1 种基金the Fundamental Research Funds for the Central Universities(Grant No.2020kfyXJJS088)the Young Elite Scientists Sponsorship Program by CAST(Grant No.YESS20200381).
文摘Triply periodic minimal surfaces(TPMS)are structures with smooth surfaces and excellent energy absorption properties.Combining new functional materials,such as shape memory alloys,with TPMS structures provides a novel and promising research field.In this study,three TPMS structures(Gyroid,Diamond,and Primitive)of Cu-11.85Al-3.2Mn-0.1Ti alloy were printed by laser powder bed fusion,which is favorable for the fabrication of complex structures.The manufacturing fidelity,mechanical response,and superelastic properties of the three structures were investigated.Stress distributions in the three structures during compression were analyzed by finite element(FE)simulation.The three structures were equipped with high-quality,glossy surfaces and uniform pores.However,due to powder adhesion and forming steps,there were volumetric errors and dimensional deviations between the samples and the CAD models.The errors were within 1.6%for the Gyroid and Diamond structures.The dimensional deviations at the nodes in the three structures were less than 0.09 mm.The microstructures of all structures wereβ1´martensite,consistent with the cubic sample.Experimental results of compression showed that the structures underwent a layer-by-layer compression failure mode,and the Primitive structures exhibited a more pronounced oscillatory process.The Diamond structures showed the highest first fracture stress and strain of 164.67 MPa and 13.89%,respectively.It also possessed the lowest yield strength(61.97 MPa)and the best energy absorption properties(7.6 MJ/m3).Through the deformation analysis,the Gyroid and Diamond structures were found to fracture at a 45°direction,while the Primitive structures fractured horizontally.These findings were consistent with the results obtained from the FE simulation,which showed equivalent stress distributions.After applying various pre-strains,the Diamond structures displayed the highest superelastic strain of up to 3.53%.The superelastic recovery of all samples ranged from 63.5%to 71.5%.
基金This work is supported by the National Key Research and Development Program of China(No.2023YFB4203000)the National Natural Science Foundation of China(No.U22A20178)
文摘Complicated loads encountered by floating offshore wind turbines(FOWTs)in real sea conditions are crucial for future optimization of design,but obtaining data on them directly poses a challenge.To address this issue,we applied machine learning techniques to obtain hydrodynamic and aerodynamic loads of FOWTs by measuring platform motion responses and wave-elevation sequences.First,a computational fluid dynamics(CFD)simulation model of the floating platform was established based on the dynamic fluid body interaction technique and overset grid technology.Then,a long short-term memory(LSTM)neural network model was constructed and trained to learn the nonlinear relationship between the waves,platform-motion inputs,and hydrodynamic-load outputs.The optimal model was determined after analyzing the sensitivity of parameters such as sample characteristics,network layers,and neuron numbers.Subsequently,the effectiveness of the hydrodynamic load model was validated under different simulation conditions,and the aerodynamic load calculation was completed based on the D'Alembert principle.Finally,we built a hybrid-scale FOWT model,based on the software in the loop strategy,in which the wind turbine was replaced by an actuation system.Model tests were carried out in a wave basin and the results demonstrated that the root mean square errors of the hydrodynamic and aerodynamic load measurements were 4.20%and 10.68%,respectively.
基金supported by the National Key Research and Development Program of China(No.2021YFB2600300).
文摘Intelligent maintenance of roads and highways requires accurate deterioration evaluation and performance prediction of asphalt pavement.To this end,we develop a time series long short-term memory(LSTM)model to predict key performance indicators(PIs)of pavement,namely the international roughness index(IRI)and rutting depth(RD).Subsequently,we propose a comprehensive performance indicator for the pavement quality index(PQI),which leverages the highway performance assessment standard method,entropy weight method,and fuzzy comprehensive evaluation method.This indicator can evaluate the overall performance condition of the pavement.The data used for the model development and analysis are extracted from tests on two full-scale accelerated test tracks,called MnRoad and RIOHTrack.Six variables are used as predictors,including temperature,precipitation,total traffic volume,asphalt surface layer thickness,pavement age,and maintenance condition.Furthermore,wavelet denoising is performed to analyze the impact of missing or abnormal data on the LSTM model accuracy.In comparison to a traditional autoregressive integrated moving average(ARIMAX)model,the proposed LSTM model performs better in terms of PI prediction and resiliency to noise.Finally,the overall prediction accuracy of our proposed performance indicator PQI is 93.8%.
基金supported by the Open Fund of Magnetic Confinement Fusion Laboratory of Anhui Province(No.2024AMF04003)the Natural Science Foundation of Anhui Province(No.228085ME142)Comprehensive Research Facility for Fusion Technology(No.20180000527301001228)。
文摘This research focuses on solving the fault detection and health monitoring of high-power thyristor converter.In terms of the critical role of thyristor converter in nuclear fusion system,a method based on long short-term memory(LSTM)neural network model is proposed to monitor the operational state of the converter and accurately detect faults as they occur.By sampling and processing a large number of thyristor converter operation data,the LSTM model is trained to identify and detect abnormal state,and the power supply health status is monitored.Compared with traditional methods,LSTM model shows higher accuracy and abnormal state detection ability.The experimental results show that this method can effectively improve the reliability and safety of the thyristor converter,and provide a strong guarantee for the stable operation of the nuclear fusion reactor.
基金supported by the Ministry of Trade,Industry & Energy(MOTIE,Korea) under Industrial Technology Innovation Program (No.10063424,'development of distant speech recognition and multi-task dialog processing technologies for in-door conversational robots')
文摘A Long Short-Term Memory(LSTM) Recurrent Neural Network(RNN) has driven tremendous improvements on an acoustic model based on Gaussian Mixture Model(GMM). However, these models based on a hybrid method require a forced aligned Hidden Markov Model(HMM) state sequence obtained from the GMM-based acoustic model. Therefore, it requires a long computation time for training both the GMM-based acoustic model and a deep learning-based acoustic model. In order to solve this problem, an acoustic model using CTC algorithm is proposed. CTC algorithm does not require the GMM-based acoustic model because it does not use the forced aligned HMM state sequence. However, previous works on a LSTM RNN-based acoustic model using CTC used a small-scale training corpus. In this paper, the LSTM RNN-based acoustic model using CTC is trained on a large-scale training corpus and its performance is evaluated. The implemented acoustic model has a performance of 6.18% and 15.01% in terms of Word Error Rate(WER) for clean speech and noisy speech, respectively. This is similar to a performance of the acoustic model based on the hybrid method.
文摘A correct and timely fault diagnosis is important for improving the safety and reliability of chemical processes. With the advancement of big data technology, data-driven fault diagnosis methods are being extensively used and still have considerable potential. In recent years, methods based on deep neural networks have made significant breakthroughs, and fault diagnosis methods for industrial processes based on deep learning have attracted considerable research attention. Therefore, we propose a fusion deeplearning algorithm based on a fully convolutional neural network(FCN) to extract features and build models to correctly diagnose all types of faults. We use long short-term memory(LSTM) units to expand our proposed FCN so that our proposed deep learning model can better extract the time-domain features of chemical process data. We also introduce the attention mechanism into the model, aimed at highlighting the importance of features, which is significant for the fault diagnosis of chemical processes with many features. When applied to the benchmark Tennessee Eastman process, our proposed model exhibits impressive performance, demonstrating the effectiveness of the attention-based LSTM FCN in chemical process fault diagnosis.
基金supported by the National Natural Science Foundation of China,No.30973782the National Natural Science Foundation for the Youth,No.81001693+1 种基金the Natural Science Foundation of Beijing,No.7102014,7122018the Science and Technology Foundation for Chinese Medicine in Beijing,No.JJ2008-042
文摘The present study established a rat model of vascular dementia induced by chronic cerebral hypoperfusion through permanent ligation of bilateral common carotid arteries.At 60 days after modeling,escape latency and swimming path length during hidden-platform acquisition training in Morris water maze significantly increased in the model group.In addition,the number of accurate crossings over the original platform significantly decreased,hippocampal CA1 synaptophysin and growth-associated protein 43 expression significantly decreased,cAMP response element-binding protein expression remained unchanged,and phosphorylated cAMP response element-binding protein expression significantly decreased.Results suggested that abnormal expression of hippocampal synaptic structural protein and cAMP response element-binding protein phosphorylation played a role in cognitive impairment following chronic cerebral hypoperfusion.
基金The National Key R&D Program of China under contract No.2016YFC1402103
文摘To explore new operational forecasting methods of waves,a forecasting model for wave heights at three stations in the Bohai Sea has been developed.This model is based on long short-term memory(LSTM)neural network with sea surface wind and wave heights as training samples.The prediction performance of the model is evaluated,and the error analysis shows that when using the same set of numerically predicted sea surface wind as input,the prediction error produced by the proposed LSTM model at Sta.N01 is 20%,18%and 23%lower than the conventional numerical wave models in terms of the total root mean square error(RMSE),scatter index(SI)and mean absolute error(MAE),respectively.Particularly,for significant wave height in the range of 3–5 m,the prediction accuracy of the LSTM model is improved the most remarkably,with RMSE,SI and MAE all decreasing by 24%.It is also evident that the numbers of hidden neurons,the numbers of buoys used and the time length of training samples all have impact on the prediction accuracy.However,the prediction does not necessary improve with the increase of number of hidden neurons or number of buoys used.The experiment trained by data with the longest time length is found to perform the best overall compared to other experiments with a shorter time length for training.Overall,long short-term memory neural network was proved to be a very promising method for future development and applications in wave forecasting.
