To ensure the reliability of learned information,most insects require multiple intervals of experience before storing the information as long-term memory(LTM),and this requirement has been validated in insects from th...To ensure the reliability of learned information,most insects require multiple intervals of experience before storing the information as long-term memory(LTM),and this requirement has been validated in insects from the behavioral to the molecular level.Recent studies have shown that some insects can form LTM after one-trial experience,although the mechanisms underlying one-trial LTM formation are not well understood.Therefore,understanding the mechanisms underlying rapid learning and subsequent preference formation in insects is crucial.Here we show that the agricultural pest Bactrocera dorsalis can rapidly form LTM,which is dependent on protein synthesis,and that the formation of LTM requires high energy support at the cost of reduced survival.Furthermore,based on a liquid chromatography-mass spectrometry(LC-MS)metabolomics approach,we found that LTM-related processes are sequentially coupled to two processes for energy generation,the TCA cycle and oxidative phosphorylation.This was further confirmed by blocking these energy generation processes.Our results provide a theoretical basis for the development of behavioral modulators in oriental fruit flies that target energy generation metabolites,as well as a new perspective on the rapid formation of LTM in insects.展开更多
Background:Mitochondrial dysfunction plays a critical role in the pathogenesis of Alzheimer’s disease(AD).Resveratrol is a promising compound for the treatment of various neurodegenerative diseases,including AD.Aims:...Background:Mitochondrial dysfunction plays a critical role in the pathogenesis of Alzheimer’s disease(AD).Resveratrol is a promising compound for the treatment of various neurodegenerative diseases,including AD.Aims:To investigate mitochondrial damage and the effects of resveratrol on inflammation,cognitive function,and mitochondrial quality control in APP/PS1 mice.Methods:Comparative analysis of mitochondrial DNA(mtDNA)damage was conducted between 10-month-old APP/PS1 mice and age-matched C57BL/6 mice.Assessments included measurement of amyloid-βlevels,inflammatory markers,swimming distance in the Morris water maze,and gut microbiome composition.Resveratrol’s effects on cytokine expression,mtDNA levels in plasma,and activation of Nuclear factor erythroid 2-related factor 2/Antioxidant response element(Nrf2/ARE)and phosphoinositide 3-kinase/protein kinase B(also known as Akt)/mechanistic target of rapamycin complex 1(PI3K/Akt/mTORC1)signaling pathways were also evaluated.Results:APP/PS1 mice exhibited significantly increased mtDNA damage in the prefrontal cortex,midbrain,and cerebellum,alongside higher amyloid-βlevels and inflammatory markers.Resveratrol treatment led to reduced expression of pro-inflammatory cytokines,a decrease in Proteobacteria levels,and lower cell-free mtDNA in plasma.Partial improvement in long-term spatial memory was observed in APP/PS1 mice following resveratrol treatment,likely due to its anti-inflammatory properties.Activation of the Nrf2/ARE signaling pathway and markers of PI3K/Akt/mTORC1 axis activation were noted,with the latter regulating long-term potentiation.Conclusion:Resveratrol demonstrates potential in mitigating inflammation and improving mitochondrial quality control in APP/PS1 mice,but it does not reduce amyloid-βlevels,highlighting the complexity of AD pathology and the need for further research.展开更多
The increasingly severe state of coal burst disaster has emerged as a critical factor constraining coal mine safety production,and it has become a challenging task to enhance the accuracy of coal burst disaster predic...The increasingly severe state of coal burst disaster has emerged as a critical factor constraining coal mine safety production,and it has become a challenging task to enhance the accuracy of coal burst disaster prediction.To address the issue of insufficient exploration of the spatio-temporal characteristic of microseismic data and the challenging selection of the optimal time window size in spatio-temporal prediction,this paper integrates deep learning methods and theory to propose a novel coal burst spatio-temporal prediction method based on Bidirectional Long Short-Term Memory(Bi-LSTM)network.The method involves three main modules,including microseismic spatio-temporal characteristic indicators construction,temporal prediction model,and spatial prediction model.To validate the effectiveness of the proposed method,engineering application tests are conducted at a high-risk working face in the Ordos mining area of Inner Mongolia,focusing on 13 high-energy microseismic events with energy levels greater than 105 J.In terms of temporal prediction,the analysis indicates that the temporal prediction results consist of 10 strong predictions and 3 medium predictions,and there is no false alarm detected throughout the entire testing period.Moreover,compared to the traditional threshold-based coal burst temporal prediction method,the accuracy of the proposed method is increased by 38.5%.In terms of spatial prediction,the distribution of spatial prediction results for high-energy events comprises 6 strong hazard predictions,3 medium hazard predictions,and 4 weak hazard predictions.展开更多
Developing efficient neural network(NN)computing systems is crucial in the era of artificial intelligence(AI).Traditional von Neumann architectures have both the issues of"memory wall"and"power wall&quo...Developing efficient neural network(NN)computing systems is crucial in the era of artificial intelligence(AI).Traditional von Neumann architectures have both the issues of"memory wall"and"power wall",limiting the data transfer between memory and processing units[1,2].Compute-in-memory(CIM)technologies,particularly analogue CIM with memristor crossbars,are promising because of their high energy efficiency,computational parallelism,and integration density for NN computations[3].In practical applications,analogue CIM excels in tasks like speech recognition and image classification,revealing its unique advantages.For instance,it efficiently processes vast amounts of audio data in speech recognition,achieving high accuracy with minimal power consumption.In image classification,the high parallelism of analogue CIM significantly speeds up feature extraction and reduces processing time.With the boosting development of AI applications,the demands for computational accuracy and task complexity are rising continually.However,analogue CIM systems are limited in handling complex regression tasks with needs of precise floating-point(FP)calculations.They are primarily suited for the classification tasks with low data precision and a limited dynamic range[4].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
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
With the rapid development of machine learning,the demand for high-efficient computing becomes more and more urgent.To break the bottleneck of the traditional Von Neumann architecture,computing-in-memory(CIM)has attra...With the rapid development of machine learning,the demand for high-efficient computing becomes more and more urgent.To break the bottleneck of the traditional Von Neumann architecture,computing-in-memory(CIM)has attracted increasing attention in recent years.In this work,to provide a feasible CIM solution for the large-scale neural networks(NN)requiring continuous weight updating in online training,a flash-based computing-in-memory with high endurance(10^(9) cycles)and ultrafast programming speed is investigated.On the one hand,the proposed programming scheme of channel hot electron injection(CHEI)and hot hole injection(HHI)demonstrate high linearity,symmetric potentiation,and a depression process,which help to improve the training speed and accuracy.On the other hand,the low-damage programming scheme and memory window(MW)optimizations can suppress cell degradation effectively with improved computing accuracy.Even after 109 cycles,the leakage current(I_(off))of cells remains sub-10pA,ensuring the large-scale computing ability of memory.Further characterizations are done on read disturb to demonstrate its robust reliabilities.By processing CIFAR-10 tasks,it is evident that~90%accuracy can be achieved after 109 cycles in both ResNet50 and VGG16 NN.Our results suggest that flash-based CIM has great potential to overcome the limitations of traditional Von Neumann architectures and enable high-performance NN online training,which pave the way for further development of artificial intelligence(AI)accelerators.展开更多
A fast-charging policy is widely employed to alleviate the inconvenience caused by the extended charging time of electric vehicles. However, fast charging exacerbates battery degradation and shortens battery lifespan....A fast-charging policy is widely employed to alleviate the inconvenience caused by the extended charging time of electric vehicles. However, fast charging exacerbates battery degradation and shortens battery lifespan. In addition, there is still a lack of tailored health estimations for fast-charging batteries;most existing methods are applicable at lower charging rates. This paper proposes a novel method for estimating the health of lithium-ion batteries, which is tailored for multi-stage constant current-constant voltage fast-charging policies. Initially, short charging segments are extracted by monitoring current switches,followed by deriving voltage sequences using interpolation techniques. Subsequently, a graph generation layer is used to transform the voltage sequence into graphical data. Furthermore, the integration of a graph convolution network with a long short-term memory network enables the extraction of information related to inter-node message transmission, capturing the key local and temporal features during the battery degradation process. Finally, this method is confirmed by utilizing aging data from 185 cells and 81 distinct fast-charging policies. The 4-minute charging duration achieves a balance between high accuracy in estimating battery state of health and low data requirements, with mean absolute errors and root mean square errors of 0.34% and 0.66%, respectively.展开更多
Multi-wall carbon nanotube filled shape memory polymer composite(MWCNT/SMC)possessed enhanced modulus,strength,and electric conductivity,as well as excellent electrothermal shape memory properties,showing wide design ...Multi-wall carbon nanotube filled shape memory polymer composite(MWCNT/SMC)possessed enhanced modulus,strength,and electric conductivity,as well as excellent electrothermal shape memory properties,showing wide design scenarios and engineering application prospects.The thermoelectrically triggered shape memory process contains complex multi-physical mechanisms,especially when coupled with finite deformation rooted on micro-mechanisms.A multi-physical finite deformation model is necessary to get a deep understanding on the coupled electro-thermomechanical properties of electrothermal shape memory composites(ESMCs),beneficial to its design and wide application.Taking into consideration of micro-physical mechanisms of the MWCNTs interacting with double-chain networks,a finite deformation theoretical model is developed in this work based on two superimposed network chains of physically crosslinked network formed among MWCNTs and the chemically crosslinked network.An intact crosslinked chemical network is considered featuring with entropic-hyperelastic properties,superimposed with a physically crosslinked network where percolation theory is based on electric conductivity and electric-heating mechanisms.The model is calibrated by experiments and used for shape recoveries triggered by heating and electric fields.It captures the coupled electro-thermomechanical behavior of ESMCs and provides design guidelines for MWCNTs filled shape memory polymers.展开更多
With the advent of physics informed neural networks(PINNs),deep learning has gained interest for solving nonlinear partial differential equations(PDEs)in recent years.In this paper,physics informed memory networks(PIM...With the advent of physics informed neural networks(PINNs),deep learning has gained interest for solving nonlinear partial differential equations(PDEs)in recent years.In this paper,physics informed memory networks(PIMNs)are proposed as a new approach to solving PDEs by using physical laws and dynamic behavior of PDEs.Unlike the fully connected structure of the PINNs,the PIMNs construct the long-term dependence of the dynamics behavior with the help of the long short-term memory network.Meanwhile,the PDEs residuals are approximated using difference schemes in the form of convolution filter,which avoids information loss at the neighborhood of the sampling points.Finally,the performance of the PIMNs is assessed by solving the Kd V equation and the nonlinear Schr?dinger equation,and the effects of difference schemes,boundary conditions,network structure and mesh size on the solutions are discussed.Experiments show that the PIMNs are insensitive to boundary conditions and have excellent solution accuracy even with only the initial conditions.展开更多
Stress changes due to changes in fluid pressure and temperature in a faulted formation may lead to the opening/shearing of the fault.This can be due to subsurface(geo)engineering activities such as fluid injections an...Stress changes due to changes in fluid pressure and temperature in a faulted formation may lead to the opening/shearing of the fault.This can be due to subsurface(geo)engineering activities such as fluid injections and geologic disposal of nuclear waste.Such activities are expected to rise in the future making it necessary to assess their short-and long-term safety.Here,a new machine learning(ML)approach to model pore pressure and fault displacements in response to high-pressure fluid injection cycles is developed.The focus is on fault behavior near the injection borehole.To capture the temporal dependencies in the data,long short-term memory(LSTM)networks are utilized.To prevent error accumulation within the forecast window,four critical measures to train a robust LSTM model for predicting fault response are highlighted:(i)setting an appropriate value of LSTM lag,(ii)calibrating the LSTM cell dimension,(iii)learning rate reduction during weight optimization,and(iv)not adopting an independent injection cycle as a validation set.Several numerical experiments were conducted,which demonstrated that the ML model can capture peaks in pressure and associated fault displacement that accompany an increase in fluid injection.The model also captured the decay in pressure and displacement during the injection shut-in period.Further,the ability of an ML model to highlight key changes in fault hydromechanical activation processes was investigated,which shows that ML can be used to monitor risk of fault activation and leakage during high pressure fluid injections.展开更多
Real-time prediction and precise control of sinter quality are pivotal for energy saving,cost reduction,quality improvement and efficiency enhancement in the ironmaking process.To advance,the accuracy and comprehensiv...Real-time prediction and precise control of sinter quality are pivotal for energy saving,cost reduction,quality improvement and efficiency enhancement in the ironmaking process.To advance,the accuracy and comprehensiveness of sinter quality prediction,an intelligent flare monitoring system for sintering machine tails that combines hybrid neural networks integrating convolutional neural network with long short-term memory(CNN-LSTM)networks was proposed.The system utilized a high-temperature thermal imager for image acquisition at the sintering machine tail and employed a zone-triggered method to accurately capture dynamic feature images under challenging conditions of high-temperature,high dust,and occlusion.The feature images were then segmented through a triple-iteration multi-thresholding approach based on the maximum between-class variance method to minimize detail loss during the segmentation process.Leveraging the advantages of CNN and LSTM networks in capturing temporal and spatial information,a comprehensive model for sinter quality prediction was constructed,with inputs including the proportion of combustion layer,porosity rate,temperature distribution,and image features obtained from the convolutional neural network,and outputs comprising quality indicators such as underburning index,uniformity index,and FeO content of the sinter.The accuracy is notably increased,achieving a 95.8%hit rate within an error margin of±1.0.After the system is applied,the average qualified rate of FeO content increases from 87.24%to 89.99%,representing an improvement of 2.75%.The average monthly solid fuel consumption is reduced from 49.75 to 46.44 kg/t,leading to a 6.65%reduction and underscoring significant energy saving and cost reduction effects.展开更多
This study investigates the application of Learnable Memory Vision Transformers(LMViT)for detecting metal surface flaws,comparing their performance with traditional CNNs,specifically ResNet18 and ResNet50,as well as o...This study investigates the application of Learnable Memory Vision Transformers(LMViT)for detecting metal surface flaws,comparing their performance with traditional CNNs,specifically ResNet18 and ResNet50,as well as other transformer-based models including Token to Token ViT,ViT withoutmemory,and Parallel ViT.Leveraging awidely-used steel surface defect dataset,the research applies data augmentation and t-distributed stochastic neighbor embedding(t-SNE)to enhance feature extraction and understanding.These techniques mitigated overfitting,stabilized training,and improved generalization capabilities.The LMViT model achieved a test accuracy of 97.22%,significantly outperforming ResNet18(88.89%)and ResNet50(88.90%),aswell as the Token to TokenViT(88.46%),ViT without memory(87.18),and Parallel ViT(91.03%).Furthermore,LMViT exhibited superior training and validation performance,attaining a validation accuracy of 98.2%compared to 91.0%for ResNet 18,96.0%for ResNet50,and 89.12%,87.51%,and 91.21%for Token to Token ViT,ViT without memory,and Parallel ViT,respectively.The findings highlight the LMViT’s ability to capture long-range dependencies in images,an areawhere CNNs struggle due to their reliance on local receptive fields and hierarchical feature extraction.The additional transformer-based models also demonstrate improved performance in capturing complex features over CNNs,with LMViT excelling particularly at detecting subtle and complex defects,which is critical for maintaining product quality and operational efficiency in industrial applications.For instance,the LMViT model successfully identified fine scratches and minor surface irregularities that CNNs often misclassify.This study not only demonstrates LMViT’s potential for real-world defect detection but also underscores the promise of other transformer-based architectures like Token to Token ViT,ViT without memory,and Parallel ViT in industrial scenarios where complex spatial relationships are key.Future research may focus on enhancing LMViT’s computational efficiency for deployment in real-time quality control systems.展开更多
With breakthroughs in data processing and pattern recognition through deep learning technologies,the use of advanced algorithmic models for analyzing and interpreting soil spectral information has provided an efficien...With breakthroughs in data processing and pattern recognition through deep learning technologies,the use of advanced algorithmic models for analyzing and interpreting soil spectral information has provided an efficient and economical method for soil quality assessment.However,traditional single-output networks exhibit limitations in the prediction process,particularly in their inability to fully utilize the correlations among various elements.As a result,single-output networks tend to be optimized for a single task,neglecting the interrelationships among different soil elements,which limits prediction accuracy and model generalizability.To overcome this limitation,in this study,a multi-task learning architecture with a progressive extraction network was implemented for the simultaneous prediction of multiple indicators in soil,including nitrogen(N),organic carbon(OC),calcium carbonate(CaCO 3),cation exchange capacity(CEC),and pH.Furthermore,while incorporating the Pearson correlation coefficient,convolutional neural networks,long short-term memory networks and attention mechanisms were combined to extract local abstract features from the original spectra,thereby further improving the model.This architecture is referred to as the Relevance-sharing Progressive Layered Extraction Network.The model employs an adaptive joint loss optimization method to update the weights of individual task losses in the multi-task learning training process.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
This paper proposes a novel multivalued recurrent neural network model driven by external inputs,along with two innovative learning algorithms.By incorporating a multivalued activation function,the proposed model can ...This paper proposes a novel multivalued recurrent neural network model driven by external inputs,along with two innovative learning algorithms.By incorporating a multivalued activation function,the proposed model can achieve multivalued many-to-one associative memory,and the newly developed algorithms enable effective storage of many-to-one patterns in the coefficient matrix while maintaining the indispensability of inputs in many-to-one associative memory.The proposed learning algorithm addresses a critical limitation of existing models which fail to ensure completely erroneous outputs when facing partial input missing in many-to-one associative memory tasks.The methodology is rigorously derived through theoretical analysis,incorporating comprehensive verification of both the existence and global exponential stability of equilibrium points.Demonstrative examples are provided in the paper to show the effectiveness of the proposed theory.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
In the face of the large number of people with motor function disabilities,rehabilitation robots have attracted more and more attention.In order to promote the active participation of the user's motion intention i...In the face of the large number of people with motor function disabilities,rehabilitation robots have attracted more and more attention.In order to promote the active participation of the user's motion intention in the assisted rehabilitation process of the robots,it is crucial to establish the human motion prediction model.In this paper,a hybrid prediction model built on long short-term memory(LSTM)neural network using surface electromyography(sEMG)is applied to predict the elbow motion of the users in advance.This model includes two sub-models:a back-propagation neural network and an LSTM network.The former extracts a preliminary prediction of the elbow motion,and the latter corrects this prediction to increase accuracy.The proposed model takes time series data as input,which includes the sEMG signals measured by electrodes and the continuous angles from inertial measurement units.The offline and online tests were carried out to verify the established hybrid model.Finally,average root mean square errors of 3.52°and 4.18°were reached respectively for offline and online tests,and the correlation coefficients for both were above 0.98.展开更多
The aircraft braking system is critical to ensure the safe take-off and landing of the aircraft.However,the braking system is often exposed to high temperatures and strong vibration working environments,which makes th...The aircraft braking system is critical to ensure the safe take-off and landing of the aircraft.However,the braking system is often exposed to high temperatures and strong vibration working environments,which makes the sensor prone to failure.Sensor failure has the potential to compromise aircraft safety.In order to improve the safety of the aircraft braking system,a fault detection and fault-tolerant control(FDFTC)strategy for the aircraft brake pressure sensor is designed.Firstly,a model based on a bidirectional long short-term memory(Bi-LSTM)network is constructed to estimate the brake pressure.Then,the residual sequence is obtained by comparing the measured pressure with the estimated pressure.On this basis,the improved sequential probability ratio test(SPRT)method based on mathematical statistics is applied to analyze the residual sequence to detect the fault.Finally,simulation and hardware-in-the-loop(HIL)testing results indicate that the proposed FDFTC strategy can detect sensor faults in time and efficiently complete braking when faults occur.Hence,the proposed FDFTC strategy can effectively deal with the faults of the aircraft brake pressure sensor,which is of great significance to improve the reliability and safety of the aircraft.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
基金funded by the National Natural Science Foundation of China(32072486 and 31971424)the Postdoctoral Fellowship Program of China Postdoctoral Science Foundation(GZC20240511)。
文摘To ensure the reliability of learned information,most insects require multiple intervals of experience before storing the information as long-term memory(LTM),and this requirement has been validated in insects from the behavioral to the molecular level.Recent studies have shown that some insects can form LTM after one-trial experience,although the mechanisms underlying one-trial LTM formation are not well understood.Therefore,understanding the mechanisms underlying rapid learning and subsequent preference formation in insects is crucial.Here we show that the agricultural pest Bactrocera dorsalis can rapidly form LTM,which is dependent on protein synthesis,and that the formation of LTM requires high energy support at the cost of reduced survival.Furthermore,based on a liquid chromatography-mass spectrometry(LC-MS)metabolomics approach,we found that LTM-related processes are sequentially coupled to two processes for energy generation,the TCA cycle and oxidative phosphorylation.This was further confirmed by blocking these energy generation processes.Our results provide a theoretical basis for the development of behavioral modulators in oriental fruit flies that target energy generation metabolites,as well as a new perspective on the rapid formation of LTM in insects.
基金supported by the Russian science foundation(grant#22-74-00115 to A.P.G.).
文摘Background:Mitochondrial dysfunction plays a critical role in the pathogenesis of Alzheimer’s disease(AD).Resveratrol is a promising compound for the treatment of various neurodegenerative diseases,including AD.Aims:To investigate mitochondrial damage and the effects of resveratrol on inflammation,cognitive function,and mitochondrial quality control in APP/PS1 mice.Methods:Comparative analysis of mitochondrial DNA(mtDNA)damage was conducted between 10-month-old APP/PS1 mice and age-matched C57BL/6 mice.Assessments included measurement of amyloid-βlevels,inflammatory markers,swimming distance in the Morris water maze,and gut microbiome composition.Resveratrol’s effects on cytokine expression,mtDNA levels in plasma,and activation of Nuclear factor erythroid 2-related factor 2/Antioxidant response element(Nrf2/ARE)and phosphoinositide 3-kinase/protein kinase B(also known as Akt)/mechanistic target of rapamycin complex 1(PI3K/Akt/mTORC1)signaling pathways were also evaluated.Results:APP/PS1 mice exhibited significantly increased mtDNA damage in the prefrontal cortex,midbrain,and cerebellum,alongside higher amyloid-βlevels and inflammatory markers.Resveratrol treatment led to reduced expression of pro-inflammatory cytokines,a decrease in Proteobacteria levels,and lower cell-free mtDNA in plasma.Partial improvement in long-term spatial memory was observed in APP/PS1 mice following resveratrol treatment,likely due to its anti-inflammatory properties.Activation of the Nrf2/ARE signaling pathway and markers of PI3K/Akt/mTORC1 axis activation were noted,with the latter regulating long-term potentiation.Conclusion:Resveratrol demonstrates potential in mitigating inflammation and improving mitochondrial quality control in APP/PS1 mice,but it does not reduce amyloid-βlevels,highlighting the complexity of AD pathology and the need for further research.
基金supported by the National Research and Development Program(2022YFC3004603)the Jiangsu Province International Collaboration Program-Key National Industrial Technology Research and Development Cooperation Projects(BZ2023050)+1 种基金the Natural Science Foundation of Jiangsu Province(BK20221109)the National Natural Science Foundation of China(52274098).
文摘The increasingly severe state of coal burst disaster has emerged as a critical factor constraining coal mine safety production,and it has become a challenging task to enhance the accuracy of coal burst disaster prediction.To address the issue of insufficient exploration of the spatio-temporal characteristic of microseismic data and the challenging selection of the optimal time window size in spatio-temporal prediction,this paper integrates deep learning methods and theory to propose a novel coal burst spatio-temporal prediction method based on Bidirectional Long Short-Term Memory(Bi-LSTM)network.The method involves three main modules,including microseismic spatio-temporal characteristic indicators construction,temporal prediction model,and spatial prediction model.To validate the effectiveness of the proposed method,engineering application tests are conducted at a high-risk working face in the Ordos mining area of Inner Mongolia,focusing on 13 high-energy microseismic events with energy levels greater than 105 J.In terms of temporal prediction,the analysis indicates that the temporal prediction results consist of 10 strong predictions and 3 medium predictions,and there is no false alarm detected throughout the entire testing period.Moreover,compared to the traditional threshold-based coal burst temporal prediction method,the accuracy of the proposed method is increased by 38.5%.In terms of spatial prediction,the distribution of spatial prediction results for high-energy events comprises 6 strong hazard predictions,3 medium hazard predictions,and 4 weak hazard predictions.
文摘Developing efficient neural network(NN)computing systems is crucial in the era of artificial intelligence(AI).Traditional von Neumann architectures have both the issues of"memory wall"and"power wall",limiting the data transfer between memory and processing units[1,2].Compute-in-memory(CIM)technologies,particularly analogue CIM with memristor crossbars,are promising because of their high energy efficiency,computational parallelism,and integration density for NN computations[3].In practical applications,analogue CIM excels in tasks like speech recognition and image classification,revealing its unique advantages.For instance,it efficiently processes vast amounts of audio data in speech recognition,achieving high accuracy with minimal power consumption.In image classification,the high parallelism of analogue CIM significantly speeds up feature extraction and reduces processing time.With the boosting development of AI applications,the demands for computational accuracy and task complexity are rising continually.However,analogue CIM systems are limited in handling complex regression tasks with needs of precise floating-point(FP)calculations.They are primarily suited for the classification tasks with low data precision and a limited dynamic range[4].
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 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This work was supported by the National Natural Science Foundation of China(Nos.62034006,92264201,and 91964105)the Natural Science Foundation of Shandong Province(Nos.ZR2020JQ28 and ZR2020KF016)the Program of Qilu Young Scholars of Shandong University.
文摘With the rapid development of machine learning,the demand for high-efficient computing becomes more and more urgent.To break the bottleneck of the traditional Von Neumann architecture,computing-in-memory(CIM)has attracted increasing attention in recent years.In this work,to provide a feasible CIM solution for the large-scale neural networks(NN)requiring continuous weight updating in online training,a flash-based computing-in-memory with high endurance(10^(9) cycles)and ultrafast programming speed is investigated.On the one hand,the proposed programming scheme of channel hot electron injection(CHEI)and hot hole injection(HHI)demonstrate high linearity,symmetric potentiation,and a depression process,which help to improve the training speed and accuracy.On the other hand,the low-damage programming scheme and memory window(MW)optimizations can suppress cell degradation effectively with improved computing accuracy.Even after 109 cycles,the leakage current(I_(off))of cells remains sub-10pA,ensuring the large-scale computing ability of memory.Further characterizations are done on read disturb to demonstrate its robust reliabilities.By processing CIFAR-10 tasks,it is evident that~90%accuracy can be achieved after 109 cycles in both ResNet50 and VGG16 NN.Our results suggest that flash-based CIM has great potential to overcome the limitations of traditional Von Neumann architectures and enable high-performance NN online training,which pave the way for further development of artificial intelligence(AI)accelerators.
基金National Key Research and Development Program of China (Grant No. 2022YFE0102700)National Natural Science Foundation of China (Grant No. 52102420)+2 种基金research project “Safe Da Batt” (03EMF0409A) funded by the German Federal Ministry of Digital and Transport (BMDV)China Postdoctoral Science Foundation (Grant No. 2023T160085)Sichuan Science and Technology Program (Grant No. 2024NSFSC0938)。
文摘A fast-charging policy is widely employed to alleviate the inconvenience caused by the extended charging time of electric vehicles. However, fast charging exacerbates battery degradation and shortens battery lifespan. In addition, there is still a lack of tailored health estimations for fast-charging batteries;most existing methods are applicable at lower charging rates. This paper proposes a novel method for estimating the health of lithium-ion batteries, which is tailored for multi-stage constant current-constant voltage fast-charging policies. Initially, short charging segments are extracted by monitoring current switches,followed by deriving voltage sequences using interpolation techniques. Subsequently, a graph generation layer is used to transform the voltage sequence into graphical data. Furthermore, the integration of a graph convolution network with a long short-term memory network enables the extraction of information related to inter-node message transmission, capturing the key local and temporal features during the battery degradation process. Finally, this method is confirmed by utilizing aging data from 185 cells and 81 distinct fast-charging policies. The 4-minute charging duration achieves a balance between high accuracy in estimating battery state of health and low data requirements, with mean absolute errors and root mean square errors of 0.34% and 0.66%, respectively.
基金supported by the National Natural Science Foundation of China(Grant No.12172125)the Science Foundation of Hunan Province(Grant No.2022JJ30119).
文摘Multi-wall carbon nanotube filled shape memory polymer composite(MWCNT/SMC)possessed enhanced modulus,strength,and electric conductivity,as well as excellent electrothermal shape memory properties,showing wide design scenarios and engineering application prospects.The thermoelectrically triggered shape memory process contains complex multi-physical mechanisms,especially when coupled with finite deformation rooted on micro-mechanisms.A multi-physical finite deformation model is necessary to get a deep understanding on the coupled electro-thermomechanical properties of electrothermal shape memory composites(ESMCs),beneficial to its design and wide application.Taking into consideration of micro-physical mechanisms of the MWCNTs interacting with double-chain networks,a finite deformation theoretical model is developed in this work based on two superimposed network chains of physically crosslinked network formed among MWCNTs and the chemically crosslinked network.An intact crosslinked chemical network is considered featuring with entropic-hyperelastic properties,superimposed with a physically crosslinked network where percolation theory is based on electric conductivity and electric-heating mechanisms.The model is calibrated by experiments and used for shape recoveries triggered by heating and electric fields.It captures the coupled electro-thermomechanical behavior of ESMCs and provides design guidelines for MWCNTs filled shape memory polymers.
文摘With the advent of physics informed neural networks(PINNs),deep learning has gained interest for solving nonlinear partial differential equations(PDEs)in recent years.In this paper,physics informed memory networks(PIMNs)are proposed as a new approach to solving PDEs by using physical laws and dynamic behavior of PDEs.Unlike the fully connected structure of the PINNs,the PIMNs construct the long-term dependence of the dynamics behavior with the help of the long short-term memory network.Meanwhile,the PDEs residuals are approximated using difference schemes in the form of convolution filter,which avoids information loss at the neighborhood of the sampling points.Finally,the performance of the PIMNs is assessed by solving the Kd V equation and the nonlinear Schr?dinger equation,and the effects of difference schemes,boundary conditions,network structure and mesh size on the solutions are discussed.Experiments show that the PIMNs are insensitive to boundary conditions and have excellent solution accuracy even with only the initial conditions.
基金supported by the US Department of Energy (DOE),the Office of Nuclear Energy,Spent Fuel and Waste Science and Technology Campaign,under Contract Number DE-AC02-05CH11231the National Energy Technology Laboratory under the award number FP00013650 at Lawrence Berkeley National Laboratory.
文摘Stress changes due to changes in fluid pressure and temperature in a faulted formation may lead to the opening/shearing of the fault.This can be due to subsurface(geo)engineering activities such as fluid injections and geologic disposal of nuclear waste.Such activities are expected to rise in the future making it necessary to assess their short-and long-term safety.Here,a new machine learning(ML)approach to model pore pressure and fault displacements in response to high-pressure fluid injection cycles is developed.The focus is on fault behavior near the injection borehole.To capture the temporal dependencies in the data,long short-term memory(LSTM)networks are utilized.To prevent error accumulation within the forecast window,four critical measures to train a robust LSTM model for predicting fault response are highlighted:(i)setting an appropriate value of LSTM lag,(ii)calibrating the LSTM cell dimension,(iii)learning rate reduction during weight optimization,and(iv)not adopting an independent injection cycle as a validation set.Several numerical experiments were conducted,which demonstrated that the ML model can capture peaks in pressure and associated fault displacement that accompany an increase in fluid injection.The model also captured the decay in pressure and displacement during the injection shut-in period.Further,the ability of an ML model to highlight key changes in fault hydromechanical activation processes was investigated,which shows that ML can be used to monitor risk of fault activation and leakage during high pressure fluid injections.
基金founded by the Open Project Program of Anhui Province Key Laboratory of Metallurgical Engineering and Resources Recycling(Anhui University of Technology)(No.SKF21-06)Research Fund for Young Teachers of Anhui University of Technology in 2020(No.QZ202001).
文摘Real-time prediction and precise control of sinter quality are pivotal for energy saving,cost reduction,quality improvement and efficiency enhancement in the ironmaking process.To advance,the accuracy and comprehensiveness of sinter quality prediction,an intelligent flare monitoring system for sintering machine tails that combines hybrid neural networks integrating convolutional neural network with long short-term memory(CNN-LSTM)networks was proposed.The system utilized a high-temperature thermal imager for image acquisition at the sintering machine tail and employed a zone-triggered method to accurately capture dynamic feature images under challenging conditions of high-temperature,high dust,and occlusion.The feature images were then segmented through a triple-iteration multi-thresholding approach based on the maximum between-class variance method to minimize detail loss during the segmentation process.Leveraging the advantages of CNN and LSTM networks in capturing temporal and spatial information,a comprehensive model for sinter quality prediction was constructed,with inputs including the proportion of combustion layer,porosity rate,temperature distribution,and image features obtained from the convolutional neural network,and outputs comprising quality indicators such as underburning index,uniformity index,and FeO content of the sinter.The accuracy is notably increased,achieving a 95.8%hit rate within an error margin of±1.0.After the system is applied,the average qualified rate of FeO content increases from 87.24%to 89.99%,representing an improvement of 2.75%.The average monthly solid fuel consumption is reduced from 49.75 to 46.44 kg/t,leading to a 6.65%reduction and underscoring significant energy saving and cost reduction effects.
基金funded by Woosong University Academic Research 2024.
文摘This study investigates the application of Learnable Memory Vision Transformers(LMViT)for detecting metal surface flaws,comparing their performance with traditional CNNs,specifically ResNet18 and ResNet50,as well as other transformer-based models including Token to Token ViT,ViT withoutmemory,and Parallel ViT.Leveraging awidely-used steel surface defect dataset,the research applies data augmentation and t-distributed stochastic neighbor embedding(t-SNE)to enhance feature extraction and understanding.These techniques mitigated overfitting,stabilized training,and improved generalization capabilities.The LMViT model achieved a test accuracy of 97.22%,significantly outperforming ResNet18(88.89%)and ResNet50(88.90%),aswell as the Token to TokenViT(88.46%),ViT without memory(87.18),and Parallel ViT(91.03%).Furthermore,LMViT exhibited superior training and validation performance,attaining a validation accuracy of 98.2%compared to 91.0%for ResNet 18,96.0%for ResNet50,and 89.12%,87.51%,and 91.21%for Token to Token ViT,ViT without memory,and Parallel ViT,respectively.The findings highlight the LMViT’s ability to capture long-range dependencies in images,an areawhere CNNs struggle due to their reliance on local receptive fields and hierarchical feature extraction.The additional transformer-based models also demonstrate improved performance in capturing complex features over CNNs,with LMViT excelling particularly at detecting subtle and complex defects,which is critical for maintaining product quality and operational efficiency in industrial applications.For instance,the LMViT model successfully identified fine scratches and minor surface irregularities that CNNs often misclassify.This study not only demonstrates LMViT’s potential for real-world defect detection but also underscores the promise of other transformer-based architectures like Token to Token ViT,ViT without memory,and Parallel ViT in industrial scenarios where complex spatial relationships are key.Future research may focus on enhancing LMViT’s computational efficiency for deployment in real-time quality control systems.
文摘With breakthroughs in data processing and pattern recognition through deep learning technologies,the use of advanced algorithmic models for analyzing and interpreting soil spectral information has provided an efficient and economical method for soil quality assessment.However,traditional single-output networks exhibit limitations in the prediction process,particularly in their inability to fully utilize the correlations among various elements.As a result,single-output networks tend to be optimized for a single task,neglecting the interrelationships among different soil elements,which limits prediction accuracy and model generalizability.To overcome this limitation,in this study,a multi-task learning architecture with a progressive extraction network was implemented for the simultaneous prediction of multiple indicators in soil,including nitrogen(N),organic carbon(OC),calcium carbonate(CaCO 3),cation exchange capacity(CEC),and pH.Furthermore,while incorporating the Pearson correlation coefficient,convolutional neural networks,long short-term memory networks and attention mechanisms were combined to extract local abstract features from the original spectra,thereby further improving the model.This architecture is referred to as the Relevance-sharing Progressive Layered Extraction Network.The model employs an adaptive joint loss optimization method to update the weights of individual task losses in the multi-task learning training process.
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.
基金supported by the National Natural Science Foundation of China(Grant Nos.62376105,12101208,and 61906072)the Fundamental Research Funds for the Central Universities(Grant No.2662022XXQD001).
文摘This paper proposes a novel multivalued recurrent neural network model driven by external inputs,along with two innovative learning algorithms.By incorporating a multivalued activation function,the proposed model can achieve multivalued many-to-one associative memory,and the newly developed algorithms enable effective storage of many-to-one patterns in the coefficient matrix while maintaining the indispensability of inputs in many-to-one associative memory.The proposed learning algorithm addresses a critical limitation of existing models which fail to ensure completely erroneous outputs when facing partial input missing in many-to-one associative memory tasks.The methodology is rigorously derived through theoretical analysis,incorporating comprehensive verification of both the existence and global exponential stability of equilibrium points.Demonstrative examples are provided in the paper to show the effectiveness of the proposed theory.
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the National Key Research and Development Program of China(No.2020YFC2007500)the Science and Technology Commission of Shanghai Municipality(No.20DZ2220400)。
文摘In the face of the large number of people with motor function disabilities,rehabilitation robots have attracted more and more attention.In order to promote the active participation of the user's motion intention in the assisted rehabilitation process of the robots,it is crucial to establish the human motion prediction model.In this paper,a hybrid prediction model built on long short-term memory(LSTM)neural network using surface electromyography(sEMG)is applied to predict the elbow motion of the users in advance.This model includes two sub-models:a back-propagation neural network and an LSTM network.The former extracts a preliminary prediction of the elbow motion,and the latter corrects this prediction to increase accuracy.The proposed model takes time series data as input,which includes the sEMG signals measured by electrodes and the continuous angles from inertial measurement units.The offline and online tests were carried out to verify the established hybrid model.Finally,average root mean square errors of 3.52°and 4.18°were reached respectively for offline and online tests,and the correlation coefficients for both were above 0.98.
基金Supported by National Natural Science Foundation of China(Grant No.52205045)National Key Research and Development Program of China(Grant No.2021YFB2011300)+2 种基金Aeronautical Science Foundation of China(Grant No.2022Z029051001)Zhejiang Provincial Natural Science Foundation of China(Grant No.LZ24E050006)Research Fund of State Key Laboratory of Mechanics and Control for Aerospace Structures(Nanjing University of Aeronautics and Astronautics)(Grant No.MCAS-E-0224G01).
文摘The aircraft braking system is critical to ensure the safe take-off and landing of the aircraft.However,the braking system is often exposed to high temperatures and strong vibration working environments,which makes the sensor prone to failure.Sensor failure has the potential to compromise aircraft safety.In order to improve the safety of the aircraft braking system,a fault detection and fault-tolerant control(FDFTC)strategy for the aircraft brake pressure sensor is designed.Firstly,a model based on a bidirectional long short-term memory(Bi-LSTM)network is constructed to estimate the brake pressure.Then,the residual sequence is obtained by comparing the measured pressure with the estimated pressure.On this basis,the improved sequential probability ratio test(SPRT)method based on mathematical statistics is applied to analyze the residual sequence to detect the fault.Finally,simulation and hardware-in-the-loop(HIL)testing results indicate that the proposed FDFTC strategy can detect sensor faults in time and efficiently complete braking when faults occur.Hence,the proposed FDFTC strategy can effectively deal with the faults of the aircraft brake pressure sensor,which is of great significance to improve the reliability and safety of the aircraft.
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.
