Aiming at the problem of insufficient consideration of the correlation between components in the prediction of the remaining life of mechanical equipment,the method of remaining life prediction that combines the self-...Aiming at the problem of insufficient consideration of the correlation between components in the prediction of the remaining life of mechanical equipment,the method of remaining life prediction that combines the self-attention mechanism with the long short-term memory neural network(LSTM-NN)is proposed,called Self-Attention-LSTM.First,the auto-encoder is used to obtain the component-level state information;second,the state information of each component is input into the self-attention mechanism to learn the correlation between components;then,the multi-component correlation matrix is added to the LSTM input gate,and the LSTM-NN is used for life prediction.Finally,combined with the commercial modular aero-propulsion system simulation data set(C-MAPSS),the experiment was carried out and compared with the existing methods.Research results show that the proposed method can achieve better prediction accuracy and verify the feasibility of the method.展开更多
There are two technical challenges in predicting slope deformation.The first one is the random displacement,which could not be decomposed and predicted by numerically resolving the observed accumulated displacement an...There are two technical challenges in predicting slope deformation.The first one is the random displacement,which could not be decomposed and predicted by numerically resolving the observed accumulated displacement and time series of a landslide.The second one is the dynamic evolution of a landslide,which could not be feasibly simulated simply by traditional prediction models.In this paper,a dynamic model of displacement prediction is introduced for composite landslides based on a combination of empirical mode decomposition with soft screening stop criteria(SSSC-EMD)and deep bidirectional long short-term memory(DBi-LSTM)neural network.In the proposed model,the time series analysis and SSSC-EMD are used to decompose the observed accumulated displacements of a slope into three components,viz.trend displacement,periodic displacement,and random displacement.Then,by analyzing the evolution pattern of a landslide and its key factors triggering landslides,appropriate influencing factors are selected for each displacement component,and DBi-LSTM neural network to carry out multi-datadriven dynamic prediction for each displacement component.An accumulated displacement prediction has been obtained by a summation of each component.For accuracy verification and engineering practicability of the model,field observations from two known landslides in China,the Xintan landslide and the Bazimen landslide were collected for comparison and evaluation.The case study verified that the model proposed in this paper can better characterize the"stepwise"deformation characteristics of a slope.As compared with long short-term memory(LSTM)neural network,support vector machine(SVM),and autoregressive integrated moving average(ARIMA)model,DBi-LSTM neural network has higher accuracy in predicting the periodic displacement of slope deformation,with the mean absolute percentage error reduced by 3.063%,14.913%,and 13.960%respectively,and the root mean square error reduced by 1.951 mm,8.954 mm and 7.790 mm respectively.Conclusively,this model not only has high prediction accuracy but also is more stable,which can provide new insight for practical landslide prevention and control engineering.展开更多
As a high efficiency hydrogen-to-power device,proton exchange membrane fuel cell(PEMFC)attracts much attention,especially for the automotive applications.Real-time prediction of output voltage and area specific resist...As a high efficiency hydrogen-to-power device,proton exchange membrane fuel cell(PEMFC)attracts much attention,especially for the automotive applications.Real-time prediction of output voltage and area specific resistance(ASR)via the on-board model is critical to monitor the health state of the automotive PEMFC stack.In this study,we use a transient PEMFC system model for dynamic process simulation of PEMFC to generate the dataset,and a long short-term memory(LSTM)deep learning model is developed to predict the dynamic per-formance of PEMFC.The results show that the developed LSTM deep learning model has much better perfor-mance than other models.A sensitivity analysis on the input features is performed,and three insensitive features are removed,that could slightly improve the prediction accuracy and significantly reduce the data volume.The neural structure,sequence duration,and sampling frequency are optimized.We find that the optimal sequence data duration for predicting ASR is 5 s or 20 s,and that for predicting output voltage is 40 s.The sampling frequency can be reduced from 10 Hz to 0.5 Hz and 0.25 Hz,which slightly affects the prediction accuracy,but obviously reduces the data volume and computation amount.展开更多
The rapid development of unmanned aerial vehicle(UAV) swarm, a new type of aerial threat target, has brought great pressure to the air defense early warning system. At present, most of the track correlation algorithms...The rapid development of unmanned aerial vehicle(UAV) swarm, a new type of aerial threat target, has brought great pressure to the air defense early warning system. At present, most of the track correlation algorithms only use part of the target location, speed, and other information for correlation.In this paper, the artificial neural network method is used to establish the corresponding intelligent track correlation model and method according to the characteristics of swarm targets.Precisely, a route correlation method based on convolutional neural networks (CNN) and long short-term memory (LSTM)Neural network is designed. In this model, the CNN is used to extract the formation characteristics of UAV swarm and the spatial position characteristics of single UAV track in the formation,while the LSTM is used to extract the time characteristics of UAV swarm. Experimental results show that compared with the traditional algorithms, the algorithm based on CNN-LSTM neural network can make full use of multiple feature information of the target, and has better robustness and accuracy for swarm targets.展开更多
Under dynamic pricing, stable and accurate electricity price forecasting on the demand side is essential forefficient energy management. We have developed a new electricity price forecasting model that providesconsist...Under dynamic pricing, stable and accurate electricity price forecasting on the demand side is essential forefficient energy management. We have developed a new electricity price forecasting model that providesconsistently accurate forecasts. The base prediction model decomposes the time series using wavelet transformand then predicts it by Long Short-Term Memory. Previous studies using this model have always decomposedtime series in the same way without changing the mother wavelet. However, this makes it difficult to respond tochanges in time series that vary daily or seasonally. Therefore, we periodically switch the mother wavelet, i.e.,flexibly change the time series decomposition method, to achieve stable and highly accurate electricity priceforecasting. In an experiment, the model improved prediction accuracy by up to 42.8% compared to predictionwith a fixed mother wavelet. Experimental results show that the proposed flexible forecasting method canconsistently provide highly accurate forecasts.展开更多
In the complex countermeasure environment,the pulse description words(PDWs)of the same type of multi-function radar emitters are similar in multiple dimensions.Therefore,it is difficult for conventional methods to dei...In the complex countermeasure environment,the pulse description words(PDWs)of the same type of multi-function radar emitters are similar in multiple dimensions.Therefore,it is difficult for conventional methods to deinterleave such emitters.In order to solve this problem,a pulse deinterleaving method based on implicit features is proposed in this paper.The proposed method introduces long short-term memory(LSTM)neural networks and statistical analysis to mine new features from similar PDW features,that is,the variation law(implicit features)of pulse sequences of different radiation sources over time.The multi-function radar emitter is deinterleaved based on the pulse sequence variation law.Statistical results show that the proposed method not only achieves satisfactory performance,but also has good robustness.展开更多
Three recent breakthroughs due to AI in arts and science serve as motivation:An award winning digital image,protein folding,fast matrix multiplication.Many recent developments in artificial neural networks,particularl...Three recent breakthroughs due to AI in arts and science serve as motivation:An award winning digital image,protein folding,fast matrix multiplication.Many recent developments in artificial neural networks,particularly deep learning(DL),applied and relevant to computational mechanics(solid,fluids,finite-element technology)are reviewed in detail.Both hybrid and pure machine learning(ML)methods are discussed.Hybrid methods combine traditional PDE discretizations with ML methods either(1)to help model complex nonlinear constitutive relations,(2)to nonlinearly reduce the model order for efficient simulation(turbulence),or(3)to accelerate the simulation by predicting certain components in the traditional integration methods.Here,methods(1)and(2)relied on Long-Short-Term Memory(LSTM)architecture,with method(3)relying on convolutional neural networks.Pure ML methods to solve(nonlinear)PDEs are represented by Physics-Informed Neural network(PINN)methods,which could be combined with attention mechanism to address discontinuous solutions.Both LSTM and attention architectures,together with modern and generalized classic optimizers to include stochasticity for DL networks,are extensively reviewed.Kernel machines,including Gaussian processes,are provided to sufficient depth for more advanced works such as shallow networks with infinite width.Not only addressing experts,readers are assumed familiar with computational mechanics,but not with DL,whose concepts and applications are built up from the basics,aiming at bringing first-time learners quickly to the forefront of research.History and limitations of AI are recounted and discussed,with particular attention at pointing out misstatements or misconceptions of the classics,even in well-known references.Positioning and pointing control of a large-deformable beam is given as an example.展开更多
Shale gas wells frequently suffer from liquid loading and insufficient formation pressure in the late stage of production.To address this issue,an intelligent production optimization method for low pressure and low pr...Shale gas wells frequently suffer from liquid loading and insufficient formation pressure in the late stage of production.To address this issue,an intelligent production optimization method for low pressure and low productivity shale gas well is proposed.Based on the artificial intelligence algorithms,this method realizes automatic production and monitoring of gas well.The method can forecast the production performance of a single well by using the long short-term memory neural network and then guide gas well production accordingly,to fulfill liquid loading warning and automatic intermittent production.Combined with adjustable nozzle,the method can keep production and pressure of gas wells stable automatically,extend normal production time of shale gas wells,enhance automatic level of well sites,and reach the goal of refined production management by making production regime for each well.Field tests show that wells with production regime optimized by this method increased 15%in estimated ultimate reserve(EUR).Compared with the development mode of drainage after depletion recovery,this method is more economical and can increase and stabilize production effectively,so it has a bright application prospect.展开更多
There are many techniques using sensors and wearable devices for detecting and monitoring patients with Parkinson’s disease(PD).A recent development is the utilization of human interaction with computer keyboards for...There are many techniques using sensors and wearable devices for detecting and monitoring patients with Parkinson’s disease(PD).A recent development is the utilization of human interaction with computer keyboards for analyzing and identifying motor signs in the early stages of the disease.Current designs for classification of time series of computer-key hold durations recorded from healthy control and PD subjects require the time series of length to be considerably long.With an attempt to avoid discomfort to participants in performing long physical tasks for data recording,this paper introduces the use of fuzzy recurrence plots of very short time series as input data for the machine training and classification with long short-term memory(LSTM)neural networks.Being an original approach that is able to both significantly increase the feature dimensions and provides the property of deterministic dynamical systems of very short time series for information processing carried out by an LSTM layer architecture,fuzzy recurrence plots provide promising results and outperform the direct input of the time series for the classification of healthy control and early PD subjects.展开更多
Water quality prediction is vital for solving water pollution and protecting the water environment.In terms of the characteristics of nonlinearity,instability,and randomness of water quality parameters,a short-term wa...Water quality prediction is vital for solving water pollution and protecting the water environment.In terms of the characteristics of nonlinearity,instability,and randomness of water quality parameters,a short-term water quality prediction model was proposed based on variational mode decomposition(VMD)and improved grasshopper optimization algorithm(IGOA),so as to optimize long short-term memory neural network(LSTM).First,VMD was adopted to decompose the water quality data into a series of relatively stable components,with the aim to reduce the instability of the original data and increase the predictability,then each component was input into the iGOA-LSTM model for prediction.Finally,each component was added to obtain the predicted values.In this study,the monitoring data from Dayangzhou Station and Shengmi Station of the Ganjiang River was used for training and prediction.The experimental results showed that the prediction accuracy of the VMDIGOA-LSTM model proposed was higher than that of the integrated model of Ensemble Empirical Mode Decomposition(EEMD),the integrated model of Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN),Nonlinear Autoregressive Network with Exogenous Inputs(NARX),Recurrent Neural Network(RNN),as well as other models,showing better performance in short-term prediction.The current study will provide a reliable solution for water quality prediction studies in other areas.展开更多
基金the National Natural Science Foundation of China(Nos.51875451 and 51834006)。
文摘Aiming at the problem of insufficient consideration of the correlation between components in the prediction of the remaining life of mechanical equipment,the method of remaining life prediction that combines the self-attention mechanism with the long short-term memory neural network(LSTM-NN)is proposed,called Self-Attention-LSTM.First,the auto-encoder is used to obtain the component-level state information;second,the state information of each component is input into the self-attention mechanism to learn the correlation between components;then,the multi-component correlation matrix is added to the LSTM input gate,and the LSTM-NN is used for life prediction.Finally,combined with the commercial modular aero-propulsion system simulation data set(C-MAPSS),the experiment was carried out and compared with the existing methods.Research results show that the proposed method can achieve better prediction accuracy and verify the feasibility of the method.
文摘There are two technical challenges in predicting slope deformation.The first one is the random displacement,which could not be decomposed and predicted by numerically resolving the observed accumulated displacement and time series of a landslide.The second one is the dynamic evolution of a landslide,which could not be feasibly simulated simply by traditional prediction models.In this paper,a dynamic model of displacement prediction is introduced for composite landslides based on a combination of empirical mode decomposition with soft screening stop criteria(SSSC-EMD)and deep bidirectional long short-term memory(DBi-LSTM)neural network.In the proposed model,the time series analysis and SSSC-EMD are used to decompose the observed accumulated displacements of a slope into three components,viz.trend displacement,periodic displacement,and random displacement.Then,by analyzing the evolution pattern of a landslide and its key factors triggering landslides,appropriate influencing factors are selected for each displacement component,and DBi-LSTM neural network to carry out multi-datadriven dynamic prediction for each displacement component.An accumulated displacement prediction has been obtained by a summation of each component.For accuracy verification and engineering practicability of the model,field observations from two known landslides in China,the Xintan landslide and the Bazimen landslide were collected for comparison and evaluation.The case study verified that the model proposed in this paper can better characterize the"stepwise"deformation characteristics of a slope.As compared with long short-term memory(LSTM)neural network,support vector machine(SVM),and autoregressive integrated moving average(ARIMA)model,DBi-LSTM neural network has higher accuracy in predicting the periodic displacement of slope deformation,with the mean absolute percentage error reduced by 3.063%,14.913%,and 13.960%respectively,and the root mean square error reduced by 1.951 mm,8.954 mm and 7.790 mm respectively.Conclusively,this model not only has high prediction accuracy but also is more stable,which can provide new insight for practical landslide prevention and control engineering.
基金This research is supported by the National Natural Science Founda-tion of China(No.52176196)the National Key Research and Devel-opment Program of China(No.2022YFE0103100)+1 种基金the China Postdoctoral Science Foundation(No.2021TQ0235)the Hong Kong Scholars Program(No.XJ2021033).
文摘As a high efficiency hydrogen-to-power device,proton exchange membrane fuel cell(PEMFC)attracts much attention,especially for the automotive applications.Real-time prediction of output voltage and area specific resistance(ASR)via the on-board model is critical to monitor the health state of the automotive PEMFC stack.In this study,we use a transient PEMFC system model for dynamic process simulation of PEMFC to generate the dataset,and a long short-term memory(LSTM)deep learning model is developed to predict the dynamic per-formance of PEMFC.The results show that the developed LSTM deep learning model has much better perfor-mance than other models.A sensitivity analysis on the input features is performed,and three insensitive features are removed,that could slightly improve the prediction accuracy and significantly reduce the data volume.The neural structure,sequence duration,and sampling frequency are optimized.We find that the optimal sequence data duration for predicting ASR is 5 s or 20 s,and that for predicting output voltage is 40 s.The sampling frequency can be reduced from 10 Hz to 0.5 Hz and 0.25 Hz,which slightly affects the prediction accuracy,but obviously reduces the data volume and computation amount.
文摘The rapid development of unmanned aerial vehicle(UAV) swarm, a new type of aerial threat target, has brought great pressure to the air defense early warning system. At present, most of the track correlation algorithms only use part of the target location, speed, and other information for correlation.In this paper, the artificial neural network method is used to establish the corresponding intelligent track correlation model and method according to the characteristics of swarm targets.Precisely, a route correlation method based on convolutional neural networks (CNN) and long short-term memory (LSTM)Neural network is designed. In this model, the CNN is used to extract the formation characteristics of UAV swarm and the spatial position characteristics of single UAV track in the formation,while the LSTM is used to extract the time characteristics of UAV swarm. Experimental results show that compared with the traditional algorithms, the algorithm based on CNN-LSTM neural network can make full use of multiple feature information of the target, and has better robustness and accuracy for swarm targets.
基金supported by JSPS,Japan KAKENHI Grant Number 22H03697,and DAIKIN Industries,Ltd.
文摘Under dynamic pricing, stable and accurate electricity price forecasting on the demand side is essential forefficient energy management. We have developed a new electricity price forecasting model that providesconsistently accurate forecasts. The base prediction model decomposes the time series using wavelet transformand then predicts it by Long Short-Term Memory. Previous studies using this model have always decomposedtime series in the same way without changing the mother wavelet. However, this makes it difficult to respond tochanges in time series that vary daily or seasonally. Therefore, we periodically switch the mother wavelet, i.e.,flexibly change the time series decomposition method, to achieve stable and highly accurate electricity priceforecasting. In an experiment, the model improved prediction accuracy by up to 42.8% compared to predictionwith a fixed mother wavelet. Experimental results show that the proposed flexible forecasting method canconsistently provide highly accurate forecasts.
基金the National Major Research&Development project of China(2018YFE0206500)the National Natural Science Foundation of China(62071140)+1 种基金the Program of China International Scientific and Technological Cooperation(2015DFR10220)the Technology Foundation for Basic Enhancement Plan(2021-JCJQ-JJ-0301).
文摘In the complex countermeasure environment,the pulse description words(PDWs)of the same type of multi-function radar emitters are similar in multiple dimensions.Therefore,it is difficult for conventional methods to deinterleave such emitters.In order to solve this problem,a pulse deinterleaving method based on implicit features is proposed in this paper.The proposed method introduces long short-term memory(LSTM)neural networks and statistical analysis to mine new features from similar PDW features,that is,the variation law(implicit features)of pulse sequences of different radiation sources over time.The multi-function radar emitter is deinterleaved based on the pulse sequence variation law.Statistical results show that the proposed method not only achieves satisfactory performance,but also has good robustness.
文摘Three recent breakthroughs due to AI in arts and science serve as motivation:An award winning digital image,protein folding,fast matrix multiplication.Many recent developments in artificial neural networks,particularly deep learning(DL),applied and relevant to computational mechanics(solid,fluids,finite-element technology)are reviewed in detail.Both hybrid and pure machine learning(ML)methods are discussed.Hybrid methods combine traditional PDE discretizations with ML methods either(1)to help model complex nonlinear constitutive relations,(2)to nonlinearly reduce the model order for efficient simulation(turbulence),or(3)to accelerate the simulation by predicting certain components in the traditional integration methods.Here,methods(1)and(2)relied on Long-Short-Term Memory(LSTM)architecture,with method(3)relying on convolutional neural networks.Pure ML methods to solve(nonlinear)PDEs are represented by Physics-Informed Neural network(PINN)methods,which could be combined with attention mechanism to address discontinuous solutions.Both LSTM and attention architectures,together with modern and generalized classic optimizers to include stochasticity for DL networks,are extensively reviewed.Kernel machines,including Gaussian processes,are provided to sufficient depth for more advanced works such as shallow networks with infinite width.Not only addressing experts,readers are assumed familiar with computational mechanics,but not with DL,whose concepts and applications are built up from the basics,aiming at bringing first-time learners quickly to the forefront of research.History and limitations of AI are recounted and discussed,with particular attention at pointing out misstatements or misconceptions of the classics,even in well-known references.Positioning and pointing control of a large-deformable beam is given as an example.
基金Supported by the China National Science and Technology Major Project(2017ZX05037-004).
文摘Shale gas wells frequently suffer from liquid loading and insufficient formation pressure in the late stage of production.To address this issue,an intelligent production optimization method for low pressure and low productivity shale gas well is proposed.Based on the artificial intelligence algorithms,this method realizes automatic production and monitoring of gas well.The method can forecast the production performance of a single well by using the long short-term memory neural network and then guide gas well production accordingly,to fulfill liquid loading warning and automatic intermittent production.Combined with adjustable nozzle,the method can keep production and pressure of gas wells stable automatically,extend normal production time of shale gas wells,enhance automatic level of well sites,and reach the goal of refined production management by making production regime for each well.Field tests show that wells with production regime optimized by this method increased 15%in estimated ultimate reserve(EUR).Compared with the development mode of drainage after depletion recovery,this method is more economical and can increase and stabilize production effectively,so it has a bright application prospect.
文摘There are many techniques using sensors and wearable devices for detecting and monitoring patients with Parkinson’s disease(PD).A recent development is the utilization of human interaction with computer keyboards for analyzing and identifying motor signs in the early stages of the disease.Current designs for classification of time series of computer-key hold durations recorded from healthy control and PD subjects require the time series of length to be considerably long.With an attempt to avoid discomfort to participants in performing long physical tasks for data recording,this paper introduces the use of fuzzy recurrence plots of very short time series as input data for the machine training and classification with long short-term memory(LSTM)neural networks.Being an original approach that is able to both significantly increase the feature dimensions and provides the property of deterministic dynamical systems of very short time series for information processing carried out by an LSTM layer architecture,fuzzy recurrence plots provide promising results and outperform the direct input of the time series for the classification of healthy control and early PD subjects.
基金the Zhejiang Provincial Natural Science Foundation of China(No.LY23H180001)the Open Research Fund of State Key Laboratory of Simulation and Regulation of Water Cycle in River Basin,the China Institute of Water Resources and Hydropower Research(No.IWHR-SKL-201905)the National Natural Science Foundation of China(No.11701363).
文摘Water quality prediction is vital for solving water pollution and protecting the water environment.In terms of the characteristics of nonlinearity,instability,and randomness of water quality parameters,a short-term water quality prediction model was proposed based on variational mode decomposition(VMD)and improved grasshopper optimization algorithm(IGOA),so as to optimize long short-term memory neural network(LSTM).First,VMD was adopted to decompose the water quality data into a series of relatively stable components,with the aim to reduce the instability of the original data and increase the predictability,then each component was input into the iGOA-LSTM model for prediction.Finally,each component was added to obtain the predicted values.In this study,the monitoring data from Dayangzhou Station and Shengmi Station of the Ganjiang River was used for training and prediction.The experimental results showed that the prediction accuracy of the VMDIGOA-LSTM model proposed was higher than that of the integrated model of Ensemble Empirical Mode Decomposition(EEMD),the integrated model of Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN),Nonlinear Autoregressive Network with Exogenous Inputs(NARX),Recurrent Neural Network(RNN),as well as other models,showing better performance in short-term prediction.The current study will provide a reliable solution for water quality prediction studies in other areas.
