Accurate acquisition and prediction of acoustic parameters of seabed sediments are crucial in marine sound propagation research.While the relationship between sound velocity and physical properties of sediment has bee...Accurate acquisition and prediction of acoustic parameters of seabed sediments are crucial in marine sound propagation research.While the relationship between sound velocity and physical properties of sediment has been extensively studied,there is still no consensus on the correlation between acoustic attenuation coefficient and sediment physical properties.Predicting the acoustic attenuation coefficient remains a challenging issue in sedimentary acoustic research.In this study,we propose a prediction method for the acoustic attenuation coefficient using machine learning algorithms,specifically the random forest(RF),support vector machine(SVR),and convolutional neural network(CNN)algorithms.We utilized the acoustic attenuation coefficient and sediment particle size data from 52 stations as training parameters,with the particle size parameters as the input feature matrix,and measured acoustic attenuation as the training label to validate the attenuation prediction model.Our results indicate that the error of the attenuation prediction model is small.Among the three models,the RF model exhibited the lowest prediction error,with a mean squared error of 0.8232,mean absolute error of 0.6613,and root mean squared error of 0.9073.Additionally,when we applied the models to predict the data collected at different times in the same region,we found that the models developed in this study also demonstrated a certain level of reliability in real prediction scenarios.Our approach demonstrates that constructing a sediment acoustic characteristics model based on machine learning is feasible to a certain extent and offers a novel perspective for studying sediment acoustic properties.展开更多
Bearing is an indispensable key component in mechanical equipment,and its working state is directly related to the stability and safety of the whole equipment.In recent years,with the rapid development of artificial i...Bearing is an indispensable key component in mechanical equipment,and its working state is directly related to the stability and safety of the whole equipment.In recent years,with the rapid development of artificial intelligence technology,especially the breakthrough of deep learning technology,it provides a new idea for bearing fault diagnosis.Deep learning can automatically learn features from a large amount of data,has a strong nonlinear modeling ability,and can effectively solve the problems existing in traditional methods.Aiming at the key problems in bearing fault diagnosis,this paper studies the fault diagnosis method based on deep learning,which not only provides a new solution for bearing fault diagnosis but also provides a reference for the application of deep learning in other mechanical fault diagnosis fields.展开更多
This article reviews the application and progress of deep learning in efficient numerical computing methods.Deep learning,as an important branch of machine learning,provides new ideas for numerical computation by cons...This article reviews the application and progress of deep learning in efficient numerical computing methods.Deep learning,as an important branch of machine learning,provides new ideas for numerical computation by constructing multi-layer neural networks to simulate the learning process of the human brain.The article explores the application of deep learning in solving partial differential equations,optimizing problems,and data-driven modeling,and analyzes its advantages in computational efficiency,accuracy,and adaptability.At the same time,this article also points out the challenges faced by deep learning numerical computation methods in terms of computational efficiency,interpretability,and generalization ability,and proposes strategies and future development directions for integrating with traditional numerical methods.展开更多
Advanced DriverAssistance Systems(ADAS)technologies can assist drivers or be part of automatic driving systems to support the driving process and improve the level of safety and comfort on the road.Traffic Sign Recogn...Advanced DriverAssistance Systems(ADAS)technologies can assist drivers or be part of automatic driving systems to support the driving process and improve the level of safety and comfort on the road.Traffic Sign Recognition System(TSRS)is one of themost important components ofADAS.Among the challengeswith TSRS is being able to recognize road signs with the highest accuracy and the shortest processing time.Accordingly,this paper introduces a new real time methodology recognizing Speed Limit Signs based on a trio of developed modules.Firstly,the Speed Limit Detection(SLD)module uses the Haar Cascade technique to generate a new SL detector in order to localize SL signs within captured frames.Secondly,the Speed Limit Classification(SLC)module,featuring machine learning classifiers alongside a newly developed model called DeepSL,harnesses the power of a CNN architecture to extract intricate features from speed limit sign images,ensuring efficient and precise recognition.In addition,a new Speed Limit Classifiers Fusion(SLCF)module has been developed by combining trained ML classifiers and the DeepSL model by using the Dempster-Shafer theory of belief functions and ensemble learning’s voting technique.Through rigorous software and hardware validation processes,the proposedmethodology has achieved highly significant F1 scores of 99.98%and 99.96%for DS theory and the votingmethod,respectively.Furthermore,a prototype encompassing all components demonstrates outstanding reliability and efficacy,with processing times of 150 ms for the Raspberry Pi board and 81.5 ms for the Nano Jetson board,marking a significant advancement in TSRS technology.展开更多
As one of the most serious geological disasters in deep underground engineering,rockburst has caused a large number of casualties.However,because of the complex relationship between the inducing factors and rockburst ...As one of the most serious geological disasters in deep underground engineering,rockburst has caused a large number of casualties.However,because of the complex relationship between the inducing factors and rockburst intensity,the problem of rockburst intensity prediction has not been well solved until now.In this study,we collect 292 sets of rockburst data including eight parameters,such as the maximum tangential stress of the surrounding rock σ_(θ),the uniaxial compressive strength of the rockσc,the uniaxial tensile strength of the rock σ_(t),and the strain energy storage index W_(et),etc.from more than 20 underground projects as training sets and establish two new rockburst prediction models based on the kernel extreme learning machine(KELM)combined with the genetic algorithm(KELM-GA)and cross-entropy method(KELM-CEM).To further verify the effect of the two models,ten sets of rockburst data from Shuangjiangkou Hydropower Station are selected for analysis and the results show that new models are more accurate compared with five traditional empirical criteria,especially the model based on KELM-CEM which has the accuracy rate of 90%.Meanwhile,the results of 10 consecutive runs of the model based on KELM-CEM are almost the same,meaning that the model has good stability and reliability for engineering applications.展开更多
As an important material for manufacturing resonant components of musical instruments,Paulownia has an important influence on the sound quality of Ruan.In this paper,a model for evaluating the sound quality of Ruan ba...As an important material for manufacturing resonant components of musical instruments,Paulownia has an important influence on the sound quality of Ruan.In this paper,a model for evaluating the sound quality of Ruan based on the vibration characteristics of wood is developed using machine learning methods.Generally,the selection of materials for Ruan manufacturing relies primarily on manually weighing,observing,striking,and listening by the instrument technician.Deficiencies in scientific theory have hindered the quality of the finished Ruan.In this study,nine Ruans were manufactured,and a prediction model of Ruan sound quality was proposed based on the raw material information of Ruans.Out of a total of 180 data sets,145 and 45 sets were chosen for training and validation,respec-tively.In this paper,typical correlation analysis was used to determine the correlation between two single indicators in two adjacent pairwise combinations of the measured objects in each stage of the production process in Ruan.The vibra-tion characteristics of the wood were tested,and a model for predicting the evaluation of Ruan’s acoustic qualities was developed by measuring the vibration characteristics of the resonating plate material.The acoustic quality of the Ruan sound board wood was evaluated and predicted using machine learning model generalized regression neural net-work.The results show that the prediction of Ruan sound quality can be achieved using Matlab simulation based on the vibration characteristics of the soundboard wood.When the model-predicted values were compared with the tradi-tional predicted results,it was found that the generalized regression neural network had good performance,achieving an accuracy of 93.8%which was highly consistent with the experimental results.It was concluded that the model can accurately predict the acoustic quality of the Ruan based on the vibration performance of the soundboards.展开更多
A new approach for flexoelectricmaterial shape optimization is proposed in this study.In this work,a proxymodel based on artificial neural network(ANN)is used to solve the parameter optimization and shape optimization...A new approach for flexoelectricmaterial shape optimization is proposed in this study.In this work,a proxymodel based on artificial neural network(ANN)is used to solve the parameter optimization and shape optimization problems.To improve the fitting ability of the neural network,we use the idea of pre-training to determine the structure of the neural network and combine different optimizers for training.The isogeometric analysis-finite element method(IGA-FEM)is used to discretize the flexural theoretical formulas and obtain samples,which helps ANN to build a proxy model from the model shape to the target value.The effectiveness of the proposed method is verified through two numerical examples of parameter optimization and one numerical example of shape optimization.展开更多
The production capacity of shale oil reservoirs after hydraulic fracturing is influenced by a complex interplay involving geological characteristics,engineering quality,and well conditions.These relationships,nonlinea...The production capacity of shale oil reservoirs after hydraulic fracturing is influenced by a complex interplay involving geological characteristics,engineering quality,and well conditions.These relationships,nonlinear in nature,pose challenges for accurate description through physical models.While field data provides insights into real-world effects,its limited volume and quality restrict its utility.Complementing this,numerical simulation models offer effective support.To harness the strengths of both data-driven and model-driven approaches,this study established a shale oil production capacity prediction model based on a machine learning combination model.Leveraging fracturing development data from 236 wells in the field,a data-driven method employing the random forest algorithm is implemented to identify the main controlling factors for different types of shale oil reservoirs.Through the combination model integrating support vector machine(SVM)algorithm and back propagation neural network(BPNN),a model-driven shale oil production capacity prediction model is developed,capable of swiftly responding to shale oil development performance under varying geological,fluid,and well conditions.The results of numerical experiments show that the proposed method demonstrates a notable enhancement in R2 by 22.5%and 5.8%compared to singular machine learning models like SVM and BPNN,showcasing its superior precision in predicting shale oil production capacity across diverse datasets.展开更多
English is a key subject in high school that troubles many students,especially in the aspect of vocabulary learning.Only by laying a good vocabulary foundation can students better complete the learning tasks such as r...English is a key subject in high school that troubles many students,especially in the aspect of vocabulary learning.Only by laying a good vocabulary foundation can students better complete the learning tasks such as reading,writing,listening,and speaking training.This paper aims to explain the importance of improving the efficiency of English vocabulary learning and discuss the effective methods of English vocabulary learning in high school,in order to help more students find their own learning methods,improve vocabulary memory and application skills,and lay a solid foundation for follow-up learning,examination,and even work.展开更多
In college badminton teaching,teachers utilize the group cooperative learning method,which not only helps to improve students’badminton skill level but also cultivates their teamwork spirit,communication skills,and s...In college badminton teaching,teachers utilize the group cooperative learning method,which not only helps to improve students’badminton skill level but also cultivates their teamwork spirit,communication skills,and self-management ability unconsciously.In view of this,this paper mainly describes the significance of applying the group cooperative learning method in college badminton teaching,analyzes the current problems in college badminton teaching,and aims to discover effective development strategies for group cooperative learning method in college badminton teaching in order to improve the effectiveness of college badminton teaching.展开更多
Federated Learning(FL),a burgeoning technology,has received increasing attention due to its privacy protection capability.However,the base algorithm FedAvg is vulnerable when it suffers from so-called backdoor attacks...Federated Learning(FL),a burgeoning technology,has received increasing attention due to its privacy protection capability.However,the base algorithm FedAvg is vulnerable when it suffers from so-called backdoor attacks.Former researchers proposed several robust aggregation methods.Unfortunately,due to the hidden characteristic of backdoor attacks,many of these aggregation methods are unable to defend against backdoor attacks.What's more,the attackers recently have proposed some hiding methods that further improve backdoor attacks'stealthiness,making all the existing robust aggregation methods fail.To tackle the threat of backdoor attacks,we propose a new aggregation method,X-raying Models with A Matrix(XMAM),to reveal the malicious local model updates submitted by the backdoor attackers.Since we observe that the output of the Softmax layer exhibits distinguishable patterns between malicious and benign updates,unlike the existing aggregation algorithms,we focus on the Softmax layer's output in which the backdoor attackers are difficult to hide their malicious behavior.Specifically,like medical X-ray examinations,we investigate the collected local model updates by using a matrix as an input to get their Softmax layer's outputs.Then,we preclude updates whose outputs are abnormal by clustering.Without any training dataset in the server,the extensive evaluations show that our XMAM can effectively distinguish malicious local model updates from benign ones.For instance,when other methods fail to defend against the backdoor attacks at no more than 20%malicious clients,our method can tolerate 45%malicious clients in the black-box mode and about 30%in Projected Gradient Descent(PGD)mode.Besides,under adaptive attacks,the results demonstrate that XMAM can still complete the global model training task even when there are 40%malicious clients.Finally,we analyze our method's screening complexity and compare the real screening time with other methods.The results show that XMAM is about 10–10000 times faster than the existing methods.展开更多
In modern transportation,pavement is one of the most important civil infrastructures for the movement of vehicles and pedestrians.Pavement service quality and service life are of great importance for civil engineers a...In modern transportation,pavement is one of the most important civil infrastructures for the movement of vehicles and pedestrians.Pavement service quality and service life are of great importance for civil engineers as they directly affect the regular service for the users.Therefore,monitoring the health status of pavement before irreversible damage occurs is essential for timely maintenance,which in turn ensures public transportation safety.Many pavement damages can be detected and analyzed by monitoring the structure dynamic responses and evaluating road surface conditions.Advanced technologies can be employed for the collection and analysis of such data,including various intrusive sensing techniques,image processing techniques,and machine learning methods.This review summarizes the state-ofthe-art of these three technologies in pavement engineering in recent years and suggests possible developments for future pavement monitoring and analysis based on these approaches.展开更多
The liquid loading is one of the most frequently encountered phenomena in the transportation of gas pipeline,reducing the transmission efficiency and threatening the flow assurance.However,most of the traditional mech...The liquid loading is one of the most frequently encountered phenomena in the transportation of gas pipeline,reducing the transmission efficiency and threatening the flow assurance.However,most of the traditional mechanism models are semi-empirical models,and have to be resolved under different working conditions with complex calculation process.The development of big data technology and artificial intelligence provides the possibility to establish data-driven models.This paper aims to establish a liquid loading prediction model for natural gas pipeline with high generalization ability based on machine learning.First,according to the characteristics of actual gas pipeline,a variety of reasonable combinations of working conditions such as different gas velocity,pipe diameters,water contents and outlet pressures were set,and multiple undulating pipeline topography with different elevation differences was established.Then a large number of simulations were performed by simulator OLGA to obtain the data required for machine learning.After data preprocessing,six supervised learning algorithms,including support vector machine(SVM),decision tree(DT),random forest(RF),artificial neural network(ANN),plain Bayesian classification(NBC),and K nearest neighbor algorithm(KNN),were compared to evaluate the performance of liquid loading prediction.Finally,the RF and KNN with better performance were selected for parameter tuning and then used to the actual pipeline for liquid loading location prediction.Compared with OLGA simulation,the established data-driven model not only improves calculation efficiency and reduces workload,but also can provide technical support for gas pipeline flow assurance.展开更多
Reservoir identification and production prediction are two of the most important tasks in petroleum exploration and development.Machine learning(ML)methods are used for petroleum-related studies,but have not been appl...Reservoir identification and production prediction are two of the most important tasks in petroleum exploration and development.Machine learning(ML)methods are used for petroleum-related studies,but have not been applied to reservoir identification and production prediction based on reservoir identification.Production forecasting studies are typically based on overall reservoir thickness and lack accuracy when reservoirs contain a water or dry layer without oil production.In this paper,a systematic ML method was developed using classification models for reservoir identification,and regression models for production prediction.The production models are based on the reservoir identification results.To realize the reservoir identification,seven optimized ML methods were used:four typical single ML methods and three ensemble ML methods.These methods classify the reservoir into five types of layers:water,dry and three levels of oil(I oil layer,II oil layer,III oil layer).The validation and test results of these seven optimized ML methods suggest the three ensemble methods perform better than the four single ML methods in reservoir identification.The XGBoost produced the model with the highest accuracy;up to 99%.The effective thickness of I and II oil layers determined during the reservoir identification was fed into the models for predicting production.Effective thickness considers the distribution of the water and the oil resulting in a more reasonable production prediction compared to predictions based on the overall reservoir thickness.To validate the superiority of the ML methods,reference models using overall reservoir thickness were built for comparison.The models based on effective thickness outperformed the reference models in every evaluation metric.The prediction accuracy of the ML models using effective thickness were 10%higher than that of reference model.Without the personal error or data distortion existing in traditional methods,this novel system realizes rapid analysis of data while reducing the time required to resolve reservoir classification and production prediction challenges.The ML models using the effective thickness obtained from reservoir identification were more accurate when predicting oil production compared to previous studies which use overall reservoir thickness.展开更多
The nonlinear Schrodinger equation is a classical integrable equation which contains plenty of significant properties and occurs in many physical areas.However,due to the difficulty of solving this equation,in particu...The nonlinear Schrodinger equation is a classical integrable equation which contains plenty of significant properties and occurs in many physical areas.However,due to the difficulty of solving this equation,in particular in high dimensions,lots of methods are proposed to effectively obtain different kinds of solutions,such as neural networks among others.Recently,a method where some underlying physical laws are embeded into a conventional neural network is proposed to uncover the equation’s dynamical behaviors from spatiotemporal data directly.Compared with traditional neural networks,this method can obtain remarkably accurate solution with extraordinarily less data.Meanwhile,this method also provides a better physical explanation and generalization.In this paper,based on the above method,we present an improved deep learning method to recover the soliton solutions,breather solution,and rogue wave solutions of the nonlinear Schrodinger equation.In particular,the dynamical behaviors and error analysis about the one-order and two-order rogue waves of nonlinear integrable equations are revealed by the deep neural network with physical constraints for the first time.Moreover,the effects of different numbers of initial points sampled,collocation points sampled,network layers,neurons per hidden layer on the one-order rogue wave dynamics of this equation have been considered with the help of the control variable way under the same initial and boundary conditions.Numerical experiments show that the dynamical behaviors of soliton solutions,breather solution,and rogue wave solutions of the integrable nonlinear Schrodinger equation can be well reconstructed by utilizing this physically-constrained deep learning method.展开更多
Active learning in semi-supervised classification involves introducing additional labels for unlabelled data to improve the accuracy of the underlying classifier.A challenge is to identify which points to label to bes...Active learning in semi-supervised classification involves introducing additional labels for unlabelled data to improve the accuracy of the underlying classifier.A challenge is to identify which points to label to best improve performance while limiting the number of new labels."Model Change"active learning quantifies the resulting change incurred in the classifier by introducing the additional label(s).We pair this idea with graph-based semi-supervised learning(SSL)methods,that use the spectrum of the graph Laplacian matrix,which can be truncated to avoid prohibitively large computational and storage costs.We consider a family of convex loss functions for which the acquisition function can be efficiently approximated using the Laplace approximation of the posterior distribution.We show a variety of multiclass examples that illustrate improved performance over prior state-of-art.展开更多
Ionic liquids(ILs),because of the advantages of low volatility,good thermal stability,high gas solubility and easy recovery,can be regarded as the green substitute for traditional solvent.However,the high viscosity an...Ionic liquids(ILs),because of the advantages of low volatility,good thermal stability,high gas solubility and easy recovery,can be regarded as the green substitute for traditional solvent.However,the high viscosity and synthesis cost limits their application,the hybrid solvent which combining ILs together with others especially water can solve this problem.Compared with the pure IL systems,the study of the ILs-H_(2)O binary system is rare,and the experimental data of corresponding thermodynamic properties(such as density,heat capacity,etc.)are less.Moreover,it is also difficult to obtain all the data through experiments.Therefore,this work establishes a predicted model on ILs-water binary systems based on the group contribution(GC)method.Three different machine learning algorithms(ANN,XGBoost,LightBGM)are applied to fit the density and heat capacity of ILs-water binary systems.And then the three models are compared by two index of MAE and R^(2).The results show that the ANN-GC model has the best prediction effect on the density and heat capacity of ionic liquid-water mixed system.Furthermore,the Shapley additive explanations(SHAP)method is harnessed to scrutinize the significance of each structure and parameter within the ANN-GC model in relation to prediction outcomes.The results reveal that system components(XIL)within the ILs-H_(2)O binary system exert the most substantial influence on density,while for the heat capacity,the substituents on the cation exhibit the greatest impact.This study not only introduces a robust prediction model for the density and heat capacity properties of IL-H_(2)O binary mixtures but also provides insight into the influence of mixture features on its density and heat capacity.展开更多
A large database is desired for machine learning(ML) technology to make accurate predictions of materials physicochemical properties based on their molecular structure.When a large database is not available,the develo...A large database is desired for machine learning(ML) technology to make accurate predictions of materials physicochemical properties based on their molecular structure.When a large database is not available,the development of proper featurization method based on physicochemical nature of target proprieties can improve the predictive power of ML models with a smaller database.In this work,we show that two new featurization methods,volume occupation spatial matrix and heat contribution spatial matrix,can improve the accuracy in predicting energetic materials' crystal density(ρ_(crystal)) and solid phase enthalpy of formation(H_(f,solid)) using a database containing 451 energetic molecules.Their mean absolute errors are reduced from 0.048 g/cm~3 and 24.67 kcal/mol to 0.035 g/cm~3 and 9.66 kcal/mol,respectively.By leave-one-out-cross-validation,the newly developed ML models can be used to determine the performance of most kinds of energetic materials except cubanes.Our ML models are applied to predict ρ_(crystal) and H_(f,solid) of CHON-based molecules of the 150 million sized PubChem database,and screened out 56 candidates with competitive detonation performance and reasonable chemical structures.With further improvement in future,spatial matrices have the potential of becoming multifunctional ML simulation tools that could provide even better predictions in wider fields of materials science.展开更多
The data-driven phenomenological models based on deformation measurements have been widely utilized to predict the slope failure time(SFT).The observational and model uncertainties could lead the predicted SFT calcula...The data-driven phenomenological models based on deformation measurements have been widely utilized to predict the slope failure time(SFT).The observational and model uncertainties could lead the predicted SFT calculated from the phenomenological models to deviate from the actual SFT.Currently,very limited study has been conducted on how to evaluate the effect of such uncertainties on SFT prediction.In this paper,a comprehensive slope failure database was compiled.A Bayesian machine learning(BML)-based method was developed to learn the model and observational uncertainties involved in SFT prediction,through which the probabilistic distribution of the SFT can be obtained.This method was illustrated in detail with an example.Verification studies show that the BML-based method is superior to the traditional inverse velocity method(INVM)and the maximum likelihood method for predicting SFT.The proposed method in this study provides an effective tool for SFT prediction.展开更多
Acquiring accurate molecular-level information about petroleum is crucial for refining and chemical enterprises to implement the“selection of the optimal processing route”strategy.With the development of data predic...Acquiring accurate molecular-level information about petroleum is crucial for refining and chemical enterprises to implement the“selection of the optimal processing route”strategy.With the development of data prediction systems represented by machine learning,it has become possible for real-time prediction systems of petroleum fraction molecular information to replace analyses such as gas chromatography and mass spectrometry.However,the biggest difficulty lies in acquiring the data required for training the neural network.To address these issues,this work proposes an innovative method that utilizes the Aspen HYSYS and full two-dimensional gas chromatography-time-of-flight mass spectrometry to establish a comprehensive training database.Subsequently,a deep neural network prediction model is developed for heavy distillate oil to predict its composition in terms of molecular structure.After training,the model accurately predicts the molecular composition of catalytically cracked raw oil in a refinery.The validation and test sets exhibit R2 values of 0.99769 and 0.99807,respectively,and the average relative error of molecular composition prediction for raw materials of the catalytic cracking unit is less than 7%.Finally,the SHAP(SHapley Additive ExPlanation)interpretation method is used to disclose the relationship among different variables by performing global and local weight comparisons and correlation analyses.展开更多
基金funded by the Basic Scientific Fund for National Public Research Institutes of China(No.2022 S01)the National Natural Science Foundation of China(Nos.42176191,42049902,and U22A2012)+5 种基金the Shandong Provincial Natural Science Foundation,China(No.ZR2022YQ40)the National Key R&D Program of China(No.2021YFF0501202)the Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai)(No.SML2023 SP232)the Fundamental Research Funds for the Central Universities,Sun Yat-sen University(No.241gqb006)Data acquisition and sample collections were supported by the National Natural Science Foundation of China Open Research Cruise(Cruise No.NORC2021-02+NORC2021301)funded by the Shiptime Sharing Project of the National Natural Science Foundation of China。
文摘Accurate acquisition and prediction of acoustic parameters of seabed sediments are crucial in marine sound propagation research.While the relationship between sound velocity and physical properties of sediment has been extensively studied,there is still no consensus on the correlation between acoustic attenuation coefficient and sediment physical properties.Predicting the acoustic attenuation coefficient remains a challenging issue in sedimentary acoustic research.In this study,we propose a prediction method for the acoustic attenuation coefficient using machine learning algorithms,specifically the random forest(RF),support vector machine(SVR),and convolutional neural network(CNN)algorithms.We utilized the acoustic attenuation coefficient and sediment particle size data from 52 stations as training parameters,with the particle size parameters as the input feature matrix,and measured acoustic attenuation as the training label to validate the attenuation prediction model.Our results indicate that the error of the attenuation prediction model is small.Among the three models,the RF model exhibited the lowest prediction error,with a mean squared error of 0.8232,mean absolute error of 0.6613,and root mean squared error of 0.9073.Additionally,when we applied the models to predict the data collected at different times in the same region,we found that the models developed in this study also demonstrated a certain level of reliability in real prediction scenarios.Our approach demonstrates that constructing a sediment acoustic characteristics model based on machine learning is feasible to a certain extent and offers a novel perspective for studying sediment acoustic properties.
文摘Bearing is an indispensable key component in mechanical equipment,and its working state is directly related to the stability and safety of the whole equipment.In recent years,with the rapid development of artificial intelligence technology,especially the breakthrough of deep learning technology,it provides a new idea for bearing fault diagnosis.Deep learning can automatically learn features from a large amount of data,has a strong nonlinear modeling ability,and can effectively solve the problems existing in traditional methods.Aiming at the key problems in bearing fault diagnosis,this paper studies the fault diagnosis method based on deep learning,which not only provides a new solution for bearing fault diagnosis but also provides a reference for the application of deep learning in other mechanical fault diagnosis fields.
文摘This article reviews the application and progress of deep learning in efficient numerical computing methods.Deep learning,as an important branch of machine learning,provides new ideas for numerical computation by constructing multi-layer neural networks to simulate the learning process of the human brain.The article explores the application of deep learning in solving partial differential equations,optimizing problems,and data-driven modeling,and analyzes its advantages in computational efficiency,accuracy,and adaptability.At the same time,this article also points out the challenges faced by deep learning numerical computation methods in terms of computational efficiency,interpretability,and generalization ability,and proposes strategies and future development directions for integrating with traditional numerical methods.
文摘Advanced DriverAssistance Systems(ADAS)technologies can assist drivers or be part of automatic driving systems to support the driving process and improve the level of safety and comfort on the road.Traffic Sign Recognition System(TSRS)is one of themost important components ofADAS.Among the challengeswith TSRS is being able to recognize road signs with the highest accuracy and the shortest processing time.Accordingly,this paper introduces a new real time methodology recognizing Speed Limit Signs based on a trio of developed modules.Firstly,the Speed Limit Detection(SLD)module uses the Haar Cascade technique to generate a new SL detector in order to localize SL signs within captured frames.Secondly,the Speed Limit Classification(SLC)module,featuring machine learning classifiers alongside a newly developed model called DeepSL,harnesses the power of a CNN architecture to extract intricate features from speed limit sign images,ensuring efficient and precise recognition.In addition,a new Speed Limit Classifiers Fusion(SLCF)module has been developed by combining trained ML classifiers and the DeepSL model by using the Dempster-Shafer theory of belief functions and ensemble learning’s voting technique.Through rigorous software and hardware validation processes,the proposedmethodology has achieved highly significant F1 scores of 99.98%and 99.96%for DS theory and the votingmethod,respectively.Furthermore,a prototype encompassing all components demonstrates outstanding reliability and efficacy,with processing times of 150 ms for the Raspberry Pi board and 81.5 ms for the Nano Jetson board,marking a significant advancement in TSRS technology.
基金funded by National Natural Science Foundation of China(Grants Nos.41825018 and 42141009)the Second Tibetan Plateau Scientific Expedition and Research Program(Grants No.2019QZKK0904)。
文摘As one of the most serious geological disasters in deep underground engineering,rockburst has caused a large number of casualties.However,because of the complex relationship between the inducing factors and rockburst intensity,the problem of rockburst intensity prediction has not been well solved until now.In this study,we collect 292 sets of rockburst data including eight parameters,such as the maximum tangential stress of the surrounding rock σ_(θ),the uniaxial compressive strength of the rockσc,the uniaxial tensile strength of the rock σ_(t),and the strain energy storage index W_(et),etc.from more than 20 underground projects as training sets and establish two new rockburst prediction models based on the kernel extreme learning machine(KELM)combined with the genetic algorithm(KELM-GA)and cross-entropy method(KELM-CEM).To further verify the effect of the two models,ten sets of rockburst data from Shuangjiangkou Hydropower Station are selected for analysis and the results show that new models are more accurate compared with five traditional empirical criteria,especially the model based on KELM-CEM which has the accuracy rate of 90%.Meanwhile,the results of 10 consecutive runs of the model based on KELM-CEM are almost the same,meaning that the model has good stability and reliability for engineering applications.
基金supported by China Postdoctoral Science Foundation(2019M651240)National Natural Science Foundation of China(31670559).
文摘As an important material for manufacturing resonant components of musical instruments,Paulownia has an important influence on the sound quality of Ruan.In this paper,a model for evaluating the sound quality of Ruan based on the vibration characteristics of wood is developed using machine learning methods.Generally,the selection of materials for Ruan manufacturing relies primarily on manually weighing,observing,striking,and listening by the instrument technician.Deficiencies in scientific theory have hindered the quality of the finished Ruan.In this study,nine Ruans were manufactured,and a prediction model of Ruan sound quality was proposed based on the raw material information of Ruans.Out of a total of 180 data sets,145 and 45 sets were chosen for training and validation,respec-tively.In this paper,typical correlation analysis was used to determine the correlation between two single indicators in two adjacent pairwise combinations of the measured objects in each stage of the production process in Ruan.The vibra-tion characteristics of the wood were tested,and a model for predicting the evaluation of Ruan’s acoustic qualities was developed by measuring the vibration characteristics of the resonating plate material.The acoustic quality of the Ruan sound board wood was evaluated and predicted using machine learning model generalized regression neural net-work.The results show that the prediction of Ruan sound quality can be achieved using Matlab simulation based on the vibration characteristics of the soundboard wood.When the model-predicted values were compared with the tradi-tional predicted results,it was found that the generalized regression neural network had good performance,achieving an accuracy of 93.8%which was highly consistent with the experimental results.It was concluded that the model can accurately predict the acoustic quality of the Ruan based on the vibration performance of the soundboards.
基金supported by a Major Research Project in Higher Education Institutions in Henan Province,with Project Number 23A560015.
文摘A new approach for flexoelectricmaterial shape optimization is proposed in this study.In this work,a proxymodel based on artificial neural network(ANN)is used to solve the parameter optimization and shape optimization problems.To improve the fitting ability of the neural network,we use the idea of pre-training to determine the structure of the neural network and combine different optimizers for training.The isogeometric analysis-finite element method(IGA-FEM)is used to discretize the flexural theoretical formulas and obtain samples,which helps ANN to build a proxy model from the model shape to the target value.The effectiveness of the proposed method is verified through two numerical examples of parameter optimization and one numerical example of shape optimization.
基金supported by the China Postdoctoral Science Foundation(2021M702304)Natural Science Foundation of Shandong Province(ZR20210E260).
文摘The production capacity of shale oil reservoirs after hydraulic fracturing is influenced by a complex interplay involving geological characteristics,engineering quality,and well conditions.These relationships,nonlinear in nature,pose challenges for accurate description through physical models.While field data provides insights into real-world effects,its limited volume and quality restrict its utility.Complementing this,numerical simulation models offer effective support.To harness the strengths of both data-driven and model-driven approaches,this study established a shale oil production capacity prediction model based on a machine learning combination model.Leveraging fracturing development data from 236 wells in the field,a data-driven method employing the random forest algorithm is implemented to identify the main controlling factors for different types of shale oil reservoirs.Through the combination model integrating support vector machine(SVM)algorithm and back propagation neural network(BPNN),a model-driven shale oil production capacity prediction model is developed,capable of swiftly responding to shale oil development performance under varying geological,fluid,and well conditions.The results of numerical experiments show that the proposed method demonstrates a notable enhancement in R2 by 22.5%and 5.8%compared to singular machine learning models like SVM and BPNN,showcasing its superior precision in predicting shale oil production capacity across diverse datasets.
文摘English is a key subject in high school that troubles many students,especially in the aspect of vocabulary learning.Only by laying a good vocabulary foundation can students better complete the learning tasks such as reading,writing,listening,and speaking training.This paper aims to explain the importance of improving the efficiency of English vocabulary learning and discuss the effective methods of English vocabulary learning in high school,in order to help more students find their own learning methods,improve vocabulary memory and application skills,and lay a solid foundation for follow-up learning,examination,and even work.
文摘In college badminton teaching,teachers utilize the group cooperative learning method,which not only helps to improve students’badminton skill level but also cultivates their teamwork spirit,communication skills,and self-management ability unconsciously.In view of this,this paper mainly describes the significance of applying the group cooperative learning method in college badminton teaching,analyzes the current problems in college badminton teaching,and aims to discover effective development strategies for group cooperative learning method in college badminton teaching in order to improve the effectiveness of college badminton teaching.
基金Supported by the Fundamental Research Funds for the Central Universities(328202204)。
文摘Federated Learning(FL),a burgeoning technology,has received increasing attention due to its privacy protection capability.However,the base algorithm FedAvg is vulnerable when it suffers from so-called backdoor attacks.Former researchers proposed several robust aggregation methods.Unfortunately,due to the hidden characteristic of backdoor attacks,many of these aggregation methods are unable to defend against backdoor attacks.What's more,the attackers recently have proposed some hiding methods that further improve backdoor attacks'stealthiness,making all the existing robust aggregation methods fail.To tackle the threat of backdoor attacks,we propose a new aggregation method,X-raying Models with A Matrix(XMAM),to reveal the malicious local model updates submitted by the backdoor attackers.Since we observe that the output of the Softmax layer exhibits distinguishable patterns between malicious and benign updates,unlike the existing aggregation algorithms,we focus on the Softmax layer's output in which the backdoor attackers are difficult to hide their malicious behavior.Specifically,like medical X-ray examinations,we investigate the collected local model updates by using a matrix as an input to get their Softmax layer's outputs.Then,we preclude updates whose outputs are abnormal by clustering.Without any training dataset in the server,the extensive evaluations show that our XMAM can effectively distinguish malicious local model updates from benign ones.For instance,when other methods fail to defend against the backdoor attacks at no more than 20%malicious clients,our method can tolerate 45%malicious clients in the black-box mode and about 30%in Projected Gradient Descent(PGD)mode.Besides,under adaptive attacks,the results demonstrate that XMAM can still complete the global model training task even when there are 40%malicious clients.Finally,we analyze our method's screening complexity and compare the real screening time with other methods.The results show that XMAM is about 10–10000 times faster than the existing methods.
基金supported by the National Key R&D Program of China(2017YFF0205600)the International Research Cooperation Seed Fund of Beijing University of Technology(2018A08)+1 种基金Science and Technology Project of Beijing Municipal Commission of Transport(2018-kjc-01-213)the Construction of Service Capability of Scientific and Technological Innovation-Municipal Level of Fundamental Research Funds(Scientific Research Categories)of Beijing City(PXM2019_014204_500032).
文摘In modern transportation,pavement is one of the most important civil infrastructures for the movement of vehicles and pedestrians.Pavement service quality and service life are of great importance for civil engineers as they directly affect the regular service for the users.Therefore,monitoring the health status of pavement before irreversible damage occurs is essential for timely maintenance,which in turn ensures public transportation safety.Many pavement damages can be detected and analyzed by monitoring the structure dynamic responses and evaluating road surface conditions.Advanced technologies can be employed for the collection and analysis of such data,including various intrusive sensing techniques,image processing techniques,and machine learning methods.This review summarizes the state-ofthe-art of these three technologies in pavement engineering in recent years and suggests possible developments for future pavement monitoring and analysis based on these approaches.
基金supported by the National Science and Technology Major Project of China(2016ZX05066005-001)Zhejiang Province Key Research and Development Plan(2021C03152)Zhoushan Science and Technology Project(2021C21011)
文摘The liquid loading is one of the most frequently encountered phenomena in the transportation of gas pipeline,reducing the transmission efficiency and threatening the flow assurance.However,most of the traditional mechanism models are semi-empirical models,and have to be resolved under different working conditions with complex calculation process.The development of big data technology and artificial intelligence provides the possibility to establish data-driven models.This paper aims to establish a liquid loading prediction model for natural gas pipeline with high generalization ability based on machine learning.First,according to the characteristics of actual gas pipeline,a variety of reasonable combinations of working conditions such as different gas velocity,pipe diameters,water contents and outlet pressures were set,and multiple undulating pipeline topography with different elevation differences was established.Then a large number of simulations were performed by simulator OLGA to obtain the data required for machine learning.After data preprocessing,six supervised learning algorithms,including support vector machine(SVM),decision tree(DT),random forest(RF),artificial neural network(ANN),plain Bayesian classification(NBC),and K nearest neighbor algorithm(KNN),were compared to evaluate the performance of liquid loading prediction.Finally,the RF and KNN with better performance were selected for parameter tuning and then used to the actual pipeline for liquid loading location prediction.Compared with OLGA simulation,the established data-driven model not only improves calculation efficiency and reduces workload,but also can provide technical support for gas pipeline flow assurance.
文摘Reservoir identification and production prediction are two of the most important tasks in petroleum exploration and development.Machine learning(ML)methods are used for petroleum-related studies,but have not been applied to reservoir identification and production prediction based on reservoir identification.Production forecasting studies are typically based on overall reservoir thickness and lack accuracy when reservoirs contain a water or dry layer without oil production.In this paper,a systematic ML method was developed using classification models for reservoir identification,and regression models for production prediction.The production models are based on the reservoir identification results.To realize the reservoir identification,seven optimized ML methods were used:four typical single ML methods and three ensemble ML methods.These methods classify the reservoir into five types of layers:water,dry and three levels of oil(I oil layer,II oil layer,III oil layer).The validation and test results of these seven optimized ML methods suggest the three ensemble methods perform better than the four single ML methods in reservoir identification.The XGBoost produced the model with the highest accuracy;up to 99%.The effective thickness of I and II oil layers determined during the reservoir identification was fed into the models for predicting production.Effective thickness considers the distribution of the water and the oil resulting in a more reasonable production prediction compared to predictions based on the overall reservoir thickness.To validate the superiority of the ML methods,reference models using overall reservoir thickness were built for comparison.The models based on effective thickness outperformed the reference models in every evaluation metric.The prediction accuracy of the ML models using effective thickness were 10%higher than that of reference model.Without the personal error or data distortion existing in traditional methods,this novel system realizes rapid analysis of data while reducing the time required to resolve reservoir classification and production prediction challenges.The ML models using the effective thickness obtained from reservoir identification were more accurate when predicting oil production compared to previous studies which use overall reservoir thickness.
基金supported by the National Natural Science Foundation of China (Grant No. 11675054)the Fund from Shanghai Collaborative Innovation Center of Trustworthy Software for Internet of Things (Grant No. ZF1213)the Project of Science and Technology Commission of Shanghai Municipality (Grant No. 18dz2271000)。
文摘The nonlinear Schrodinger equation is a classical integrable equation which contains plenty of significant properties and occurs in many physical areas.However,due to the difficulty of solving this equation,in particular in high dimensions,lots of methods are proposed to effectively obtain different kinds of solutions,such as neural networks among others.Recently,a method where some underlying physical laws are embeded into a conventional neural network is proposed to uncover the equation’s dynamical behaviors from spatiotemporal data directly.Compared with traditional neural networks,this method can obtain remarkably accurate solution with extraordinarily less data.Meanwhile,this method also provides a better physical explanation and generalization.In this paper,based on the above method,we present an improved deep learning method to recover the soliton solutions,breather solution,and rogue wave solutions of the nonlinear Schrodinger equation.In particular,the dynamical behaviors and error analysis about the one-order and two-order rogue waves of nonlinear integrable equations are revealed by the deep neural network with physical constraints for the first time.Moreover,the effects of different numbers of initial points sampled,collocation points sampled,network layers,neurons per hidden layer on the one-order rogue wave dynamics of this equation have been considered with the help of the control variable way under the same initial and boundary conditions.Numerical experiments show that the dynamical behaviors of soliton solutions,breather solution,and rogue wave solutions of the integrable nonlinear Schrodinger equation can be well reconstructed by utilizing this physically-constrained deep learning method.
基金supported by the DOD National Defense Science and Engineering Graduate(NDSEG)Research Fellowshipsupported by the NGA under Contract No.HM04762110003.
文摘Active learning in semi-supervised classification involves introducing additional labels for unlabelled data to improve the accuracy of the underlying classifier.A challenge is to identify which points to label to best improve performance while limiting the number of new labels."Model Change"active learning quantifies the resulting change incurred in the classifier by introducing the additional label(s).We pair this idea with graph-based semi-supervised learning(SSL)methods,that use the spectrum of the graph Laplacian matrix,which can be truncated to avoid prohibitively large computational and storage costs.We consider a family of convex loss functions for which the acquisition function can be efficiently approximated using the Laplace approximation of the posterior distribution.We show a variety of multiclass examples that illustrate improved performance over prior state-of-art.
基金financially supported by the National Natural Science Foundation of China(22208253)the Key Laboratory of Hubei Province for Coal Conversion and New Carbon Materials(Wuhan University of Science and Technology,WKDM202202).
文摘Ionic liquids(ILs),because of the advantages of low volatility,good thermal stability,high gas solubility and easy recovery,can be regarded as the green substitute for traditional solvent.However,the high viscosity and synthesis cost limits their application,the hybrid solvent which combining ILs together with others especially water can solve this problem.Compared with the pure IL systems,the study of the ILs-H_(2)O binary system is rare,and the experimental data of corresponding thermodynamic properties(such as density,heat capacity,etc.)are less.Moreover,it is also difficult to obtain all the data through experiments.Therefore,this work establishes a predicted model on ILs-water binary systems based on the group contribution(GC)method.Three different machine learning algorithms(ANN,XGBoost,LightBGM)are applied to fit the density and heat capacity of ILs-water binary systems.And then the three models are compared by two index of MAE and R^(2).The results show that the ANN-GC model has the best prediction effect on the density and heat capacity of ionic liquid-water mixed system.Furthermore,the Shapley additive explanations(SHAP)method is harnessed to scrutinize the significance of each structure and parameter within the ANN-GC model in relation to prediction outcomes.The results reveal that system components(XIL)within the ILs-H_(2)O binary system exert the most substantial influence on density,while for the heat capacity,the substituents on the cation exhibit the greatest impact.This study not only introduces a robust prediction model for the density and heat capacity properties of IL-H_(2)O binary mixtures but also provides insight into the influence of mixture features on its density and heat capacity.
基金support from the Ministry of Education(MOE) Singapore Tier 1 (RG8/20)。
文摘A large database is desired for machine learning(ML) technology to make accurate predictions of materials physicochemical properties based on their molecular structure.When a large database is not available,the development of proper featurization method based on physicochemical nature of target proprieties can improve the predictive power of ML models with a smaller database.In this work,we show that two new featurization methods,volume occupation spatial matrix and heat contribution spatial matrix,can improve the accuracy in predicting energetic materials' crystal density(ρ_(crystal)) and solid phase enthalpy of formation(H_(f,solid)) using a database containing 451 energetic molecules.Their mean absolute errors are reduced from 0.048 g/cm~3 and 24.67 kcal/mol to 0.035 g/cm~3 and 9.66 kcal/mol,respectively.By leave-one-out-cross-validation,the newly developed ML models can be used to determine the performance of most kinds of energetic materials except cubanes.Our ML models are applied to predict ρ_(crystal) and H_(f,solid) of CHON-based molecules of the 150 million sized PubChem database,and screened out 56 candidates with competitive detonation performance and reasonable chemical structures.With further improvement in future,spatial matrices have the potential of becoming multifunctional ML simulation tools that could provide even better predictions in wider fields of materials science.
基金substantially supported by the Shuguang Program from Shanghai Education Development FoundationShanghai Municipal Education Commission, China (Grant No. 19SG19)+1 种基金National Natural Science Foundation of China (Grant No. 42072302)Fundamental Research Funds for the Central Universities, China
文摘The data-driven phenomenological models based on deformation measurements have been widely utilized to predict the slope failure time(SFT).The observational and model uncertainties could lead the predicted SFT calculated from the phenomenological models to deviate from the actual SFT.Currently,very limited study has been conducted on how to evaluate the effect of such uncertainties on SFT prediction.In this paper,a comprehensive slope failure database was compiled.A Bayesian machine learning(BML)-based method was developed to learn the model and observational uncertainties involved in SFT prediction,through which the probabilistic distribution of the SFT can be obtained.This method was illustrated in detail with an example.Verification studies show that the BML-based method is superior to the traditional inverse velocity method(INVM)and the maximum likelihood method for predicting SFT.The proposed method in this study provides an effective tool for SFT prediction.
基金the National Natural Science Foundation of China(22108307)the Natural Science Foundation of Shandong Province(ZR2020KB006)the Outstanding Youth Fund of Shandong Provincial Natural Science Foundation(ZR2020YQ17).
文摘Acquiring accurate molecular-level information about petroleum is crucial for refining and chemical enterprises to implement the“selection of the optimal processing route”strategy.With the development of data prediction systems represented by machine learning,it has become possible for real-time prediction systems of petroleum fraction molecular information to replace analyses such as gas chromatography and mass spectrometry.However,the biggest difficulty lies in acquiring the data required for training the neural network.To address these issues,this work proposes an innovative method that utilizes the Aspen HYSYS and full two-dimensional gas chromatography-time-of-flight mass spectrometry to establish a comprehensive training database.Subsequently,a deep neural network prediction model is developed for heavy distillate oil to predict its composition in terms of molecular structure.After training,the model accurately predicts the molecular composition of catalytically cracked raw oil in a refinery.The validation and test sets exhibit R2 values of 0.99769 and 0.99807,respectively,and the average relative error of molecular composition prediction for raw materials of the catalytic cracking unit is less than 7%.Finally,the SHAP(SHapley Additive ExPlanation)interpretation method is used to disclose the relationship among different variables by performing global and local weight comparisons and correlation analyses.
