The Underwater Acoustic(UWA)channel is bandwidth-constrained and experiences doubly selective fading.It is challenging to acquire perfect channel knowledge for Orthogonal Frequency Division Multiplexing(OFDM)communica...The Underwater Acoustic(UWA)channel is bandwidth-constrained and experiences doubly selective fading.It is challenging to acquire perfect channel knowledge for Orthogonal Frequency Division Multiplexing(OFDM)communications using a finite number of pilots.On the other hand,Deep Learning(DL)approaches have been very successful in wireless OFDM communications.However,whether they will work underwater is still a mystery.For the first time,this paper compares two categories of DL-based UWA OFDM receivers:the DataDriven(DD)method,which performs as an end-to-end black box,and the Model-Driven(MD)method,also known as the model-based data-driven method,which combines DL and expert OFDM receiver knowledge.The encoder-decoder framework and Convolutional Neural Network(CNN)structure are employed to establish the DD receiver.On the other hand,an unfolding-based Minimum Mean Square Error(MMSE)structure is adopted for the MD receiver.We analyze the characteristics of different receivers by Monte Carlo simulations under diverse communications conditions and propose a strategy for selecting a proper receiver under different communication scenarios.Field trials in the pool and sea are also conducted to verify the feasibility and advantages of the DL receivers.It is observed that DL receivers perform better than conventional receivers in terms of bit error rate.展开更多
To study the dynamic behavior of a process,time-resolved data are collected at different time instants during each of a series of experiments,which are usually designed with the design of experiments or the design of ...To study the dynamic behavior of a process,time-resolved data are collected at different time instants during each of a series of experiments,which are usually designed with the design of experiments or the design of dynamic experiments methodologies.For utilizing such time-resolved data to model the dynamic behavior,dynamic response surface methodology(DRSM),a datadriven modeling method,has been proposed.Two approaches can be adopted in the estimation of the model parameters:stepwise regression,used in several of previous publications,and Lasso regression,which is newly incorporated in this paper for the estimation of DRSM models.Here,we show that both approaches yield similarly accurate models,while the computational time of Lasso is on average two magnitude smaller.Two case studies are performed to show the advantages of the proposed method.In the first case study,where the concentrations of different species are modeled directly,DRSM method provides more accurate models compared to the models in the literature.The second case study,where the reaction extents are modeled instead of the species concentrations,illustrates the versatility of the DRSM methodology.Therefore,DRSM with Lasso regression can provide faster and more accurate datadriven models for a variety of organic synthesis datasets.展开更多
Platelets,one of the most significant materials in treating leukemia,have a limited shelf life of approximately five days.Because platelets cannot be manufactured and can only be centrifuged from whole or donated bloo...Platelets,one of the most significant materials in treating leukemia,have a limited shelf life of approximately five days.Because platelets cannot be manufactured and can only be centrifuged from whole or donated blood directly,an accurate ordering policy is necessary for the efficient use of this limited blood resource.Given this motivation,the present study examines an ordering policy for platelets to minimize the expected shortage and overage.Rather than using the two-step model-driven method that first fits a demand distribution and then optimizes the order quantity,we solve the issue using an integrated datadriven method.Specifically,the data-driven method works directly with demand data and does not rely on the assumption of demand distribution.Consequently,we derive theoretical insights into the optimal solutions.Through a comparative analysis,we find that the data-driven method has a mean anchoring effect,and the amounts of shortage and overage reduced by this method are greater than those reduced by the model-driven method.Finally,we present an extended model with the service level requirement and conclude that the order decided by the data-driven method can precisely satisfy the service level requirement;however,the order decided by the model-driven method may be either higher or lower than the service level requirement and can lead to a higher cost.展开更多
Reasonable prediction of concrete creep is the basis of studying long-term deflection of concrete structures.In this paper,a hybrid model-driven and data-driven(HMD)method for predicting concrete creep is proposed by ...Reasonable prediction of concrete creep is the basis of studying long-term deflection of concrete structures.In this paper,a hybrid model-driven and data-driven(HMD)method for predicting concrete creep is proposed by using the sequence integration strategy.Then,a novel uncertainty prediction model(UPM)is developed considering uncertainty quantification.Finally,the effectiveness of the proposed method is validated by using the North-western University(NU)database of creep,and the effect of uncertainty on prediction results are also discussed.The analysis results show that the proposed HMD method outperforms the model-driven and three data-driven methods,including the genetic algorithm-back propagation neural network(GA-BPNN),particle swarm optimization-support vector regression(PSO-SVR)and convolutional neural network only method,in accuracy and time efficiency.The proposed UPM of concrete creep not only ensures relatively good prediction accuracy,but also quantifies the model and measurement uncertainties during the prediction process.Additionally,although incorporating measurement uncertainty into concrete creep prediction can improve the prediction performance of UPM,the prediction interval of the creep compliance is more sensitive to model uncertainty than to measurement uncertainty,and the mean contribution of variance attributed to the model uncertainty to the total variance is about 90%.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
The discipline of damage tolerance assessment has experienced significant advancements due to the emergence of smart materials and self-repairable structures.This review offers a comprehensive look into both tradition...The discipline of damage tolerance assessment has experienced significant advancements due to the emergence of smart materials and self-repairable structures.This review offers a comprehensive look into both traditional and innovative methodologies employed in damage tolerance assessment.After a detailed exploration of damage tolerance concepts and their historical progression,the review juxtaposes the proven techniques of damage assessment with the cutting-edge innovations brought about by smart materials and self-repairable structures.The subsequent sections delve into the synergistic integration of smart materials with self-repairable structures,marking a pivotal stride in damage tolerance by establishing an autonomous system for immediate damage identification and self-repair.This holistic approach broadens the applicability of these technologies across diverse sectors yet brings forth unique challenges demanding further innovation and research.Additionally,the review examines future prospects that combine advanced manufacturing processes with data-centric methodologies,amplifying the capabilities of these‘intelligent’structures.The review culminates by highlighting the transformative potential of this union between smart materials and self-repairable structures,promoting a sustainable and efficient engineering paradigm.展开更多
Microbial electrorespiration harnesses bacteria to drive reductive dechlorination,offering a sustainable method to remediate environments contaminated with persistent chlorinated organic pollutants(COPs).However,aquif...Microbial electrorespiration harnesses bacteria to drive reductive dechlorination,offering a sustainable method to remediate environments contaminated with persistent chlorinated organic pollutants(COPs).However,aquifers'complex hydrogeological and hydrochemical conditions,combined with uneven COP distribution,create substantial spatial and temporal variability in biochemical reactions,environmental factors,and microbial communities.Traditional trial-and-error experiments are laborintensive and slow,impeding the quick identification of conditions that accelerate dechlorination rates.Here we show that a machine learning framework,integrating experimental design with cathodic biofilm data,uncovers key interrelationships among environmental variables,dechlorination kinetics,electrochemical properties,and functional microbes,enabling rapid optimization of bioelectrodechlorination.Trained on literature-derived datasets using models such as extreme gradient boosting,random forest,and multilayer perceptron,this framework identifies temperature and cathode potential as primary drivers in experimental design while highlighting key biofilm genera,including Clostridium,Desulfovibrio,Dehalococcoides,Pseudomonas,Dehalobacter,Arcobacter,Lactococcus,and Geobacter.It supports inverse design to determine optimal parameters—such as cathode potential,temperature,and additives—for dechlorinating representative COPs,including tetrachloroethene,trichloroethene,and 1,2-dichloroethane,achieving reaction rate predictions with errors below 6%.This approach surpasses conventional methods by increasing efficiency,cutting costs,and accelerating bioremediation without extensive laboratory testing.By incorporating microbial community insights into predictive models,our data-driven strategy advances the scalable application of microbial electrorespiration for COP-contaminated water remediation and paves the way for broader bioelectrochemical uses in environmental engineering.展开更多
The performance of existing maneuvering target tracking methods for highly maneuvering targets in cluttered environments is unsatisfactory.This paper proposes a hybrid-driven approach for tracking multiple highly mane...The performance of existing maneuvering target tracking methods for highly maneuvering targets in cluttered environments is unsatisfactory.This paper proposes a hybrid-driven approach for tracking multiple highly maneuvering targets,leveraging the advantages of both data-driven and model-based algorithms.The time-varying constant velocity model is integrated into the Gaussian process(GP)of online learning to improve the performance of GP prediction.This integration is further combined with a generalized probabilistic data association algorithm to realize multi-target tracking.Through the simulations,it has been demonstrated that the hybrid-driven approach exhibits significant performance improvements in comparison with widely used algorithms such as the interactive multi-model method and the data-driven GP motion tracker.展开更多
基金funded in part by the National Natural Science Foundation of China under Grant 62401167 and 62192712in part by the Key Laboratory of Marine Environmental Survey Technology and Application,Ministry of Natural Resources,P.R.China under Grant MESTA-2023-B001in part by the Stable Supporting Fund of National Key Laboratory of Underwater Acoustic Technology under Grant JCKYS2022604SSJS007.
文摘The Underwater Acoustic(UWA)channel is bandwidth-constrained and experiences doubly selective fading.It is challenging to acquire perfect channel knowledge for Orthogonal Frequency Division Multiplexing(OFDM)communications using a finite number of pilots.On the other hand,Deep Learning(DL)approaches have been very successful in wireless OFDM communications.However,whether they will work underwater is still a mystery.For the first time,this paper compares two categories of DL-based UWA OFDM receivers:the DataDriven(DD)method,which performs as an end-to-end black box,and the Model-Driven(MD)method,also known as the model-based data-driven method,which combines DL and expert OFDM receiver knowledge.The encoder-decoder framework and Convolutional Neural Network(CNN)structure are employed to establish the DD receiver.On the other hand,an unfolding-based Minimum Mean Square Error(MMSE)structure is adopted for the MD receiver.We analyze the characteristics of different receivers by Monte Carlo simulations under diverse communications conditions and propose a strategy for selecting a proper receiver under different communication scenarios.Field trials in the pool and sea are also conducted to verify the feasibility and advantages of the DL receivers.It is observed that DL receivers perform better than conventional receivers in terms of bit error rate.
基金Yachao Dong is grateful for the financial support of Fundamental Research Funds for the Central Universities(Grant No.DUT20RC(3)070).
文摘To study the dynamic behavior of a process,time-resolved data are collected at different time instants during each of a series of experiments,which are usually designed with the design of experiments or the design of dynamic experiments methodologies.For utilizing such time-resolved data to model the dynamic behavior,dynamic response surface methodology(DRSM),a datadriven modeling method,has been proposed.Two approaches can be adopted in the estimation of the model parameters:stepwise regression,used in several of previous publications,and Lasso regression,which is newly incorporated in this paper for the estimation of DRSM models.Here,we show that both approaches yield similarly accurate models,while the computational time of Lasso is on average two magnitude smaller.Two case studies are performed to show the advantages of the proposed method.In the first case study,where the concentrations of different species are modeled directly,DRSM method provides more accurate models compared to the models in the literature.The second case study,where the reaction extents are modeled instead of the species concentrations,illustrates the versatility of the DRSM methodology.Therefore,DRSM with Lasso regression can provide faster and more accurate datadriven models for a variety of organic synthesis datasets.
文摘Platelets,one of the most significant materials in treating leukemia,have a limited shelf life of approximately five days.Because platelets cannot be manufactured and can only be centrifuged from whole or donated blood directly,an accurate ordering policy is necessary for the efficient use of this limited blood resource.Given this motivation,the present study examines an ordering policy for platelets to minimize the expected shortage and overage.Rather than using the two-step model-driven method that first fits a demand distribution and then optimizes the order quantity,we solve the issue using an integrated datadriven method.Specifically,the data-driven method works directly with demand data and does not rely on the assumption of demand distribution.Consequently,we derive theoretical insights into the optimal solutions.Through a comparative analysis,we find that the data-driven method has a mean anchoring effect,and the amounts of shortage and overage reduced by this method are greater than those reduced by the model-driven method.Finally,we present an extended model with the service level requirement and conclude that the order decided by the data-driven method can precisely satisfy the service level requirement;however,the order decided by the model-driven method may be either higher or lower than the service level requirement and can lead to a higher cost.
基金supported by the National Natural Science Foundation of China(Grant Nos.52208166 and 52108135)the National Key Research and Development Program of China(No.2021YFB2600900)+1 种基金the Science and Technology Innovation Program of Hunan Province(No.2022RC1186)the Aid program for Science and Technology Innovative Research Team in Higher Educational Institutions of Hunan Province.
文摘Reasonable prediction of concrete creep is the basis of studying long-term deflection of concrete structures.In this paper,a hybrid model-driven and data-driven(HMD)method for predicting concrete creep is proposed by using the sequence integration strategy.Then,a novel uncertainty prediction model(UPM)is developed considering uncertainty quantification.Finally,the effectiveness of the proposed method is validated by using the North-western University(NU)database of creep,and the effect of uncertainty on prediction results are also discussed.The analysis results show that the proposed HMD method outperforms the model-driven and three data-driven methods,including the genetic algorithm-back propagation neural network(GA-BPNN),particle swarm optimization-support vector regression(PSO-SVR)and convolutional neural network only method,in accuracy and time efficiency.The proposed UPM of concrete creep not only ensures relatively good prediction accuracy,but also quantifies the model and measurement uncertainties during the prediction process.Additionally,although incorporating measurement uncertainty into concrete creep prediction can improve the prediction performance of UPM,the prediction interval of the creep compliance is more sensitive to model uncertainty than to measurement uncertainty,and the mean contribution of variance attributed to the model uncertainty to the total variance is about 90%.
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The discipline of damage tolerance assessment has experienced significant advancements due to the emergence of smart materials and self-repairable structures.This review offers a comprehensive look into both traditional and innovative methodologies employed in damage tolerance assessment.After a detailed exploration of damage tolerance concepts and their historical progression,the review juxtaposes the proven techniques of damage assessment with the cutting-edge innovations brought about by smart materials and self-repairable structures.The subsequent sections delve into the synergistic integration of smart materials with self-repairable structures,marking a pivotal stride in damage tolerance by establishing an autonomous system for immediate damage identification and self-repair.This holistic approach broadens the applicability of these technologies across diverse sectors yet brings forth unique challenges demanding further innovation and research.Additionally,the review examines future prospects that combine advanced manufacturing processes with data-centric methodologies,amplifying the capabilities of these‘intelligent’structures.The review culminates by highlighting the transformative potential of this union between smart materials and self-repairable structures,promoting a sustainable and efficient engineering paradigm.
基金supported by the National Natural Science Foundation of China(No.52370163)National Key Research and Development Program of China(No.2022YFA0912501)State Key Laboratory of Urbanrural Water Resource&Environment(Harbin Institute of Technology)(No.2025DX12).
文摘Microbial electrorespiration harnesses bacteria to drive reductive dechlorination,offering a sustainable method to remediate environments contaminated with persistent chlorinated organic pollutants(COPs).However,aquifers'complex hydrogeological and hydrochemical conditions,combined with uneven COP distribution,create substantial spatial and temporal variability in biochemical reactions,environmental factors,and microbial communities.Traditional trial-and-error experiments are laborintensive and slow,impeding the quick identification of conditions that accelerate dechlorination rates.Here we show that a machine learning framework,integrating experimental design with cathodic biofilm data,uncovers key interrelationships among environmental variables,dechlorination kinetics,electrochemical properties,and functional microbes,enabling rapid optimization of bioelectrodechlorination.Trained on literature-derived datasets using models such as extreme gradient boosting,random forest,and multilayer perceptron,this framework identifies temperature and cathode potential as primary drivers in experimental design while highlighting key biofilm genera,including Clostridium,Desulfovibrio,Dehalococcoides,Pseudomonas,Dehalobacter,Arcobacter,Lactococcus,and Geobacter.It supports inverse design to determine optimal parameters—such as cathode potential,temperature,and additives—for dechlorinating representative COPs,including tetrachloroethene,trichloroethene,and 1,2-dichloroethane,achieving reaction rate predictions with errors below 6%.This approach surpasses conventional methods by increasing efficiency,cutting costs,and accelerating bioremediation without extensive laboratory testing.By incorporating microbial community insights into predictive models,our data-driven strategy advances the scalable application of microbial electrorespiration for COP-contaminated water remediation and paves the way for broader bioelectrochemical uses in environmental engineering.
基金Project supported by the Technology Foundation for Basic Enhancement Plan,China (No.2021-JCJQ-JJ-0301)the National Major Research and Development Project of China (No.2018YFE0206500)+1 种基金the National Natural Science Foundation of China (No.62071140)the National Special for International Scientific and Technological Cooperation of China (No.2015DFR10220)。
文摘The performance of existing maneuvering target tracking methods for highly maneuvering targets in cluttered environments is unsatisfactory.This paper proposes a hybrid-driven approach for tracking multiple highly maneuvering targets,leveraging the advantages of both data-driven and model-based algorithms.The time-varying constant velocity model is integrated into the Gaussian process(GP)of online learning to improve the performance of GP prediction.This integration is further combined with a generalized probabilistic data association algorithm to realize multi-target tracking.Through the simulations,it has been demonstrated that the hybrid-driven approach exhibits significant performance improvements in comparison with widely used algorithms such as the interactive multi-model method and the data-driven GP motion tracker.
