Multi-constrained pipes conveying fluid,such as aircraft hydraulic control pipes,are susceptible to resonance fatigue in harsh vibration environments,which may lead to system failure and even catastrophic accidents.In...Multi-constrained pipes conveying fluid,such as aircraft hydraulic control pipes,are susceptible to resonance fatigue in harsh vibration environments,which may lead to system failure and even catastrophic accidents.In this study,a machine learning(ML)-assisted weak vibration design method under harsh environmental excitations is proposed.The dynamic model of a typical pipe is developed using the absolute nodal coordinate formulation(ANCF)to determine its vibrational characteristics.With the harsh vibration environments as the preserved frequency band(PFB),the safety design is defined by comparing the natural frequency with the PFB.By analyzing the safety design of pipes with different constraint parameters,the dataset of the absolute safety length and the absolute resonance length of the pipe is obtained.This dataset is then utilized to develop genetic programming(GP)algorithm-based ML models capable of producing explicit mathematical expressions of the pipe's absolute safety length and absolute resonance length with the location,stiffness,and total number of retaining clips as design variables.The proposed ML models effectively bridge the dataset with the prediction results.Thus,the ML model is utilized to stagger the natural frequency,and the PFB is utilized to achieve the weak vibration design.The findings of the present study provide valuable insights into the practical application of weak vibration design.展开更多
Machine learning(ML)has recently enabled many modeling tasks in design,manufacturing,and condition monitoring due to its unparalleled learning ability using existing data.Data have become the limiting factor when impl...Machine learning(ML)has recently enabled many modeling tasks in design,manufacturing,and condition monitoring due to its unparalleled learning ability using existing data.Data have become the limiting factor when implementing ML in industry.However,there is no systematic investigation on how data quality can be assessed and improved for ML-based design and manufacturing.The aim of this survey is to uncover the data challenges in this domain and review the techniques used to resolve them.To establish the background for the subsequent analysis,crucial data terminologies in ML-based modeling are reviewed and categorized into data acquisition,management,analysis,and utilization.Thereafter,the concepts and frameworks established to evaluate data quality and imbalance,including data quality assessment,data readiness,information quality,data biases,fairness,and diversity,are further investigated.The root causes and types of data challenges,including human factors,complex systems,complicated relationships,lack of data quality,data heterogeneity,data imbalance,and data scarcity,are identified and summarized.Methods to improve data quality and mitigate data imbalance and their applications in this domain are reviewed.This literature review focuses on two promising methods:data augmentation and active learning.The strengths,limitations,and applicability of the surveyed techniques are illustrated.The trends of data augmentation and active learning are discussed with respect to their applications,data types,and approaches.Based on this discussion,future directions for data quality improvement and data imbalance mitigation in this domain are identified.展开更多
Finding materials with specific properties is a hot topic in materials science.Traditional materials design relies on empirical and trial-and-error methods,requiring extensive experiments and time,resulting in high co...Finding materials with specific properties is a hot topic in materials science.Traditional materials design relies on empirical and trial-and-error methods,requiring extensive experiments and time,resulting in high costs.With the development of physics,statistics,computer science,and other fields,machine learning offers opportunities for systematically discovering new materials.Especially through machine learning-based inverse design,machine learning algorithms analyze the mapping relationships between materials and their properties to find materials with desired properties.This paper first outlines the basic concepts of materials inverse design and the challenges faced by machine learning-based approaches to materials inverse design.Then,three main inverse design methods—exploration-based,model-based,and optimization-based—are analyzed in the context of different application scenarios.Finally,the applications of inverse design methods in alloys,optical materials,and acoustic materials are elaborated on,and the prospects for materials inverse design are discussed.The authors hope to accelerate the discovery of new materials and provide new possibilities for advancing materials science and innovative design methods.展开更多
Traditional inverse neural network(INN)approaches for inverse design typically require auxiliary feedforward networks,leading to increased computational complexity and architectural dependencies.This study introduces ...Traditional inverse neural network(INN)approaches for inverse design typically require auxiliary feedforward networks,leading to increased computational complexity and architectural dependencies.This study introduces a standalone INN methodology that eliminates the need for feedforward networks while maintaining high reconstruction accuracy.The approach integrates Principal Component Analysis(PCA)and Partial Least Squares(PLS)for optimized feature space learning,enabling the standalone INN to effectively capture bidirectionalmappings between geometric parameters and mechanical properties.Validation using established numerical datasets demonstrates that the standalone INN architecture achieves reconstruction accuracy equal or better than traditional tandem approaches while completely eliminating the workload and training time required for Feedforward Neural Networks(FNN).These findings contribute to AI methodology development by proving that standalone invertible architectures can achieve comparable performance to complex hybrid systems with significantly improved computational efficiency.展开更多
Photonic inverse design concerns the problem of finding photonic structures with target optical properties.However,traditional methods based on optimization algorithms are time-consuming and computationally expensive....Photonic inverse design concerns the problem of finding photonic structures with target optical properties.However,traditional methods based on optimization algorithms are time-consuming and computationally expensive.Recently,deep learning-based approaches have been developed to tackle the problem of inverse design efficiently.Although most of these neural network models have demonstrated high accuracy in different inverse design problems,no previous study has examined the potential effects under given constraints in nanomanufacturing.Additionally,the relative strength of different deep learning-based inverse design approaches has not been fully investigated.Here,we benchmark three commonly used deep learning models in inverse design:Tandem networks,Variational Auto-Encoders,and Generative Adversarial Networks.We provide detailed comparisons in terms of their accuracy,diversity,and robustness.We find that tandem networks and Variational Auto-Encoders give the best accuracy,while Generative Adversarial Networks lead to the most diverse predictions.Our findings could serve as a guideline for researchers to select the model that can best suit their design criteria and fabrication considerations.In addition,our code and data are publicly available,which could be used for future inverse design model development and benchmarking.展开更多
Rational design of ionic liquids(ILs),which is highly dependent on the accuracy of the model used,has always been crucial for CO_(2)separation from flue gas.In this study,a support vector machine(SVM)model which is a ...Rational design of ionic liquids(ILs),which is highly dependent on the accuracy of the model used,has always been crucial for CO_(2)separation from flue gas.In this study,a support vector machine(SVM)model which is a machine learning approach is established,so as to improve the prediction accuracy and range of IL melting points.Based on IL melting points data with 600 training data and 168 testing data,the estimated average absolute relative deviations(AARD)and squared correlation coefficients(R^(2))are 3.11%,0.8820 and 5.12%,0.8542 for the training set and testing set of the SVM model,respectively.Then,through the melting points model and other rational design processes including conductor-like screening model for real solvents(COSMO-RS)calculation and physical property constraints,cyano-based ILs are obtained,in which tetracyanoborate[TCB]-is often ruled out due to incorrect estimation of melting points model in the literature.Subsequently,by means of process simulation using Aspen Plus,optimal IL are compared with excellent IL reported in the literature.Finally,1-ethyl-3-methylimidazolium tricyanomethanide[EMIM][TCM]is selected as a most suitable solvent for CO_(2)separation from flue gas,the process of which leads to 12.9%savings on total annualized cost compared to that of 1-ethyl-3-methylimidazolium bis(trifluoromethylsulfonyl)amide[EMIM][Tf_(2)N].展开更多
As the density of wireless networks increases globally, the vulnerability of overlapped dense wireless communications to interference by hidden nodes and denial-of-service (DoS) attacks is becoming more apparent. Ther...As the density of wireless networks increases globally, the vulnerability of overlapped dense wireless communications to interference by hidden nodes and denial-of-service (DoS) attacks is becoming more apparent. There exists a gap in research on the detection and response to attacks on Medium Access Control (MAC) mechanisms themselves, which would lead to service outages between nodes. Classifying exploitation and deceptive jamming attacks on control mechanisms is particularly challengingdue to their resemblance to normal heavy communication patterns. Accordingly, this paper proposes a machine learning-based selective attack mitigation model that detects DoS attacks on wireless networks by monitoring packet log data. Based on the type of detected attack, it implements effective corresponding mitigation techniques to restore performance to nodes whose availability has been compromised. Experimental results reveal that the accuracy of the proposed model is 14% higher than that of a baseline anomaly detection model. Further, the appropriate mitigation techniques selected by the proposed system based on the attack type improve the average throughput by more than 440% compared to the case without a response.展开更多
Visual question answering(VQA)is a multimodal task,involving a deep understanding of the image scene and the question’s meaning and capturing the relevant correlations between both modalities to infer the appropriate...Visual question answering(VQA)is a multimodal task,involving a deep understanding of the image scene and the question’s meaning and capturing the relevant correlations between both modalities to infer the appropriate answer.In this paper,we propose a VQA system intended to answer yes/no questions about real-world images,in Arabic.To support a robust VQA system,we work in two directions:(1)Using deep neural networks to semantically represent the given image and question in a fine-grainedmanner,namely ResNet-152 and Gated Recurrent Units(GRU).(2)Studying the role of the utilizedmultimodal bilinear pooling fusion technique in the trade-o.between the model complexity and the overall model performance.Some fusion techniques could significantly increase the model complexity,which seriously limits their applicability for VQA models.So far,there is no evidence of how efficient these multimodal bilinear pooling fusion techniques are for VQA systems dedicated to yes/no questions.Hence,a comparative analysis is conducted between eight bilinear pooling fusion techniques,in terms of their ability to reduce themodel complexity and improve themodel performance in this case of VQA systems.Experiments indicate that these multimodal bilinear pooling fusion techniques have improved the VQA model’s performance,until reaching the best performance of 89.25%.Further,experiments have proven that the number of answers in the developed VQA system is a critical factor that a.ects the effectiveness of these multimodal bilinear pooling techniques in achieving their main objective of reducing the model complexity.The Multimodal Local Perception Bilinear Pooling(MLPB)technique has shown the best balance between the model complexity and its performance,for VQA systems designed to answer yes/no questions.展开更多
High-entropy alloys(HEAs)have attracted considerable attention because of their excellent properties and broad compositional design space.However,traditional trial-and-error methods for screening HEAs are costly and i...High-entropy alloys(HEAs)have attracted considerable attention because of their excellent properties and broad compositional design space.However,traditional trial-and-error methods for screening HEAs are costly and inefficient,thereby limiting the development of new materials.Although density functional theory(DFT),molecular dynamics(MD),and thermodynamic modeling have improved the design efficiency,their indirect connection to properties has led to limitations in calculation and prediction.With the awarding of the Nobel Prize in Physics and Chemistry to artificial intelligence(AI)related researchers,there has been a renewed enthusiasm for the application of machine learning(ML)in the field of alloy materials.In this study,common and advanced ML models and strategies in HEA design were introduced,and the mechanism by which ML can play a role in composition optimization and performance prediction was investigated through case studies.The general workflow of ML application in material design was also introduced from the programmer’s point of view,including data preprocessing,feature engineering,model training,evaluation,optimization,and interpretability.Furthermore,data scarcity,multi-model coupling,and other challenges and opportunities at the current stage were analyzed,and an outlook on future research directions was provided.展开更多
Against the backdrop of escalating global climate change and energy crises,the resource utilization of carbon dioxide(CO_(2)),a major greenhouse gas,has become a crucial pathway for achieving carbon peaking and carbon...Against the backdrop of escalating global climate change and energy crises,the resource utilization of carbon dioxide(CO_(2)),a major greenhouse gas,has become a crucial pathway for achieving carbon peaking and carbon neutrality goals.The hydrogenation of CO_(2)to methanol not only enables carbon sequestration and recycling,but also provides a route to produce high value-added fuels and basic chemical feedstocks,holding significant environmental and economic potential.However,this conversion process is thermodynamically and kinetically limited,and traditional catalyst systems(e.g.,Cu/ZnO/Al_(2)O_(3))exhibit inadequate activity,selectivity,and stability under mild conditions.Therefore,the development of novel high-performance catalysts with precisely tunable structures and functionalities is imperative.Metal-organic frameworks(MOFs),as crystalline porous materials with high surface area,tunable pore structures,and diverse metal-ligand compositions,have the great potential in CO_(2)hydrogenation catalysis.Their structural design flexibility allows for the construction of well-dispersed active sites,tailored electronic environments,and enhanced metal-support interactions.This review systematically summarizes the recent advances in MOF-based and MOF-derived catalysts for CO_(2)hydrogenation to methanol,focusing on four design strategies:(1)spatial confinement and in situ construction,(2)defect engineering and ion-exchange,(3)bimetallic synergy and hybrid structure design,and(4)MOF-derived nanomaterial synthesis.These approaches significantly improve CO_(2)conversion and methanol selectivity by optimizing metal dispersion,interfacial structures,and reaction pathways.The reaction mechanism is further explored by focusing on the three main reaction pathways:the formate pathway(HCOO*),the RWGS(Reverse Water Gas Shift reaction)+CO*hydrogenation pathway,and the trans-COOH pathway.In situ spectroscopic studies and density functional theory(DFT)calculations elucidate the formation and transformation of key intermediates,as well as the roles of active sites,metal-support interfaces,oxygen vacancies,and promoters.Additionally,representative catalytic performance data for MOFbased systems are compiled and compared,demonstrating their advantages over traditional catalysts in terms of CO_(2)conversion,methanol selectivity,and space-time yield.Future perspectives for MOF-based CO_(2)hydrogenation catalysts will prioritize two main directions:structural design and mechanistic understanding.The precise construction of active sites through multi-metallic synergy,defect engineering,and interfacial electronic modulation should be made to enhance catalyst selectivity and stability.In addition,advanced in situ characterization techniques combined with theoretical modeling are essential to unravel the detailed reaction mechanisms and intermediate behaviors,thereby guiding rational catalyst design.Moreover,to enable industrial application,challenges related to thermal/hydrothermal stability,catalyst recyclability,and cost-effective large-scale synthesis must be addressed.The development of green,scalable preparation methods and the integration of MOF catalysts into practical reaction systems(e.g.,flow reactors)will be crucial for bridging the gap between laboratory research and commercial deployment.Ultimately,multi-scale structure-performance optimization and catalytic system integration will be vital for accelerating the industrialization of MOF-based CO_(2)-to-methanol technologies.展开更多
Recently,deep learning has been used to establish the nonlinear and nonintuitive mapping between physical structures and electromagnetic responses of meta-atoms for higher computational efficiency.However,to obtain su...Recently,deep learning has been used to establish the nonlinear and nonintuitive mapping between physical structures and electromagnetic responses of meta-atoms for higher computational efficiency.However,to obtain sufficiently accurate predictions,the conventional deep-learning-based method consumes excessive time to collect the data set,thus hindering its wide application in this interdisciplinary field.We introduce a spectral transfer-learning-based metasurface design method to achieve excellent performance on a small data set with only 1000 samples in the target waveband by utilizing open-source data from another spectral range.We demonstrate three transfer strategies and experimentally quantify their performance,among which the“frozen-none”robustly improves the prediction accuracy by∼26%compared to direct learning.We propose to use a complex-valued deep neural network during the training process to further improve the spectral predicting precision by∼30%compared to its real-valued counterparts.We design several typical teraherz metadevices by employing a hybrid inverse model consolidating this trained target network and a global optimization algorithm.The simulated results successfully validate the capability of our approach.Our work provides a universal methodology for efficient and accurate metasurface design in arbitrary wavebands,which will pave the way toward the automated and mass production of metasurfaces.展开更多
This paper studied a tactical liner shipping schedule design issue under sail and port time uncertainties,which is the determination of the planned arrival time at each port call as well as the punctuality rate and nu...This paper studied a tactical liner shipping schedule design issue under sail and port time uncertainties,which is the determination of the planned arrival time at each port call as well as the punctuality rate and number of assigned ship on the route.A number of studies have tried to introduce the operational speed adjustment measure into this tactical schedule design issue,to alleviate the discrepancies between designed schedule and maritime practice.On the one hand,weather conditions can lead to speed loss phenomenon of ships,which may result in the failure of ships’punctual arrivals.On the other hand,improving the ability of speed adjustment can decrease the late-arrival compensation,but increase the fuel consumption cost.Then,we formulated a machine learning-based liner shipping schedule design model aiming at above-mentioned two limitations on speed adjustment measure.And a machine learning-based approach has been designed,where the speed adjustment simulation,the neural network training and the reinforcement learning were included.Numerical experiments were conducted to validate our results and derive managerial insights,and then the applicability of machine learning method in shipping optimization issue has been confirmed.展开更多
Recent years have witnessed transformative changes brought about by artificial intelligence(AI)techniques with billions of parameters for the realization of high accuracy,proposing high demand for the advanced and AI ...Recent years have witnessed transformative changes brought about by artificial intelligence(AI)techniques with billions of parameters for the realization of high accuracy,proposing high demand for the advanced and AI chip to solve these AI tasks efficiently and powerfully.Rapid progress has been made in the field of advanced chips recently,such as the development of photonic computing,the advancement of the quantum processors,the boost of the biomimetic chips,and so on.Designs tactics of the advanced chips can be conducted with elaborated consideration of materials,algorithms,models,architectures,and so on.Though a few reviews present the development of the chips from their unique aspects,reviews in the view of the latest design for advanced and AI chips are few.Here,the newest development is systematically reviewed in the field of advanced chips.First,background and mechanisms are summarized,and subsequently most important considerations for co-design of the software and hardware are illustrated.Next,strategies are summed up to obtain advanced and AI chips with high excellent performance by taking the important information processing steps into consideration,after which the design thought for the advanced chips in the future is proposed.Finally,some perspectives are put forward.展开更多
The traditional teaching methods of one-way cultivation of students can no longer meet the requirements of talent cultivation at this stage.The issue of how to promote students from passive acceptance to the independe...The traditional teaching methods of one-way cultivation of students can no longer meet the requirements of talent cultivation at this stage.The issue of how to promote students from passive acceptance to the independent cognitive understanding stage(i.e.deep learning)has become the focus of geography teaching.Therefore,under the guidance of deep learning theory,this paper takes the“landforms”knowledge unit of the Humanistic Education Edition as an example,improves the classroom teaching means through the unit teaching mode,reconstructs the“landforms”teaching unit,and explores the specific teaching of high school geography unit based on deep learning.This study provides a good example and guidelines for high school geography teaching and learning.展开更多
Facility management and maintenance of the Thermal-Energy-Storage Air-Conditioning(TES-AC)system is a tedious task at a large scale mainly due to the charging load that can increase energy consumption if needed to be ...Facility management and maintenance of the Thermal-Energy-Storage Air-Conditioning(TES-AC)system is a tedious task at a large scale mainly due to the charging load that can increase energy consumption if needed to be charged at peak hours.Besides,maintenance of TES-AC at a large scale gets complex as it contains many sensor data.By utilizing deep learning techniques on the sensor data,charging load prediction can be made possible,so facility managers can prepare in advance.However,a deep learning-based application will be unusable if it is not deployed in a user-friendly manner where facility managers can benefit from this application.Hence,this research focuses on gathering design guidelines for a deep learning-based application and further validates the design considerations with a developed application for efficient human-computer interaction through qualitative analysis.The approach taken to gather design guidelines demonstrated a positive correlation between expert-suggested features and the user-friendly aspect of the application as 67.08%of participants found the features suggested by experts to be most satisfactory.Furthermore,it evaluates user satisfaction with the advanced developed application for TES-AC according to the gathered design guidelines.展开更多
The vehicle routing problem(VRP)is a typical discrete combinatorial optimization problem,and many models and algorithms have been proposed to solve the VRP and its variants.Although existing approaches have contribute...The vehicle routing problem(VRP)is a typical discrete combinatorial optimization problem,and many models and algorithms have been proposed to solve the VRP and its variants.Although existing approaches have contributed significantly to the development of this field,these approaches either are limited in problem size or need manual intervention in choosing parameters.To solve these difficulties,many studies have considered learning-based optimization(LBO)algorithms to solve the VRP.This paper reviews recent advances in this field and divides relevant approaches into end-to-end approaches and step-by-step approaches.We performed a statistical analysis of the reviewed articles from various aspects and designed three experiments to evaluate the performance of four representative LBO algorithms.Finally,we conclude the applicable types of problems for different LBO algorithms and suggest directions in which researchers can improve LBO algorithms.展开更多
A learning-based approach for solving wall shear stresses from Shear-Sensitive Liquid Crystal Coating(SSLCC) color images is presented in this paper. The approach is able to learn and establish the mapping relationshi...A learning-based approach for solving wall shear stresses from Shear-Sensitive Liquid Crystal Coating(SSLCC) color images is presented in this paper. The approach is able to learn and establish the mapping relationship between the SSLCC color-change responses in different observation directions and the shear stress vectors, and then uses the mapping relationship to solve wall shear stress vectors from SSLCC color images. Experimental results show that the proposed approach can solve wall shear stress vectors using two or more SSLCC images, and even using only one image for symmetrical flow field. The accuracy of the approach using four or more observations is found to be comparable to that of the traditional multi-view Gauss curve fitting approach;the accuracy is slightly reduced when using two or fewer observations. The computational efficiency is significantly improved when compared with the traditional Gauss curve fitting approach, and the wall shear stress vectors can be solved in nearly real time. The learning-based approach has no strict requirements on illumination direction and observation directions and is therefore more flexible to use in practical wind tunnel measurement when compared with traditional liquid crystal-based methods.展开更多
This paper reviews recent developments in learning-based adaptive optimal output regulation that aims to solve the problem of adaptive and optimal asymptotic tracking with disturbance rejection.The proposed framework ...This paper reviews recent developments in learning-based adaptive optimal output regulation that aims to solve the problem of adaptive and optimal asymptotic tracking with disturbance rejection.The proposed framework aims to bring together two separate topics—output regulation and adaptive dynamic programming—that have been under extensive investigation due to their broad applications in modern control engineering.Under this framework,one can solve optimal output regulation problems of linear,partially linear,nonlinear,and multi-agent systems in a data-driven manner.We will also review some practical applications based on this framework,such as semi-autonomous vehicles,connected and autonomous vehicles,and nonlinear oscillators.展开更多
基金Project supported by the Foundation for Innovative Research Groups of the National Natural Science Foundation of China(No.12421002)the National Science Funds for Distinguished Young Scholars of China(No.12025204)+1 种基金the National Natural Science Foundation of China(No.12372015)China Scholarship Council(No.202206890065)。
文摘Multi-constrained pipes conveying fluid,such as aircraft hydraulic control pipes,are susceptible to resonance fatigue in harsh vibration environments,which may lead to system failure and even catastrophic accidents.In this study,a machine learning(ML)-assisted weak vibration design method under harsh environmental excitations is proposed.The dynamic model of a typical pipe is developed using the absolute nodal coordinate formulation(ANCF)to determine its vibrational characteristics.With the harsh vibration environments as the preserved frequency band(PFB),the safety design is defined by comparing the natural frequency with the PFB.By analyzing the safety design of pipes with different constraint parameters,the dataset of the absolute safety length and the absolute resonance length of the pipe is obtained.This dataset is then utilized to develop genetic programming(GP)algorithm-based ML models capable of producing explicit mathematical expressions of the pipe's absolute safety length and absolute resonance length with the location,stiffness,and total number of retaining clips as design variables.The proposed ML models effectively bridge the dataset with the prediction results.Thus,the ML model is utilized to stagger the natural frequency,and the PFB is utilized to achieve the weak vibration design.The findings of the present study provide valuable insights into the practical application of weak vibration design.
基金funded by the McGill University Graduate Excellence Fellowship Award(00157)the Mitacs Accelerate Program(IT13369)the McGill Engineering Doctoral Award(MEDA).
文摘Machine learning(ML)has recently enabled many modeling tasks in design,manufacturing,and condition monitoring due to its unparalleled learning ability using existing data.Data have become the limiting factor when implementing ML in industry.However,there is no systematic investigation on how data quality can be assessed and improved for ML-based design and manufacturing.The aim of this survey is to uncover the data challenges in this domain and review the techniques used to resolve them.To establish the background for the subsequent analysis,crucial data terminologies in ML-based modeling are reviewed and categorized into data acquisition,management,analysis,and utilization.Thereafter,the concepts and frameworks established to evaluate data quality and imbalance,including data quality assessment,data readiness,information quality,data biases,fairness,and diversity,are further investigated.The root causes and types of data challenges,including human factors,complex systems,complicated relationships,lack of data quality,data heterogeneity,data imbalance,and data scarcity,are identified and summarized.Methods to improve data quality and mitigate data imbalance and their applications in this domain are reviewed.This literature review focuses on two promising methods:data augmentation and active learning.The strengths,limitations,and applicability of the surveyed techniques are illustrated.The trends of data augmentation and active learning are discussed with respect to their applications,data types,and approaches.Based on this discussion,future directions for data quality improvement and data imbalance mitigation in this domain are identified.
基金funded by theNationalNatural Science Foundation of China(52061020)Major Science and Technology Projects in Yunnan Province(202302AG050009)Yunnan Fundamental Research Projects(202301AV070003).
文摘Finding materials with specific properties is a hot topic in materials science.Traditional materials design relies on empirical and trial-and-error methods,requiring extensive experiments and time,resulting in high costs.With the development of physics,statistics,computer science,and other fields,machine learning offers opportunities for systematically discovering new materials.Especially through machine learning-based inverse design,machine learning algorithms analyze the mapping relationships between materials and their properties to find materials with desired properties.This paper first outlines the basic concepts of materials inverse design and the challenges faced by machine learning-based approaches to materials inverse design.Then,three main inverse design methods—exploration-based,model-based,and optimization-based—are analyzed in the context of different application scenarios.Finally,the applications of inverse design methods in alloys,optical materials,and acoustic materials are elaborated on,and the prospects for materials inverse design are discussed.The authors hope to accelerate the discovery of new materials and provide new possibilities for advancing materials science and innovative design methods.
基金funding by the Deutsche Forschungsgemeinschaft under Germany’s Excellence Strategy within the Cluster of Excellence PhoenixD(EXC 2122,Project ID 390833453).
文摘Traditional inverse neural network(INN)approaches for inverse design typically require auxiliary feedforward networks,leading to increased computational complexity and architectural dependencies.This study introduces a standalone INN methodology that eliminates the need for feedforward networks while maintaining high reconstruction accuracy.The approach integrates Principal Component Analysis(PCA)and Partial Least Squares(PLS)for optimized feature space learning,enabling the standalone INN to effectively capture bidirectionalmappings between geometric parameters and mechanical properties.Validation using established numerical datasets demonstrates that the standalone INN architecture achieves reconstruction accuracy equal or better than traditional tandem approaches while completely eliminating the workload and training time required for Feedforward Neural Networks(FNN).These findings contribute to AI methodology development by proving that standalone invertible architectures can achieve comparable performance to complex hybrid systems with significantly improved computational efficiency.
文摘Photonic inverse design concerns the problem of finding photonic structures with target optical properties.However,traditional methods based on optimization algorithms are time-consuming and computationally expensive.Recently,deep learning-based approaches have been developed to tackle the problem of inverse design efficiently.Although most of these neural network models have demonstrated high accuracy in different inverse design problems,no previous study has examined the potential effects under given constraints in nanomanufacturing.Additionally,the relative strength of different deep learning-based inverse design approaches has not been fully investigated.Here,we benchmark three commonly used deep learning models in inverse design:Tandem networks,Variational Auto-Encoders,and Generative Adversarial Networks.We provide detailed comparisons in terms of their accuracy,diversity,and robustness.We find that tandem networks and Variational Auto-Encoders give the best accuracy,while Generative Adversarial Networks lead to the most diverse predictions.Our findings could serve as a guideline for researchers to select the model that can best suit their design criteria and fabrication considerations.In addition,our code and data are publicly available,which could be used for future inverse design model development and benchmarking.
基金the financial support by the National Natural Science Foundation of China(Project No.21878054)the Natural Science Foundation of Fujian Province of China(2020J01515)
文摘Rational design of ionic liquids(ILs),which is highly dependent on the accuracy of the model used,has always been crucial for CO_(2)separation from flue gas.In this study,a support vector machine(SVM)model which is a machine learning approach is established,so as to improve the prediction accuracy and range of IL melting points.Based on IL melting points data with 600 training data and 168 testing data,the estimated average absolute relative deviations(AARD)and squared correlation coefficients(R^(2))are 3.11%,0.8820 and 5.12%,0.8542 for the training set and testing set of the SVM model,respectively.Then,through the melting points model and other rational design processes including conductor-like screening model for real solvents(COSMO-RS)calculation and physical property constraints,cyano-based ILs are obtained,in which tetracyanoborate[TCB]-is often ruled out due to incorrect estimation of melting points model in the literature.Subsequently,by means of process simulation using Aspen Plus,optimal IL are compared with excellent IL reported in the literature.Finally,1-ethyl-3-methylimidazolium tricyanomethanide[EMIM][TCM]is selected as a most suitable solvent for CO_(2)separation from flue gas,the process of which leads to 12.9%savings on total annualized cost compared to that of 1-ethyl-3-methylimidazolium bis(trifluoromethylsulfonyl)amide[EMIM][Tf_(2)N].
基金supported by the Ministry of Trade,Industry and Energy(MOTIE)under Training Industrial Security Specialist for High-Tech Industry(RS-2024-00415520)supervised by the Korea Institute for Advancement of Technology(KIAT)the Ministry of Science and ICT(MSIT)under the ICT Challenge and Advanced Network of HRD(ICAN)Program(No.IITP-2022-RS-2022-00156310)supervised by the Institute of Information&Communication Technology Planning&Evaluation(IITP).
文摘As the density of wireless networks increases globally, the vulnerability of overlapped dense wireless communications to interference by hidden nodes and denial-of-service (DoS) attacks is becoming more apparent. There exists a gap in research on the detection and response to attacks on Medium Access Control (MAC) mechanisms themselves, which would lead to service outages between nodes. Classifying exploitation and deceptive jamming attacks on control mechanisms is particularly challengingdue to their resemblance to normal heavy communication patterns. Accordingly, this paper proposes a machine learning-based selective attack mitigation model that detects DoS attacks on wireless networks by monitoring packet log data. Based on the type of detected attack, it implements effective corresponding mitigation techniques to restore performance to nodes whose availability has been compromised. Experimental results reveal that the accuracy of the proposed model is 14% higher than that of a baseline anomaly detection model. Further, the appropriate mitigation techniques selected by the proposed system based on the attack type improve the average throughput by more than 440% compared to the case without a response.
文摘Visual question answering(VQA)is a multimodal task,involving a deep understanding of the image scene and the question’s meaning and capturing the relevant correlations between both modalities to infer the appropriate answer.In this paper,we propose a VQA system intended to answer yes/no questions about real-world images,in Arabic.To support a robust VQA system,we work in two directions:(1)Using deep neural networks to semantically represent the given image and question in a fine-grainedmanner,namely ResNet-152 and Gated Recurrent Units(GRU).(2)Studying the role of the utilizedmultimodal bilinear pooling fusion technique in the trade-o.between the model complexity and the overall model performance.Some fusion techniques could significantly increase the model complexity,which seriously limits their applicability for VQA models.So far,there is no evidence of how efficient these multimodal bilinear pooling fusion techniques are for VQA systems dedicated to yes/no questions.Hence,a comparative analysis is conducted between eight bilinear pooling fusion techniques,in terms of their ability to reduce themodel complexity and improve themodel performance in this case of VQA systems.Experiments indicate that these multimodal bilinear pooling fusion techniques have improved the VQA model’s performance,until reaching the best performance of 89.25%.Further,experiments have proven that the number of answers in the developed VQA system is a critical factor that a.ects the effectiveness of these multimodal bilinear pooling techniques in achieving their main objective of reducing the model complexity.The Multimodal Local Perception Bilinear Pooling(MLPB)technique has shown the best balance between the model complexity and its performance,for VQA systems designed to answer yes/no questions.
基金the National Natural Science Foundation of China(52161011)the Central Guiding Local Science and Technology Development Fund Project(Guike ZY23055005,Guike ZY24212036 and GuikeAB25069457)+5 种基金the Guangxi Science and Technology Project(2023GXNSFDA026046 and Guike AB24010247)the Scientifc Research and Technology Development Program of Guilin(20220110-3 and 20230110-3)the Scientifc Research and Technology Development Program of Nanning Jiangnan district(20230715-02)the Guangxi Key Laboratory of Superhard Material(2022-K-001)the Guangxi Key Laboratory of Information Materials(231003-Z,231033-K and 231013-Z)the Innovation Project of GUET Graduate Education(2025YCXS177)for the fnancial support given to this work.
文摘High-entropy alloys(HEAs)have attracted considerable attention because of their excellent properties and broad compositional design space.However,traditional trial-and-error methods for screening HEAs are costly and inefficient,thereby limiting the development of new materials.Although density functional theory(DFT),molecular dynamics(MD),and thermodynamic modeling have improved the design efficiency,their indirect connection to properties has led to limitations in calculation and prediction.With the awarding of the Nobel Prize in Physics and Chemistry to artificial intelligence(AI)related researchers,there has been a renewed enthusiasm for the application of machine learning(ML)in the field of alloy materials.In this study,common and advanced ML models and strategies in HEA design were introduced,and the mechanism by which ML can play a role in composition optimization and performance prediction was investigated through case studies.The general workflow of ML application in material design was also introduced from the programmer’s point of view,including data preprocessing,feature engineering,model training,evaluation,optimization,and interpretability.Furthermore,data scarcity,multi-model coupling,and other challenges and opportunities at the current stage were analyzed,and an outlook on future research directions was provided.
基金Supported by the National Key Research and Development Program of China(2023YFB4104500,2023YFB4104502)the National Natural Science Foundation of China(22138013)the Taishan Scholar Project(ts201712020).
文摘Against the backdrop of escalating global climate change and energy crises,the resource utilization of carbon dioxide(CO_(2)),a major greenhouse gas,has become a crucial pathway for achieving carbon peaking and carbon neutrality goals.The hydrogenation of CO_(2)to methanol not only enables carbon sequestration and recycling,but also provides a route to produce high value-added fuels and basic chemical feedstocks,holding significant environmental and economic potential.However,this conversion process is thermodynamically and kinetically limited,and traditional catalyst systems(e.g.,Cu/ZnO/Al_(2)O_(3))exhibit inadequate activity,selectivity,and stability under mild conditions.Therefore,the development of novel high-performance catalysts with precisely tunable structures and functionalities is imperative.Metal-organic frameworks(MOFs),as crystalline porous materials with high surface area,tunable pore structures,and diverse metal-ligand compositions,have the great potential in CO_(2)hydrogenation catalysis.Their structural design flexibility allows for the construction of well-dispersed active sites,tailored electronic environments,and enhanced metal-support interactions.This review systematically summarizes the recent advances in MOF-based and MOF-derived catalysts for CO_(2)hydrogenation to methanol,focusing on four design strategies:(1)spatial confinement and in situ construction,(2)defect engineering and ion-exchange,(3)bimetallic synergy and hybrid structure design,and(4)MOF-derived nanomaterial synthesis.These approaches significantly improve CO_(2)conversion and methanol selectivity by optimizing metal dispersion,interfacial structures,and reaction pathways.The reaction mechanism is further explored by focusing on the three main reaction pathways:the formate pathway(HCOO*),the RWGS(Reverse Water Gas Shift reaction)+CO*hydrogenation pathway,and the trans-COOH pathway.In situ spectroscopic studies and density functional theory(DFT)calculations elucidate the formation and transformation of key intermediates,as well as the roles of active sites,metal-support interfaces,oxygen vacancies,and promoters.Additionally,representative catalytic performance data for MOFbased systems are compiled and compared,demonstrating their advantages over traditional catalysts in terms of CO_(2)conversion,methanol selectivity,and space-time yield.Future perspectives for MOF-based CO_(2)hydrogenation catalysts will prioritize two main directions:structural design and mechanistic understanding.The precise construction of active sites through multi-metallic synergy,defect engineering,and interfacial electronic modulation should be made to enhance catalyst selectivity and stability.In addition,advanced in situ characterization techniques combined with theoretical modeling are essential to unravel the detailed reaction mechanisms and intermediate behaviors,thereby guiding rational catalyst design.Moreover,to enable industrial application,challenges related to thermal/hydrothermal stability,catalyst recyclability,and cost-effective large-scale synthesis must be addressed.The development of green,scalable preparation methods and the integration of MOF catalysts into practical reaction systems(e.g.,flow reactors)will be crucial for bridging the gap between laboratory research and commercial deployment.Ultimately,multi-scale structure-performance optimization and catalytic system integration will be vital for accelerating the industrialization of MOF-based CO_(2)-to-methanol technologies.
基金support from the National Natural Science Foundation of China (Grant Nos.62027820,61975143,61735012,and 62205380).
文摘Recently,deep learning has been used to establish the nonlinear and nonintuitive mapping between physical structures and electromagnetic responses of meta-atoms for higher computational efficiency.However,to obtain sufficiently accurate predictions,the conventional deep-learning-based method consumes excessive time to collect the data set,thus hindering its wide application in this interdisciplinary field.We introduce a spectral transfer-learning-based metasurface design method to achieve excellent performance on a small data set with only 1000 samples in the target waveband by utilizing open-source data from another spectral range.We demonstrate three transfer strategies and experimentally quantify their performance,among which the“frozen-none”robustly improves the prediction accuracy by∼26%compared to direct learning.We propose to use a complex-valued deep neural network during the training process to further improve the spectral predicting precision by∼30%compared to its real-valued counterparts.We design several typical teraherz metadevices by employing a hybrid inverse model consolidating this trained target network and a global optimization algorithm.The simulated results successfully validate the capability of our approach.Our work provides a universal methodology for efficient and accurate metasurface design in arbitrary wavebands,which will pave the way toward the automated and mass production of metasurfaces.
基金the National Natural Science Foundation of China(Nos.71572022 and 61473053)the National Social Science Foundation of China(No.18VHQ005)。
文摘This paper studied a tactical liner shipping schedule design issue under sail and port time uncertainties,which is the determination of the planned arrival time at each port call as well as the punctuality rate and number of assigned ship on the route.A number of studies have tried to introduce the operational speed adjustment measure into this tactical schedule design issue,to alleviate the discrepancies between designed schedule and maritime practice.On the one hand,weather conditions can lead to speed loss phenomenon of ships,which may result in the failure of ships’punctual arrivals.On the other hand,improving the ability of speed adjustment can decrease the late-arrival compensation,but increase the fuel consumption cost.Then,we formulated a machine learning-based liner shipping schedule design model aiming at above-mentioned two limitations on speed adjustment measure.And a machine learning-based approach has been designed,where the speed adjustment simulation,the neural network training and the reinforcement learning were included.Numerical experiments were conducted to validate our results and derive managerial insights,and then the applicability of machine learning method in shipping optimization issue has been confirmed.
基金supported by the Hong Kong Polytechnic University(1-WZ1Y,1-W34U,4-YWER).
文摘Recent years have witnessed transformative changes brought about by artificial intelligence(AI)techniques with billions of parameters for the realization of high accuracy,proposing high demand for the advanced and AI chip to solve these AI tasks efficiently and powerfully.Rapid progress has been made in the field of advanced chips recently,such as the development of photonic computing,the advancement of the quantum processors,the boost of the biomimetic chips,and so on.Designs tactics of the advanced chips can be conducted with elaborated consideration of materials,algorithms,models,architectures,and so on.Though a few reviews present the development of the chips from their unique aspects,reviews in the view of the latest design for advanced and AI chips are few.Here,the newest development is systematically reviewed in the field of advanced chips.First,background and mechanisms are summarized,and subsequently most important considerations for co-design of the software and hardware are illustrated.Next,strategies are summed up to obtain advanced and AI chips with high excellent performance by taking the important information processing steps into consideration,after which the design thought for the advanced chips in the future is proposed.Finally,some perspectives are put forward.
文摘The traditional teaching methods of one-way cultivation of students can no longer meet the requirements of talent cultivation at this stage.The issue of how to promote students from passive acceptance to the independent cognitive understanding stage(i.e.deep learning)has become the focus of geography teaching.Therefore,under the guidance of deep learning theory,this paper takes the“landforms”knowledge unit of the Humanistic Education Edition as an example,improves the classroom teaching means through the unit teaching mode,reconstructs the“landforms”teaching unit,and explores the specific teaching of high school geography unit based on deep learning.This study provides a good example and guidelines for high school geography teaching and learning.
文摘Facility management and maintenance of the Thermal-Energy-Storage Air-Conditioning(TES-AC)system is a tedious task at a large scale mainly due to the charging load that can increase energy consumption if needed to be charged at peak hours.Besides,maintenance of TES-AC at a large scale gets complex as it contains many sensor data.By utilizing deep learning techniques on the sensor data,charging load prediction can be made possible,so facility managers can prepare in advance.However,a deep learning-based application will be unusable if it is not deployed in a user-friendly manner where facility managers can benefit from this application.Hence,this research focuses on gathering design guidelines for a deep learning-based application and further validates the design considerations with a developed application for efficient human-computer interaction through qualitative analysis.The approach taken to gather design guidelines demonstrated a positive correlation between expert-suggested features and the user-friendly aspect of the application as 67.08%of participants found the features suggested by experts to be most satisfactory.Furthermore,it evaluates user satisfaction with the advanced developed application for TES-AC according to the gathered design guidelines.
文摘The vehicle routing problem(VRP)is a typical discrete combinatorial optimization problem,and many models and algorithms have been proposed to solve the VRP and its variants.Although existing approaches have contributed significantly to the development of this field,these approaches either are limited in problem size or need manual intervention in choosing parameters.To solve these difficulties,many studies have considered learning-based optimization(LBO)algorithms to solve the VRP.This paper reviews recent advances in this field and divides relevant approaches into end-to-end approaches and step-by-step approaches.We performed a statistical analysis of the reviewed articles from various aspects and designed three experiments to evaluate the performance of four representative LBO algorithms.Finally,we conclude the applicable types of problems for different LBO algorithms and suggest directions in which researchers can improve LBO algorithms.
基金co-supported by the National Natural Science Foundation of China(No.11602107)the Natural Science Foundation of Jiangsu Province of China(No.BK20150733)。
文摘A learning-based approach for solving wall shear stresses from Shear-Sensitive Liquid Crystal Coating(SSLCC) color images is presented in this paper. The approach is able to learn and establish the mapping relationship between the SSLCC color-change responses in different observation directions and the shear stress vectors, and then uses the mapping relationship to solve wall shear stress vectors from SSLCC color images. Experimental results show that the proposed approach can solve wall shear stress vectors using two or more SSLCC images, and even using only one image for symmetrical flow field. The accuracy of the approach using four or more observations is found to be comparable to that of the traditional multi-view Gauss curve fitting approach;the accuracy is slightly reduced when using two or fewer observations. The computational efficiency is significantly improved when compared with the traditional Gauss curve fitting approach, and the wall shear stress vectors can be solved in nearly real time. The learning-based approach has no strict requirements on illumination direction and observation directions and is therefore more flexible to use in practical wind tunnel measurement when compared with traditional liquid crystal-based methods.
文摘This paper reviews recent developments in learning-based adaptive optimal output regulation that aims to solve the problem of adaptive and optimal asymptotic tracking with disturbance rejection.The proposed framework aims to bring together two separate topics—output regulation and adaptive dynamic programming—that have been under extensive investigation due to their broad applications in modern control engineering.Under this framework,one can solve optimal output regulation problems of linear,partially linear,nonlinear,and multi-agent systems in a data-driven manner.We will also review some practical applications based on this framework,such as semi-autonomous vehicles,connected and autonomous vehicles,and nonlinear oscillators.
