This study describes an integrated framework in which basic aerospace engineering aspects(performance, aerodynamics, and structure) and practical aspects(configuration visualization and manufacturing) are coupled and ...This study describes an integrated framework in which basic aerospace engineering aspects(performance, aerodynamics, and structure) and practical aspects(configuration visualization and manufacturing) are coupled and considered in one fully automated design optimization of rotor blades. A number of codes are developed to robustly perform estimation of helicopter configuration from sizing, performance analysis, trim analysis, to rotor blades configuration representation. These codes are then integrated with a two-dimensional airfoil analysis tool to fully design rotor blades configuration including rotor planform and airfoil shape for optimal aerodynamics in both hover and forward flights. A modular structure design methodology is developed for realistic composite rotor blades with a sophisticated cross-sectional geometry. A D-spar cross-sectional structure is chosen as a baseline. The framework is able to analyze all realistic inner configurations including thicknesses of D-spar, skin, web, number and ply angles of layers of each composite part,and materials. A number of codes and commercial software(ANSYS, Gridgen, VABS, Pre VABS,etc.) are implemented to automate the structural analysis from aerodynamic data processing to sectional properties and stress analysis. An integrated model for manufacturing cost estimation ofcomposite rotor blades developed at the Aerodynamic Analysis and Design Laboratory(AADL),Aerospace Information Engineering Department, Konkuk University is integrated into the framework to provide a rapid and dynamic feedback to configuration design. The integration of three modules has constructed a framework where the size of a helicopter, aerodynamic performance analysis, structure analysis, and manufacturing cost estimation could be quickly investigated. All aspects of a rotor blade including planform, airfoil shape, and inner structure are considered in a multidisciplinary design optimization without an exception of critical configuration.展开更多
Consistency identification in task-oriented dialogue(CI-ToD)can prevent inconsistent dialogue response generation,which has recently emerged as an important and growing research area.This paper takes the first step to...Consistency identification in task-oriented dialogue(CI-ToD)can prevent inconsistent dialogue response generation,which has recently emerged as an important and growing research area.This paper takes the first step to explore a pre-training paradigm for CI-ToD.Nevertheless,pre-training for CI-ToD is non-trivial because it requires a large amount of multi-turn KB-grounded dialogues,which are extremely hard to collect.To alleviate the data scarcity problem for pre-training,we introduce a modularized pre-training framework(MPFToD),which is capable of utilizing large amounts of KB-free dialogues.Specifically,such modularization allows us to decouple CI-ToD into three sub-modules and propose three pre-training tasks including(i)query response matching pre-training;(ii)dialogue history consistent identification pre-training;and(iii)KB mask language modeling to enhance different abilities of CI-ToD model.As different sub-tasks are solved separately,MPFToD can learn from large amounts of KB-free dialogues for different modules,which are much easier to obtain.Results on the CI-ToD benchmark show that MPFToD pushes the state-of-the-art performance from 56.3%to 61.0%.Furthermore,we show its transferability with promising performance on other downstream tasks(i.e.,dialog act recognition,sentiment classification and table fact checking).展开更多
This study presents TriFireNet,a modular framework designed to address the challenges of smoke and fire detection in complex and dynamic environments.TriFireNet efficiently captures multiscale variability,overlapping ...This study presents TriFireNet,a modular framework designed to address the challenges of smoke and fire detection in complex and dynamic environments.TriFireNet efficiently captures multiscale variability,overlapping regions,and irregular patterns by combining bidirectional deep cross-fusion,directed multiscale extraction,and progressive stochastic augmentation.The proposed framework outperforms state-of-the-art models,providing an F1-score of 67.5%,mAP50 of 65.7%,and recall of 64.5%,ensuring minimal missed detections—a crucial feature for safety-critical applications.Precision and computational cost are balanced by TriFireNet's effective architecture,which offers accurate detection with less computation overhead and a 9.8 ms inference time.These advantages make it the ideal option for safety monitoring and real-time fire prevention,particularly in situations where effectiveness and reliability are critical.展开更多
基金supported by the National Foundation for Science and Technology Development (NAFOSTED) of Vietnam (No. 107.04-2012.25)
文摘This study describes an integrated framework in which basic aerospace engineering aspects(performance, aerodynamics, and structure) and practical aspects(configuration visualization and manufacturing) are coupled and considered in one fully automated design optimization of rotor blades. A number of codes are developed to robustly perform estimation of helicopter configuration from sizing, performance analysis, trim analysis, to rotor blades configuration representation. These codes are then integrated with a two-dimensional airfoil analysis tool to fully design rotor blades configuration including rotor planform and airfoil shape for optimal aerodynamics in both hover and forward flights. A modular structure design methodology is developed for realistic composite rotor blades with a sophisticated cross-sectional geometry. A D-spar cross-sectional structure is chosen as a baseline. The framework is able to analyze all realistic inner configurations including thicknesses of D-spar, skin, web, number and ply angles of layers of each composite part,and materials. A number of codes and commercial software(ANSYS, Gridgen, VABS, Pre VABS,etc.) are implemented to automate the structural analysis from aerodynamic data processing to sectional properties and stress analysis. An integrated model for manufacturing cost estimation ofcomposite rotor blades developed at the Aerodynamic Analysis and Design Laboratory(AADL),Aerospace Information Engineering Department, Konkuk University is integrated into the framework to provide a rapid and dynamic feedback to configuration design. The integration of three modules has constructed a framework where the size of a helicopter, aerodynamic performance analysis, structure analysis, and manufacturing cost estimation could be quickly investigated. All aspects of a rotor blade including planform, airfoil shape, and inner structure are considered in a multidisciplinary design optimization without an exception of critical configuration.
基金supported by the National Natural Science Foundation of China(NSFC)(Grant Nos.62306342,62176076)the Excellent Young Scientists Fund in Hunan Province(2024JJ4070)+3 种基金supported by the Natural Science Foundation of Guangdong(2023A1515012922)Shenzhen Foundational Research Funding(JCYJ20220818102415032)The Major Key Project of PCL(PCL2023A09)Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies(2022B1212010005k).
文摘Consistency identification in task-oriented dialogue(CI-ToD)can prevent inconsistent dialogue response generation,which has recently emerged as an important and growing research area.This paper takes the first step to explore a pre-training paradigm for CI-ToD.Nevertheless,pre-training for CI-ToD is non-trivial because it requires a large amount of multi-turn KB-grounded dialogues,which are extremely hard to collect.To alleviate the data scarcity problem for pre-training,we introduce a modularized pre-training framework(MPFToD),which is capable of utilizing large amounts of KB-free dialogues.Specifically,such modularization allows us to decouple CI-ToD into three sub-modules and propose three pre-training tasks including(i)query response matching pre-training;(ii)dialogue history consistent identification pre-training;and(iii)KB mask language modeling to enhance different abilities of CI-ToD model.As different sub-tasks are solved separately,MPFToD can learn from large amounts of KB-free dialogues for different modules,which are much easier to obtain.Results on the CI-ToD benchmark show that MPFToD pushes the state-of-the-art performance from 56.3%to 61.0%.Furthermore,we show its transferability with promising performance on other downstream tasks(i.e.,dialog act recognition,sentiment classification and table fact checking).
基金Science and Technology Planning Project of Guangdong Province,China,Grant/Award Number:2024B1111100001.
文摘This study presents TriFireNet,a modular framework designed to address the challenges of smoke and fire detection in complex and dynamic environments.TriFireNet efficiently captures multiscale variability,overlapping regions,and irregular patterns by combining bidirectional deep cross-fusion,directed multiscale extraction,and progressive stochastic augmentation.The proposed framework outperforms state-of-the-art models,providing an F1-score of 67.5%,mAP50 of 65.7%,and recall of 64.5%,ensuring minimal missed detections—a crucial feature for safety-critical applications.Precision and computational cost are balanced by TriFireNet's effective architecture,which offers accurate detection with less computation overhead and a 9.8 ms inference time.These advantages make it the ideal option for safety monitoring and real-time fire prevention,particularly in situations where effectiveness and reliability are critical.
