Accurate engine performance models are important for model-based performance evaluation of aero engine.The accuracy of the model often depends on engine component maps,so there is a need for a method that can accurate...Accurate engine performance models are important for model-based performance evaluation of aero engine.The accuracy of the model often depends on engine component maps,so there is a need for a method that can accurately correct the component maps of the model over a wide range.In this paper,a new method for modifying component maps is proposed,this method combines the correction of the scaling factors with the solution process of the off-design working point,and uses the adjustment of the variable geometric parameters of the engine to change the position of the working line,in order to obtain more correction results and guarantee high accuracy in a wider range.The method is validated by taking the main fan of the Adaptive Cycle Engine(ACE),an ideal power unit for a new generation of multi-purpose and ultra-wide working range aircraft,as an example.The results show that the maximum error between the corrected component maps and the target maps is less than 1%.New possibility for more precise component maps can be realized in this paper.展开更多
Three-dimensional(3D)phenotyping is important for studying plant structure and function.Light detection and ranging(LiDAR)has gained prominence in 3D plant phenotyping due to its ability to collect 3D point clouds.How...Three-dimensional(3D)phenotyping is important for studying plant structure and function.Light detection and ranging(LiDAR)has gained prominence in 3D plant phenotyping due to its ability to collect 3D point clouds.However,organ-level branch detection remains challenging due to small targets,sparse points,and low signal-to-noise ratios.In addition,extracting biologically relevant angle traits is difficult.In this study,we developed a stratified,clustered,and growing-based algorithm(SCAG)for soybean branch detection and branch angle calculation from LiDAR data,which is heuristic,open-source,and expandable.SCAG achieved high branch detection accuracy(F-score=0.77)and branch angle calculation accuracy(r=0.84)when evaluated on 152 diverse soybean varieties.Meanwhile,the SCAG outperformed 2 other classic algorithms,the support vector machine(F-score=0.53)and density-based methods(F-score=0.55).Moreover,after applying the SCAG to 405 soybean varieties over 2 consecutive years,we quantified various 3D traits,including canopy width,height,stem length,and average angle.After data filtering,we identified novel heritable and repeatable traits for evaluating soybean density tolerance potential,such as the ratio of average angle to height and the ratio of average angle to stem length,which showed greater potential than the well-known ratio of canopy width to height trait.Our work demonstrates remarkable advances in 3D phenotyping and plant architecture screening.The algorithm can be applied to other crops,such as maize and tomato.Our dataset,scripts,and software are public,which can further benefit the plant science community by enhancing plant architecture characterization and ideal variety selection.展开更多
Plant phenomics,the comprehensive study of plant phenotypes,has gained prominence as a vital tool for un-derstanding the intricate relationships between genotypes and the environment.Image-based plant phenomics has pr...Plant phenomics,the comprehensive study of plant phenotypes,has gained prominence as a vital tool for un-derstanding the intricate relationships between genotypes and the environment.Image-based plant phenomics has progressed rapidly,and three-dimensional(3D)phenotyping is a valuable extension of traditional 2D phe-nomics.However,the increased data dimensionality poses challenges to feature extraction and phenotyping.In recent decades,deep learning has led to remarkable progress in revolutionizing 3D phenotyping.Therefore,this review highlights the importance of using deep learning in 3D plant phenomics.It systematically overviews the capabilities of deep learning for 3D computer vision,covering 3D representation,classification,detection and tracking,semantic segmentation,instance segmentation,and generation.Additionally,deep learning techniques for 3D point preprocessing(e.g.,annotation,downsampling,and dataset organization)and various plant phe-notyping tasks are discussed.Finally,the challenges and perspectives associated with deep learning in 3D plant phenomics are summarized,including(1)benchmark dataset construction by using synthetic datasets and methods such as generative artificial intelligence and unsupervised or weakly supervised learning;(2)accurate and efficient 3D point cloud analysis by leveraging multitask learning,lightweight models,and self-supervised learning;and(3)deep learning for 3D plant phenomics by exploring interpretability,extensibility,and multi-modal data utilization.The exploration of deep learning in 3D plant phenomics is poised to spur breakthroughs in a new dimension of plant science.展开更多
基金funded by National Nature Science Foundation of China(NSFC)(Nos.51776010,and 91860205)the support from Collaborative Innovation Center of Advanced Aero-Engine,china。
文摘Accurate engine performance models are important for model-based performance evaluation of aero engine.The accuracy of the model often depends on engine component maps,so there is a need for a method that can accurately correct the component maps of the model over a wide range.In this paper,a new method for modifying component maps is proposed,this method combines the correction of the scaling factors with the solution process of the off-design working point,and uses the adjustment of the variable geometric parameters of the engine to change the position of the working line,in order to obtain more correction results and guarantee high accuracy in a wider range.The method is validated by taking the main fan of the Adaptive Cycle Engine(ACE),an ideal power unit for a new generation of multi-purpose and ultra-wide working range aircraft,as an example.The results show that the maximum error between the corrected component maps and the target maps is less than 1%.New possibility for more precise component maps can be realized in this paper.
基金supported in part by the Science and Technology Innovation 2030-Major Project(2023ZD04034)the Fundamental Research Funds for the Central Universities(KYCYXT2022017 and KYQN2023021)+6 种基金Hainan Yazhou Bay Seed Laboratory(B21HJ1005)Jiangsu Province Key Research and Development Program(BE2023369)the Natural Science Foundation of Jiangsu Province(BK20231469)the National Natural Science Foundation of China(32201656)J.Z.was supported by the Sanya Yazhou Bay Science and Technology City(SCKJ-JYRC-2022-20)J.Wu was supported by the HKU Seed Funding for Strategic Interdisciplinary Research Schemethe Innovation and Technology Fund(funding support to State Key Laboratories in Hong Kong of Agrobiotechnology)of the HKSA R,China.
文摘Three-dimensional(3D)phenotyping is important for studying plant structure and function.Light detection and ranging(LiDAR)has gained prominence in 3D plant phenotyping due to its ability to collect 3D point clouds.However,organ-level branch detection remains challenging due to small targets,sparse points,and low signal-to-noise ratios.In addition,extracting biologically relevant angle traits is difficult.In this study,we developed a stratified,clustered,and growing-based algorithm(SCAG)for soybean branch detection and branch angle calculation from LiDAR data,which is heuristic,open-source,and expandable.SCAG achieved high branch detection accuracy(F-score=0.77)and branch angle calculation accuracy(r=0.84)when evaluated on 152 diverse soybean varieties.Meanwhile,the SCAG outperformed 2 other classic algorithms,the support vector machine(F-score=0.53)and density-based methods(F-score=0.55).Moreover,after applying the SCAG to 405 soybean varieties over 2 consecutive years,we quantified various 3D traits,including canopy width,height,stem length,and average angle.After data filtering,we identified novel heritable and repeatable traits for evaluating soybean density tolerance potential,such as the ratio of average angle to height and the ratio of average angle to stem length,which showed greater potential than the well-known ratio of canopy width to height trait.Our work demonstrates remarkable advances in 3D phenotyping and plant architecture screening.The algorithm can be applied to other crops,such as maize and tomato.Our dataset,scripts,and software are public,which can further benefit the plant science community by enhancing plant architecture characterization and ideal variety selection.
基金supported in part by the STI 2030-Major Projects(2023ZD0405605)the Fundamental Research Funds for the Central Universities(KYT2024005,QTPY2025006)+6 种基金the National Natural Science Foundation of China(32201656)the Jiangsu Province Key Research and Development Program(BE2023369)the Natural Science Foundation of Jiangsu Province(BK20231469)the JBGS Project of Seed Industry Revitalization in Jiangsu Province(JBGS[2021]007)2025 AI for Graduate Education Program(2025AIYJSZX-YB031)the Jiangs Innovation Support Program for International Science and Technology Cooperation Project(BZ2023049)the Young Elite Scientists Sponsorship Program by CAST(YESS).
文摘Plant phenomics,the comprehensive study of plant phenotypes,has gained prominence as a vital tool for un-derstanding the intricate relationships between genotypes and the environment.Image-based plant phenomics has progressed rapidly,and three-dimensional(3D)phenotyping is a valuable extension of traditional 2D phe-nomics.However,the increased data dimensionality poses challenges to feature extraction and phenotyping.In recent decades,deep learning has led to remarkable progress in revolutionizing 3D phenotyping.Therefore,this review highlights the importance of using deep learning in 3D plant phenomics.It systematically overviews the capabilities of deep learning for 3D computer vision,covering 3D representation,classification,detection and tracking,semantic segmentation,instance segmentation,and generation.Additionally,deep learning techniques for 3D point preprocessing(e.g.,annotation,downsampling,and dataset organization)and various plant phe-notyping tasks are discussed.Finally,the challenges and perspectives associated with deep learning in 3D plant phenomics are summarized,including(1)benchmark dataset construction by using synthetic datasets and methods such as generative artificial intelligence and unsupervised or weakly supervised learning;(2)accurate and efficient 3D point cloud analysis by leveraging multitask learning,lightweight models,and self-supervised learning;and(3)deep learning for 3D plant phenomics by exploring interpretability,extensibility,and multi-modal data utilization.The exploration of deep learning in 3D plant phenomics is poised to spur breakthroughs in a new dimension of plant science.
