This study aimed to address the challenge of accurately and reliably detecting tomatoes in dense planting environments,a critical prerequisite for the automation implementation of robotic harvesting.However,the heavy ...This study aimed to address the challenge of accurately and reliably detecting tomatoes in dense planting environments,a critical prerequisite for the automation implementation of robotic harvesting.However,the heavy reliance on extensive manually annotated datasets for training deep learning models still poses significant limitations to their application in real-world agricultural production environments.To overcome these limitations,we employed domain adaptive learning approach combined with the YOLOv5 model to develop a novel tomato detection model called as TDA-YOLO(tomato detection domain adaptation).We designated the normal illumination scenes in dense planting environments as the source domain and utilized various other illumination scenes as the target domain.To construct bridge mechanism between source and target domains,neural preset for color style transfer is introduced to generate a pseudo-dataset,which served to deal with domain discrepancy.Furthermore,this study combines the semi-supervised learning method to enable the model to extract domain-invariant features more fully,and uses knowledge distillation to improve the model's ability to adapt to the target domain.Additionally,for purpose of promoting inference speed and low computational demand,the lightweight FasterNet network was integrated into the YOLOv5's C3 module,creating a modified C3_Faster module.The experimental results demonstrated that the proposed TDA-YOLO model significantly outperformed original YOLOv5s model,achieving a mAP(mean average precision)of 96.80%for tomato detection across diverse scenarios in dense planting environments,increasing by 7.19 percentage points;Compared with the latest YOLOv8 and YOLOv9,it is also 2.17 and 1.19 percentage points higher,respectively.The model's average detection time per image was an impressive 15 milliseconds,with a FLOPs(floating point operations per second)count of 13.8 G.After acceleration processing,the detection accuracy of the TDA-YOLO model on the Jetson Xavier NX development board is 90.95%,the mAP value is 91.35%,and the detection time of each image is 21 ms,which can still meet the requirements of real-time detection of tomatoes in dense planting environment.The experimental results show that the proposed TDA-YOLO model can accurately and quickly detect tomatoes in dense planting environment,and at the same time avoid the use of a large number of annotated data,which provides technical support for the development of automatic harvesting systems for tomatoes and other fruits.展开更多
Projection Pursuit (PP) model is a technique of falling high dimension. Real coding based on Accelerating Genetic Algorithm (RAGA) is a method of optimum. Through combining the PP model and RAGA, the paper applies the...Projection Pursuit (PP) model is a technique of falling high dimension. Real coding based on Accelerating Genetic Algorithm (RAGA) is a method of optimum. Through combining the PP model and RAGA, the paper applies the model in the water environment quality evaluation. The writer takes the water quality evaluated indexes of each sample as projection direction and turns high dimension data into low dimension projection value. Thus, the writer achieves on evaluating the grade of water samples and its optimum order. Based on this, the writer overcomes the jamming of weights calculated on fuzzy synthesize judge and gray system valuation. The paper can provide a new thought for water environment quality evaluation and other falling high dimension and optimum issue.展开更多
Virtual manufacturing is fast becoming an affordable technology with wide-ranging applications in modern manufacturing. Its advantages over existing technology are primarily that users can visualize, feel involvement ...Virtual manufacturing is fast becoming an affordable technology with wide-ranging applications in modern manufacturing. Its advantages over existing technology are primarily that users can visualize, feel involvement and interact with virtual representations of real world activities in real time. In this paper, a virtual cutting system is built which can simulate turning process, estimate tool wear and cutting force using artificial neural network etc. Using the simulated machining environment in virtual reality (VR), the user can practise and preview the operations for possible problems that might occur during implementation. This approach enables designers to evaluate and design feasible machining processes in a consistent manner as early as possible during the development process.展开更多
Expansive soil is sensitive to dry and wet environment change. And the volume deformation and inflation pressure of expansive soil may induce to cause the deformation failure of roadbed or many other adverse effects. ...Expansive soil is sensitive to dry and wet environment change. And the volume deformation and inflation pressure of expansive soil may induce to cause the deformation failure of roadbed or many other adverse effects. Aimed at a high-speed railway engineering practice in the newly built Yun-Gui high-speed railway expansive soil section in China, indoor vibration test on a full-scaled new cutting subgrade model is carried out. Based on the established track-subgrade-foundation of expansive soil system dynamic model test platform, dynamic behavior of new cutting subgrade structure under train loads coupling with extreme service environment(dry, raining, and groundwater level rising) is analyzed comparatively. The results show that the subgrade dynamic response is significantly influenced by service conditions and the dynamic response of subgrade gradually becomes stable with the increasing vibration times under various service environment conditions. The vertical dynamic soil stress is related with the depth in an approximate exponential function, and the curves of vertical dynamic soil stress present a "Z" shape distribution along transverse distance. The peak value of dynamic soil stress appears below the rail, and it increases more obviously near the roadbed surface. However, the peak value of dynamic soil stress is little affected outside 5.0 m of center line. The vibration velocity and acceleration are in a quadratic curve with an increase in depth, and the raining and groundwater level rising increase both the vibration velocity and the acceleration. The vertical deformations at different depths are differently affected by service environment in roadbed. The deformation of roadbed increases sharply when the water gets in the foundation of expansive soil, and more than 60% of the total deformation of roadbed occurs in expansive soil foundation. The laid waterproofing and drainage structure layer, which weakens the dynamic stress and improves the track regularity, presents a positive effect on the control deformation of roadbed surface. An improved empirical formula is then proposed to predict the dynamic stress of ballasted tracks subgrade of expansive soil.展开更多
A great number of visual simultaneous localization and mapping(VSLAM)systems need to assume static features in the environment.However,moving objects can vastly impair the performance of a VSLAM system which relies on...A great number of visual simultaneous localization and mapping(VSLAM)systems need to assume static features in the environment.However,moving objects can vastly impair the performance of a VSLAM system which relies on the static-world assumption.To cope with this challenging topic,a real-time and robust VSLAM system based on ORB-SLAM2 for dynamic environments was proposed.To reduce the influence of dynamic content,we incorporate the deep-learning-based object detection method in the visual odometry,then the dynamic object probability model is added to raise the efficiency of object detection deep neural network and enhance the real-time performance of our system.Experiment with both on the TUM and KITTI benchmark dataset,as well as in a real-world environment,the results clarify that our method can significantly reduce the tracking error or drift,enhance the robustness,accuracy and stability of the VSLAM system in dynamic scenes.展开更多
To solve the problem of stray interference to star point target identification while a star sensor imaging to the sky, a study on space luminous environment adaptability of missile-borne star sensor was carried out. B...To solve the problem of stray interference to star point target identification while a star sensor imaging to the sky, a study on space luminous environment adaptability of missile-borne star sensor was carried out. By Plank blackbody radiation law and some astronomic knowledge, irradiancies of the stray at the star sensor working height were estimated. By relative astrophysical and mathematics knowledge, included angles between the star sensor optical axis point and the stray at any moment were calculated. The calculation correctness was verified with the star map software of Stellarium. By combining the upper analysis with the baffle suppression effect, a real-time model for space luminous environment of missile-borne star sensor was proposed. By signal-noise rate （SNR） criterion, the adaptability of missile-borne star sensor to space luminous environment was studied. As an example, a certain type of star sensor was considered when imaging to the starry sky on June 22, 2011 （the Summer Solstice） and September 20, 2011 （August 23 of the lunar year, last quarter moon） in Beijing. The space luminous environment and the adaptability to it were simulated and analyzed at the star sensor working height. In each period of time, the stray suppression of the baffle is analyzed by comparing the calculated included angle between the star sensor optical axis point and the stray with the shielded provided by system index. When the included angle is larger than the shielded angle and less than 90~, the stray is restrained by the baffle. The stray effect on star point target identification is analyzed by comparing the irradiancy of 6 magnitude star with that of the stray on star sensor sensitization surface. When the irradiancy of 6 magnitude star is 5 times more than that of the stray, there is no effect on the star point target identification. The simulation results are identicat with the actual situation. The space luminous environment of the missile-borne star sensor can be estimated real-timely by this model. The adaptability of the star sensor to space luminous environment can be analyzed conveniently. A basis for determining the relative star sensor indexes, the navigation star chosen strategy and the missile launch window can be provided.展开更多
A brief review of the basic terminology on simulation, simulation life-cycle activities such as model-based activities, behavior-oriented activities, and quality assurance activities is given. Then, the challenges and...A brief review of the basic terminology on simulation, simulation life-cycle activities such as model-based activities, behavior-oriented activities, and quality assurance activities is given. Then, the challenges and opportunities for the advancement of the state-of-the-art in simulation environments are discussed under the following headings: modelling environments, simulation environments, mixed simulation environments, and comprehensive simulation environments.展开更多
Products are often subject to dynamic environmental conditions in field use.When stress transition occurs,products may be exposed to instantaneous shocks that result in shock damages to the products,causing a permanen...Products are often subject to dynamic environmental conditions in field use.When stress transition occurs,products may be exposed to instantaneous shocks that result in shock damages to the products,causing a permanent change of the degradation signals.Meanwhile,under some conditions,instantaneous shocks also lead to stress drift,causing a temporary change of the degradation signals.In this paper,a degradation model is proposed to assess the reliability and predict the residual lifetime of products operating in a dynamic environment considering shock damage and stress drift.The model is established based on a Wiener process which combines a stress-dependent degradation rate function,a shock damage function and a stress drift function in response to the dynamic environment.The shock damage function is established as a linear function of the stress transition start level and the stress level increment.The stress drift function is established as the difference value of a specified function at the stress transition start and end levels.A simulation study is presented to demonstrate the application of the model,and a case study for miniature light bulbs is used to validate the effectiveness of the proposed model.展开更多
In this paper, according to the rule of unbalanced sediment transport and the analysis of field data, different water diversion schemes were theoretically studied, including the erosion and sedimentation trend as well...In this paper, according to the rule of unbalanced sediment transport and the analysis of field data, different water diversion schemes were theoretically studied, including the erosion and sedimentation trend as well as their impacts on the environment of the middle and lower reaches of the Hanjiang River. The results showed that the 95×10 8m 3 water diversion scheme will cause less erosion and water level decrease than the 15×10 8m 3 water diversion scheme. Using a water diversion scheme of 95×10 8m 3, the decrease of water quantity can impact the river hydrodynamic regime substantially and the environments of the middle and lower reaches of the Hanjiang River will be greatly affected. It is therefore necessary to develop new water resources or build projects to meet the need of the environment and the needs for navigation.展开更多
Nowadays,crowded environment and high-speed life pace are likely to bring mental stress and fatigue to citizens.How to apply achievements of the restorative environment into urban planning and environmental design has...Nowadays,crowded environment and high-speed life pace are likely to bring mental stress and fatigue to citizens.How to apply achievements of the restorative environment into urban planning and environmental design has received more attention in recent years.Earlier research does not provide detailed information about the specific components of the physical environment that support restoration.This study explores which characteristics of the street environment and psychological factors of the street environment have an impact on subjective restoration.The streets were sampled from Shenzhen.Each street was represented by a single photo.The photo was quantified in terms of the different objective street components and also rated on psychological variables related to restoration.The rating on the psychological variables,being away,fascination,coherence,scope,the likelihood of restoration,and preference were provided by people of various ages and occupations.The results show that:1)the proportion of natural elements have the greatest impact on street restoration benefits and preference,and its impact is robust;2)the two characteristics of street safety and quiet are important to street restoration benefits and preferences;3)fascination and being away have a greater impact on restorative benefits of streets,followed by coherence,and the scope of the street has no significant effect on restorative benefits.The study could provide evidence for policy-makers and urban design and planning interventions.展开更多
基金The National Natural Science Foundation of China (32371993)The Natural Science Research Key Project of Anhui Provincial University(2022AH040125&2023AH040135)The Key Research and Development Plan of Anhui Province (202204c06020022&2023n06020057)。
文摘This study aimed to address the challenge of accurately and reliably detecting tomatoes in dense planting environments,a critical prerequisite for the automation implementation of robotic harvesting.However,the heavy reliance on extensive manually annotated datasets for training deep learning models still poses significant limitations to their application in real-world agricultural production environments.To overcome these limitations,we employed domain adaptive learning approach combined with the YOLOv5 model to develop a novel tomato detection model called as TDA-YOLO(tomato detection domain adaptation).We designated the normal illumination scenes in dense planting environments as the source domain and utilized various other illumination scenes as the target domain.To construct bridge mechanism between source and target domains,neural preset for color style transfer is introduced to generate a pseudo-dataset,which served to deal with domain discrepancy.Furthermore,this study combines the semi-supervised learning method to enable the model to extract domain-invariant features more fully,and uses knowledge distillation to improve the model's ability to adapt to the target domain.Additionally,for purpose of promoting inference speed and low computational demand,the lightweight FasterNet network was integrated into the YOLOv5's C3 module,creating a modified C3_Faster module.The experimental results demonstrated that the proposed TDA-YOLO model significantly outperformed original YOLOv5s model,achieving a mAP(mean average precision)of 96.80%for tomato detection across diverse scenarios in dense planting environments,increasing by 7.19 percentage points;Compared with the latest YOLOv8 and YOLOv9,it is also 2.17 and 1.19 percentage points higher,respectively.The model's average detection time per image was an impressive 15 milliseconds,with a FLOPs(floating point operations per second)count of 13.8 G.After acceleration processing,the detection accuracy of the TDA-YOLO model on the Jetson Xavier NX development board is 90.95%,the mAP value is 91.35%,and the detection time of each image is 21 ms,which can still meet the requirements of real-time detection of tomatoes in dense planting environment.The experimental results show that the proposed TDA-YOLO model can accurately and quickly detect tomatoes in dense planting environment,and at the same time avoid the use of a large number of annotated data,which provides technical support for the development of automatic harvesting systems for tomatoes and other fruits.
文摘Projection Pursuit (PP) model is a technique of falling high dimension. Real coding based on Accelerating Genetic Algorithm (RAGA) is a method of optimum. Through combining the PP model and RAGA, the paper applies the model in the water environment quality evaluation. The writer takes the water quality evaluated indexes of each sample as projection direction and turns high dimension data into low dimension projection value. Thus, the writer achieves on evaluating the grade of water samples and its optimum order. Based on this, the writer overcomes the jamming of weights calculated on fuzzy synthesize judge and gray system valuation. The paper can provide a new thought for water environment quality evaluation and other falling high dimension and optimum issue.
文摘Virtual manufacturing is fast becoming an affordable technology with wide-ranging applications in modern manufacturing. Its advantages over existing technology are primarily that users can visualize, feel involvement and interact with virtual representations of real world activities in real time. In this paper, a virtual cutting system is built which can simulate turning process, estimate tool wear and cutting force using artificial neural network etc. Using the simulated machining environment in virtual reality (VR), the user can practise and preview the operations for possible problems that might occur during implementation. This approach enables designers to evaluate and design feasible machining processes in a consistent manner as early as possible during the development process.
基金Projects(51478484,51308551,51678571)supported by the National Natural Science Foundation of ChinaProject(2016zzts063)supported by Fundamental Research Funds for the Central Universities,China
文摘Expansive soil is sensitive to dry and wet environment change. And the volume deformation and inflation pressure of expansive soil may induce to cause the deformation failure of roadbed or many other adverse effects. Aimed at a high-speed railway engineering practice in the newly built Yun-Gui high-speed railway expansive soil section in China, indoor vibration test on a full-scaled new cutting subgrade model is carried out. Based on the established track-subgrade-foundation of expansive soil system dynamic model test platform, dynamic behavior of new cutting subgrade structure under train loads coupling with extreme service environment(dry, raining, and groundwater level rising) is analyzed comparatively. The results show that the subgrade dynamic response is significantly influenced by service conditions and the dynamic response of subgrade gradually becomes stable with the increasing vibration times under various service environment conditions. The vertical dynamic soil stress is related with the depth in an approximate exponential function, and the curves of vertical dynamic soil stress present a "Z" shape distribution along transverse distance. The peak value of dynamic soil stress appears below the rail, and it increases more obviously near the roadbed surface. However, the peak value of dynamic soil stress is little affected outside 5.0 m of center line. The vibration velocity and acceleration are in a quadratic curve with an increase in depth, and the raining and groundwater level rising increase both the vibration velocity and the acceleration. The vertical deformations at different depths are differently affected by service environment in roadbed. The deformation of roadbed increases sharply when the water gets in the foundation of expansive soil, and more than 60% of the total deformation of roadbed occurs in expansive soil foundation. The laid waterproofing and drainage structure layer, which weakens the dynamic stress and improves the track regularity, presents a positive effect on the control deformation of roadbed surface. An improved empirical formula is then proposed to predict the dynamic stress of ballasted tracks subgrade of expansive soil.
基金the National Natural Science Foundation of China(No.61671470).
文摘A great number of visual simultaneous localization and mapping(VSLAM)systems need to assume static features in the environment.However,moving objects can vastly impair the performance of a VSLAM system which relies on the static-world assumption.To cope with this challenging topic,a real-time and robust VSLAM system based on ORB-SLAM2 for dynamic environments was proposed.To reduce the influence of dynamic content,we incorporate the deep-learning-based object detection method in the visual odometry,then the dynamic object probability model is added to raise the efficiency of object detection deep neural network and enhance the real-time performance of our system.Experiment with both on the TUM and KITTI benchmark dataset,as well as in a real-world environment,the results clarify that our method can significantly reduce the tracking error or drift,enhance the robustness,accuracy and stability of the VSLAM system in dynamic scenes.
文摘To solve the problem of stray interference to star point target identification while a star sensor imaging to the sky, a study on space luminous environment adaptability of missile-borne star sensor was carried out. By Plank blackbody radiation law and some astronomic knowledge, irradiancies of the stray at the star sensor working height were estimated. By relative astrophysical and mathematics knowledge, included angles between the star sensor optical axis point and the stray at any moment were calculated. The calculation correctness was verified with the star map software of Stellarium. By combining the upper analysis with the baffle suppression effect, a real-time model for space luminous environment of missile-borne star sensor was proposed. By signal-noise rate （SNR） criterion, the adaptability of missile-borne star sensor to space luminous environment was studied. As an example, a certain type of star sensor was considered when imaging to the starry sky on June 22, 2011 （the Summer Solstice） and September 20, 2011 （August 23 of the lunar year, last quarter moon） in Beijing. The space luminous environment and the adaptability to it were simulated and analyzed at the star sensor working height. In each period of time, the stray suppression of the baffle is analyzed by comparing the calculated included angle between the star sensor optical axis point and the stray with the shielded provided by system index. When the included angle is larger than the shielded angle and less than 90~, the stray is restrained by the baffle. The stray effect on star point target identification is analyzed by comparing the irradiancy of 6 magnitude star with that of the stray on star sensor sensitization surface. When the irradiancy of 6 magnitude star is 5 times more than that of the stray, there is no effect on the star point target identification. The simulation results are identicat with the actual situation. The space luminous environment of the missile-borne star sensor can be estimated real-timely by this model. The adaptability of the star sensor to space luminous environment can be analyzed conveniently. A basis for determining the relative star sensor indexes, the navigation star chosen strategy and the missile launch window can be provided.
文摘A brief review of the basic terminology on simulation, simulation life-cycle activities such as model-based activities, behavior-oriented activities, and quality assurance activities is given. Then, the challenges and opportunities for the advancement of the state-of-the-art in simulation environments are discussed under the following headings: modelling environments, simulation environments, mixed simulation environments, and comprehensive simulation environments.
基金supported by the National Natural Science Foundation of China(NSFC71601009)the Technical Foundation Program from the Ministry of Industry and Information Technology of China(JSZL2015601B010)
文摘Products are often subject to dynamic environmental conditions in field use.When stress transition occurs,products may be exposed to instantaneous shocks that result in shock damages to the products,causing a permanent change of the degradation signals.Meanwhile,under some conditions,instantaneous shocks also lead to stress drift,causing a temporary change of the degradation signals.In this paper,a degradation model is proposed to assess the reliability and predict the residual lifetime of products operating in a dynamic environment considering shock damage and stress drift.The model is established based on a Wiener process which combines a stress-dependent degradation rate function,a shock damage function and a stress drift function in response to the dynamic environment.The shock damage function is established as a linear function of the stress transition start level and the stress level increment.The stress drift function is established as the difference value of a specified function at the stress transition start and end levels.A simulation study is presented to demonstrate the application of the model,and a case study for miniature light bulbs is used to validate the effectiveness of the proposed model.
文摘In this paper, according to the rule of unbalanced sediment transport and the analysis of field data, different water diversion schemes were theoretically studied, including the erosion and sedimentation trend as well as their impacts on the environment of the middle and lower reaches of the Hanjiang River. The results showed that the 95×10 8m 3 water diversion scheme will cause less erosion and water level decrease than the 15×10 8m 3 water diversion scheme. Using a water diversion scheme of 95×10 8m 3, the decrease of water quantity can impact the river hydrodynamic regime substantially and the environments of the middle and lower reaches of the Hanjiang River will be greatly affected. It is therefore necessary to develop new water resources or build projects to meet the need of the environment and the needs for navigation.
文摘Nowadays,crowded environment and high-speed life pace are likely to bring mental stress and fatigue to citizens.How to apply achievements of the restorative environment into urban planning and environmental design has received more attention in recent years.Earlier research does not provide detailed information about the specific components of the physical environment that support restoration.This study explores which characteristics of the street environment and psychological factors of the street environment have an impact on subjective restoration.The streets were sampled from Shenzhen.Each street was represented by a single photo.The photo was quantified in terms of the different objective street components and also rated on psychological variables related to restoration.The rating on the psychological variables,being away,fascination,coherence,scope,the likelihood of restoration,and preference were provided by people of various ages and occupations.The results show that:1)the proportion of natural elements have the greatest impact on street restoration benefits and preference,and its impact is robust;2)the two characteristics of street safety and quiet are important to street restoration benefits and preferences;3)fascination and being away have a greater impact on restorative benefits of streets,followed by coherence,and the scope of the street has no significant effect on restorative benefits.The study could provide evidence for policy-makers and urban design and planning interventions.
