The growing global competition compels manufacturing organizations to engage themselves in all productivity improvement activities. In this direction, the consideration of mixed-model assembly line balancing problem a...The growing global competition compels manufacturing organizations to engage themselves in all productivity improvement activities. In this direction, the consideration of mixed-model assembly line balancing problem and implementing in industries plays a major role in improving organizational productivity. In this paper, the mixed model assembly line balancing problem with deterministic task times is considered. The authors made an attempt to develop a genetic algorithm for realistic design of the mixed-model assembly line balancing problem. The design is made using the originnal task times of the models, which is a realistic approach. Then, it is compared with the generally perceived design of the mixed-model assembly line balancing problem.展开更多
Microorganisms can colonize the surface of microplastics(MPs)to form a distinctive microbiome,known as a“plastisphere”which is regarded as an anthropogenic niche for microbial growth.However,bacterial community asse...Microorganisms can colonize the surface of microplastics(MPs)to form a distinctive microbiome,known as a“plastisphere”which is regarded as an anthropogenic niche for microbial growth.However,bacterial community assembly in virgin and aging MP plastispheres across different habitats is poorly understood.This study aims to assess the variations in bacterial community assembly across different niches and habitats with an in situ ex-periment,in which constructed forest wetland(FW),natural lake wetland(LW),and lotus pond wetland(LP)were habitats,and plastispheres of virgin and aging low-density polyethylene(LDPE)MPs,as well as surround-ing wetland soils were niches.Significant niche-related differences in bacterial communities were observed,with lower diversity and enrichment of potential plastic-degrading bacteria in the plastisphere than in the soil bacterial communities.Furthermore,habitat-related differences exerted a more pronounced influence on the beta-diversity patterns of the bacterial communities.The linear regression analyses indicated that the local species pool con-tributed more to bacterial community assembly in the LW wetland,whereas the relative abundance of species was the primary factor in the LP wetland.The null model analysis indicated that plastisphere bacterial communi-ties were predominantly driven by the stochastic process,with a more deterministic assembly observed in the LP wetland and soil bacterial communities.Additionally,the primary ecological process shaping plastisphere com-munities shifted from drift in the virgin LDPE to homogenising dispersal in the aging LDPE.This study provides new insights into the fate and ecological impacts of MPs in wetlands,thereby facilitating the effective regulations of plastic pollution.展开更多
Transformer-based models have significantly advanced binary code similarity detection(BCSD)by leveraging their semantic encoding capabilities for efficient function matching across diverse compilation settings.Althoug...Transformer-based models have significantly advanced binary code similarity detection(BCSD)by leveraging their semantic encoding capabilities for efficient function matching across diverse compilation settings.Although adversarial examples can strategically undermine the accuracy of BCSD models and protect critical code,existing techniques predominantly depend on inserting artificial instructions,which incur high computational costs and offer limited diversity of perturbations.To address these limitations,we propose AIMA,a novel gradient-guided assembly instruction relocation method.Our method decouples the detection model into tokenization,embedding,and encoding layers to enable efficient gradient computation.Since token IDs of instructions are discrete and nondifferentiable,we compute gradients in the continuous embedding space to evaluate the influence of each token.The most critical tokens are identified by calculating the L2 norm of their embedding gradients.We then establish a mapping between instructions and their corresponding tokens to aggregate token-level importance into instructionlevel significance.To maximize adversarial impact,a sliding window algorithm selects the most influential contiguous segments for relocation,ensuring optimal perturbation with minimal length.This approach efficiently locates critical code regions without expensive search operations.The selected segments are relocated outside their original function boundaries via a jump mechanism,which preserves runtime control flow and functionality while introducing“deletion”effects in the static instruction sequence.Extensive experiments show that AIMA reduces similarity scores by up to 35.8%in state-of-the-art BCSD models.When incorporated into training data,it also enhances model robustness,achieving a 5.9%improvement in AUROC.展开更多
Aircraft assembly is characterized by stringent precedence constraints,limited resource availability,spatial restrictions,and a high degree of manual intervention.These factors lead to considerable variability in oper...Aircraft assembly is characterized by stringent precedence constraints,limited resource availability,spatial restrictions,and a high degree of manual intervention.These factors lead to considerable variability in operator workloads and significantly increase the complexity of scheduling.To address this challenge,this study investigates the Aircraft Pulsating Assembly Line Scheduling Problem(APALSP)under skilled operator allocation,with the objective of minimizing assembly completion time.A mathematical model considering skilled operator allocation is developed,and a Q-Learning improved Particle Swarm Optimization algorithm(QLPSO)is proposed.In the algorithm design,a reverse scheduling strategy is adopted to effectively manage large-scale precedence constraints.Moreover,a reverse sequence encoding method is introduced to generate operation sequences,while a time decoding mechanism is employed to determine completion times.The problem is further reformulated as a Markov Decision Process(MDP)with explicitly defined state and action spaces.Within QLPSO,the Q-learning mechanism adaptively adjusts inertia weights and learning factors,thereby achieving a balance between exploration capability and convergence performance.To validate the effectiveness of the proposed approach,extensive computational experiments are conducted on benchmark instances of different scales,including small,medium,large,and ultra-large cases.The results demonstrate that QLPSO consistently delivers stable and high-quality solutions across all scenarios.In ultra-large-scale instances,it improves the best solution by 25.2%compared with the Genetic Algorithm(GA)and enhances the average solution by 16.9%over the Q-learning algorithm,showing clear advantages over the comparative methods.These findings not only confirm the effectiveness of the proposed algorithm but also provide valuable theoretical references and practical guidance for the intelligent scheduling optimization of aircraft pulsating assembly lines.展开更多
Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone t...Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone to errors and lacks consistency,emphasizing the need for a reliable and automated inspection system.Leveraging both object detection and image segmentation approaches,this research proposes a vision-based solution for the detection of various kinds of tools in the toolkit using deep learning(DL)models.Two Intel RealSense D455f depth cameras were arranged in a top down configuration to capture both RGB and depth images of the toolkits.After applying multiple constraints and enhancing them through preprocessing and augmentation,a dataset consisting of 3300 annotated RGB-D photos was generated.Several DL models were selected through a comprehensive assessment of mean Average Precision(mAP),precision-recall equilibrium,inference latency(target≥30 FPS),and computational burden,resulting in a preference for YOLO and Region-based Convolutional Neural Networks(R-CNN)variants over ViT-based models due to the latter’s increased latency and resource requirements.YOLOV5,YOLOV8,YOLOV11,Faster R-CNN,and Mask R-CNN were trained on the annotated dataset and evaluated using key performance metrics(Recall,Accuracy,F1-score,and Precision).YOLOV11 demonstrated balanced excellence with 93.0%precision,89.9%recall,and a 90.6%F1-score in object detection,as well as 96.9%precision,95.3%recall,and a 96.5%F1-score in instance segmentation with an average inference time of 25 ms per frame(≈40 FPS),demonstrating real-time performance.Leveraging these results,a YOLOV11-based windows application was successfully deployed in a real-time assembly line environment,where it accurately processed live video streams to detect and segment tools within toolkits,demonstrating its practical effectiveness in industrial automation.The application is capable of precisely measuring socket dimensions by utilising edge detection techniques on YOLOv11 segmentation masks,in addition to detection and segmentation.This makes it possible to do specification-level quality control right on the assembly line,which improves the ability to examine things in real time.The implementation is a big step forward for intelligent manufacturing in the Industry 4.0 paradigm.It provides a scalable,efficient,and accurate way to do automated inspection and dimensional verification activities.展开更多
In-house part supply affects the efficiency of mixed-model assembly lines considerably. Hence, we propose a reliable Just-In-Time part supply strategy with the use of decentralized supermarkets. For a given production...In-house part supply affects the efficiency of mixed-model assembly lines considerably. Hence, we propose a reliable Just-In-Time part supply strategy with the use of decentralized supermarkets. For a given production sequence and line layout, the proposed strategy schedules tow train routing and delivery problems jointly to minimize the number of employed town trains and the traveling time, while ensuring that stations never run out of parts. To solve this problem, a mathematical formulation is proposed for each sub-problem aiming at minimizing supply cost. Then, a dynamic programming algorithm for routing and a greedy algorithm for delivery are developed, both of which are of polynomial runtime. Finally, a computational study is implemented to validate the effectiveness of the strategy, and to investigate the effects of the delivery capacity of tow trains and storage capacity of stations on supply cost.展开更多
This paper studies the parameter design and the performance optimization of a Kanban system without stockouts in a multi-stage, mixed-model assembly line. The model of a Kanban system based on production processes is ...This paper studies the parameter design and the performance optimization of a Kanban system without stockouts in a multi-stage, mixed-model assembly line. The model of a Kanban system based on production processes is established by examining the relationship among the set-up time, the amount of work in process （WIP）, the capacity indicated by a Kanban, and the takt-time ratio. A novel method for optimizing performance on the premise of no stockouts is proposed. Empirical results show that the amount of WIP is reduced remarkably after optimization.展开更多
To solve the sequencing problem in mixed-model flexible assembly lines (MMFALs) with variable launching intervals, a mathematical model aiming to minimize the cost of utility and idle times is developed. To obtain hig...To solve the sequencing problem in mixed-model flexible assembly lines (MMFALs) with variable launching intervals, a mathematical model aiming to minimize the cost of utility and idle times is developed. To obtain high-quality sequences, an advanced scatter search (ASS) algorithm is proposed. A heuristic approach, i.e. launching intervals between products algorithm (LIBPA), is incorporated into the ASS algorithm to solve the launching interval problem for each sequence. Numerical experiments with different scales are conducted to compare the performance of ASS with genetic algorithm (GA). In addition, we compare the cost of variable launching intervals approach with fixed launching intervals approach. The results indicate that the ASS is efficient and effective, and considering variable launching intervals in mixed-model assembly lines (MMALs) sequencing problem can improve the performance of the line.展开更多
Material handling has become one of the major challenges in modern production management.Consequently,this paper intends to investigate the part delivery of mixedmodel assembly lines with decentralized supermarkets an...Material handling has become one of the major challenges in modern production management.Consequently,this paper intends to investigate the part delivery of mixedmodel assembly lines with decentralized supermarkets and tow trains.Besides,uncertain exception disturbances,including tow train failures and adjustments of the production sequence,are also considered.To solve this problem,a heuristic-based dynamic delivery strategy is proposed,which dynamically schedules the route,departure time,quantities and types of loaded parts for each tour.To evaluate the performance of this strategy,it is used to solve an instance in comparison with the periodic delivery strategy,experimental results are reported and their performances are compared under different metrics.Moreover,a multi-scenario analysis is employed to determinate the long-term decisions,including the number of tow trains and the route layout.Finally,the critical storage is suggested to be set for each station to avoid part starvation resulting from disturbances,and its effect on the delivery performance is investigated.展开更多
Juglans sigillata is an economically valuable nut crop renowned for its nutritional richness,including essential nutrients,antioxidants,and healthy fats,which boost human cardial,brain and gut health.Despite its impor...Juglans sigillata is an economically valuable nut crop renowned for its nutritional richness,including essential nutrients,antioxidants,and healthy fats,which boost human cardial,brain and gut health.Despite its importance,the lack of a complete genome assembly has been a stumbling block in its biological breeding process.Therefore,we generated deep coverage ultralong Oxford Nanopore Technology(ONT)and PacBio HiFi reads to construct a telomere-to-telomere(T2T)genome assembly.The final assembly spans 537.27 Mb with no gaps,demonstrating a remarkable completeness of 98.1%.We utilized a combination of transcriptome data and homologous proteins to annotate the genome,identifying 36018 protein-coding genes.Furthermore,we profiled global cytosine DNA methylations using ONT sequencing data.Global methylome analysis revealed high methylation levels in transposable element(TE)-rich chromosomal regions juxtaposed with comparatively lower methylation in gene-rich areas.By integrating a detailed multi-omics data analysis,we obtained valuable insights into the mechanism underlying endopleura coloration.This investigation led to the identification of eight candidate genes(e.g.ANR)involved in anthocyanin biosynthesis pathways,which are crucial for the development of color in plants.The comprehensive genome assembly and the understanding of the genetic basis of important traits like endopleura coloration will open avenues for more efficient breeding programs and improved crop quality.展开更多
The application of photocatalytic technology in algae killing is limited by the non-floatability and difficulty in recycling of the photocatalysts.Loading photocatalyst on magnetic or floatable carriers is the most po...The application of photocatalytic technology in algae killing is limited by the non-floatability and difficulty in recycling of the photocatalysts.Loading photocatalyst on magnetic or floatable carriers is the most popular method for overcoming the above inadequacies.In this work,a CdZnS/TiO_(2) membrane photocatalyst with adjustable suspended depth(include floating)and flexible assembly is designed,which is less prone to dislodgement due to in situ synthesis and has a wider range of applicability than previously reported photocatalysts.The photocatalytic removal of Microcystis aeruginosa revealed that the suspended depth and distribution format of the CdZnS/TiO_(2) membrane photocatalysts have striking effects on the photocatalytic removal performance of Microcystis aeruginosa,the photocatalytic removal efficiency of CdZnS/TiO_(2)-2 membrane photocatalysts for Microcystis aeruginosa could reach to 98.6%in 60 min when the photocatalysts assembled in the form of 3×3 arrays suspended at a depth of 2 cm from the liquid surface.A tiny amount of TiO_(2) loading allows the formation of Z-Scheme heterojunction,resulting in accelerating the separation efficiency of photogenerated carriers,preserving the photogenerated electrons and holes with stronger reduction and oxidation ability and inhabiting the photo-corrosion of CdZnS.展开更多
Membrane electrode assembly(MEA)is widely considered to be the most promising type of electrolyzer for the practical application of electrochemical CO_(2) reduction reaction(CO_(2)RR).In MEAs,a square-shaped cross-sec...Membrane electrode assembly(MEA)is widely considered to be the most promising type of electrolyzer for the practical application of electrochemical CO_(2) reduction reaction(CO_(2)RR).In MEAs,a square-shaped cross-section in the flow channel is normally adopted,the configuration optimization of which could potentially enhance the performance of the electrolyzer.This paper describes the numerical simulation study on the impact of the flow-channel cross-section shapes in the MEA electrolyzer for CO_(2)RR.The results show that wide flow channels with low heights are beneficial to the CO_(2)RR by providing a uniform flow field of CO_(2),especially at high current densities.Moreover,the larger the electrolyzer,the more significant the effect is.This study provides a theoretical basis for the design of high-performance MEA electrolyzers for CO_(2)RR.展开更多
A unitized regenerative fuel cell(URFC)is a device that may function reversibly as either a fuel cell(FC)or water elec-trolysis(WE).An important component of this device is the Membrane electrode assembly(MEA).Therefo...A unitized regenerative fuel cell(URFC)is a device that may function reversibly as either a fuel cell(FC)or water elec-trolysis(WE).An important component of this device is the Membrane electrode assembly(MEA).Therefore,this study aimed to compare the performance outcomes of MEA using electrodes with single and three catalyst layers.This study measured Electrochemical Surface Area(ECSA),Electrochemical Impedance Spectroscopy(EIS),X-ray Diffraction analysis(XRD),and X-ray Fluorescence(XRF).Furthermore,the round-trip efficiency(RTE)of the MEA,as w ell as the performance in FC and WE mode,was measured.In comparison,The ECSA values of Pt-Ru/C and Pt/C with three catalyst layers were higher than the single catalyst layer.This result was supported by electrode characterization data for XRD and XRF.The respective electrical conductivity values of Pt-Ru/C and Pt/C with three catalyst layers are also higher than the single cata-lyst layer,and the performance of URFC using MEA with three catalyst layers has the highest value of RTE among the MEA performances of URFC,which is 100%at a current density of 4 mA·cm-2.展开更多
Assembly precision greatly influences the performance of complex high-end equipment.The traditional industrial assembly process and deviation transfer are implicit and uncertain,causing problems like poor component fi...Assembly precision greatly influences the performance of complex high-end equipment.The traditional industrial assembly process and deviation transfer are implicit and uncertain,causing problems like poor component fit and hard-to-trace assembly stress concentration.Assemblers can only check whether the dimensional tolerance of the component design is exceeded step by step in combination with prior knowledge.Inversion in industrial assembly optimizes assembly and design by comparing real and theoretical results and doing inversion analysis to reduce assembly deviation.The digital twin(DT)technology visualizes and predicts the assembly process by mapping real and virtual model parameters and states simultaneously,expanding parameter range for inversion analysis and improving inversion result accuracy.Problems in improving industrial assembly precision and the significance and research status of DT-driven parametric inversion of assembly tools,processes and object precision are summarized.It analyzes vital technologies for assembly precision inversion such as multi-attribute assembly process parameter sensing,virtual modeling of high-fidelity assembly systems,twin synchronization of assembly process data models,multi-physical field simulation,and performance twin model construction of the assembly process.Combined with human-cyber-physical system,augmented reality,and generative intelligence,the outlook of DT-driven assembly precision inversion is proposed,providing support for DT's use in industrial assembly and precision improvement.展开更多
As the demands for assembly quality and efficiency increase,robot-assisted assembly applications are becoming more widespread.Peg-in-hole assembly,as a typical form of assembly,has been widely researched by scholars.C...As the demands for assembly quality and efficiency increase,robot-assisted assembly applications are becoming more widespread.Peg-in-hole assembly,as a typical form of assembly,has been widely researched by scholars.Currently,robotic peg-in-hole assembly faces challenges such as complex analysis of part contact forces,difficulties in task modeling,and the failure of traditional strategies.Simply controlling the position of the robot's end effector cannot achieve high precision,high efficiency peg-in-hole assembly.Flexible assembly,especially intelligent flexible assembly,is becoming the future development trend.So there is a lack of comprehensive reviews on robotic flexible peg-in-hole assembly.This paper first outlines the basic components of peg-in-hole assembly and summarizes the two basic operational processes of peg-in-hole assembly,along with their related theoretical foundations.We then review and analyze the research on passive compliant assembly,active compliant assembly,and intelligent flexible assembly.Finally,it presents an outlook on the future development directions of robotic peg-in-hole assembly.展开更多
To address the challenges of insufficient visualization in the industrial robot assembly operation system and the limitation of visualizing only geometric attributes of physical properties,a method is proposed for con...To address the challenges of insufficient visualization in the industrial robot assembly operation system and the limitation of visualizing only geometric attributes of physical properties,a method is proposed for constructing an industrial robot assembly system based on virtual reality technology.Focusing on the shaft hole assembly,the mechanical characteristics of the industrial robot shaft hole assembly process are analyzed and a dynamic model is established for shaft hole assembly operations.The key elements of virtual assembly operations for industrial robots are summarized and a five-dimensional model is proposed for industrial robot virtual operations.Utilizing the Unity3D engine based on the 5-D model for industrial robot virtual operations,an industrial robot shaft hole assembly system is developed.This system enables virtual assembly operations,displays physical attributes,and provides valuable references for the research of virtual systems.展开更多
Molecular recognition of fullerene using various host compounds is well-known in literature.But most studies focus on host-vip complexation in solution using host compounds with a single binding cavity.Herein,we rep...Molecular recognition of fullerene using various host compounds is well-known in literature.But most studies focus on host-vip complexation in solution using host compounds with a single binding cavity.Herein,we report a series of highly preorganized janusarene derivatives with homoditopic binding sites.These novel janusarenes can bind and align various fullerenes such as C_(60),C_(70),C_(84),and Gd@C_(82)in a highly efficient manner.Robust shape complementary association and assembly are observed in solution,in the bulk solid state,in the liquid crystalline state,or on surface,and the assembled structures are characterized by nuclear magnetic resonance(NMR)titration,X-ray diffraction,polarized optical microscopy,and scanning tunneling microscopy.展开更多
Despite the gradual transformation of traditional manufacturing by the Human-Robot Collaboration Assembly(HRCA),challenges remain in the robot’s ability to understand and predict human assembly intentions.This study ...Despite the gradual transformation of traditional manufacturing by the Human-Robot Collaboration Assembly(HRCA),challenges remain in the robot’s ability to understand and predict human assembly intentions.This study aims to enhance the robot’s comprehension and prediction capabilities of operator assembly intentions by capturing and analyzing operator behavior and movements.We propose a video feature extraction method based on the Temporal Shift Module Network(TSM-ResNet50)to extract spatiotemporal features from assembly videos and differentiate various assembly actions using feature differences between video frames.Furthermore,we construct an action recognition and segmentation model based on the Refined-Multi-Scale Temporal Convolutional Network(Refined-MS-TCN)to identify assembly action intervals and accurately acquire action categories.Experiments on our self-built reducer assembly action dataset demonstrate that our network can classify assembly actions frame by frame,achieving an accuracy rate of 83%.Additionally,we develop a HiddenMarkovModel(HMM)integrated with assembly task constraints to predict operator assembly intentions based on the probability transition matrix and assembly task constraints.The experimental results show that our method for predicting operator assembly intentions can achieve an accuracy of 90.6%,which is a 13.3%improvement over the HMM without task constraints.展开更多
Scratch damage can reduce both the aesthetic appearance and structural integrity of polymer surfaces.To optimize and enhance the scratch resistance of polycarbonate,this study investigates the influence of assembly pr...Scratch damage can reduce both the aesthetic appearance and structural integrity of polymer surfaces.To optimize and enhance the scratch resistance of polycarbonate,this study investigates the influence of assembly pre-tensile and pre-compressive stresses,with scratch experiments being conducted under both linearly increasing and constant normal load modes.Experimental results and finite element simulations are used to analyze scratch resistance and visibility.The results indicate that the application of 20%pre-compressive stress increases the critical normal load for onset of scratch visibility by 42%compared with the case in which no assembly pre-stress is applied,and it effectively decreases residual scratch depth,shoulder height,shoulder width,and tangential load.This is because assembly pre-compressive stress can effectively counteract the extrusion of material at the front and sides caused by the sliding scratch tip.Pre-compressive stress hinders scratch groove formation,improving the scratch resistance of polycarbonate.By contrast,pre-tensile stress weakens these characteristics.This study provides valuable insights for enhancing the surface damage resistance of polycarbonate materials.展开更多
文摘The growing global competition compels manufacturing organizations to engage themselves in all productivity improvement activities. In this direction, the consideration of mixed-model assembly line balancing problem and implementing in industries plays a major role in improving organizational productivity. In this paper, the mixed model assembly line balancing problem with deterministic task times is considered. The authors made an attempt to develop a genetic algorithm for realistic design of the mixed-model assembly line balancing problem. The design is made using the originnal task times of the models, which is a realistic approach. Then, it is compared with the generally perceived design of the mixed-model assembly line balancing problem.
基金supported by Shanghai Municipal Natural Science Foundation,China(No.21ZR1446800)the National Natural Science Foundation of China(No.41877425)the Fundamental Research Funds for the Central Universities(No.226-2024-00052)。
文摘Microorganisms can colonize the surface of microplastics(MPs)to form a distinctive microbiome,known as a“plastisphere”which is regarded as an anthropogenic niche for microbial growth.However,bacterial community assembly in virgin and aging MP plastispheres across different habitats is poorly understood.This study aims to assess the variations in bacterial community assembly across different niches and habitats with an in situ ex-periment,in which constructed forest wetland(FW),natural lake wetland(LW),and lotus pond wetland(LP)were habitats,and plastispheres of virgin and aging low-density polyethylene(LDPE)MPs,as well as surround-ing wetland soils were niches.Significant niche-related differences in bacterial communities were observed,with lower diversity and enrichment of potential plastic-degrading bacteria in the plastisphere than in the soil bacterial communities.Furthermore,habitat-related differences exerted a more pronounced influence on the beta-diversity patterns of the bacterial communities.The linear regression analyses indicated that the local species pool con-tributed more to bacterial community assembly in the LW wetland,whereas the relative abundance of species was the primary factor in the LP wetland.The null model analysis indicated that plastisphere bacterial communi-ties were predominantly driven by the stochastic process,with a more deterministic assembly observed in the LP wetland and soil bacterial communities.Additionally,the primary ecological process shaping plastisphere com-munities shifted from drift in the virgin LDPE to homogenising dispersal in the aging LDPE.This study provides new insights into the fate and ecological impacts of MPs in wetlands,thereby facilitating the effective regulations of plastic pollution.
基金supported by Key Laboratory of Cyberspace Security,Ministry of Education,China。
文摘Transformer-based models have significantly advanced binary code similarity detection(BCSD)by leveraging their semantic encoding capabilities for efficient function matching across diverse compilation settings.Although adversarial examples can strategically undermine the accuracy of BCSD models and protect critical code,existing techniques predominantly depend on inserting artificial instructions,which incur high computational costs and offer limited diversity of perturbations.To address these limitations,we propose AIMA,a novel gradient-guided assembly instruction relocation method.Our method decouples the detection model into tokenization,embedding,and encoding layers to enable efficient gradient computation.Since token IDs of instructions are discrete and nondifferentiable,we compute gradients in the continuous embedding space to evaluate the influence of each token.The most critical tokens are identified by calculating the L2 norm of their embedding gradients.We then establish a mapping between instructions and their corresponding tokens to aggregate token-level importance into instructionlevel significance.To maximize adversarial impact,a sliding window algorithm selects the most influential contiguous segments for relocation,ensuring optimal perturbation with minimal length.This approach efficiently locates critical code regions without expensive search operations.The selected segments are relocated outside their original function boundaries via a jump mechanism,which preserves runtime control flow and functionality while introducing“deletion”effects in the static instruction sequence.Extensive experiments show that AIMA reduces similarity scores by up to 35.8%in state-of-the-art BCSD models.When incorporated into training data,it also enhances model robustness,achieving a 5.9%improvement in AUROC.
基金supported by the National Natural Science Foundation of China(Grant No.52475543)Natural Science Foundation of Henan(Grant No.252300421101)+1 种基金Henan Province University Science and Technology Innovation Talent Support Plan(Grant No.24HASTIT048)Science and Technology Innovation Team Project of Zhengzhou University of Light Industry(Grant No.23XNKJTD0101).
文摘Aircraft assembly is characterized by stringent precedence constraints,limited resource availability,spatial restrictions,and a high degree of manual intervention.These factors lead to considerable variability in operator workloads and significantly increase the complexity of scheduling.To address this challenge,this study investigates the Aircraft Pulsating Assembly Line Scheduling Problem(APALSP)under skilled operator allocation,with the objective of minimizing assembly completion time.A mathematical model considering skilled operator allocation is developed,and a Q-Learning improved Particle Swarm Optimization algorithm(QLPSO)is proposed.In the algorithm design,a reverse scheduling strategy is adopted to effectively manage large-scale precedence constraints.Moreover,a reverse sequence encoding method is introduced to generate operation sequences,while a time decoding mechanism is employed to determine completion times.The problem is further reformulated as a Markov Decision Process(MDP)with explicitly defined state and action spaces.Within QLPSO,the Q-learning mechanism adaptively adjusts inertia weights and learning factors,thereby achieving a balance between exploration capability and convergence performance.To validate the effectiveness of the proposed approach,extensive computational experiments are conducted on benchmark instances of different scales,including small,medium,large,and ultra-large cases.The results demonstrate that QLPSO consistently delivers stable and high-quality solutions across all scenarios.In ultra-large-scale instances,it improves the best solution by 25.2%compared with the Genetic Algorithm(GA)and enhances the average solution by 16.9%over the Q-learning algorithm,showing clear advantages over the comparative methods.These findings not only confirm the effectiveness of the proposed algorithm but also provide valuable theoretical references and practical guidance for the intelligent scheduling optimization of aircraft pulsating assembly lines.
基金National Science and Technology Council,the Republic of China,under grants NSTC 113-2221-E-194-011-MY3 and Research Center on Artificial Intelligence and Sustainability,National Chung Cheng University under the research project grant titled“Generative Digital Twin System Design for Sustainable Smart City Development in Taiwan.
文摘Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone to errors and lacks consistency,emphasizing the need for a reliable and automated inspection system.Leveraging both object detection and image segmentation approaches,this research proposes a vision-based solution for the detection of various kinds of tools in the toolkit using deep learning(DL)models.Two Intel RealSense D455f depth cameras were arranged in a top down configuration to capture both RGB and depth images of the toolkits.After applying multiple constraints and enhancing them through preprocessing and augmentation,a dataset consisting of 3300 annotated RGB-D photos was generated.Several DL models were selected through a comprehensive assessment of mean Average Precision(mAP),precision-recall equilibrium,inference latency(target≥30 FPS),and computational burden,resulting in a preference for YOLO and Region-based Convolutional Neural Networks(R-CNN)variants over ViT-based models due to the latter’s increased latency and resource requirements.YOLOV5,YOLOV8,YOLOV11,Faster R-CNN,and Mask R-CNN were trained on the annotated dataset and evaluated using key performance metrics(Recall,Accuracy,F1-score,and Precision).YOLOV11 demonstrated balanced excellence with 93.0%precision,89.9%recall,and a 90.6%F1-score in object detection,as well as 96.9%precision,95.3%recall,and a 96.5%F1-score in instance segmentation with an average inference time of 25 ms per frame(≈40 FPS),demonstrating real-time performance.Leveraging these results,a YOLOV11-based windows application was successfully deployed in a real-time assembly line environment,where it accurately processed live video streams to detect and segment tools within toolkits,demonstrating its practical effectiveness in industrial automation.The application is capable of precisely measuring socket dimensions by utilising edge detection techniques on YOLOv11 segmentation masks,in addition to detection and segmentation.This makes it possible to do specification-level quality control right on the assembly line,which improves the ability to examine things in real time.The implementation is a big step forward for intelligent manufacturing in the Industry 4.0 paradigm.It provides a scalable,efficient,and accurate way to do automated inspection and dimensional verification activities.
基金supported in part by the National Key Technology Research and Development Program(No.2012BAF15G01)
文摘In-house part supply affects the efficiency of mixed-model assembly lines considerably. Hence, we propose a reliable Just-In-Time part supply strategy with the use of decentralized supermarkets. For a given production sequence and line layout, the proposed strategy schedules tow train routing and delivery problems jointly to minimize the number of employed town trains and the traveling time, while ensuring that stations never run out of parts. To solve this problem, a mathematical formulation is proposed for each sub-problem aiming at minimizing supply cost. Then, a dynamic programming algorithm for routing and a greedy algorithm for delivery are developed, both of which are of polynomial runtime. Finally, a computational study is implemented to validate the effectiveness of the strategy, and to investigate the effects of the delivery capacity of tow trains and storage capacity of stations on supply cost.
基金supported by the Guangdong Natural Science Foundation under Grant No.B6080170
文摘This paper studies the parameter design and the performance optimization of a Kanban system without stockouts in a multi-stage, mixed-model assembly line. The model of a Kanban system based on production processes is established by examining the relationship among the set-up time, the amount of work in process （WIP）, the capacity indicated by a Kanban, and the takt-time ratio. A novel method for optimizing performance on the premise of no stockouts is proposed. Empirical results show that the amount of WIP is reduced remarkably after optimization.
基金the National Natural Science Foundation of China(No.71071115)the National High Technology Research and Development Program (863) of China(No.2009AA043000)
文摘To solve the sequencing problem in mixed-model flexible assembly lines (MMFALs) with variable launching intervals, a mathematical model aiming to minimize the cost of utility and idle times is developed. To obtain high-quality sequences, an advanced scatter search (ASS) algorithm is proposed. A heuristic approach, i.e. launching intervals between products algorithm (LIBPA), is incorporated into the ASS algorithm to solve the launching interval problem for each sequence. Numerical experiments with different scales are conducted to compare the performance of ASS with genetic algorithm (GA). In addition, we compare the cost of variable launching intervals approach with fixed launching intervals approach. The results indicate that the ASS is efficient and effective, and considering variable launching intervals in mixed-model assembly lines (MMALs) sequencing problem can improve the performance of the line.
基金supported in part by National Science and Technology Support Program Under Grant 2012BAF15G01.
文摘Material handling has become one of the major challenges in modern production management.Consequently,this paper intends to investigate the part delivery of mixedmodel assembly lines with decentralized supermarkets and tow trains.Besides,uncertain exception disturbances,including tow train failures and adjustments of the production sequence,are also considered.To solve this problem,a heuristic-based dynamic delivery strategy is proposed,which dynamically schedules the route,departure time,quantities and types of loaded parts for each tour.To evaluate the performance of this strategy,it is used to solve an instance in comparison with the periodic delivery strategy,experimental results are reported and their performances are compared under different metrics.Moreover,a multi-scenario analysis is employed to determinate the long-term decisions,including the number of tow trains and the route layout.Finally,the critical storage is suggested to be set for each station to avoid part starvation resulting from disturbances,and its effect on the delivery performance is investigated.
基金supported by the Yunnan Seed Laboratory,China(202205AR070001-15)the National Natural Science Foundation of China,China(Grant No.32160697)。
文摘Juglans sigillata is an economically valuable nut crop renowned for its nutritional richness,including essential nutrients,antioxidants,and healthy fats,which boost human cardial,brain and gut health.Despite its importance,the lack of a complete genome assembly has been a stumbling block in its biological breeding process.Therefore,we generated deep coverage ultralong Oxford Nanopore Technology(ONT)and PacBio HiFi reads to construct a telomere-to-telomere(T2T)genome assembly.The final assembly spans 537.27 Mb with no gaps,demonstrating a remarkable completeness of 98.1%.We utilized a combination of transcriptome data and homologous proteins to annotate the genome,identifying 36018 protein-coding genes.Furthermore,we profiled global cytosine DNA methylations using ONT sequencing data.Global methylome analysis revealed high methylation levels in transposable element(TE)-rich chromosomal regions juxtaposed with comparatively lower methylation in gene-rich areas.By integrating a detailed multi-omics data analysis,we obtained valuable insights into the mechanism underlying endopleura coloration.This investigation led to the identification of eight candidate genes(e.g.ANR)involved in anthocyanin biosynthesis pathways,which are crucial for the development of color in plants.The comprehensive genome assembly and the understanding of the genetic basis of important traits like endopleura coloration will open avenues for more efficient breeding programs and improved crop quality.
基金financially supported by the Natural Science Foundation of ShanDong(Nos.ZR2023QD152 and ZR2021MD002).
文摘The application of photocatalytic technology in algae killing is limited by the non-floatability and difficulty in recycling of the photocatalysts.Loading photocatalyst on magnetic or floatable carriers is the most popular method for overcoming the above inadequacies.In this work,a CdZnS/TiO_(2) membrane photocatalyst with adjustable suspended depth(include floating)and flexible assembly is designed,which is less prone to dislodgement due to in situ synthesis and has a wider range of applicability than previously reported photocatalysts.The photocatalytic removal of Microcystis aeruginosa revealed that the suspended depth and distribution format of the CdZnS/TiO_(2) membrane photocatalysts have striking effects on the photocatalytic removal performance of Microcystis aeruginosa,the photocatalytic removal efficiency of CdZnS/TiO_(2)-2 membrane photocatalysts for Microcystis aeruginosa could reach to 98.6%in 60 min when the photocatalysts assembled in the form of 3×3 arrays suspended at a depth of 2 cm from the liquid surface.A tiny amount of TiO_(2) loading allows the formation of Z-Scheme heterojunction,resulting in accelerating the separation efficiency of photogenerated carriers,preserving the photogenerated electrons and holes with stronger reduction and oxidation ability and inhabiting the photo-corrosion of CdZnS.
基金the National Key R&D Program of China(No.2021YFA1501503)the National Natural Science Foundation of China(Nos.22250008,22121004,22108197)+3 种基金the Haihe Laboratory of Sustainable Chemical Transformations(No.CYZC202107)the Natural Science Foundation of Tianjin City(No.21JCZXJC00060)the Program of Introducing Talents of Discipline to Universities(No.BP0618007)the Xplorer Prize for financial support。
文摘Membrane electrode assembly(MEA)is widely considered to be the most promising type of electrolyzer for the practical application of electrochemical CO_(2) reduction reaction(CO_(2)RR).In MEAs,a square-shaped cross-section in the flow channel is normally adopted,the configuration optimization of which could potentially enhance the performance of the electrolyzer.This paper describes the numerical simulation study on the impact of the flow-channel cross-section shapes in the MEA electrolyzer for CO_(2)RR.The results show that wide flow channels with low heights are beneficial to the CO_(2)RR by providing a uniform flow field of CO_(2),especially at high current densities.Moreover,the larger the electrolyzer,the more significant the effect is.This study provides a theoretical basis for the design of high-performance MEA electrolyzers for CO_(2)RR.
基金support from the Ministry of Higher Education Malaysia under grant HICOE-2023-005.
文摘A unitized regenerative fuel cell(URFC)is a device that may function reversibly as either a fuel cell(FC)or water elec-trolysis(WE).An important component of this device is the Membrane electrode assembly(MEA).Therefore,this study aimed to compare the performance outcomes of MEA using electrodes with single and three catalyst layers.This study measured Electrochemical Surface Area(ECSA),Electrochemical Impedance Spectroscopy(EIS),X-ray Diffraction analysis(XRD),and X-ray Fluorescence(XRF).Furthermore,the round-trip efficiency(RTE)of the MEA,as w ell as the performance in FC and WE mode,was measured.In comparison,The ECSA values of Pt-Ru/C and Pt/C with three catalyst layers were higher than the single catalyst layer.This result was supported by electrode characterization data for XRD and XRF.The respective electrical conductivity values of Pt-Ru/C and Pt/C with three catalyst layers are also higher than the single cata-lyst layer,and the performance of URFC using MEA with three catalyst layers has the highest value of RTE among the MEA performances of URFC,which is 100%at a current density of 4 mA·cm-2.
基金Supported by National Key Research and Development Program of China(Grant No.2022YFB3304200)National Natural Science Foundation of China(Grant No.52205288)+1 种基金China Postdoctoral Science Foundation(Grant Nos.2024T170795,2024M762815)Zhejiang Provincial Key Research and Development Program(Grant No.2024C01029)。
文摘Assembly precision greatly influences the performance of complex high-end equipment.The traditional industrial assembly process and deviation transfer are implicit and uncertain,causing problems like poor component fit and hard-to-trace assembly stress concentration.Assemblers can only check whether the dimensional tolerance of the component design is exceeded step by step in combination with prior knowledge.Inversion in industrial assembly optimizes assembly and design by comparing real and theoretical results and doing inversion analysis to reduce assembly deviation.The digital twin(DT)technology visualizes and predicts the assembly process by mapping real and virtual model parameters and states simultaneously,expanding parameter range for inversion analysis and improving inversion result accuracy.Problems in improving industrial assembly precision and the significance and research status of DT-driven parametric inversion of assembly tools,processes and object precision are summarized.It analyzes vital technologies for assembly precision inversion such as multi-attribute assembly process parameter sensing,virtual modeling of high-fidelity assembly systems,twin synchronization of assembly process data models,multi-physical field simulation,and performance twin model construction of the assembly process.Combined with human-cyber-physical system,augmented reality,and generative intelligence,the outlook of DT-driven assembly precision inversion is proposed,providing support for DT's use in industrial assembly and precision improvement.
基金Supported by National Natural Science Foundation of China(Grant Nos.52475509 and U22A20203)Beijing Municipal Natural Science Foundation(Grant No.L248005)Hebei Provincial Natural Science Foundation(Grant No.E2023105059)。
文摘As the demands for assembly quality and efficiency increase,robot-assisted assembly applications are becoming more widespread.Peg-in-hole assembly,as a typical form of assembly,has been widely researched by scholars.Currently,robotic peg-in-hole assembly faces challenges such as complex analysis of part contact forces,difficulties in task modeling,and the failure of traditional strategies.Simply controlling the position of the robot's end effector cannot achieve high precision,high efficiency peg-in-hole assembly.Flexible assembly,especially intelligent flexible assembly,is becoming the future development trend.So there is a lack of comprehensive reviews on robotic flexible peg-in-hole assembly.This paper first outlines the basic components of peg-in-hole assembly and summarizes the two basic operational processes of peg-in-hole assembly,along with their related theoretical foundations.We then review and analyze the research on passive compliant assembly,active compliant assembly,and intelligent flexible assembly.Finally,it presents an outlook on the future development directions of robotic peg-in-hole assembly.
基金Sponsored by the National Natural Science Foundation of China(Grant No.52005003)the Science and Technology Planning Project of Wuhu City(Grant No.2022jc41)。
文摘To address the challenges of insufficient visualization in the industrial robot assembly operation system and the limitation of visualizing only geometric attributes of physical properties,a method is proposed for constructing an industrial robot assembly system based on virtual reality technology.Focusing on the shaft hole assembly,the mechanical characteristics of the industrial robot shaft hole assembly process are analyzed and a dynamic model is established for shaft hole assembly operations.The key elements of virtual assembly operations for industrial robots are summarized and a five-dimensional model is proposed for industrial robot virtual operations.Utilizing the Unity3D engine based on the 5-D model for industrial robot virtual operations,an industrial robot shaft hole assembly system is developed.This system enables virtual assembly operations,displays physical attributes,and provides valuable references for the research of virtual systems.
基金supported by the National Natural Science Foundation of China(Nos.22325111,2220312,21871298,91956118)Guangdong Basic Research Center of Excellence for Functional Molecular Engineeringthe Sun Yat-sen University。
文摘Molecular recognition of fullerene using various host compounds is well-known in literature.But most studies focus on host-vip complexation in solution using host compounds with a single binding cavity.Herein,we report a series of highly preorganized janusarene derivatives with homoditopic binding sites.These novel janusarenes can bind and align various fullerenes such as C_(60),C_(70),C_(84),and Gd@C_(82)in a highly efficient manner.Robust shape complementary association and assembly are observed in solution,in the bulk solid state,in the liquid crystalline state,or on surface,and the assembled structures are characterized by nuclear magnetic resonance(NMR)titration,X-ray diffraction,polarized optical microscopy,and scanning tunneling microscopy.
文摘Despite the gradual transformation of traditional manufacturing by the Human-Robot Collaboration Assembly(HRCA),challenges remain in the robot’s ability to understand and predict human assembly intentions.This study aims to enhance the robot’s comprehension and prediction capabilities of operator assembly intentions by capturing and analyzing operator behavior and movements.We propose a video feature extraction method based on the Temporal Shift Module Network(TSM-ResNet50)to extract spatiotemporal features from assembly videos and differentiate various assembly actions using feature differences between video frames.Furthermore,we construct an action recognition and segmentation model based on the Refined-Multi-Scale Temporal Convolutional Network(Refined-MS-TCN)to identify assembly action intervals and accurately acquire action categories.Experiments on our self-built reducer assembly action dataset demonstrate that our network can classify assembly actions frame by frame,achieving an accuracy rate of 83%.Additionally,we develop a HiddenMarkovModel(HMM)integrated with assembly task constraints to predict operator assembly intentions based on the probability transition matrix and assembly task constraints.The experimental results show that our method for predicting operator assembly intentions can achieve an accuracy of 90.6%,which is a 13.3%improvement over the HMM without task constraints.
基金supported by the National Natural Science Foundation of China(Grant Nos.12272326,12102073,HWG2022001)the China Postdoctoral Science Foundation(Grant Nos.2024M763860 and 2024M763861).
文摘Scratch damage can reduce both the aesthetic appearance and structural integrity of polymer surfaces.To optimize and enhance the scratch resistance of polycarbonate,this study investigates the influence of assembly pre-tensile and pre-compressive stresses,with scratch experiments being conducted under both linearly increasing and constant normal load modes.Experimental results and finite element simulations are used to analyze scratch resistance and visibility.The results indicate that the application of 20%pre-compressive stress increases the critical normal load for onset of scratch visibility by 42%compared with the case in which no assembly pre-stress is applied,and it effectively decreases residual scratch depth,shoulder height,shoulder width,and tangential load.This is because assembly pre-compressive stress can effectively counteract the extrusion of material at the front and sides caused by the sliding scratch tip.Pre-compressive stress hinders scratch groove formation,improving the scratch resistance of polycarbonate.By contrast,pre-tensile stress weakens these characteristics.This study provides valuable insights for enhancing the surface damage resistance of polycarbonate materials.
