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
To maintain the reliability of power systems,routine inspections using drones equipped with advanced object detection algorithms are essential for preempting power-related issues.The increasing resolution of drone-cap...To maintain the reliability of power systems,routine inspections using drones equipped with advanced object detection algorithms are essential for preempting power-related issues.The increasing resolution of drone-captured images has posed a challenge for traditional target detection methods,especially in identifying small objects in high-resolution images.This study presents an enhanced object detection algorithm based on the Faster Regionbased Convolutional Neural Network(Faster R-CNN)framework,specifically tailored for detecting small-scale electrical components like insulators,shock hammers,and screws in transmission line.The algorithm features an improved backbone network for Faster R-CNN,which significantly boosts the feature extraction network’s ability to detect fine details.The Region Proposal Network is optimized using a method of guided feature refinement(GFR),which achieves a balance between accuracy and speed.The incorporation of Generalized Intersection over Union(GIOU)and Region of Interest(ROI)Align further refines themodel’s accuracy.Experimental results demonstrate a notable improvement in mean Average Precision,reaching 89.3%,an 11.1%increase compared to the standard Faster R-CNN.This highlights the effectiveness of the proposed algorithm in identifying electrical components in high-resolution aerial images.展开更多
In smart driving for rail transit,a reliable obstacle detection system is an important guarantee for the safety of trains.Therein,the detection of the rail area directly affects the accuracy of the system to identify ...In smart driving for rail transit,a reliable obstacle detection system is an important guarantee for the safety of trains.Therein,the detection of the rail area directly affects the accuracy of the system to identify dangerous targets.Both the rail line and the lane are presented as thin line shapes in the image,but the rail scene is more complex,and the color of the rail line is more difficult to distinguish from the background.By comparison,there are already many deep learning-based lane detection algorithms,but there is a lack of public datasets and targeted deep learning detection algorithms for rail line detection.To address this,this paper constructs a rail image dataset RailwayLine and labels the rail line for the training and testing of models.This dataset contains rich rail images including single-rail,multi-rail,straight rail,curved rail,crossing rails,occlusion,blur,and different lighting conditions.To address the problem of the lack of deep learning-based rail line detection algorithms,we improve the CLRNet algorithm which has an excellent performance in lane detection,and propose the CLRNet-R algorithm for rail line detection.To address the problem of the rail line being thin and occupying fewer pixels in the image,making it difficult to distinguish from complex backgrounds,we introduce an attention mechanism to enhance global feature extraction ability and add a semantic segmentation head to enhance the features of the rail region by the binary probability of rail lines.To address the poor curve recognition performance and unsmooth output lines in the original CLRNet algorithm,we improve the weight allocation for line intersection-over-union calculation in the original framework and propose two loss functions based on local slopes to optimize the model’s local sampling point training constraints,improving the model’s fitting performance on curved rails and obtaining smooth and stable rail line detection results.Through experiments,this paper demonstrates that compared with other mainstream lane detection algorithms,the algorithm proposed in this paper has a better performance for rail line detection.展开更多
The published article titled“Puerarin inhibits proliferation and induces apoptosis by upregulation of miR-16 in bladder cancer cell line T24”has been retracted from Oncology Research,Vol.26,No.8,2018,pp.1227–1234.
In response to the deficiencies of commonly used optimization methods for assembly lines,a production demand-oriented optimization method for assembly lines is proposed.Taking a certain compressor assembly line as an ...In response to the deficiencies of commonly used optimization methods for assembly lines,a production demand-oriented optimization method for assembly lines is proposed.Taking a certain compressor assembly line as an example,the production rhythm and the number of workstations are calculated based on production requirements and working systems.With assembly rhythm and smoothing index as optimization goals,an improved particle swarm optimization algorithm is employed for process allocation.Subsequently,Flexsim simulation is used to analyze the assembly line.The final results show that after optimization using the improved particle swarm algorithm,the assembly line balance rate increased from 71.1%to 85.9%,and the assembly line smoothing index decreased from 47.4 to 29.8,significantly enhancing assembly efficiency.This demonstrates the effectiveness of the proposed optimization method for the assembly line and provides a reference for other products in the same industry.展开更多
Exploring advanced techniques capable of probing nanometric acoustic waves in nanostructures is critically important for the development of miniaturized acoustic devices.In this study,we probe the optically-excited ac...Exploring advanced techniques capable of probing nanometric acoustic waves in nanostructures is critically important for the development of miniaturized acoustic devices.In this study,we probe the optically-excited acoustic waves in a single silicon nanowire(NW)using the time-resolved(tr-)high-order Laue-zone(HOLZ)lines under convergent-beam electron diffraction(CBED)conditions in an ultrafast transmission electron microscope(UTEM).We devise an experimental scheme to obtain tr-HOLZ lines under off-zone-axis CBED conditions.We also propose a geometric description of HOLZ line formation and use this alternative description to quantitatively evaluate the dynamics of optically-excited silicon NW.Using part of the deformation gradient tensor,our simulations of the dynamics of Si NW reproduce the experimental results.We further discuss the feasibility of a full retrieval of the deformation gradient tensor by using a set of HOLZ lines from three zone axes.Our findings illustrate a strategy for the quantitative access to dynamical acoustic waves optically excited in micro-and nano-structures using UTEM.展开更多
Power transmission lines are a critical component of the entire power system,and ice accretion incidents caused by various types of power systems can result in immeasurable harm.Currently,network models used for ice d...Power transmission lines are a critical component of the entire power system,and ice accretion incidents caused by various types of power systems can result in immeasurable harm.Currently,network models used for ice detection on power transmission lines require a substantial amount of sample data to support their training,and their drawback is that detection accuracy is significantly affected by the inaccurate annotation among training dataset.Therefore,we propose a transformer-based detection model,structured into two stages to collectively address the impact of inaccurate datasets on model training.In the first stage,a spatial similarity enhancement(SSE)module is designed to leverage spatial information to enhance the construction of the detection framework,thereby improving the accuracy of the detector.In the second stage,a target similarity enhancement(TSE)module is introduced to enhance object-related features,reducing the impact of inaccurate data on model training,thereby expanding global correlation.Additionally,by incorporating a multi-head adaptive attention window(MAAW),spatial information is combined with category information to achieve information interaction.Simultaneously,a quasi-wavelet structure,compatible with deep learning,is employed to highlight subtle features at different scales.Experimental results indicate that the proposed model in this paper outperforms existing mainstream detection models,demonstrating superior performance and stability.展开更多
Incorporation of the Monte Carlo(MC)algorithm in optimizing CyberKnife(CK)plans is cumbersome,and early models unconfigured MC calculations,therefore,this study investigated algorithm-based dose calculation discrepanc...Incorporation of the Monte Carlo(MC)algorithm in optimizing CyberKnife(CK)plans is cumbersome,and early models unconfigured MC calculations,therefore,this study investigated algorithm-based dose calculation discrepancies by selecting different prescription isodose lines(PIDLs)in head and lung CK plans.CK plans were based on anthropomorphic phantoms.Four shells were set at 2-60 mm from the target,and the constraint doses were adjusted according to the design stratcgy.After optimization,30%-90%PIDL plans were generated by ray tracing(RT).In the evaluation module,CK plans were recalculated using the MC algorithm.Therefore,the dosimetric parameters of different PIDL plans based on the RT and MC algorithms were obtained and analyzed.The discrepancies(mean+SD)were 3.72%+0.31%,3.40%+0.11%,3.47%+0.32%,0.17%+0.11%,0.64%+3.60%,7.73%+1.60%,14.62%+3.21%and 10.10%+1.57%for Djs,Dmeam),Dys,and coverage of the PTV,DGI,V,,V;and V,in the head plans and-6.32%+1.15%,-13.46%+0.98%,-20.63%+2.25%,-34.78%+25.03%,12248%+175.60%,-12.92%+5.41%,3.19%+4.67%and 7.13%+1.56%in the lung plans,respectively.The following parameters were significantly correlated with PIDL:dp98%at the 0.05 level and dpal,dys and dv3 at the 0.01 level for the head plans;dp98e%at the 0.05 level and do1e%,dpmeam,Ccoweange,dool,dvs and dv;at the 0.01 level for the lung plans.RT may be used to calculate the dose in CK head plans,but when the dose of organs at risk is close to the limit,it is necessary to refer to the MC results or to further optimize the CK plan to reduce the dose.For lung plans,the MC algorithm is recommended.For early models without the MC algorithm,a lower PIDL plan is recommended;otherwise,a large PIDL plan risks serious underdosage in the target area.展开更多
The control design, based on self-adaptive PID with genetic algorithms(GA) tuning on-line was investigated, for the temperature control of industrial microwave drying rotary device with the multi-layer(IMDRDWM) and wi...The control design, based on self-adaptive PID with genetic algorithms(GA) tuning on-line was investigated, for the temperature control of industrial microwave drying rotary device with the multi-layer(IMDRDWM) and with multivariable nonlinear interaction of microwave and materials. The conventional PID control strategy incorporated with optimization GA was put forward to maintain the optimum drying temperature in order to keep the moisture content below 1%, whose adaptation ability included the cost function of optimization GA according to the output change. Simulations on five different industrial process models and practical temperature process control system for selenium-enriched slag drying intensively by using IMDRDWM were carried out systematically, indicating the reliability and effectiveness of control design. The parameters of proposed control design are all on-line implemented without iterative predictive calculations, and the closed-loop system stability is guaranteed, which makes the developed scheme simpler in its synthesis and application, providing the practical guidelines for the control implementation and the parameter design.展开更多
In this paper, the Eigenvalue Complementarity Problem (EiCP) with real symmetric matrices is addressed, which appears in the study of contact problem in mechanics. We discuss a quadratic programming formulation to the...In this paper, the Eigenvalue Complementarity Problem (EiCP) with real symmetric matrices is addressed, which appears in the study of contact problem in mechanics. We discuss a quadratic programming formulation to the problem. The resulting problems are nonlinear programs that can be solved by a line search filter-SQP algorithm.展开更多
[Objective] The study aimed to provide theoretical basis for development and application of molecular marker breeding technique to obtain Bombyx mori near-isogenic lines （NILs）. [Method] Thermotolerance gene was int...[Objective] The study aimed to provide theoretical basis for development and application of molecular marker breeding technique to obtain Bombyx mori near-isogenic lines （NILs）. [Method] Thermotolerance gene was introduced into sensitive variety Ou17 by developing NILs and recurrent backcross,then through six generations of backcross,thermotolerance-assisted selection,and two generations of self-cross. [Result] Bombyx mori NILs carrying thermotolerance gene （new germplasm） were produced. Meanwhile,thermotolerance level of progenies of each backcross and molecular markers of NILs were determined,and then attempts were made to produce practical thermotolerance hybrids by using thermotolerance varieties whose thermotolerance gene is linked to SSR markers. [Conclusion] The study successfully construct thermotolerance NILs,monitor thermotolerance level and breeding results of progenies of each backcross,and determine molecular marker of NILs.展开更多
Affymetrix U133A oligonucleotide microarrays were used to study the differences of gene expressions between high （H） metastatic ovarian cancer cell line, HO-8910PM, and normal ovarian tissues （C）. Bioinformatics w...Affymetrix U133A oligonucleotide microarrays were used to study the differences of gene expressions between high （H） metastatic ovarian cancer cell line, HO-8910PM, and normal ovarian tissues （C）. Bioinformatics was used to identify their chromosomal localizations. A total of 1,237 genes were found to have a difference in expression levels more than eight times. Among them 597 were upregulated [Signal Log Ratio （SLR） ≥3], and 640 genes were downregulated （SLR≤-3）. Except one gene, whose location was unknown, all these genes were randomly distributed on all the chromosomes. However, chromosome 1 contained the most differentially expressed genes （115 genes, 9.3%）, followed by chromosome 2 （94 genes, 7.6%）, chromosome 12 （88 genes, 7.1%）, chromosome 11 （76 genes, 6.1%）, chromosomes X （71 genes, 5.7%）, and chromosomes l7 （69 genes, 5.6%）. These genes were localized on short-arm of chromosome （q）, which had 805 （65.1%） genes, and the short arms of No.13, 14, 15, 21, and 22 chromosomes were the only parts of the chromosomes where the differentially expressed genes were localized. Functional classification showed that most of the genes （306 genes, 24.7%） belonged to the enzymes and their regulator groups. The subsequent group was the nucleic acid binding genes （144 genes, 11.6%）. The rest of the top two groups were signal transduction genes （137 genes, 11.1%） and proteins binding genes （116 genes, 9.4%）. These comprised 56.8% of all the differentially expressed genes. There were also 207 genes whose functions were unknown （16.7 %）. Therefore it was concluded that differentially expressed genes in high metastatic ovarian cancer cell were supposed to be randomly distributed across the genome, but the majority were found on chromosomes 1, 2, 12, 11, 17, and X. Abnormality in four groups of genes, including in enzyme and its regulator, nucleic acid binding, signal transduction and protein binding associated genes, might play important roles in ovarian cancer metastasis. Those genes need to be further studied.展开更多
A hidden line removal algorithm for bi parametric surfaces is presented and illustrated by some experimental results. The enclosure test is done using area coordinates. A technique of moving box of encirclement is p...A hidden line removal algorithm for bi parametric surfaces is presented and illustrated by some experimental results. The enclosure test is done using area coordinates. A technique of moving box of encirclement is presented. It is found that the algorithm is of general purpose, requires minimal computer storage, has high accuracy and simplicity, and is very easy to be implemented on a computer.展开更多
Lung cancer is a leading cause of cancer death worldwide. Some lung cancer patients correlate with a gas of radon besides smoking. To search for common chromosomal aberrations in lung cancer cell lines established fro...Lung cancer is a leading cause of cancer death worldwide. Some lung cancer patients correlate with a gas of radon besides smoking. To search for common chromosomal aberrations in lung cancer cell lines established from patients induced by different factors, a combined approach of chromosome sorting, forward and reverse chromosome painting was used to characterize karyotypes of two lung adenocarcinoma cell lines： A549 and GLC-82 with the latter line derived from a patient who has suffered long-term exposure to environmental radon gas pollution. The chromosome painting results revealed that complex chromosomal rearrangements occurred in these two lung adenocarcinoma cell lines. Thirteen and twenty-four abnormal chromosomes were identified An A549 and GLC-82 cell lines, respectively. Almost half of abnormal chromosomes in these two cell lines were formed by non-reciprocal translocations, the others were derived from deletions and duplication/or amplification in some chromosomal regions. Furthermore, two apparently common breakpoints, HSA8q24 and 12q14 were found in these two lung cancer cell lines.展开更多
本研究采用不同的3种方法对绵羊基因组进行注释,筛选出适合绵羊转座元件注释的方法,并进行转座元件的演化历史分析。结果表明,采用从头预测(de novo prediction)和同源预测(homology?based prediction)相结合的策略对绵羊基因组进行注...本研究采用不同的3种方法对绵羊基因组进行注释,筛选出适合绵羊转座元件注释的方法,并进行转座元件的演化历史分析。结果表明,采用从头预测(de novo prediction)和同源预测(homology?based prediction)相结合的策略对绵羊基因组进行注释效果最佳,鉴定出绵羊基因组中转座元件占比为47.34%,其中长散布核元件(LINE)占比最高(35.34%),其余依次为长末端重复序列(LTR,5.43%)、短散布核元件(SINE,3.66%)、DNA转座元件(2.44%)和未知家族(0.56%)。LINE中的牛B型逆转录转座元件(RTE?BovB)占比达16.47%。转座元件在绵羊基因组中广泛分布,但在X染色体上富集显著,占比高达57.22%。研究通过Kimura双参数模型分析转座元件的演化历史,发现绵羊基因组经历了两次转座“爆发”事件:第1次以LINE转座元件为主,第2次则同时涉及LINE和SINE转座元件的扩增,且具有时序性。综上,LINE转座元件的持续活跃是绵羊基因组扩增的主要驱动力,且其演化历史与反刍动物的基因组进化密切相关。展开更多
Due to the NP-hardness of the two-sided assembly line balancing （TALB） problem, multiple constraints existing in real applications are less studied, especially when one task is involved with several constraints. In ...Due to the NP-hardness of the two-sided assembly line balancing （TALB） problem, multiple constraints existing in real applications are less studied, especially when one task is involved with several constraints. In this paper, an effective hybrid algorithm is proposed to address the TALB problem with multiple constraints （TALB-MC）. Considering the discrete attribute of TALB-MC and the continuous attribute of the standard teaching-learning-based optimization （TLBO） algorithm, the random-keys method is hired in task permutation representation, for the purpose of bridging the gap between them. Subsequently, a special mechanism for handling multiple constraints is developed. In the mechanism, the directions constraint of each task is ensured by the direction check and adjustment. The zoning constraints and the synchronism constraints are satisfied by teasing out the hidden correlations among constraints. The positional constraint is allowed to be violated to some extent in decoding and punished in cost fimction. Finally, with the TLBO seeking for the global optimum, the variable neighborhood search （VNS） is further hybridized to extend the local search space. The experimental results show that the proposed hybrid algorithm outperforms the late acceptance hill-climbing algorithm （LAHC） for TALB-MC in most cases, especially for large-size problems with multiple constraints, and demonstrates well balance between the exploration and the exploitation. This research proposes an effective and efficient algorithm for solving TALB-MC problem by hybridizing the TLBO and VNS.展开更多
The objective of this article is to reveal the variations of ramie inbred lines in DNA level and discuss their molecular background to provide a theoretical basis for ramie cross breeding. In the present study, the ge...The objective of this article is to reveal the variations of ramie inbred lines in DNA level and discuss their molecular background to provide a theoretical basis for ramie cross breeding. In the present study, the genetic relationships among 33 inbred line accessions and two wild types that originated from China and Brazil were estimated using sequence-related amplified polymorphism （SRAP） markers. The results showed that 33 out of 81 primer combinations turned out to be polymorphic and 332 polymorphism bands were obtained. On the basis of the appearance of the markers, the genetic relationships were analyzed using unweighted pair-group method of arithmetic average cluster analysis （UPGMA）, and the genetic Jaccard similarity coefficients were calculated. The inbred-lines originating from China and Brazil formed a cluster suggesting a possibility that the Brazilian cultivars could have developed from cultivars introduced from China. Within ramie inbred-lines, the groupings also indicated that the greatest genetic relationship among cultivars was correlated to the region of origin of cultivars. The results provided the evidence that SRAP was an efficient approach, suitable for taxonomic analysis of ramie inbred lines, To the authors＇ knowledge, this is the first application of SRAP marker on the systematics of ramie inbred lines.展开更多
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.
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 by the Shanghai Science and Technology Innovation Action Plan High-Tech Field Project(Grant No.22511100601)for the year 2022 and Technology Development Fund for People’s Livelihood Research(Research on Transmission Line Deep Foundation Pit Environmental Situation Awareness System Based on Multi-Source Data).
文摘To maintain the reliability of power systems,routine inspections using drones equipped with advanced object detection algorithms are essential for preempting power-related issues.The increasing resolution of drone-captured images has posed a challenge for traditional target detection methods,especially in identifying small objects in high-resolution images.This study presents an enhanced object detection algorithm based on the Faster Regionbased Convolutional Neural Network(Faster R-CNN)framework,specifically tailored for detecting small-scale electrical components like insulators,shock hammers,and screws in transmission line.The algorithm features an improved backbone network for Faster R-CNN,which significantly boosts the feature extraction network’s ability to detect fine details.The Region Proposal Network is optimized using a method of guided feature refinement(GFR),which achieves a balance between accuracy and speed.The incorporation of Generalized Intersection over Union(GIOU)and Region of Interest(ROI)Align further refines themodel’s accuracy.Experimental results demonstrate a notable improvement in mean Average Precision,reaching 89.3%,an 11.1%increase compared to the standard Faster R-CNN.This highlights the effectiveness of the proposed algorithm in identifying electrical components in high-resolution aerial images.
基金the Sichuan Science and Technology Program(No.2022YFS0557)the National Natural Science Foundation of China(No.61972271)。
文摘In smart driving for rail transit,a reliable obstacle detection system is an important guarantee for the safety of trains.Therein,the detection of the rail area directly affects the accuracy of the system to identify dangerous targets.Both the rail line and the lane are presented as thin line shapes in the image,but the rail scene is more complex,and the color of the rail line is more difficult to distinguish from the background.By comparison,there are already many deep learning-based lane detection algorithms,but there is a lack of public datasets and targeted deep learning detection algorithms for rail line detection.To address this,this paper constructs a rail image dataset RailwayLine and labels the rail line for the training and testing of models.This dataset contains rich rail images including single-rail,multi-rail,straight rail,curved rail,crossing rails,occlusion,blur,and different lighting conditions.To address the problem of the lack of deep learning-based rail line detection algorithms,we improve the CLRNet algorithm which has an excellent performance in lane detection,and propose the CLRNet-R algorithm for rail line detection.To address the problem of the rail line being thin and occupying fewer pixels in the image,making it difficult to distinguish from complex backgrounds,we introduce an attention mechanism to enhance global feature extraction ability and add a semantic segmentation head to enhance the features of the rail region by the binary probability of rail lines.To address the poor curve recognition performance and unsmooth output lines in the original CLRNet algorithm,we improve the weight allocation for line intersection-over-union calculation in the original framework and propose two loss functions based on local slopes to optimize the model’s local sampling point training constraints,improving the model’s fitting performance on curved rails and obtaining smooth and stable rail line detection results.Through experiments,this paper demonstrates that compared with other mainstream lane detection algorithms,the algorithm proposed in this paper has a better performance for rail line detection.
文摘The published article titled“Puerarin inhibits proliferation and induces apoptosis by upregulation of miR-16 in bladder cancer cell line T24”has been retracted from Oncology Research,Vol.26,No.8,2018,pp.1227–1234.
文摘In response to the deficiencies of commonly used optimization methods for assembly lines,a production demand-oriented optimization method for assembly lines is proposed.Taking a certain compressor assembly line as an example,the production rhythm and the number of workstations are calculated based on production requirements and working systems.With assembly rhythm and smoothing index as optimization goals,an improved particle swarm optimization algorithm is employed for process allocation.Subsequently,Flexsim simulation is used to analyze the assembly line.The final results show that after optimization using the improved particle swarm algorithm,the assembly line balance rate increased from 71.1%to 85.9%,and the assembly line smoothing index decreased from 47.4 to 29.8,significantly enhancing assembly efficiency.This demonstrates the effectiveness of the proposed optimization method for the assembly line and provides a reference for other products in the same industry.
基金supported by the Guangxi Natural Science Foundation(Grant No.2024GXNSFDA010014)the National Natural Science Foundation of China(Grant Nos.12364018 and U22A6005)+1 种基金the Guangxi Science and Technology Major Program(Grant No.AA23073019)the Innovation Project of Guangxi Graduate Education(Grant Nos.YCBZ2022049 and YCBZ2023015)。
文摘Exploring advanced techniques capable of probing nanometric acoustic waves in nanostructures is critically important for the development of miniaturized acoustic devices.In this study,we probe the optically-excited acoustic waves in a single silicon nanowire(NW)using the time-resolved(tr-)high-order Laue-zone(HOLZ)lines under convergent-beam electron diffraction(CBED)conditions in an ultrafast transmission electron microscope(UTEM).We devise an experimental scheme to obtain tr-HOLZ lines under off-zone-axis CBED conditions.We also propose a geometric description of HOLZ line formation and use this alternative description to quantitatively evaluate the dynamics of optically-excited silicon NW.Using part of the deformation gradient tensor,our simulations of the dynamics of Si NW reproduce the experimental results.We further discuss the feasibility of a full retrieval of the deformation gradient tensor by using a set of HOLZ lines from three zone axes.Our findings illustrate a strategy for the quantitative access to dynamical acoustic waves optically excited in micro-and nano-structures using UTEM.
文摘Power transmission lines are a critical component of the entire power system,and ice accretion incidents caused by various types of power systems can result in immeasurable harm.Currently,network models used for ice detection on power transmission lines require a substantial amount of sample data to support their training,and their drawback is that detection accuracy is significantly affected by the inaccurate annotation among training dataset.Therefore,we propose a transformer-based detection model,structured into two stages to collectively address the impact of inaccurate datasets on model training.In the first stage,a spatial similarity enhancement(SSE)module is designed to leverage spatial information to enhance the construction of the detection framework,thereby improving the accuracy of the detector.In the second stage,a target similarity enhancement(TSE)module is introduced to enhance object-related features,reducing the impact of inaccurate data on model training,thereby expanding global correlation.Additionally,by incorporating a multi-head adaptive attention window(MAAW),spatial information is combined with category information to achieve information interaction.Simultaneously,a quasi-wavelet structure,compatible with deep learning,is employed to highlight subtle features at different scales.Experimental results indicate that the proposed model in this paper outperforms existing mainstream detection models,demonstrating superior performance and stability.
基金This study was supported by grants from National Key Research and Development Plan for Digital Diagnostic Equipment Research and Development(No.2016YFC0106700)the Natural Science Foundation of Union Hospital,Tongji Medical College,Huazhong University of Science and Technology(No.02.03.2018-131).
文摘Incorporation of the Monte Carlo(MC)algorithm in optimizing CyberKnife(CK)plans is cumbersome,and early models unconfigured MC calculations,therefore,this study investigated algorithm-based dose calculation discrepancies by selecting different prescription isodose lines(PIDLs)in head and lung CK plans.CK plans were based on anthropomorphic phantoms.Four shells were set at 2-60 mm from the target,and the constraint doses were adjusted according to the design stratcgy.After optimization,30%-90%PIDL plans were generated by ray tracing(RT).In the evaluation module,CK plans were recalculated using the MC algorithm.Therefore,the dosimetric parameters of different PIDL plans based on the RT and MC algorithms were obtained and analyzed.The discrepancies(mean+SD)were 3.72%+0.31%,3.40%+0.11%,3.47%+0.32%,0.17%+0.11%,0.64%+3.60%,7.73%+1.60%,14.62%+3.21%and 10.10%+1.57%for Djs,Dmeam),Dys,and coverage of the PTV,DGI,V,,V;and V,in the head plans and-6.32%+1.15%,-13.46%+0.98%,-20.63%+2.25%,-34.78%+25.03%,12248%+175.60%,-12.92%+5.41%,3.19%+4.67%and 7.13%+1.56%in the lung plans,respectively.The following parameters were significantly correlated with PIDL:dp98%at the 0.05 level and dpal,dys and dv3 at the 0.01 level for the head plans;dp98e%at the 0.05 level and do1e%,dpmeam,Ccoweange,dool,dvs and dv;at the 0.01 level for the lung plans.RT may be used to calculate the dose in CK head plans,but when the dose of organs at risk is close to the limit,it is necessary to refer to the MC results or to further optimize the CK plan to reduce the dose.For lung plans,the MC algorithm is recommended.For early models without the MC algorithm,a lower PIDL plan is recommended;otherwise,a large PIDL plan risks serious underdosage in the target area.
基金Project(51090385) supported by the Major Program of National Natural Science Foundation of ChinaProject(2011IB001) supported by Yunnan Provincial Science and Technology Program,China+1 种基金Project(2012DFA70570) supported by the International Science & Technology Cooperation Program of ChinaProject(2011IA004) supported by the Yunnan Provincial International Cooperative Program,China
文摘The control design, based on self-adaptive PID with genetic algorithms(GA) tuning on-line was investigated, for the temperature control of industrial microwave drying rotary device with the multi-layer(IMDRDWM) and with multivariable nonlinear interaction of microwave and materials. The conventional PID control strategy incorporated with optimization GA was put forward to maintain the optimum drying temperature in order to keep the moisture content below 1%, whose adaptation ability included the cost function of optimization GA according to the output change. Simulations on five different industrial process models and practical temperature process control system for selenium-enriched slag drying intensively by using IMDRDWM were carried out systematically, indicating the reliability and effectiveness of control design. The parameters of proposed control design are all on-line implemented without iterative predictive calculations, and the closed-loop system stability is guaranteed, which makes the developed scheme simpler in its synthesis and application, providing the practical guidelines for the control implementation and the parameter design.
文摘In this paper, the Eigenvalue Complementarity Problem (EiCP) with real symmetric matrices is addressed, which appears in the study of contact problem in mechanics. We discuss a quadratic programming formulation to the problem. The resulting problems are nonlinear programs that can be solved by a line search filter-SQP algorithm.
基金Supported by Jiangsu High-tech projects(BG2007322) "Good feature of new varieties of Silkworm BreedingPh.D., University of Jiangsu Science and Technology Fund~~
文摘[Objective] The study aimed to provide theoretical basis for development and application of molecular marker breeding technique to obtain Bombyx mori near-isogenic lines （NILs）. [Method] Thermotolerance gene was introduced into sensitive variety Ou17 by developing NILs and recurrent backcross,then through six generations of backcross,thermotolerance-assisted selection,and two generations of self-cross. [Result] Bombyx mori NILs carrying thermotolerance gene （new germplasm） were produced. Meanwhile,thermotolerance level of progenies of each backcross and molecular markers of NILs were determined,and then attempts were made to produce practical thermotolerance hybrids by using thermotolerance varieties whose thermotolerance gene is linked to SSR markers. [Conclusion] The study successfully construct thermotolerance NILs,monitor thermotolerance level and breeding results of progenies of each backcross,and determine molecular marker of NILs.
基金National Natural Science Foundation of China (No. 30471819).
文摘Affymetrix U133A oligonucleotide microarrays were used to study the differences of gene expressions between high （H） metastatic ovarian cancer cell line, HO-8910PM, and normal ovarian tissues （C）. Bioinformatics was used to identify their chromosomal localizations. A total of 1,237 genes were found to have a difference in expression levels more than eight times. Among them 597 were upregulated [Signal Log Ratio （SLR） ≥3], and 640 genes were downregulated （SLR≤-3）. Except one gene, whose location was unknown, all these genes were randomly distributed on all the chromosomes. However, chromosome 1 contained the most differentially expressed genes （115 genes, 9.3%）, followed by chromosome 2 （94 genes, 7.6%）, chromosome 12 （88 genes, 7.1%）, chromosome 11 （76 genes, 6.1%）, chromosomes X （71 genes, 5.7%）, and chromosomes l7 （69 genes, 5.6%）. These genes were localized on short-arm of chromosome （q）, which had 805 （65.1%） genes, and the short arms of No.13, 14, 15, 21, and 22 chromosomes were the only parts of the chromosomes where the differentially expressed genes were localized. Functional classification showed that most of the genes （306 genes, 24.7%） belonged to the enzymes and their regulator groups. The subsequent group was the nucleic acid binding genes （144 genes, 11.6%）. The rest of the top two groups were signal transduction genes （137 genes, 11.1%） and proteins binding genes （116 genes, 9.4%）. These comprised 56.8% of all the differentially expressed genes. There were also 207 genes whose functions were unknown （16.7 %）. Therefore it was concluded that differentially expressed genes in high metastatic ovarian cancer cell were supposed to be randomly distributed across the genome, but the majority were found on chromosomes 1, 2, 12, 11, 17, and X. Abnormality in four groups of genes, including in enzyme and its regulator, nucleic acid binding, signal transduction and protein binding associated genes, might play important roles in ovarian cancer metastasis. Those genes need to be further studied.
文摘A hidden line removal algorithm for bi parametric surfaces is presented and illustrated by some experimental results. The enclosure test is done using area coordinates. A technique of moving box of encirclement is presented. It is found that the algorithm is of general purpose, requires minimal computer storage, has high accuracy and simplicity, and is very easy to be implemented on a computer.
基金supported partly by grants from the Ministry of Science and Technology of China(2005DKA21502)the Joint Foundation of Science and Technology Bureau of Yunnan Province and Kunming Medical University(2007C0024R)
文摘Lung cancer is a leading cause of cancer death worldwide. Some lung cancer patients correlate with a gas of radon besides smoking. To search for common chromosomal aberrations in lung cancer cell lines established from patients induced by different factors, a combined approach of chromosome sorting, forward and reverse chromosome painting was used to characterize karyotypes of two lung adenocarcinoma cell lines： A549 and GLC-82 with the latter line derived from a patient who has suffered long-term exposure to environmental radon gas pollution. The chromosome painting results revealed that complex chromosomal rearrangements occurred in these two lung adenocarcinoma cell lines. Thirteen and twenty-four abnormal chromosomes were identified An A549 and GLC-82 cell lines, respectively. Almost half of abnormal chromosomes in these two cell lines were formed by non-reciprocal translocations, the others were derived from deletions and duplication/or amplification in some chromosomal regions. Furthermore, two apparently common breakpoints, HSA8q24 and 12q14 were found in these two lung cancer cell lines.
文摘本研究采用不同的3种方法对绵羊基因组进行注释,筛选出适合绵羊转座元件注释的方法,并进行转座元件的演化历史分析。结果表明,采用从头预测(de novo prediction)和同源预测(homology?based prediction)相结合的策略对绵羊基因组进行注释效果最佳,鉴定出绵羊基因组中转座元件占比为47.34%,其中长散布核元件(LINE)占比最高(35.34%),其余依次为长末端重复序列(LTR,5.43%)、短散布核元件(SINE,3.66%)、DNA转座元件(2.44%)和未知家族(0.56%)。LINE中的牛B型逆转录转座元件(RTE?BovB)占比达16.47%。转座元件在绵羊基因组中广泛分布,但在X染色体上富集显著,占比高达57.22%。研究通过Kimura双参数模型分析转座元件的演化历史,发现绵羊基因组经历了两次转座“爆发”事件:第1次以LINE转座元件为主,第2次则同时涉及LINE和SINE转座元件的扩增,且具有时序性。综上,LINE转座元件的持续活跃是绵羊基因组扩增的主要驱动力,且其演化历史与反刍动物的基因组进化密切相关。
基金Supported by National Natural Science Foundation of China(Grant Nos.51275366,50875190,51305311)Specialized Research Fund for the Doctoral Program of Higher Education of China(Grant No.20134219110002)
文摘Due to the NP-hardness of the two-sided assembly line balancing （TALB） problem, multiple constraints existing in real applications are less studied, especially when one task is involved with several constraints. In this paper, an effective hybrid algorithm is proposed to address the TALB problem with multiple constraints （TALB-MC）. Considering the discrete attribute of TALB-MC and the continuous attribute of the standard teaching-learning-based optimization （TLBO） algorithm, the random-keys method is hired in task permutation representation, for the purpose of bridging the gap between them. Subsequently, a special mechanism for handling multiple constraints is developed. In the mechanism, the directions constraint of each task is ensured by the direction check and adjustment. The zoning constraints and the synchronism constraints are satisfied by teasing out the hidden correlations among constraints. The positional constraint is allowed to be violated to some extent in decoding and punished in cost fimction. Finally, with the TLBO seeking for the global optimum, the variable neighborhood search （VNS） is further hybridized to extend the local search space. The experimental results show that the proposed hybrid algorithm outperforms the late acceptance hill-climbing algorithm （LAHC） for TALB-MC in most cases, especially for large-size problems with multiple constraints, and demonstrates well balance between the exploration and the exploitation. This research proposes an effective and efficient algorithm for solving TALB-MC problem by hybridizing the TLBO and VNS.
基金the National High Technology Research and Development Program of China(2001AA241121)948 Project of the Ministry of Agriculture of China(2006-G18(03))the Key Technology R&D Program of Hubei Province,China(2007AA201C49)
文摘The objective of this article is to reveal the variations of ramie inbred lines in DNA level and discuss their molecular background to provide a theoretical basis for ramie cross breeding. In the present study, the genetic relationships among 33 inbred line accessions and two wild types that originated from China and Brazil were estimated using sequence-related amplified polymorphism （SRAP） markers. The results showed that 33 out of 81 primer combinations turned out to be polymorphic and 332 polymorphism bands were obtained. On the basis of the appearance of the markers, the genetic relationships were analyzed using unweighted pair-group method of arithmetic average cluster analysis （UPGMA）, and the genetic Jaccard similarity coefficients were calculated. The inbred-lines originating from China and Brazil formed a cluster suggesting a possibility that the Brazilian cultivars could have developed from cultivars introduced from China. Within ramie inbred-lines, the groupings also indicated that the greatest genetic relationship among cultivars was correlated to the region of origin of cultivars. The results provided the evidence that SRAP was an efficient approach, suitable for taxonomic analysis of ramie inbred lines, To the authors＇ knowledge, this is the first application of SRAP marker on the systematics of ramie inbred lines.
