Automated deep learning system for power line inspection image analysis and processing: architecture and design issues

The continuous growth in the scale of unmanned aerial vehicle（UAV） applications in transmission line inspection has resulted in a corresponding increase in the demand for UAV inspection image processing. Owing to its excellent performance in computer vision, deep learning has been applied to UAV inspection image processing tasks such as power line identification and insulator defect detection. Despite their excellent performance, electric power UAV inspection image processing models based on deep learning face several problems such as a small application scope, the need for constant retraining and optimization, and high R＆D monetary and time costs due to the black-box and scene data-driven characteristics of deep learning. In this study, an automated deep learning system for electric power UAV inspection image analysis and processing is proposed as a solution to the aforementioned problems. This system design is based on the three critical design principles of generalizability, extensibility, and automation. Pre-trained models, fine-tuning（downstream task adaptation）, and automated machine learning, which are closely related to these design principles, are reviewed. In addition, an automated deep learning system architecture for electric power UAV inspection image analysis and processing is presented. A prototype system was constructed and experiments were conducted on the two electric power UAV inspection image analysis and processing tasks of insulator self-detonation and bird nest recognition. The models constructed using the prototype system achieved 91.36%and 86.13% mAP for insulator self-detonation and bird nest recognition, respectively. This demonstrates that the system design concept is reasonable and the system architecture feasible.     

基于LabVIEW软件和NI硬件,开发移动式X射线成像诊断系统

0引言移动式X射线成像系统提供了X光透视检查和三维计算机断层扫描(CT)图像模式,主要应用于骨科和神经外科手术室(OR)中.X光透视检查成像模式可提供患者在不同角度的实时内部结构图像,方便外科医生作出准确的诊断.三维CT图像模式则可以帮助医生在手术室中检查病人的当前状态,免去了移动病人的麻烦.通常情况下,完成手术后,只有在CT扫描室里才能检查病人的状态.因此,该系统的诞生可以节省大量检查手术效果的时间,避免重复手术.此外,三维CT图像模式还可以与导航系统配合使用,外科医生能够使用GPS导航系统,结合三维CT图像查看手术仪器的确切位置,从而作出精确的手术切割.     

穿流板结构参数对复合塔板的性能影响

对不同开孔率、不同孔径的穿流筛板与250Y规整填料组成的各种复合塔板的性能进行研究。结果表明:开孔率越大,复合塔板的处理量越大;压降越小,操作弹性越小;存在流体力学性能较佳的孔径8mm,孔径小于等于8mm时,孔径越小,压降越大,操作弹性越小;孔径大于8mm时,孔径越大,压降越大,操作弹性越小。孔径对效率影响不大。     

Exploring the synergy of building massing and façade design through evolutionary optimization

In performance-based architectural design optimization, the design of building massings and façades is commonly separated, which weakens the effectiveness in performance improvement. In response, this study proposes a hybrid massing-façade integrated design generation and optimization workflow to integrate the two elements in an evolutionary design process. Compared with the existing approaches, the proposed workflow emphasizes the diversity of building design generation, with which various combinations of building massing forms and façade patterns can be systematically explored. Two case studies and a corresponding comparison study are presented to demonstrate the efficacy of the proposed workflow. Results show that the optimization can produce designs coupling the potential of building massings and façades in performance improvement. In addition, the optimization can provide information that supports early-stage architectural design exploration. Such information also enables the architect to understand the performance implications associated with the synergy of building massing and façade design.     

用4％Ni变质处理的13％Cr铸钢的组织和机械性能之间的关系

<正> 用4％Ni变质处理的13％Cr钢,由于有良好的机械性能、耐腐蚀性和耐气蚀性,又有良好的工艺性,所以最适用于生产要求严格的水轮机的大部分大型铸件。然而,随着由这种钢制成的铸件的重量的不断增长,在达到40t以上时,在冶金方面、铸造方面     

Biocompatibility of hydrophilic silica-coated CdTe quantum dots and magnetic nanoparticles

Fluorescent magnetic nanoparticles exhibit great application prospects in biomedical engineering. Herein, we reported the effects of hydrophilic silica-coated CdTe quantum dots and magnetic nanoparticles (FMNPs) on human embryonic kidney 293 (HEK293) cells and mice with the aim of investigating their biocompatibility. FMNPs with 150 nm in diameter were prepared, and characterized by high-resolution transmission electron microscopy and photoluminescence (PL) spectra and magnetometer. HEK293 cells were cultured with different doses of FMNPs (20, 50, and 100μ g/ml) for 1-4 days. Cell viability and adhesion ability were analyzed by CCK8 method and Western blotting. 30 mice were randomly divided into three groups, and were, respectively, injected via tail vein with 20, 60, and 100 μg FMNPs, and then were, respectively, raised for 1, 7, and 30 days, then their lifespan, important organs, and blood biochemical parameters were analyzed. Results show that the prepared water-soluble FMNPs had high fluorescent and magnetic properties, less than 50 μg/ml of FMNPs exhibited good biocompatibility to HEK293 cells, the cell viability, and adhesion ability were similar to the control HEK293 cells. FMNPs primarily accumulated in those organs such as lung, liver, and spleen. Lung exposed to FMNPs displayed a dose-dependent inflammatory response, blood biochemical parameters such as white blood cell count (WBC), alanine aminotransferase (ALT), and aspartate aminotransferase (AST), displayed significant increase when the FMNPs were injected into mice at dose of 100μg. In conclusion, FMNPs exhibit good biocompatibility to cells under the dose of less than 50 μg/ml, and to mice under the dose of less than 2mg/kg body weight. The FMNPs' biocompatibility must be considered when FMNPs are used for in vivo diagnosis and therapy.     

Selective dissolution of eodiagenesis cements and its impact on the quality evolution of reservoirs in the Xing’anling Group, Suderte Oil Field, Hailar Basin, China

Reservoirs in the Xing’anling Group in the Suderte Oil Field, Hailar Basin exhibit ultra-low to low permeability and high tuffaceous material content. This study comprehensively analyzed diagenesis and quality evolution of these low-permeability reservoirs using thin sections, SEM samples, rock physical properties, pore water data, as well as geochemical numerical simulations. Calcite and analcite are the two main types of cements precipitated in the eodiagenetic stage at shallow burial depths in the reservoirs. These two cements occupied significant primary intergranular pores and effectively retarded deep burial compaction. Petrography textures suggest selective dissolution of massive analcite and little dissolution of calcite in the mesodiagenetic stage. Chemical calculations utilizing the Geochemist’s Workbench 9.0 indicated that the equilibrium constant of the calcite leaching reaction is significantly smaller than that of the analcite leaching reaction, resulting in extensive dissolution of analcite rather than calcite in the geochemical system with both minerals present. Numerical simulations with constraints of kinetics and pore water chemistry demonstrated that the pore water in the Xing’anling group is saturated with respect to calcite, but undersaturated with analcite, leading to dissolution of large amounts of analcite and no dissolution of calcite. Significant secondary intergranular pores have formed in analcite-cemented reservoirs from selective dissolution of analcite in the mesodiagenetic stage; the analcite dissolution formed preferential flow paths in the reservoirs, which promoted feldspar dissolution; and dissolution of such minerals led to the present reservoirs with medium porosity and low permeability. Calcite-cemented tight reservoirs have not experienced extensive dissolution of cements, so they exhibit ultra-low porosity and permeability.