基于人工神经网络的智能化架空线路应变快速解调方法北大核心

为了提高智能化光纤复合架空线路态势感知的实时性,将人工神经网络方法应用于光纤沿线应变解调,确定了神经网络的结构。编程实现了基于洛伦兹模型的最小二乘谱拟合方法和神经网络方法,采用不同信噪比和布里渊频移的布里渊谱训练神经网络,将它们应用于某光纤复合架空线路沿线光纤应变的测量,从不同角度比较了两种方法的计算结果。计算结果表明,神经网络方法能有效获得光纤沿线的布里渊频移进而获得应变,具有与谱拟合方法相似的准确性,但应变解调时间仅约为谱拟合方法的1/20000。研究结果为提高智能光纤复合架空线路态势感知的实时性提供了参考。     

转基因甜菜GTSB77品系特异性实时荧光聚合酶链式反应检测方法建立

目的 为实现转基因甜菜GTSB77的标识管理,建立其品系特异性实时荧光聚合酶链式反应(PCR)检测方法。方法 针对GTSB77的3′端外源插入片段与甜菜基因组DNA之间的邻接区序列设计引物和探针,建立GTSB77品系特异性实时荧光PCR检测方法,并对该方法的特异性、灵敏度和重复性进行检测。结果 建立的GTSB77检测方法特异性强,定量限(LOQ)为16拷贝,扩增效率为102%,重复性测试结果相对标准偏差(RSD)介于0.21%～1.66%之间。结论 建立的实时荧光PCR方法可应用于GTSB77的鉴定检测。     

基于自适应阈值活动语音检测和最小均方误差对数谱幅度估计的低信噪比降噪算法

针对低信噪比(SNR)环境下传统方法对声信号降噪的局限性，提出了一种联合自适应阈值活动语音检测（VAD）算法和最小均方误差对数谱幅度估计（MMSE-LSA）的实时降噪算法。首先，在VAD算法中通过基于能量概率最大值的概率统计来对背景噪声进行估计，对得到的背景噪声进行实时更新并保存；然后，将实时更新的背景噪声作为MMSE-LSA的参考噪声，并对噪声幅度谱进行自适应更新，最后进行降噪处理。通过在真实场景中对四类声信号进行实验，结果表明，该算法在保证对低SNR声信号的实时处理的情况下，相较于传统MMSE-LSA算法，降噪信号的SNR能够提高10~15 dB，且不存在信号过减的情况，可应用于实际工程。     

数据驱动的机床等待过程节能方法研究

为了降低机床等待过程中的能耗，提出了一种实时数据驱动的机床等待时间预测与节能控制方法。首先，建立了射频识别驱动的生产进度评估方法，并以生产进度数据作为输入，构建了基于堆栈降噪自编码的机床等待时间预测模型；其次，依据预测的机床等待时间，提出了机床状态切换方法，以降低机床能耗；最后，通过一个电梯零部件制造车间的案例分析，表明该方法的预测误差仅为4.1%，同时将机床等待过程能耗降低了57%，实现了制造车间的节能减排。     

考虑围岩稳定性评价的引水隧洞施工过程仿真系统

根据施工过程中的围岩稳定情况确定出合理的施工进尺并实时可视化评价结构安全状况具有重要的工程意义。首先利用BIM建模软件建立三维基础模型,通过对建模软件进行二次开发并结合系统仿真原理得到引水隧洞施工进度;其次将几何模型转换为数值计算模型并建立进度数据库与引水隧洞数值模型之间的映射关系,通过有限元分析围压系统的安全状况,根据不同进尺下的进度计算及围岩稳定分析结果,合理选择施工进尺;最后基于Python+VB.net混合编程技术编制了引水隧洞施工进度与围岩稳定安全仿真系统。工程应用表明,该系统将隧洞施工进度、支护体系与围岩稳定性进行结合,可为合理制定施工计划及施工现场控制提供可视化技术及数据支持。     

Deployment of a cloud pipeline for real-time visual inspection using fast streaming high-definition images

We investigate the challenges of building an end-to-end cloud pipeline for real-time intelligent visual inspection system for use in automotive manufacturing. Current methods of visual detection in automotive assembly are highly labor intensive, and thus prone to errors. An automated process is sought that can operate within the real-time constraints of the assembly line and can reduce errors. Components of the cloud pipeline include capture of a large set of high-definition images from a camera setup at the assembly location, transfer and storage of the images as needed, execution of object detection, and notification to a human operator when a fault is detected. The end-to-end execution must complete within a fixed time frame before the next car arrives in the assembly line. In this article, we report the design, development, and experimental evaluation of the tradeoffs of performance, accuracy, and scalability for a cloud system.     

Investigations of geometrical structure and morphology of samples made of hard machinable materials after wire electrical discharge machining and vibro‐abrasive finishing

In this article the results concerned influence of processing conditions of the wire electrical discharge machining and vibro‐abrasive machining on the surface layer and morphology of samples made of hard machinable materials used in aircraft industry like: Titanium 5553 β, Inconel 617, Hastelloy X and Magnesium AZ31 have been presented. For this purpose the cubic and cylindrical samples made of hard machinable alloys have been prepared using optimal electric parameters of wire‐cut electrical discharge machining and finally they have been polished using circular vibratory finishing technology and different ceramic shaped stones.     

Investigation of the piezoelectric and anti-reduction properties of (Ba,Ca) (Ti,Sn, Hf) textured ceramics prepared under low oxygen partial pressure conditions at low sintering temperatures

Multilayer piezoelectric ceramics must be sintered in a reducing atmosphere, preventing oxidation of the inner base metal. Plate-like textured (Ba, Ca)(Ti, Sn, Hf)O₃ ceramics with a <001> preferred orientation were successfully developed at a low oxygen partial pressure (PO₂:10^?8 atm) using a BaTiO₃ (BT) template with sintering temperatures < 1300 °C, which is beneficial for multilayer applications using base metal co-firing with ceramics. When adding the 3 wt% BT template, the proposed samples had a Lottgering factor of 84 %, piezoelectric coefficients d₃₃ = 324 pC/N, -d₃₁ = 122 (pC/N), and Q_m = 452, and the strain values increased from 0.07 % for the randomly oriented ceramics to 0.115 % at 20 kV/cm for the textured ceramics, confirming that the texturing behavior assisted the grain growth and improved both the soft and hard behaviors and insulation resistance of the proposed lead-free ceramics. These findings make a significant contribution to the production of high-power piezoelectric components.     

水产品及其制品中大西洋鲑鱼实时荧光PCR检测方法建立

目的:三文鱼营养丰富,含有ω-3不饱和脂肪酸,深受大众喜爱,但存在产品标签标示错误、掺伪掺假、以次充好的现象。目前采用检测标准SN/T 3589.7—2013《出口食品中常见鱼类及其制品的鉴伪方法第七部》对鲑鱼成分检测,无法区分大西洋鲑鱼和其他种类的三文鱼。因此有必要建立一种用于区分上述几种三文鱼的快速检测方法。方法:研究建立了针对大西洋鲑鱼成分鉴定的实时荧光PCR法,并对该方法的特异性和检出限进行了验证。结果:该方法具有良好的特异性,检出限为1%(w/w)。结论:可应用于大西洋鲑鱼的日常检测,为监管部门提供技术支持。     

多晶硅锭中硬质点分析及控制研究

以多晶硅锭中硬质点为研究对象,通过实验研究和数值模拟的方法,对多晶硅锭中硬质点进行形貌和成分分析,并提出改善控制方法。研究结果表明硅锭中部的硬质点较细小,主要由SiC组成;硅锭头部的硬质点较粗大,主要由SiC和Si3N4组成,还有少量O的存在。进一步研究发现多晶硅定向凝固铸锭炉的热场结构对于多晶硅锭硬质点形成有直接影响,通过改进热场结构,优化晶体生长界面,显著减少了铸锭中硬质点的数量。