基于异构物联网络的输电线路智慧巡检方法

为解决高海拔地区输电线路运行维护检修存在的传感器供电可靠性差、无移动信号区域数据传输难度大的问题,文中提出了一种基于异构物联网络的输电线路智慧巡检方法。首先,研究了风光协同的传感器供电技术,实现了高海拔地区恶劣环境下输电线路监测传感器的可靠供电;其次,建立了异构的输电线路物联网络,实现了输电线路无移动信号传感器的数据采集。在此基础上,通过深度学习对所采集数据样本进行分析,实现对输电线路的智慧巡检;最后,将所提方法在某无信号地区110 kV线路的现场运行,其结果验证了所提方法的有效性和可行性。     

Hygroresponsive Torsional Yarns and Actuators Based on Cascade Amplification of the Deformation

Fiber-based hygroresponsive torsional actuators provide desirable merits, such as light weight and shapeability, for developing smart systems to harvest energy from moisture which is a ubiquitous natural resource. A key challenge in this development is to realize moisture-triggered actuation combining large actuation and rapid responses. Here, a multiscale design strategy is explored to create high-performance hygroresponsive torsional actuators consisting of chitosan and multiwalled carbon nanotubes (MWCNTs). The superior actuation performance arises from the synergism of contributing factors at different scales, including 1) MWNCTs accelerate the water transport in primary twisted fibers (PTFs), fostering the rotation of PTFs upon moisture stimuli; 2) in situ-formed hierarchically-assembled twists realize cascade amplification of moisture-triggered actuation. Specifically, PTFs are self-twisted to generate secondary helical yarns, that are subsequently over-twisted to yield tertiary coiled yarn. The resultant yarn actuator can reach a maximum rotation speed of 11 400 rpm in 5 s, output gravitational potential energy of 2.4 J kg⁻¹ and gravitational potential power of 0.053 W kg⁻¹ during contraction. This work represents the first design of fiber-based actuators by virtue of moisture-triggered in situ formation of yarns. The established principles of multiscale design will enable high-performance fiber-based hygroresponsive actuators toward advanced intelligent textile and soft robotics.     

冷轧带钢板形测控技术的发展状况和关键问题

 冷轧带钢属于高端精品钢材,板形在线检测与控制是冷轧带钢的高端核心关键技术。自主创新研制板形测控系统是实现中国钢铁工业发展升级、建设钢铁强国的重大需求。目前,板形测控技术市场国外占据优势,国产系统正在代替进口,扩大应用规模,推进技术完善。研制先进的板形测控系统需要解决的关键技术有高精度高质量的板形仪、功能完备强大的控制手段和方法、高精度高速度的数学模型。板形仪主要有接触式和非接触式两大类,接触式板形仪通过测量带钢张力的横向分布反映板形,非接触式板形仪通过测量带钢浪形反映板形。接触式板形仪可靠耐用精度高,应用广泛,发展趋势为整辊式板形检测辊、无线式信号传输装置、板形数据的精确处理。板形控制数学模型的主要类型,按建模的原理和方法可分为机理模型和智能模型;按模型的性质和作用可分为分析模型和控制模型;按板形的表示方法可分为多点控制模型和分量控制模型。板形控制模型的发展趋势为机理与智能协同建模、动态模拟预报和动态解耦控制、多种手段和方法的协同优化。进一步提高板形测控技术水平需要突破3项关键问题,即整辊式板形仪通道耦合与解耦的机理模型、板形控制的动态模拟和动态解耦模型、板形控制的高精度智能建模方法。     

弧焊逆变电源的发展趋势分析

本文针对弧焊逆变电源中的几个关键问题，如功率开关器件的性能特点，增大输出变压器的功率，逆变电源的智能控制等，评述了当前的技术水平及今后的发展趋势。     

伪随机流场法在堤坝渗漏探测中的应用与研究

伪随机流场法具有快捷、直接、精确有效等优点,逐步成为堤坝渗漏探测的主流方法。利用该方法,在漏水区域、库区无穷远段进行高压供电,库区内网格状布置测点,可查找渗漏入水点。通过对各异常区域的区域面积、异常区域内各测点的异常平均值以及对于严重渗漏的临界值进行计算,可判断水库渗漏通道和各渗漏点的渗漏量比例。此外,由于该方法快速便捷的特点,可以运用该方法进行实时监测。应用于某混凝土面板堆石坝的探测结果表明,利用堤坝周边已经存在的监测孔或在灌浆帷幕下游进行钻孔,进行伪随机电位差或者电流测试,可在无损条件下判断渗漏来源和通道发育方向,检测防渗处理效果。该方法可为堤坝渗漏监测预警、拟定防渗处理方案提供依据。     

硅酸根分析仪在火电厂水处理中的应用

FIA－33型自动分析仪是采用先进的流动注射技术，固体冷光源光纤技术及现代微机技术相结合的一种智能型在线水质分析仪器，成功地实现 了锅炉水（汽）硅酸根的快速在线实时监测，阐述了硅酸根自动分析仪的特点，分析流程及工作原理，并结合近几年来的现场应用实践进行分析总结。     

Decision support and intelligent systems in the textile and apparel supply chain: An academic review of research articles

This article provides a comprehensive review of research articles related to the application of decision support and intelligent systems in the textile and apparel supply chains. Data were obtained from 77 articles published from 1994 to 2009 in 35 journals. The articles were categorized according to their applicability into three basic sectors – textile production, apparel manufacture, and distribution/sales. They were further categorized into 16 subsectors based on their operational and management/control processes. A comprehensive list of categorized journal articles identified in this study provides insights and relevant references for both researchers and practitioners on the application of decision support and intelligent systems to various stages of a textile and apparel supply chain. In light of the developed classification framework, we identify gaps in extending the use of the decision support and artificial intelligent systems in the industry and suggest potential and applicable research areas for further consideration in this subject area.     

A hybrid intelligent system for medical data classification

In this paper, a hybrid intelligent system that consists of the Fuzzy Min–Max neural network, the Classification and Regression Tree, and the Random Forest model is proposed, and its efficacy as a decision support tool for medical data classification is examined. The hybrid intelligent system aims to exploit the advantages of the constituent models and, at the same time, alleviate their limitations. It is able to learn incrementally from data samples (owing to Fuzzy Min–Max neural network), explain its predicted outputs (owing to the Classification and Regression Tree), and achieve high classification performances (owing to Random Forest). To evaluate the effectiveness of the hybrid intelligent system, three benchmark medical data sets, viz., Breast Cancer Wisconsin, Pima Indians Diabetes, and Liver Disorders from the UCI Repository of Machine Learning, are used for evaluation. A number of useful performance metrics in medical applications which include accuracy, sensitivity, specificity, as well as the area under the Receiver Operating Characteristic curve are computed. The results are analyzed and compared with those from other methods published in the literature. The experimental outcomes positively demonstrate that the hybrid intelligent system is effective in undertaking medical data classification tasks. More importantly, the hybrid intelligent system not only is able to produce good results but also to elucidate its knowledge base with a decision tree. As a result, domain users (i.e., medical practitioners) are able to comprehend the prediction given by the hybrid intelligent system; hence accepting its role as a useful medical decision support tool.     

六面顶金刚石压机液压系统压力及超高压优化控制

针对六面顶人造金刚石压机的复杂生产流程要求,设计开发了六面顶人造金刚石压机液压系统的计算机控制装置.其中液压系统压力控制部分采用外置模拟式PI调节器,可根据生产工序的要求自动优化控制器设定值;超高压控制部分采用智能预测与纯比例控制相结合的控制策略,明显提高了人造金刚石压机的液压控制精度.该控制装置已投入实际运行,在改善产品质量品级方面取得了显著的经济效益.     

水泥回转窑的智能控制

文章介绍了PIT Navigator对水泥熟料生产自动化控制的实现,基于神经网络的自学习、自适应控制元件,将相关的过程数据记录下来,随后借助数据关联性进行分析,在预测和自学习过程模型(模型预测控制)中处理这些数据,并计算过程参数的实时预测,使用这些工具,可以实现更稳定的窑况,同时提高产量和降低能耗。