NEURAL NETWORK INTELLIGENT SYSTEM FOR THE ON-LINE OPTIMIZATION IN CHEMICAL PLANTS

A strategy of developing on-line optimization intelligent systems based on combiningflowsheeting simulation and optimization package with artificial neural networks(ANN)is presented inthis paper.A number of optimization cases for a certain chemical plant are obtained off-line byusing PROCESS-Ⅱ or other flowsheeting programming with optimization.Then,taking these cases astraining examples,we establish a neural network systems which can be used on-line as an optimizer toobtain setpoints from input data sampled from distributed control system through gross error detectionand data reconciliation procedures.Such an on-line optimizer possesses two advantages over nonlinearprogramming package:first of all,there is no convergence problem for the trained ANN to be usedonline;secondly,the frequency for setpoints updating is not limited because only algebraic calculationrather than optimization is required to be carried out on-line.Here two key problems ofimplementing ANN approaches to the on-line optimization

On-line Condition Monitoring and Diagnostic Network System for Rotating Machine Set

Several industrial computers and a server are combined to set up the on-line monitoring and diagnostic system of turbo-generator sets. The main function of the system is to monitor machine sets' running condition. Through analyzing running data, technicians can detect whether there exist faults and where they occur. To share and transmit the dynamic information of the turbo-generator sets, a distributed network system is introduced. NetWare network operating system is used in the LAN (Local Area Network) system. The LAN is extended to realize the sharing of data and remote transmission of information. Furthermore, functions of monitoring and diagnostic clients are listed.

ON-LINE STATE PREDICTION OF ENGINES BASED ON FLAT NEURAL NETWORK

A flat neural network is designed for the on line state prediction of engine. To reduce the computational cost of weight matrix, a fast recursive algorithm is derived according to the pseudoinverse formula of a partition matrix. Furthermore, the forgetting factor approach is introduced to improve predictive accuracy and robustness of the model. The experiment results indicate that the improved neural network is of good accuracy and strong robustness in prediction, and can apply for the on line prediction of nonlinear multi input multi output systems like vehicle engines.

RESEARCH ON EXPERT SYSTEM OF FAULT DETECTION AND DIAGNOSING FOR PNEUMATIC SYSTEM OF AUTOMATIC PRODUCTION LINE

Fault detection and diagnosis for pneumatic system of automatic productionline are studied. An expert system using fuzzy-neural network and pneumatic circuit fault diagnosisinstrument are deigned. The mathematical model of various pneumatic faults and experimental deviceare built. In the end, some experiments are done, which shows that the expert system usingfuzzy-neural network can diagnose fast and truly fault of pneumatic circuit.

The Technique of Building a Networked Manufacturing Process Monitoring System

This paper introduces the constitute,structure and the software model of a set of networked manufacturing process monitoring system,using JAVA network technique to realize a set of three layer distributed manufacturing process monitoring sys- tem which is comprised with remote manage center,manufacturing process supervision center and the units of measure and control layer such as displacement sensor,the device of temperature measure and alarm etc.The network integration of the production management layer,the process control layer and the hard ware control layer is realized via using this approach.The design using object-oriented technique based on JAVA can easily transport to different operation systems with high performance of the expansibili- ty.

Optimum line reclosing time for the enhancement of interconnected power system stability

Automatic line reclosing schemes used in an extra-high-voltage power system is an economical and effective means to maintain transient stability. A novel method is proposed in the paper to adaptively optimize the automatic line reclosing time after a transient fault for enhancement of interconnected power system transient stability. Both the study on the transient energy over network and the structure-preserving multi-machines power system model illustrate that the excessive convergence of potential energy on the lines with a certain cutset deteriorate power system stability, and therefore, an optimum line reclosing strategy can be established by minimizing the change in transient potential energy distribution across a cutset lines in the vicinity of the faulty line as an optimization target, and the optimal reclosure time is set to the time of minimum line phase angle difference. Without any pre-determined knowledge, the method is adaptive to various power system operation modes and fault conditions, and easy to implement because only a limited number of data measured at one location on a tie-line linking sub-networks are required. Simulations have been performed with the OMIB(One Machine and Infinite Bus System) and a real inter-connected power system to verify the applicability of the method proposed.

基于计算机网络算法的智能采摘机器人设计

为了提高采摘机器人的路径规划能力,基于计算机网络算法设计了智能采摘系统。首先,采摘机器人采集农田图像时,基于PSPNet网络算法,设计改进型计算机网络算法,实现农田环境因素识别;其次,识别获得道路特征图,并进行图像处理,得到道路边缘,拾取道路两边缘中线离散点,进行引导线拟合;最后,采用双目视觉系统实现障碍物定位,进而建立路径规划函数,当路径规划函数取最小值时,道路规划最优。对引导线精度进行测试,结果表明:误差分布范围为-1.2%~5.3%。对障碍物测距进行测试,结果表明:机器人和行人之间的相对偏差分布区间为[-2.2%,2.8%],和车辆之间的相对误差分布区间为[-2.9%,3.4%]。

基于GIS技术的电力通信光缆线路故障智能定位系统

为提升电力通信光缆线路故障定位性能,设计基于GIS技术的电力通信光缆线路故障智能定位系统。搭建系统硬件网络架构,描述光时域反射计的内部结构,分析光时域反射计检测过程的示意图,利用公式计算光缆线路长度,得到实测的OTDR曲线。软件设计方面,将通信光缆线路遥感数据以及其他信息经过变换、拼接、矢量化处理后完成GIS地图数字化转换,根据这些数据进行故障智能定位算法设计。测试结果表明:设计系统的故障定位结果与实际值间偏差小,获得了电力通信光缆线路故障高精度定位结果。

多点起爆技术及应用研究进展

综述了爆炸网络多点起爆技术和直列式多点起爆技术的发展,介绍了爆炸网络多点起爆技术的多点同步爆炸网络和多点逻辑爆炸网络的应用现状,分析了两者的优势及不足;对比了直列式多点起爆技术的国内外研究现状,讨论了多点起爆点数、起爆方位参数对多点起爆系统性能的影响,指出多点起爆技术未来研究方向为:多点起爆精确控制方法研究,多点起爆装置模块化与集成化研究,低成本多点起爆技术研究,复杂环境下多点起爆系统安全性与可靠性研究。

杭州地铁9号线临平段可视化接地系统联网改造设计方案

杭州地铁9号线全线统一设置可视化接地系统,临平段为原1号线支线,需进行可视化接地系统改造。介绍了临平段可视化接地系统的联网设计方案及联网改造方案,并对设置可视化接地系统后带电检测信号的上传进行了说明。

配电网线损新型定位技术的开发与应用

文章旨在探讨一种新型的配电网线损定位技术,旨在提高电力系统的运行效率,减少能源损失。文章介绍了线损的概念和影响因素,分析了新型定位技术的核心和实施流程,并验证了该技术的可行性和有效性。

基于5G的输电线路在线监测通信网络设计研究

通信网络是输电线路在线监测系统的重要组成部分,关系到监测数据的完整性和安全性。由于现行通信网络在实际监测中的数据通信效果并不理想,吞吐量较低且丢包率较高,通信网络性能存在一定缺陷。为解决这一问题,文章提出基于5G的输电线路在线监测通信网络设计。利用5G技术来设计输电线路在线监测的通信网络模型和信道,同时基于开放式系统互连(Open System Interconnect,OSI)参考模型来设计通信网络协议,从而完成基于5G的输电线路在线监测通信网络的整体设计。经实验验证,所设计的通信网络吞吐性能良好,丢包率在1%以下,输电线路在线监测通信效果良好。

基于POD-ANNS的架空输电线路舞动响应预测

针对塔线体系下覆冰八分裂导线的舞动特性,通常采用有限元法(FEM)获取舞动响应,但是FEM往往会花费大量时间,获取舞动响应的时间成本巨大,有限模型搭建难度大、类型繁多,同时也必须考虑动力学求解中计算不收敛等棘手问题。因此,获得不同参数、工况下的舞动响应比较困难。该文提出了一种混合代理模型,该模型能基于本征正交分解(POD)和人工神经网络(ANNS)实现舞动响应的快速预测。将FEM得到的舞动响应组合成快照矩阵,然后基于POD方法得到快照矩阵的POD模态基系数和POD模态;使用3种代理模型(BPNN、RBFNN、CNN)预测POD模态基系数,线性组合预测的POD模态基系数和POD模态,实现舞动响应的快速预测;还对比了3种混合模型下(POD-BPNN、POD-RBFNN、POD-CNN)的预测误差,预测时间。结果表明:3种混合模型均能快速、准确地得到目标响应,并且POD-RBFNN混合模型的误差更小;快照数量达到60个,基本可表征出全部样本的特征。

新型电力系统下大规模新能源接入配电网的线损变化趋势分析

分布式光伏发电具有随机性、波动性、地域性等特点,接入配电网中会造成功率波动,进而影响配电网的电能损耗。但是现有的电网线损计算分析并未考虑大规模新能源接入对线损的影响,如果沿用现有方法进行计算及开展接入工作则会造成较大的误差。本文针对分布式光伏发电近年来在贵州爆发式增长的现状及当前并网情况,从分布式光伏发电特征、台区用电特征等方面展开分析,并对光伏接入对台区线损影响进行理论计算与仿真分析;文中以光伏接入电网的实际台区为例,通过历史数据比对和现场应用情况分析,从接入位置、接入容量等方面进行相关验证;最后,总结分布式光伏接入配电网对分线、分台区线损的影响趋势并提出相应策略,为贵州电网10千伏及以下分布式光伏接入系统的方案提供参考依据。

LTE-M技术在大连地铁13号线信号CBTC系统的规划研究

随着通信技术的迭代发展,基于CBTC的无线列车控制系统已逐步代替基于轨道电路的车地通信技术。其中,WLAN技术应用广泛。大连城市轨道交通中地铁1、2号线信号数据通信系统采用2.4 GHz频段的WLAN技术。近几年,随着我国无线网络的迅速普及、Wi-Fi的大量使用,对地铁1、2号线信号系统车地无线通信的稳定性带来了隐患。因此,大连地铁13号线在修建过程中,信号数据通信网络DCS系统采用了1.8 GHz专用频段的LTE-M技术。文章以此为切入点,对大连地铁13号线信号系统LTE-M技术方案进行详细介绍,同时通过对WLAN技术以及LTE技术对比分析,阐述LTE技术在轨道交通车地无线通信系统中具有的技术优势。

Contributing Factors for Delays during the Morning Commute Hours and the Impact of the Spread of COVID-19 for Metropolitan Train Lines in Japan

The present study aims to conduct 2 types of statistical analysis to reveal the impact of the spread of COVID-19 on train delays by comparing the potential contributing factors before, during and after the outbreak of the virus in the metropolitan train lines in Japan. First of all, the result of the present study clearly revealed the changes in contributing factors for train delays caused by the spread of COVID-19. Specifically, the contributing factors for train delays changed due to the decrease of passengers by the effect of the outbreak of the virus. Additionally, though large terminal stations were considered to be a major contributing factor in causing and increasing train delays in the past, this was not the case after the spread of COVID-19. Therefore, under such conditions, it is more effective to make improvements in small to medium stations and tracks rather than terminal stations. Furthermore, as the decrease in passengers also decreased train delays in commuter lines going to the suburbs due to the spread of COVID-19, the contributing factor for such lines is the excessive number of passengers. Therefore, as for countermeasures for train delays after the effects of COVID-19, it is necessary to disperse passengers in order to avoid passengers concentrating in the same time zones and train lines.

输电线路检修无人机机械臂感知检测系统

由于输电线路受到天气、环境和外界因素的影响,导致输电线路出现各种故障和损伤,无法确保电力系统安全稳定运行。为此,设计了输电线路检修无人机机械臂感知检测系统。硬件结构设计包括无人机模块、通信模块、机载吊舱模块、数据处理模块和无人机机械臂零值检测模块,5个功能模块协调配合工作,增强无人机机械臂感知效果。通过模糊神经网络计算无人机机械臂运动轨迹期望位置,实现无人机机械臂感知。实验结果表明,所设计系统具有较好的检测效果,能够有效提高检测精度。

Avian-power line interactions in the Gobi Desert of Mongolia:are mitigation actions effective?

Background:Electrocution and collisions on power lines are among the leading causes of non-natural mortality for birds.Power lines are exponentially increasing,particularly in developing countries,but mitigation strategies to prevent bird mortality are questionable.Mongolia combines a recently increased power line network,an abundant raptor population,a dangerous crossarm configuration and a habitat with no natural perches,producing many bird-power line interactions.Our aim is to assess the bird mortality caused by power lines in the Gobi Desert of Mongolia,to determine the factors increasing the risk of bird electrocution,and to evaluate the effectiveness of used retrofitting measures.Methods:In July 2019 we covered 132.9 km of 15 kV power lines checking 1092 poles.We also conducted bird tran-sects to record raptor and corvid richness and abundance,to assess species vulnerability to electrocution.Results:We recorded 76 electrocuted birds of 7 species.Electrocution rate was 6.96 birds/100 poles.The most affected species were Common Raven(Corvus corax)and Upland Buzzard(Buteo hemilasius),highlighting the electro-cution of 5 endangered Saker Falcons(Falco cherrug).By contrast,we only recorded 8 individuals of 5 species collid-ing with wires,the most affected being Pallas’s Sandgrouse(Syrrhaptes paradoxus).About 76.1%of sampled poles had some mitigation measure.Of these,96.6%were brush perch deflectors and 3.4%rotating-mirrors perch deter-rents.We found differences in electrocution rates among crossarm configurations,with the strain insulator with one jumper being the most lethal.Additionally,we found no correlation between bird abundance and electrocution rates,suggesting that some species are more sensitive to electrocution.Although no differences in total bird electrocu-tion rates were detected between poles with and without perch deterrents,when bird size is considered,deterrents reduced the mortality rate of small birds,while they were ineffective for medium-sized birds.Conclusions:Despite the widespread use of perch deterrents in the Mongolian power line network,there is still an alarming electrocution rate.This strategy is ineffective and some mechanisms,such as brush perch deflectors,may increase the electrocution rate for some medium-sized birds.Finally,we propose strategies to minimize the avian electrocution rate in the Gobi Desert.

计及控制响应的多端混合直流输电系统短路电流近似计算方法

多端混合直流输电系统故障发展迅速、短路电流水平超标问题严重,换流站高度非线性特征使现有短路电流求解忽略了控制系统的响应过程且多依赖建模仿真结果,无法得到短路电流的具体解析式,实现故障特性的定量分析计算。为此,该文提出三种兼顾准确性与计算复杂程度的系统模型简化措施,并在此基础上提出计及控制系统作用的短路电流复频域近似求解方法,利用Pade逼近以及分段线性化法对模型进行降阶处理,通过拉普拉斯逆变换求得短路电流的时域解析式。最后,基于PSCAD/EMTDC对不同故障距离、过渡电阻以及故障类型进行了仿真分析。结果表明,该方法能在故障的暂态阶段(10 ms内)对短路电流有较为准确的刻画,能为直流保护定值整定、断路器额定容量选取、直流输电控制策略切换以及系统规划设计等提供重要依据。