神经网络球磨机出力软测量模型的建立

为了准确地获得球磨机的制粉出力,提出了用灰熵关联分析法分析球磨机制粉出力的影响因素,选择对球磨机制粉出力影响较大的几个因素作为辅助变量建立模型,以最优拉丁超立方法选取的数据作为训练样本,基于BP神经网络建立球磨机出力软测量模型,并选出几组样本验证所建模型的可靠度.结果表明:所建立的球磨机出力软测量模型预测输出误差较小,有较强的泛化能力,具有很好的测量性能.     

球磨机料位软测量及其低能耗高效运行研究

球磨机是制粉系统中的重要设备,同时也是耗能较大的设备之一,用电量高达厂用电的20％左右。制粉系统球磨机料位受多个因素影响,文中根据多传感器变量软测量的思路,应用CMAC神经网络原理和方法,对其影响因素中有很高控制价值的量进行软测量建模,并设计实验测试模型性能。证明该模型可较好地反映实时料位,提高了球磨机的效率,降低了电耗,为制粉系统球磨机的控制和优化提供了指导。     

灰色软测量在球磨机料位检测中的应用

1引言目前我国电厂锅炉制粉系统相当一部分配备了低速钢球磨煤机,采用中间仓储式结构,但该系统绝大部分未能达到经济工况运行,原因之一是磨内负荷难以直接测量[1]。因此,解决磨内负荷的测量问题不论对于其控制还是经济运行和监测均具有十分重要的意义。近年来,对球磨机筒内负荷     

球磨机料位监控技术及制粉系统优化运行

由于钢球磨煤机运行时只有载煤量的监控技术,球磨机制粉系统只能采用手动调节的习惯运行方式。本文阐述了球磨机制粉系统的能量平衡,球磨机和排粉机的负荷功率特性和负荷的稳定性,球磨机科位监控技术,制粉系统优化运行。     

基于神经网络的风力发电系统风速软测量

对风力发电并网系统的有效风速测量问题进行研究.鉴于神经网络可应用于非线性系统的模型与辨识,不受非线性模型类的限制,且可给出工程上易于实现的学习算法,提出基于神经网络的有效风速软测量.对实时采集的风力发电机组的风速样本参数集进行分析、训练及拟合,获得相应的有效风速计算网络.仿真结果表明,有效风速软测量可代替风速仪的作用,是一种非常有效的风速估计方法.     

基于延迟特性的NOx浓度软测量与喷氨优化

针对NO_x浓度测量延迟导致NO_x排放浓度波动较大的问题,为提升脱硝系统运行的稳定性,试验分析了NO_x浓度测量的延迟时间和锅炉关键控制参数改变后SCR入口NO_x浓度的响应时间,建立了表征锅炉运行动态特性的SCR入口NO_x浓度软测量的数据结构,进一步建立了基于XGBoost算法的动态工况下SCR入口NO_x浓度实时软测量模型。结果表明：SCR入口NO_x质量浓度的测量延迟时间约为1 min,软测量模型能够提前近1 min得到实际NO_x质量浓度,软测量曲线与实际曲线具有理想的跟随性和准确性;软测量模型在660 MW机组上投入应用后,喷氨流量曲线和NO_x排放质量浓度曲线的稳定性得到显著提升。     

中间储仓式制粉系统球磨机模糊控制理论与实践

对中间储仓式制粉系统的自动控制问题进行了理论研究和分析,提出了分级、预测的模糊控制算法。在３００ＭＷ发电机组的实际应用表明,这种控制方法可提高系统的可靠性和经济性,使系统的运行品质得到明显改善。     

基于神经网络的电站锅炉飞灰含碳量软测量系统

借助于正交试验设计,对某台200MW机组燃煤锅炉飞灰含碳量特性进行了多工况热态测试,获得了数据样本,采用基于Levenberg-Marquardt(LM)算法的BP神经网络,建立了飞灰含碳量软测量模型,通过仿真计算,证明了飞灰含碳量软测量模型的正确性和有效性。     

基于数据融合的烟气含氧量软测量技术综述

软测量技术在过程控制领域中有重要的应用,对于关键的且难于检测的过程变量,研究如何对其建立软测量模型有着重要的意义.将数据融合技术应用到软测量的数据处理上,有效提高了软测量预测值可靠性和准确性.锅炉烟气含氧量是计算锅炉过量空气系数的关键参数.在实际生产过程中,用于测量此参数的氧化锆传感器可靠性不佳.针对这一问题,关于烟气含氧量的软测量建模研究硕果连连.在参考大量相关文献的基础上,对其研究现状及发展前景做了简单的归纳.然而糖厂锅炉有其自身的特殊性,其燃料有蔗渣和煤两种,而蔗渣燃烧时,过量空气系数通过CO2的检测更为简单,这就对软测量建模提出了新的要求.     

基于模糊神经元网络的球磨机控制系统的改进

球磨机是一个多变量的复杂非线性系统,介绍了设计的由模糊控制器和神经元控制器结合的控制系统,用PLC加以实现,取得了对球磨机良好的控制效果.     

Research on the optimizing control technology based on fuzzy-neural network for hydrogen-fueled engines

Hydrogen fuel is regarded as one of the most promising alternative fuels for automobiles in future. Technology of the optimum control on hydrogen-fueled engines is a key to improve its performances in every respect. In this paper, based on the experiments, the policy of optimum control on hydrogen-fueled engines has been shown. Moreover, a new optimizing control model on hydrogen-fueled engines has been constructed, in which ignition timing, injection timing and injection duration were separately selected as control variation, and output power and rate of fuel consumption are separately chosen as performance index function. Further, a new method ingeniously adopting fuzzy-neural network (FNN) system to calculate the optimizing control laws for the optimizing control model has been designed, and a series connection control system has been set up, which is composed of FNN controllers combined with an adaptive controller for ignition timing to realize open-loop or closed-loop control pattern with stepping regulation of ignition timing. Last, the calculated results of the control variations with an improved FNN system were contrasted with experimental results; the contrasting result has shown that the maximum absolute error is less than 1 °C A, the maximum relative error is less than 5%, mean square error is 0.381 °C A. Therefore, the calculation method with FNN system is practical and satisfactory.     

无密封风机的双进双出磨煤机正压直吹式制粉系统设计

国电聊城电厂二期2×600MW超临界机组工程,设计煤质、校核煤质均为低挥发分贫煤,制粉系统采用了双进双出钢球磨煤机正压直吹系统。在初步设计阶段,每台炉设置了两台100％容量的密封风机,之后的施工图设计中,经过充分调研,制粉系统中取消了密封风机,磨煤机的密封风取自冷一次风。经一系列的设计优化,最终使磨煤机的密封风压力高于制造厂家的要求。从试运行一直到满负荷发电,现已运行近一年的时间,磨煤机没有出现漏风、漏粉现象,现场制粉系统运行良好。电厂节能、降耗效果显著。     

基于多智能体的发动机智能控制仿真与试验研究

本文研究了多智能体在发动机控制中的应用。所提出的发动机多智能体控制系统是由不同功能的多个独立智能体组成,通过信息融合,可将发动机控制的各种任务分配给不同的智能体。每个智能体完成各自承担的任务,由一个系统的智能体监控、协调所有智能体的动作并负责整个控制系统的运行。该控制方法的显著特点是模仿人的思路将复杂的问题简化,选择不同方法对多工况、非线形系统进行有效地控制。控制软件采用分层模块化结构,便于采用分时多任务机制,提高了控制效果。仿真和试验结果表明：多智能体控制系统比常规控制方法具有更好的稳定性、更快的动态响应特性。     

基于模糊决策的路灯节电等级控制系统的设计

此节能型路灯照明智能控制系统以单片机为核心,采用了电压、时间及光控制相结合的方法,利用模糊决策理论对节电等级进行控制,可有效改善路灯照明质量,节约电能及延长灯具的使用寿命,达到了很好的节电效果。     

基于GIS的城市生活垃圾规划管理智能决策系统

提出对城市生活垃圾治理系统实施规划管理,是实现垃圾治理”减量化、资源化、无害化”目标,推进城市经济可持续发展的根本方法。系统地分析了“基于GIS的城市生活垃圾规划管理智能决策系统”的总体架构,确定了应用系统的组成及各部分功能。     

Preparation and evaluation of a new hybrid support based on exfoliation of graphite by ball milling for Ni nanoparticles in hydrogen evolution reaction

A mixture of graphene/graphite as new support was prepared by ball milling procedure and was used for Nickel nanoparticles supported that was employed as a cathode catalyst for hydrogen evolution reaction (HER) in the KOH solution. The structure and electrocatalytic activity of electrocatalyst were investigated by Fourier transform infrared spectroscopy (FTIR), Raman spectroscopy, transmission electron microscopy (TEM), X-ray diffraction (XRD) analysis, and electrochemical techniques. The results indicated that by raising the time of the ball milling from 0 to 270 min, the HER activity of electrocatalyst first increased, and then decreased according to the increase of active sites and then agglomeration of Ni nanoparticles. Ni nanoparticles supported on the mixture with 180 min ball milling exhibited the highest HER activity with a low overpotential (205 mV at 10 mA cm^?2), Tafel slope of 84 mV dec^?1, and remarkable durability.     

Research on optimizing control model of hydrogen fueled engines based on thermodynamics and state space analysis method about nonlinear system

With its obvious advantages, hydrogen is expected to be greatly used as a new energy, which can reduce vehicle emissions effectively and efficiently. Besides, it can be adopted as an alternative fuel for petroleum fuel of internal combustion engine. However, due to its unique physical and chemical characteristics, hydrogen often leads to abnormal combustion and decay of power, which can be effectively dealt with by optimal control. In this paper, thermodynamic analysis methods, like mass transfer and energy transfer, is combined with state space analysis methods of nonlinear control system, so that an optimal control model of nonlinear combustion control system for hydrogen fueled engines can be established. Through illustrating the inner relations between combustion and energy transfer of hydrogen fueled engines and operating parameter, state parameter and performance index, this paper provides theoretical analysis and found experimental research for promoting abnormal combustion and performance index after controlling operating parameters optimally and changing state parameters of the cylinder. Based on nonlinear programming theory and multi-objective genetic algorithm, the methods of establishing the optimal control model and carrying out the optimal value of operating parameters are shown in this paper. What’s more, some new ways are proposed to integrate the optimal control aspects of multi-variate, multiple targets and multiple constraints for hydrogen fueled engines by changing the multi-objective and multi-constraint optimal control into the single-target integrated optimal control.     

浅析电信撬箱体智能监控识别系统的应用

当前,人工智能给人们的生产和生活方式带来革命性变化,油气田开发领域也将陆续进入智能化时代,未来将实现全自动钻井,一些关键的作业将实现远程操控,通过现场智能控制平台将地面智能化和井下智能化组成一个有机整体,通过物联网将现场智能钻井与远程实时智能控制中心构成一个大的有机整体,实现现场+远程的大闭环控制。现有技术中,钻井工程的电力传动、控制、通信等系统撬装化技术日益成熟,为站场的供配电系统、自动控制系统、通信系统的整体技术集成及设备撬装化提供了可行的解决方案。