大型火电机组热力系统变工况经济性分析

基于热力系统的小扰动理论,在热系统变工况计算中考虑汽轮机内汽态膨胀线变化,建立了大型火电机组热力系统变工况计算的数学模型。利用该模型计算得到了主蒸汽温度、主蒸汽压力、真空、再热汽温度、过热器喷水量和再热器喷水量发生扰动时,对机组效率和标准煤耗的定量影响。结果表明,主汽温度、再热汽温度、过热器喷水、再热器喷水的影响基本呈线性关系,而主汽压力和汽轮机真空对机组的影响则是非线性的。     

基于QPSO-LSTM网络的火电机组一次调频能力建模

为了提升火电机组一次调频能力,提出一种基于长短期记忆网络(Long Short Term Memory Network, LSTM)与量子粒子群算法(Quantum behaved Particle Swarm Optimization, QPSO)的一次调频能力计算方法。将负荷指令、机组实发功率、主蒸汽压力、汽轮机总阀位开度和发电机转速作为特征变量,基于某600 MW燃煤火电机组调峰运行工况下的实际数据,构建一次调频能力计算模型。利用QPSO算法优化模型隐含层节点数、训练次数和学习率,解决了因网络结构及模型参数的不确定性产生的精度问题,并将该模型与传统的神经网络模型进行了对比。结果表明：本文所提出的方法具有更高的模型精度,从而能够为机组一次调频能力的限制因素分析和调频性能的优化提升提供模型基础。     

基于遗传算法的BP神经网络在电站锅炉主蒸汽温度控制系统中的应用研究

在现代火力发电厂中,对锅炉主蒸汽温度的控制是非常严格的。由于主蒸汽温度具有延迟大、惯性大、非线性等特性,导致对其控制比较困难。利用神经网络的学习能力和鲁棒性以及遗传算法的全局随机搜索能力,在常规PID控制基础上,提出采用二者相结合的PID控制策略。通过计算机仿真表明,基于遗传算法的BP神经网络的PID控制策略具有更好的控制品质,具有较广阔的应用前景。     

F级余热锅炉蒸汽温度控制策略

以9FA燃气轮机配套的余热锅炉为例,介绍了F级余热锅炉特点及蒸汽减温配置,主蒸汽温度、二级高压过热器出口温度及再热蒸汽温度的控制策略,过热度保护和最小流量保护的实现方法。机组启动阶段,IGV参与燃气轮机排气温度控制,此时采用IGV角度前馈来稳定启动期间的主蒸汽温度。     

A neural net model-based multivariable long-range predictivecontrol strategy applied in thermal power plant control

A constrained multivariable control strategy along with its application in more efficient thermal power plant control is presented in this paper. A neural network model-based nonlinear long-range predictive control algorithm is derived, which provides offset-free closed-loop behavior with a proper and consistent treatment of modeling errors and other disturbances. A multivariable controller is designed and implemented using this algorithm. The system constraints are taken into account by including them in the control algorithm using real-time optimization. By running a simulation of a 200 MW oil-fired drum-boiler thermal power plant over a load-profile along with suitable PRBS signals superimposed on controls, the operating data is generated. Neural network (NN) modeling techniques have been used for identifying global dynamic models (NNARX models) of the plant variables off-line from the data. To demonstrate the superiority of the strategy in a MIMO case, the controller has been used in the simulation to control main steam pressure and temperature, and reheat steam temperature during load-cycling and other severe plant operating conditions     

高中压合缸汽轮机的冷却蒸汽确定方法试验研究

叙述了高中压缸合缸汽轮机结构及主要特点。对于高中压合缸机组采用不同高压调节阀全开(两阀、三阀、四阀)状态下,通过分别改变主蒸汽温度和再热蒸汽温度试验,可求得高压缸进入中压缸蒸汽量占再热蒸汽量份额,为确定再热蒸汽流量和计算汽轮机热耗率提供依据。通过试验研究,对于采用高压缸后轴封一漏到中排布置的反动式汽轮机,高压调节阀三阀全开状态下得到的影响系数,较两阀全开状态下受到高压缸排汽影响要小,其结果更接近实际。     

电厂过热汽温控制系统的改进及其PID鲁棒整定

根据某300MW火电机组锅炉过热器的结构特点，对原有的过热汽温控制系统结构进行了改进，改进后的控制系统能够减小过热蒸汽混合前两侧温度的偏差，从而减小过热器出口温度的波动，同时有利于锅炉的安全运行。考虑到汽温对象在负荷变化过程中的不确定性，引入了鲁棒性指标，并采用遗传算法寻优对PID控制器的参数进行了整定，实际运行结果显示了改进后控制系统的实用性。图8参6     

Modelling of a Superheater Heat Exchanger with Complex Flow Arrangement Including Flow and Temperature Maldistribution

A network approach was used to develop a thermofluid process model of a cross-flow primary superheater heat exchanger with complex flow arrangement in the convective pass of a coal-fired boiler. The model solves the transient one-dimensional forms of the conservation equations for mass, energy, and momentum, combined with the applicable closure relations, boundary values, and initial values. The dual-tube 12-pass superheater was discretized along the flue gas flow path as well as along the steam flow path. The model accounts for the convective thermal resistance on the steam side, the conductive thermal resistances of the tube wall, and scaling or fouling on the tube walls, as well as the convective and radiative thermal resistances on the flue gas side. The model was qualitatively validated using real plant data and for reference purposes also systematically compared to conventional lumped parameter models. The ability of the model to analyze the effect of the ramp rate during load changes on the tube metal temperature was demonstrated, as well as the ability to determine the maldistribution of flow and temperature on the steam and flue gas sides. Models such as this can be employed to study complex thermofluid process phenomena that may occur during intermittent, transient, and low-load operation of power plants. This could form the basis for improving operations and for the development of advanced tools for online process condition monitoring.     

Dynamic behavior of superheated steam and ways of control

A simple way of calculating the dynamic behavior of a superheater is presented. A comparison of the measured data with the calculated result verifies the accuracy of this simple method. It is the first time that a phase compensation for real roots, i.e., the twin lead/lag loop which is facile for engineering applications, is used in superheated steam temperature control. Numerous simulation results show that both the response time lapse and maximal dynamic deviation are greatly reduced. Moreover, a formula to calculate the setting parameters is presented, together with a practical example of its engineering application in superheated steam temperature control with single-stage attemperation in a power plant boiler. This method can remarkably improve the control performance of superheated steam temperature and makes it possible for one stage attemperation to be sufficient for the superheater of power plant boilers, thus simplifying the superheater system and reducing investment. Because the control performance is remarkably raised, the set values of the steam temperature control system can be raised above rated values and also the operational economy, without impairing the operation safety.     

Dynamic behavior of superheated steam and ways of control

A simple way of calculating the dynamic behavior of a superheater is presented. A comparison of the measured data with the calculated result verifies the accuracy of this simple method. It is the first time that a phase compensation for real roots, i.e., the twin lead/lag loop which is facile for engineering applications, is used in superheated steam temperature control. Numerous simulation results show that both the response time lapse and maximal dynamic deviation are greatly reduced. Moreover, a formula to calculate the setting parameters is presented, together with a practical example of its engineering application in superheated steam temperature control with single-stage attemperation in a power plant boiler. This method can remarkably improve the control performance of superheated steam temperature and makes it possible for one stage attemperation to be sufficient for the superheater of power plant boilers, thus simplifying the superheater system and reducing investment. Because the control performance is remarkably raised, the set values of the steam temperature control system can be raised above rated values and also the operational economy, without impairing the operation safety. __________ Translated from Journal of Power Engineering, 2007, 27(2): 199–203 [译自: 动力工程]     

基于BP神经网络的供热机组低压缸质量流量在线监测方法

汽轮机低压缸质量流量的实时监测对极寒地区大型供热机组具有重要意义,但却存在难以在现场直接测量的问题。提出了一种基于BP神经网络的供热机组低压缸质量流量在线监测方法。以机组负荷、主蒸汽流量、主蒸汽压力和中压缸排汽压力作为输入,以低压缸质量流量为输出,建立BP神经网络计算模型,利用插值方法获取样本数据。最后,基于PI数据平台开发了汽轮机低压缸质量流量的实时监测系统,并在2台600MW供热机组上进行了实际应用测试。结果表明,该系统给出的常运行工况监测值与经验值是相吻合的,对极寒温度下机组低负荷、大流量供热运行时的空冷岛防冻预警具有一定的指导意义。     

基于XGBoost建模及改进灰狼优化算法的再热汽温预测优化控制

为改善燃煤机组频繁变负荷过程中再热汽温的控制效果,提出一种基于机器学习的再热汽温预测优化控制方法。首先利用机组变负荷历史运行数据和XGBoost算法进行再热汽温特性建模,并采用随机搜索算法对模型参数进行优化以提高其预测精度。以最终的模型为基础,采用改进的灰狼优化算法(IGWO)对烟气侧再热挡板开度和蒸汽侧喷水减温阀指令进行实时寻优,实现再热汽温的预测优化控制。利用仿真机进行优化控制仿真试验。试验结果表明：采用智能预测优化控制方案可有效改善再热汽温控制效果,明显减少减温喷水用量,有助于提高机组的经济性。     

Modeling of Thermal Performance of a Cooling Tower Using an Artificial Neural Network

Abstract

In the present study, the ability of an artificial neural network model to evaluate the thermal performance of a cooling tower, which used in the heating, ventilating, and air conditioning industries to reject heat to the atmosphere, is examined. The network is trained with the following experimental values: the ratio of the water mass flow rate to air mass flow rate, the inlet water temperature, and the outlet water temperature, and the inlet air wet-bulb temperature are selected as input variables, while the output is the coefficient of performance. It is concluded that a well-trained neural network provides fast, accurate, and consistent results, making it an easy-to use tool for preliminary engineering studies.     

Optimal thermodynamic and economic volume of a heat recovery steam generator by constructal design

The ratios of gas flow to steam flow are huge in heat recovery steam generators (HRSGs) compared to other steam generators. So the volume which is occupied by components of the HRSG such as economizer, evaporator and superheater is important factor when the HRSG is applied in structures including buildings and ships. The optimum volume of a HRSG is deduced through optimization of entropy generation and cost evaluation. By increasing volume, second law of thermodynamics is improved, but this improvement may not be economical. In this work, the best dimensions and arrangements of flows in HRSG are obtained by constructal design and the optimization method is algorithm genetic. In this case, super heater temperature, pinch point, water/steam flow rate and gas pressure drop are derived from configuration which designed by constructal theory for HRSG. The effects of gas flow rate and inlet gas temperature are examined on the values of optimum volume.     

神经网锅炉自动控制系统

本文建立了ｉ－５－１神经网络结构。通过对网络的训练,建立了母管压力、汽包压力、锅炉蒸发量、锅炉给水温度等参数与给煤机转速和二次风门开度之间的关系。实践证明：锅炉计算机自动控制系统中用神经网预测被调节参数可以大大提高控制效果。     

Assessment of the Superheater Ash Fouling Using a Numerical Model of the Superheater

ABSTRACT

Superheaters are high-temperature cross-flow heat exchangers. Steam flows inside the tubes, and the flue gas outside in a direction perpendicular to the axes of the tubes. However, they differ very substantially from the other heat exchangers operating at low temperatures. Superheaters are characterized by complex flow system and high tube walls temperature. Superheaters are among the most exposed to damaging pressure elements of steam boilers. Damage to the superheater causes about 40% of emergency shutdowns of boilers. The paper presents the boiler superheater model with distributed parameters, which is used to determine on-line the degree of superheater fouling by ash.     

基于改进型GA优化FNNC的SG水位控制系统仿真研究

蒸汽发生器水位直接影响到整个核电站的安全及稳定运行,但蒸汽发生器本身由于所具有的高度复杂性、非线性性、时变性等特性,导致传统的串级PID控制等方法难以取得好的控制效果.本研究在串级控制的基础上,采用模糊神经网络来对蒸汽发生器水位进行控制,该控制算法能够充分发挥模糊控制及神经网络的优点.另外,为了减小模糊神经网络参数初值的选择对控制器的性能影响,将一种改进型遗传算法用于模糊神经网络控制器的参数优化.仿真结果表明,设计的控制方法无论是抗干扰能力还是在鲁棒性方面与传统的串级PID控制及常规的模糊神经网络控制相比较都有了很大的提高.     

循环流化床锅炉燃烧系统动态特性分析

根据循环流化床锅炉(CFBB)的工作特点以及燃烧系统输入和输出过程变量间的耦合关系,讨论了CFBB的蒸汽压力和床温的动态特性。认为引起蒸汽压力变动的主要原因在于燃料量(内扰)和汽轮机调门的变化(外扰);而影响床温变化的主要因素是给煤量、风量、物料循环量的变动,并从传热和燃烧过程分析了这些因素间的相互耦合关系。这对CFBB燃烧自动控制系统的设计与调试,以及整个控制系统的可靠运行都至关重要。     

Performance prediction of a RPF‐fired boiler using artificial neural networks

In order to provide adequate engineering assistance and to improve the energy efficiency in process industries, it is crucial to evaluate the operational performance of a boiler in terms of its practical requirements, viz. temperature, pressure, and mass flow rate of steam. This study was aimed at assessing and optimizing the performance of a refuse plastic fuel‐fired boiler using artificial neural networks. A feed‐forward back propagation neural network model was developed and trained using existing plant data (5 months), to predict temperature, pressure, and mass flow rate of steam, using the following input parameters: feed water pressure, feed water temperature, conveyor speed, and incinerator exit temperature. The predictive capability of the model was evaluated in terms of mean absolute percentage error between the model fitted and actual plant data, while sensitivity analysis was performed on the input parameters by determining the absolute average sensitivity values. The higher absolute average sensitivity value of the incinerator exit temperature in comparison to that of feed water pressure, feed water temperature and conveyor speed suggested that the change of incineration exit temperature has a significant influence on the selected outputs (steam properties). Overall, the good results observed from this work demonstrate the fact that artificial neural networks can efficiently predict the data on steam properties and could serve as a good tool to monitor boiler behavior under real‐time conditions. Copyright © 2013 John Wiley & Sons, Ltd.     

Application of artificial neural networks (ANN) for modeling of industrial hydrogen plant

A back propagation feed forward artificial neural network (ANN) with three layers is used for modeling of industrial hydrogen plant. The required operating data for training of ANN is obtained by modeling and simulation of an industrial hydrogen plant. The operating data are calculated by changing effective parameters such as feed temperature, reformer pressure, steam to carbon ratio and carbon dioxide to methane ratio in feed stream. Tangent sigmoid transfer function is used in the hidden and output layer and the proposed neural network is trained with a gradient descent algorithm. The optimum number of neurons in hidden layer is determined as optimum value with minimizing of the mean square error (MSE). With changing of effective parameters, the model predicts temperature, pressure and mole fraction of hydrogen and carbon monoxide in the product of the hydrogen plant. The result can be used to gain better knowledge and optimize of the hydrogen production plants.