基于现场数据与神经网络的热工对象动态建模

基于神经网络可以建立热工对象的线性或非线性动态数学模型,在论述神经网络辨识与建模原理的基础上,通过对电厂现场数据的分析,分别建立了汽包水位相对于给水流量的线性数学模型和过热汽温相对于比值β的非线性模型。基于神经网络建模计算速度快及模型精度高,模型输出基本上反映了热工对象的实际运行状况。     

HVAC在科威特苏比亚配水工程C1标中的施工设计和应用

室内外空气计算参数的选取是影响HVAC设计的主要因素之一。给出了科威特与我国空气计算参数的比较,并对招标设计中主要设计变更及其原因进行了分析,阐述了承包商在进行HVAC投标报价和施工设计时应注意的事项,以求达到降低承包商在工程施工中的风险和被动因素。经验和教训对国内外水电施工企业提供了较好的借鉴。     

基于小波分析和灰色BP神经网络的滑坡位移预测

滑坡位移时间序列预测对滑坡灾害预警和防治具有重要意义。滑坡位移时间序列具有高度的非线性特征,含有大量噪音且采用常规非线性模型难以准确预测。对此,提出基于小波分析(WA)—灰色BP神经网络的滑坡位移预测模型。该模型先采用小波分析法将滑坡位移时间序列分解为不同频率分量的滑坡子位移,然后采用灰色BP神经网络对各滑坡子位移进行预测,在此基础上将预测得到的各子位移值相加,最终得到预测出的滑坡位移值。以GPS监测获得的郑家大沟滑坡#1监测点的位移时间序列为例,采用WA-灰色BP神经网络模型对其位移进行预测,并与WA-BP神经网络模型及未进行小波分析的单独灰色BP神经网络模型进行对比分析。结果表明,WA-灰色BP神经网络模型准确预测出郑家大沟滑坡#1监测点的位移值,且具有比WA-BP神经网络模型和单独灰色BP神经网络模型更高的预测精度。     

BP/RBF神经网络与模糊规则耦合的电站锅炉燃烧控制

针对电站锅炉NO_x浓度和发电效率的非线性及复杂耦合关系问题,分别建立某320 MW火电机组RBF神经网络模型、BP神经网络模型和模糊规则模型。采用满负荷70%～80%的常规工况进行训练,RBF神经网络有效地预测了发电效率及NO_x排放浓度,平均相对误差分别为2.03%和2.41%。根据专家经验制定25条模糊控制规则,将RBF神经网络的输出值作为模糊控制器输入值,对锅炉运行参数进行调整,并将调整后的值输入BP神经网络进行预测。结合RBF/BP神经网络和模糊控制规则建立了综合优化模型,使NO_x调整值相对于实际值平均下降了7.89 mg/m~3,发电效率提高了1.08%。     

基于遗传神经网络的坝区初始渗流场反分析

为尝试采用遗传神经网络法解决无渗漏量资料的多目标渗流反分析问题,根据遗传神经网络的非线性映射特性,提出了基于遗传神经网络的初始渗流场反演方法,采用正交设计法设计渗流场参数样本,通过有限元分析获得钻孔水位样本,并利用遗传神经网络学习钻孔水位与渗流场各参数的非线性关系得到各参数的反演值。以卡拉水电站右岸坝区为例,反演了岩体和结构面的渗透系数和右岸边界水头,验证表明该方法在渗流场反演中具有较高的精度。     

基于扩展最小资源分配网络的热工过程辨识

针对热工过程中表现出的非线性、时变性、大迟延和大惯性等特点,在分析热工过程辨识实际需要的基础上,采用扩展最小资源分配网络,建立了热工过程的非线性在线网络模型.这种模型能较好地解决神经网络序列在线学习问题,其计算量小、计算精度较高.实例计算验证了这种建模方法的有效性和快速性,为热工过程非线性模型的建立提供了一种新的方法.     

管道阻力计算优化的最短路方法

论述了HVAC系统在管道布线多种方案的情况下 ,根据各点之间的阻力值 ,运用最短路算法选择最优的方案 ,以达到系统的优化节能效果。并通过举例说明     

基于ACC-RBF的水布垭面板堆石坝参数反演分析

蚁群聚类径向基函数(ACC-RBF)神经网络是将蚁群聚类算法和径向基函数神经网络组合运用的一种新型神经网络模型,把该网络用于水布垭高面板坝堆石体的多参数反演问题,在室内试验参数的基础上用有限元计算获得学习样本,采用该网络对坝体堆石料的邓肯E-B模型参数进行反演分析,用反演所得参数结合三维非线性有限元计算坝体应力变形,并...     

基于BP神经网络的主蒸汽流量计算模型

目前大容量机组的主蒸汽流量是由调节级后压力等参数间接计算得到的。由于通流部分状况改变、负荷变动等原因,由传统公式计算得到的结果存在较大偏差。借助神经网络较强的非线性拟合能力、网络泛化及容错能力,构建了基于BP神经网络的主蒸汽流量计算模型。计算结果表明该模型具有较高的准确性和稳定性,调节级后压力的非正常波动对模型的计算结果影响很小,为实际生产过程中主蒸汽流量的计算提供了一种新的思路和方法。     

基于Elman神经网络的工业节水潜力计算方法及应用

工业节水潜力计算是政府制定工业用水规划的重要依据,同时可促进工业节水技术的进步和增强全社会节水意识。基于工业节水潜力计算的研究现状,提出一种新的计算方法,通过定量分析历年节水数据,选取合理的工业节水指标,引入Elman神经网络和误差反传算法进行工业节水潜力计算,并以泰安市工业用水情况为例验证了该计算方法的可行性。结果表明,Elman神经网络模型对节水潜力计算过程中存在的函数关系具有良好的非线性逼近能力。     

Applications of artificial neural networks for refrigeration, air-conditioning and heat pump systems—A review

In this paper, an attempt has been made to review the applications of artificial neural networks (ANN) for energy and exergy analysis of refrigeration, air conditioning and heat pump (RACHP) systems. The studies reported are categorized into eight groups as follows: (i) vapour compression systems (ii) RACHP systems components, (iii) vapour absorption systems, (iv) prediction of refrigerant properties (v) control of RACHP systems, (vi) phase change characteristics of refrigerants, (vii) heat ventilation air conditioning (HVAC) systems and (viii) other special purpose heating and cooling applications. More than 90 published articles in this area are reviewed. Additionally, the limitations with ANN models are highlighted. This paper concludes that ANN can be successfully applied in the field of RACHP systems with acceptable accuracy.     

Short-term prediction of household electricity consumption: Assessing weather sensitivity in a Mediterranean area

Urban microclimatic variations, along with a rapid reduction of unit cost of air-conditioning (AC) equipments, can be addressed as some of the main causes of the raising residential energy demand in the more developed countries. This paper presents a forecasting model based on an Elman artificial neural network (ANN) for the short-time prediction of the household electricity consumption related to a suburban area. Due to the lack of information about the real penetration of electric appliances in the investigated area and their utilization profiles it was not possible to implement a statistical model to define the weather and climate sensitivities of appliance energy consumption. For this reason an ANN model was used to predict the household electric energy demand of the investigated area and to evaluate the influence of the AC equipments on the overall consumption.The data used to train the network were recorded in Palermo (Italy) and include electric current intensity and weather variables as temperature, relative humidity, global solar radiation, atmospheric pressure and wind speed values between June 1, 2002 and September 10, 2003.The work pointed out the importance of a thermal discomfort index, the Humidex index, for a simple but effective evaluation of the conditions affecting the occupant behaviour and thus influencing the household electricity consumption related to the use of heating, ventilation and air conditioning (HVAC) appliances. The prediction performances of the model are satisfying and bear out the ability of ANNs to manage incomplete and noisy data, solve nonlinear problems and learn complex underlying relationships between input and output patterns.     

Comparing linear and nonlinear forecasts for Taiwan's electricity consumption

This paper uses linear and nonlinear statistical models, including artificial neural network (ANN) methods, to investigate the influence of the four economic factors, which are the national income (NI), population (POP), gross of domestic production (GDP), and consumer price index (CPI) on the electricity consumption in Taiwan and then to develop an economic forecasting model. Both methods agree that POP and NI influence electricity consumption the most, whereas GDP the least. The results of comparing the out-of-sample forecasting capabilities of the two methods indicate the following. (1) If given a large amount of historical data, the forecasts of ARMAX are better than the other linear models. (2) The linear model is weaker on foretelling peaks and bottoms regardless the amount of historical data. (3) The forecasting performance of ANN is higher than the other linear models based on two sets of historical data considered in the paper. This is probably due to the fact that the ANN model is capable of catching sophisticated nonlinear integrating effects through a learning process. To sum up, the ANN method is more appropriate than the linear method for developing a forecasting model of electricity consumption. Moreover, researchers can employ either ANN or linear model to extract the important economic factors of the electricity consumption in Taiwan.     

Forecasting of Turkey's net electricity energy consumption on sectoral bases

In this study forecast of Turkey's net electricity energy consumption on sectoral basis until 2020 is explored. Artificial neural networks (ANN) is preferred as forecasting tool. The reasons behind choosing ANN are the ability of ANN to forecast future values of more than one variable at the same time and to model the nonlinear relation in the data structure. Founded forecast results by ANN are compared with official forecasts.     

Development of a neural network based saturation model forsynchronous generator analysis

This paper presents a new approach to model synchronous generator saturation based on a feedforward artificial neural network (ANN) model. The machine loading conditions, excitation levels and rotor positions are all included in the modeling process. The nonlinear saturation characteristics of a three-phase salient-pole synchronous machine rated at 5 kVA and 240 V is studied using the ANN model. An appropriate selection of input/output pattern for the ANN model training based on an error back-propagation scheme is developed using the on-line small-disturbance responses and the well-known maximum-likelihood estimation algorithm. The developed ANN model is implemented in the generator dynamic transient stability study requiring only small computational alteration in saturation model representation     

Artificial-Neural-Network-Based Sensorless Nonlinear Control of Induction Motors

In this paper, two architectures of artificial neural networks (ANNs) are developed and used to correct the performance of sensorless nonlinear control of induction motor systems. Feedforward multilayer perception, an Elman recurrent ANN, and a two-layer feedforward ANN is used in the control process. The method is based on the use of ANN to get an appropriate correction for improving the estimated speed. Simulation and experimental results were carried out for the proposed control system. An induction motor fed by voltage source inverter was used in the experimental system. A digital signal processor and field-programmable gate arrays were used to implement the control algorithm.     

Development and optimization of artificial neural network algorithms for the prediction of building specific local temperature for HVAC control

This research accounts for the outcome of a major cloud-based smart dual fuel switching system (SDFSS) project, which is a dual-fuel integrated hybrid heating, ventilation, and air conditioning (HVAC) system in residential homes. The SDFSS was developed to enable optimized, flexible, and cost-effective switching between the natural gas furnace and electric air source heat pump (ASHP). In order to meet the optimal energy consumption requirements in the house and provide thermal comfort for the residents, various high-quality sensors and meters were installed to record multiple data points inside and outside the house. The performance of the system was monitored in the long term, which is a common practice in energy monitoring projects. Outdoor temperature data plays the most crucial role in operating HVAC systems and also is a key variable in the decision-making algorithm of the SDFSS controller. Therefore, this study introduces an innovative and unique approach to obtain the outdoor temperature that could potentially replace high precision sensors with a data-driven model utilizing weather station data at a time resolution of 2 minutes and 1 hour. In this work, a series of artificial neural network algorithms were developed, optimized, and implemented to predict the outdoor temperature with an average of 0.99 coefficient of correlation (R), 1.011 mean absolute error (MAE), and 1.315 root mean square error (RMSE). It has been demonstrated that the developed ANN is a reliable and powerful tool in predicting outdoor temperature. Thus, the proposed model is strongly suggested to be implemented as an alternative to temperature sensors in hybrid energy systems or similar systems requiring accurate ambient temperature measurements.     

On-line adaptive artificial neural network based vector control ofpermanent magnet synchronous motors

This paper presents a novel approach of speed control for a permanent magnet synchronous motor (PMSM) using on-line self tuning artificial neural network (ANN). Based on motor dynamics and nonlinear load characteristics, an ANN speed controller is developed and integrated with the vector control scheme of the PMSM drive. The combined use of off-line and on-line weights and biases adjustments offers a unique feature of on-line system identification and precise speed control of a high performance PMSM drive. The complete drive system is implemented in real time using a digital signal processor controller board-DS1102 on a laboratory 1 HP PMSM. Using the experimental setup, the performances of the proposed drive system are evaluated under various operating conditions. The test results validate the efficacy of the ANN for precise speed control of the PMSM drive. Furthermore, the use of ANN makes the drive system robust, accurate and insensitive to parameter variations     

Identification and control of a DC motor using back-propagationneural networks

An artificial-neural-network (ANN)-based high-performance speed-control system for a DC motor is introduced. The rotor speed of the DC motor can be made to follow an arbitrarily selected trajectory. The purpose is to achieve accurate trajectory control of the speed, especially when motor and load parameters are unknown. The unknown nonlinear dynamics of the motor and the load are captured by the ANN. The trained neural-network identifier is combined with a desired reference model to achieve trajectory control of speed. The performances of the identification and control algorithms are evaluated by simulating them on a typical DC motor model. It is shown that a DC motor can be successfully controlled using an ANN     

A continually online trained neurocontroller for excitation andturbine control of a turbogenerator

The increasing complexity of the modern power grid highlights the need for advanced modeling and control techniques for effective control of turbogenerators. This paper presents the design of a continually online trained (COT) artificial neural network (ANN) based controller for a turbogenerator connected to an infinite bus through a transmission line. Two COT ANNs are used for the implementation; one ANN, the neuroidentifier, to identify the complex nonlinear dynamics of the power system and the other ANN, the neurocontroller, to control the turbogenerator. The neurocontroller replaces the conventional automatic voltage regulator (AVR) and turbine governor. Simulation and practical implementation results are presented to show that COT neurocontrollers can control turbogenerators under steady state as well as transient conditions