Artificial neural network based modelling of desiccant wheel

In this article, the concept of artificial neural network and goal oriented design have been used to propose a computer design tool that can help designers to evaluate performance of desiccant cooling system and behaviour of the desiccant wheel. Based on the experimental observations on desiccant wheel, a neural network model has been developed using a neural network toolbox of MATLAB^® with feed forward back propagation method. The model has been validated against experimental data sets. A number of training algorithms with feed forward back propagation method have been used for the modelling of desiccant wheel to identify a training algorithm with least mean square error (MSE). The performance of all training algorithms has been analyzed and training algorithm trainlm (Levenberg-Marquardt back propagation) is found most suitable for the prediction of outputs which have least mean square error of 0.064462 and 0.007575 for specific humidity and temperatures respectively. The proposed model can predict the specific humidity and temperature at the outlet of desiccant wheel within the range of experimental values.     

Estimating moment capacity of ferrocement members using self-evolving network

In this paper, an empirical model based on self-evolving neural network is proposed for predicting the flexural behavior of ferrocement elements. The model is meant to serve as a simple but reliable tool for estimating the moment capacity of ferrocement members. The proposed model is trained and validated using experimental data obtained from the literature. The data consists of information regarding flexural tests on ferrocement specimens which include moment capacity and cross-sectional dimensions of specimens, concrete cube compressive strength, tensile strength and volume fraction of wire mesh. Comparisons of predictions of the proposed models with experimental data indicated that the models are capable of accurately estimating the moment capacity of ferrocement members. The proposed models also make better predictions compared to methods such as the plastic analysis method and the mechanism approach. Further comparisons with other data mining techniques including the back-propagation network, the adaptive spline, and the Kriging regression models indicated that the proposed models are superior in terms prediction accuracy despite being much simpler models. The performance of the proposed models was also found to be comparable to the GEP-based surrogate model.     

型钢高强混凝土框架柱位移延性系数研究

基于80根混凝土设计强度等级为C60—C80的型钢高强混凝土(SRHSC)框架柱的低周反复加载试验结果,对其位移延性系数进行研究。基于MATLAB利用人工神经网络原理建立4-6-1型BP神经网络模型,分析了混凝土强度、轴压比、体积配箍率和剪跨比等试验设计参数对SRHSC框架柱位移延性的影响规律和机理。结合各因素对SRHSC框架柱位移延性的影响规律,建立位移延性系数计算模型。通过对试验数据和网络预测数据进行多元非线性回归分析,得到考虑多影响因素的SRHSC框架柱位移延性系数经验公式。研究成果可为SRHSC框架柱的抗震与优化设计提供参考。     

一种基于历史数据的输电线路覆冰增长快速预测方法

2008年初极端冰雪灾害给中国南方输电线路造成了极大破坏,引起了对架空输电线路覆冰模型研究的重视。导线覆冰增长的物理过程极为复杂,受气候环境多变和气象、季节、地形地理条件、海拔、线路走向、导线本身等各种复杂因素的影响,给基于在线监测数据预测短期覆冰增长带来困难。提出一种基于在线监测的覆冰厚度历史数据的覆冰发展趋势快速预测方法——组合灰色神经网络预测模型。首先远程采集力学数据,根据模型求得覆冰厚度的历史数据;然后分别建立GM(1,1)、Verhulst和DGM(1,1)三种灰色模型,得到三组覆冰厚度趋势数据;最后将三组数据作为神经网络输入,得到覆冰趋势曲线。以云南电网和广西电网典型的两次不同类型覆冰过程为例进行了验证。结果表明,在缺乏微气象和地形条件的贫信息状态下,此模型在覆冰增长快速预测中是适用的,有效的。     

Failure Criterion of Concrete under Triaxial Stresses Using Neural Networks

A neural network approach to model the strength of concrete under triaxial stresses is presented in this paper. A radial basis function neural network (RBFNN) and a backpropagation neural network (BPNN) are used for training and testing the experimental data in order to acquire the failure criterion of concrete strength. Unlike the traditional regression analyses where the explicit forms of the equation must be defined first, the neural network approach provides a general form of strength envelope. The study shows that the RBFNN model provides better prediction than the BPNN model. Parametric studies on both models are carried out to find the best neural network structure. Finally, a comparison study between the neural network model and two regression models is made.     

BP网络预测再生混凝土性能研究

利用BP神经网络模型,对再生混凝土强度及工作性能的预测方法进行了探讨。根据再生混凝土的特殊性,找出影响其强度和坍落度、保水性的主要因素,对试验中通过主观观察得到的数据进行量化,在此基础上建立预测其强度和工作性能的BP神经网络模型,针对所建模型,输入一定量的实测数据样本,对网络进行训练。为了验证训练好的网络的推广性能,用预留的一组试验数据进行仿真训练的效率和误差及仿真计算的结果表明,采用优化的BP网络模型及合适的样本参数训练出的预测系统对再生混凝土的强度及工作性能进行预测是可行的。     

基于混合神经网络模型的污水COD值预估法

提出了一种基于物理测量的COD值快速预估方法，它采用混合神经网络模型直接由UV分光光度计测得的吸光度数据预估出水样的COD值。实例分析表明，采用该混合模型具有比常规的BP网络和传统回归模型更好的预估精度，同时混合模型的预估值与标准分析值之间也有着良好的相关性。     

Integrated wheel loader simulation model for improving performance and energy flow

This paper describes an integrated wheel loader simulation model for improving performance and energy flow. The proposed integrated wheel loader simulation model includes a driver model that is designed to perform the two objectives of working and driving. The driver model for working was designed according to eight conditions considered as events and environment information. The driver model for driving is composed of throttle, brake, and steering inputs which represent an actual driver's input characteristics. By analyzing experimental test data of V-pattern working, human driving characteristics have been derived and applied in the driver model by using linear quadratic regulator (LQR) and model predictive control (MPC). The wheel loader dynamic simulation model with the driver model used in this study consists of four parts: mechanical powertrain, hydraulic powertrain, vehicle dynamic model, and working dynamic model with a simplified load model. All simulation models have been constructed in the Matlab/Simulink environment, and the proposed driver model has been validated from experimental test data. Working performance with the optimized path, energy flow, and loss analysis during V-pattern working was predicted and evaluated with the developed human driver and dynamic simulation model of a wheel loader. The driver model can be utilized in the design stage for prediction and evaluation of a wheel loader's working performance. It is also expected that an investigation of the optimal working pattern and energy flow for various working cycles of wheel loaders will be possible with the driver-model-in-the-loop simulation.     

Modelling biocide leaching from facades

Biocides leach from facades during rain events and subsequently enter the aquatic environment with storm water. Little is known about the losses of an entire settlement, since most studies referred to wash-off experiments conducted under laboratory conditions. Their results show a fast decrease of concentrations in the beginning, which subsequently slows down. The aim of this study is to develop a simple model to understand the mechanisms leading to these losses as well as to simulate losses under various rainfall and application conditions.We developed a four-box model based on the knowledge gained from fits of an exponential function to an existing experimental data set of a wash-off experiment. The model consists of two mobile stocks from which biocides are washed off during a rain event. These mobile stocks are supplied with biocides from storage stocks by diffusion-type processes. The model accurately reproduced the measured data of wash-off during single cycles as well as peak wash-offs over all cycles.Our model results for diuron losses showed that a large proportion (∼70%) of the applied biocides are still in the stocks even after a rain volume corresponding to several years (1100 mm y⁻¹, Swiss Plateau). Applications to realistic outdoor conditions showed that losses can not be neglected for urban environments and that knowledge about the amount of rainfall turned into runoff and the decay constants of the biocides in the facades are crucial. The model increased our understanding of the processes leading to the observed dynamic in laboratory experiments and was used to simulate losses for various rainfall and application conditions.     

Estimation of air losses in compressed air tunneling using neural network

This paper explores the capabilities of neural networks to predict the air losses in compressed air tunneling. Field data from the Feldmoching tunnel in Munich were used in this study. In this project, compressed air was used to retain the groundwater and shotcrete was used as temporary support. The final permanent lining was installed in free air. The tunnel passed through variable ground conditions ranging from coarse gravel to sand and clay. Grouting, an additional layer of shotcrete and a layer of mortar were occasionally used to control the air losses. A back-propagation feed forward neural network was trained and used to predict the air losses from the Feldmoching tunnel. The results of the prediction of the air losses from the tunnel using a neural network were compared with the field measurements. Data from different tunnel lengths were used for training. In each case, the trained network was used to predict the air losses during the excavation of the rest of the tunnel. It is shown that, not only can a neural network learn the relationship between appropriate soil and tunnel parameters and air losses, it can also generalize the learning to predict air losses for very different geological and geometric conditions. It is also shown that data from a very short length (50 m in one case) of the tunnel (five data point only, in this case) may contain enough information for the neural network to learn and predict the air losses in the remaining (585 m) length of the tunnel with a good degree of accuracy. This can be of considerable value to tunnel engineers in control of tunneling operations and help them in preparation for possible changes in air losses with tunnel advance, with changes in ground conditions and tunnel geometry and with time.     

Peak shear strength prediction for discontinuities between two different rock types using a neural network approach

The peak shear strength of discontinuities between two different rock types is essential to evaluate the stability of a rock slope with interlayered rocks. However, current research has paid little attention to shear strength parameters of discontinuities with different joint wall compressive strength (DDJCS). In this paper, a neural network methodology was used to predict the peak shear strength of DDJCS considering the effect of joint wall strength combination, normal stress and joint roughness. The database was developed by laboratory direct shear tests on artificial joint specimens with seven different joint wall strength combinations, four designed joint surface topographies and six types of normal stresses. A part of the experimental data was used to train a back-propagation neural network model with a single-hidden layer. The remaining experimental data was used to validate the trained neural network model. The best geometry of the neural network model was determined by the trial-and-error method. For the same data, multivariate regression analysis was also conducted to predict the peak shear strength of DDJCS. Prediction precision of the neural network model and multivariate regression model was evaluated by comparing the predicted peak shear strength of DDJCS with experimental data. The results showed that the capability of the developed neural network model was strong and better than the multivariate regression model. Finally, the established neural network model was applied in the stability evaluation of a typical rock slope with DDJCS as the critical surface in the Badong formation of China.

     

基于PCA-GA-BP 的工程项目工期风险预测研究

为了在工程项目实施前准确地预测出工期风险的大小,在介绍BP 神经网络、遗传算法、主成分分析等理论的基础上,针对现有预测模型的缺点以及BP 神经网络自身缺陷,采用主成分分析法对样本数据进行降维处理,并利用遗传算法对 BP 神经网络的初始权值阈值进行优化,提出了基于PCA-GA-BP 的工程项目工期风险预测模型。将以往工程风险数据作为学习样本,训练并构建模型对待建工程项目工期风险进行预测。实例证明该模型有效、可靠,对指导实际工程具有重要意义。     

Modeling and simulation of desiccant wheel for air conditioning

This paper presents the modeling of a desiccant wheel used for dehumidifying the ventilation air of an air-conditioning system. The simulation of the combined heat and mass transfer processes that occur in a solid desiccant wheel is carried out with MATLAB Simulink. Using the numerical method, the performance of an adiabatic rotary dehumidifier is parametrically studied, and the optimal rotational speed is determined by examining the outlet adsorption-side humidity profiles. The solutions of the simulation at different conditions used in air dehumidifier have been investigated according to the previous published studies. The model is validated through comparison the simulated results with the published actual values of an experimental work. This method is useful to study and modelling of solid desiccant dehumidification and cooling system. The modeling solutions are used to develop simple correlations for the outlet air conditions of humidity and temperature of air through the wheel as a function of the physically measurable input variables. These correlations will be used to simulate the desiccant cooling cycle in an HVAC system in order to define the year round efficiency.     

基于数据挖掘技术的黄土分类问题研究

依据数据挖掘技术,采用分类回归树决策树和概率神经网络对黄土的分类规则进行挖掘。利用主成分分析法对数据进行了清洗和降维处理,以处理后的新变量作为挖掘对象,使挖掘出的分类模型和规则得到了简化,提高了计算精度;同时归纳出了影响黄土分类的因素,所挖掘出的分类规则可用于黄土地层的智能划分。研究结果表明,挖掘出的知识具有良好的实用性。     

Comparison between detailed model simulation and artificial neural network for forecasting building energy consumption

There are several ways to attempt to model a building and its heat gains from external sources as well as internal ones in order to evaluate a proper operation, audit retrofit actions, and forecast energy consumption. Different techniques, varying from simple regression to models that are based on physical principles, can be used for simulation. A frequent hypothesis for all these models is that the input variables should be based on realistic data when they are available, otherwise the evaluation of energy consumption might be highly under or over estimated.In this paper, a comparison is made between a simple model based on artificial neural network (ANN) and a model that is based on physical principles (EnergyPlus) as an auditing and predicting tool in order to forecast building energy consumption. The Administration Building of the University of São Paulo is used as a case study. The building energy consumption profiles are collected as well as the campus meteorological data.Results show that both models are suitable for energy consumption forecast. Additionally, a parametric analysis is carried out for the considered building on EnergyPlus in order to evaluate the influence of several parameters such as the building profile occupation and weather data on such forecasting.     

基于GIS和BP神经网络的洪灾损失评估模型的研究

本文在分析已有洪灾损失评估模型的基础上,构建了一种基于GIS和BP神经网络的洪灾损失评估模型,包括选取洪水致灾、地形条件、防洪能力、社会经济等因子;然后以鄱阳湖区为例进行了洪灾损失评估系统应用。结果表明建立的基于GIS和BP神经网络的洪灾损失评估模型具有较好的可行性和实用性。     

基于QPSO-BP 神经网络的火灾预警算法

为了进一步提高油库消防系统的安全性,针对其火灾报警信息系统进行了改进,构建基于量子粒子群算法优化BP神经网络的火灾智能预警算法,以温度、烟雾浓度以及CO 浓度数据作为神经网络的输入,以无火、明火以及阴燃火的概率作为神经网络的输出。使用量子粒子群算法优化BP 神经网络运行中随机产生的权值和阈值,加快神经网络收敛到期望误差的速度,增强全局搜索能力。通过MATLAB 软件对智能火灾预警算法的模型进行仿真,模型输出的火情概率与实际值基本吻合。设计了多传感器数据采集设备,获取火灾现场数据,输入网络模型,能够有效识别明火、阴燃火和无火情况,验证了该算法可提高消防预警系统的准确性。     

寒区隧道地源热泵型供热系统取热段温度场解析

为解决寒区隧道冻害问题,将地源热泵型供热系统应用于内蒙古博牙高速林场隧道中。供热系统由取热段、加热段、热泵和分、集水管路组成,可用于隧道洞口段衬砌和排水系统加热。取热段位于隧道中部,获取围岩中的地热能。隧道取热段温度场由热交换管外围岩温度场和热交换管内流体温度场两部分组成。建立考虑衬砌结构和热源的隧道取热段热交换管外围岩传热模型,利用叠加原理、拉普拉斯变换和积分变换相结合的方法获得取热段温度场解析解。基于能量守恒原理建立热交换管内流体传热模型,根据热交换管外围岩温度场,利用迭代法计算热交换管的出口温度。采用反分析的方法确定试验段围岩的综合热物性参数,将理论解与现场试验数据对比分析,其精度满足工程要求。取热段温度场理论解为系统的设计提供理论指导。     

优化神经网络在多传感器火灾探测中的应用

针对BP神经网络在拟合过程中探测精度低、容易陷入局部最优的问题,提出一种基于遗传算法（GA）和模拟退火算法（SA）共同改进的BP神经网络模型,该网络模型可以有效提高火灾识别准确率,同时避免网络过拟合现象,使预测结果跳出局部最优从而达到全局最优。首先,通过GA改进隐藏层结构部分,然后通过SA改进连接权重部分,最后利用优化后的GA-SA-BP模型对火灾实验数据进行信息融合实现火灾探测。实验研究表明,对比单一BP神经网络,经GA和SA改进后的BP神经网络能够有效改善网络拟合能力,并提升火灾探测精度至98.91%。     

Experimental validation of a simplified approach for a desiccant wheel model

This work presents an experimental validation of a simplified approach for a desiccant wheel model, based on the concept of the analogy method and the formulation proposed by Jurinak for the respective combined potentials. The present work experimentally investigates the validity of the assumption of the efficiency factors of the wheel, with regard to the combined potentials, remaining constant over a sufficiently wide range of operation conditions. The results prove the validity of the discussed assumption. The same analysis is implemented with regard to the technical data about the performance of the wheel, usually provided by the manufacturer in the form of software, the results being also positive. Thus, the respective efficiency factors can be calculated through a limited number of measurements, or even simpler, through the use of the manufacturer's performance software accompanying the product.