A Bayesian Network model for predicting cooling load of commercial buildings

Cooling load prediction is indispensable to many building energy saving strategies. In this paper, we proposed a new method for predicting the cooling load of commercial buildings. The proposed approach employs a Bayesian Network model to relate the cooling load to outdoor weather conditions and internal building activities. The proposed method is computationally efficient and implementable for use in real buildings, as it does not involve sophisticated mathematical theories. In this paper, we described the proposed method and demonstrated its use via a case study. In this case study, we considered three candidate models for cooling load prediction and they are the proposed Bayesian Network model, a Support Vector Machine model, and an Artificial Neural Network model. We trained the three models with fourteen different training data datasets, each of which had varying amounts and quality of data that were sampled on-site. The prediction results for a testing week shows that the Bayesian Network model achieves similar accuracy as the Support Vector Machine model but better accuracy than the Artificial Neural Network model. Notable in this comparison is that the training process of the Bayesian Network model is fifty-eight times faster than that of the Artificial Neural Network model. The results also suggest that all three models will have much larger prediction deviations if the testing data points are not covered by the training dataset for the studied case (The maximum absolute deviation of the predictions that are not covered by the training dataset can be up to seven times larger than that of the predictions covered by the training dataset). In addition, we also found the uncertainties in the weather forecast significantly affected the accuracy of the cooling load prediction for the studied case and the Support Vector Machine model was more sensitive to those uncertainties than the other two models.     

边坡位移非线性时间序列采用支持向量机算法的智能建模与预测研究

介绍了人工智能领域最新的基于结构风险最小化原理的数据挖掘算法---支持向量机算法,运用Matlab语言编写了程序,采用不同的核函数对具体的边坡工程实例作了计算,并将人工神经元网络计算结果与之对比,可见无论是在学习或预测精度方面,支持向量机算法较基于经验风险最小化原理的人工神经元网络算法都有很大的优越性,可以运用于实际工程。     

BP神经网络在青弋江水质评价上的应用

文章根据青弋江芜湖市区段水质特点构建了合适的BP神经网络评价模型,并通过插值的方法增加了样本数量。训练和评价的结果说明BP网络模型在青弋江水质的评价方面是一种简单有效的方法。     

应用人工神经网络技术的建筑物成新度评估

针对建筑物成新度评估中存在的问题,利用人工神经网络理论,建立了建筑物成新度评估的人工神经网络模型,从而为其准确评估提供了科学的依据。     

不同刀具配置下隧道掘进机高效破岩机理与推力预估

为解决隧道掘进机刀盘刀具破岩的安全性、可靠性、高效性这一隧道掘进机施工难题,从高效破岩机理和刀盘刀具与围岩耦合作用规律两个方面进行了研究,对单刀及多刀破岩理论体系进行了完善。结合理论分析和滚刀岩机作用综合实验台上的实验结果,提出了红砂岩、石灰岩和花岗岩等3种常见岩石的最优破岩刀间距,并给出了当岩石强度位于40～170 MPa之间时的最优刀间距计算式。综合考虑各种因素对隧道掘进机总推力、刀盘扭矩的影响,提出了复合式隧道掘进机总推力、刀盘扭矩估算的理论公式。通过工程实例验证,该理论计算式具有较高的科学性和精确性。研究成果可直接用于刀具选型布置、推力、扭矩设计,从而降低隧道掘进机的制造成本、提高施工效率。     

Study of the geometry of a voided clay brick using non-rectangular perforations to optimise its thermal properties

This study seeks to improve the geometrical distribution of bricks to optimise the equivalent thermal transmittance of a wall built of Termoarcilla^® ECO 29 voided clay bricks, using calculations according to Spanish UNE [1], AENOR [10], European EN [6], [7], [8] and [9] and international ISO [11] and [12] standards.The objective is to study improvements in the wall's thermal conductivity, always remembering the limitations imposed by the manufacturing process. Simulations are made using a finite elements application [14].It is concluded that, within the possibilities allowed by the manufacturing process, with non-rectangular voids the heat flux has to cross a higher number of voids, which improves its thermal properties. A rhomboid layout of voids with the longer diagonal at right angles to the heat flux is the best internal void layout. If the internal perforations are also extended to the end of the tongue and groove, the direct thermal bridge in this type of brick is broken.Finally, a 290 mm wide brick with 25 rows is obtained with the geometrical properties described above which shows an improvement of almost 16% over the original ECO 29 brick, performing well in all climatic areas of Spain, with a full-bed mortar joint 30 mm thick.     

人工神经网络在房地产估价中的应用研究

将人工神经网络引入房地产估价领域,阐述了B—P神经网络的原理和特点,并提出基于B—P神经网络的房地产估价程序,为房地产估价提供了一种新的解决方法、一种新的思想。     

Uncertainty analysis in building performance simulation for design support

Building performance simulation (BPS) has the potential to provide relevant design information by indicating directions for design solutions. A major challenge in simulation tools is how to deal with difficulties through large variety of parameters and complexity of factors such as non-linearity, discreteness, and uncertainty.The purpose of uncertainty and sensitivity analysis can be described as identifying uncertainties in input and output of a system or simulation tool [1], [2] and [3].In practice uncertainty and sensitivity analysis have many additional benefits including: (1) With the help of parameter screening it enables the simplification of a model [4]. (2) It allows the analysis of the robustness of a model [5]. (3) It makes aware of unexpected sensitivities that may lead to errors and/or wrong specifications (quality assurance) [6], [7], [8], [9] and [10]. (4) By changing the input of the parameters and showing the effect on the outcome of a model, it provides a “what-if analysis” (decision support). [11].In this paper a case study is performed based on an office building with respect to various building performance parameters. Uncertainty analysis (UA) is carried out and implications for the results considering energy consumption and thermal comfort are demonstrated and elaborated. The added value and usefulness of the integration of UA in BPS is shown.     

高强度围岩隧洞TBM刀具磨损规律研究

刀具磨损是影响TBM掘进效率的重要因素,该文以北疆供水二期工程XEVIII标段隧洞为依托,开展高强度围岩条件下刀具磨损规律研究.该标段已掘进段围岩强度最大为160MPa,平均为120MPa.根据掘进过程中的刀具磨损统计资料,分析不同刀位的刀具磨损值、围岩强度和掘进参数对刀具磨损的影响以及不同掘进参数对刀具磨损的敏感度,...     

Rebuttal of “Problems in the extreme value analysis”

This paper rebuts claims published in this journal [33] as well as elsewhere [31], [32] and [34]: (a) that improved methodologies for extreme value analysis (EVA) developed over the past 60 years are invalid; (b) that EVA methodologies should revert to the status quo ante 1939; and (c) that, consequently, all regulations and codes of practice for extreme winds should be reassessed. This paper rebuts these claims and shows current EVA methodologies to be valid. The paper also shows that uncertainty due to sampling error, viz. how well a single observed sample represents the random process sampled, dominates over the choice of methodology.     

基于人工神经网络的住宅造价估算

造价估算是建筑工程项目可行性研究中关键性的工作,其结果直接影响投资决策的判断。针对现行造价估算方法存在未考虑造价的动态性且受主观因素影响的缺陷,引入人工神经网络理论,根据其基本原理,结合影响住宅工程造价的主要因素,利用MATLAB平台建立了造价估算的数学模型,并用重庆市区已建典型工程资料对模型进行了训练和检验,证明了此方法的可行性。     

城市出租汽车需求量预测模型及应用

分析了我国出租汽车现状保有量和影响出租汽车需求量的各方面因素,提出了基于神经网络理论的出租汽车需求量预测模型,并在算例中从影响出租汽车容量的各因素入手对成都市出租汽车需求量进行预测。     

基于ANN吸收式冷水机组模型的遗传算法最优控制

文章讨论了吸收式溴化锂冷水机组目前在其系统控制上存在经典控制理论无法解决的问题,所以提出采用人工智能领域的技术来实现它的控制方案,其中结合了遗传算法和神经网络的优点。文章还探讨了如何有效的实现这种结合,并将其运用到实际的模拟控制中,实现最优化控制。同时,分别就可能的最优化控制方案与标准控制方案进行比较,文中给出各种最优化控制方案的性能。     

基于神经网络的粉喷单桩荷载-沉降关系建模

本文探讨了神经网络在粉喷单桩荷载 沉降关系建模中的应用 ,针对较少的信息 ,提出了区间映射构造样本模式对的方法。通过实例 ,与其它多个模式进行对比 ,验证了所建模型的有效性     

京珠高速K108边坡软弱夹层流变参数的智能反演

岩土体的流变特性是影响边坡变形及稳定性的重要因素,对边坡进行稳定性评价、结合变形监测资料对边坡进行预警预报,都有必要考虑岩土体的流变效应。本文以京珠高速K108边坡为研究对象,采用粘弹塑性数值方法建立该边坡的计算模型,通过大量的数值分析获得神经网络的训练样本,由人工神经网络的非线性映射功能建立岩土体流变位移与待反演参数之间的特征关系,将实测位移代入训练好的神经网络进行反分析得到软弱夹层的流变参数,通过后验差的方法验证了反演结果的合理性,得到的结果可用于后续的边坡稳定分析及预警。     

Comparison of surface roughness of Locust acacia (Robinia pseudoacacia L.) and European oak (Quercus petraea (Mattu.) Lieble.) in terms of the preparative process by planing

Effects of number of the cutters (planing knives), feed rate (operational speed) and cutting depth (biting thickness) on the surface roughness of Locust acacia (Robinia pseudoacacia L.) and European oak (Quercus petraea (Mattu.) Lieble.) were investigated on the base of the preparative differences by planing. The specimens were prepared by planing with two and four knives at 5 and 9 m/min feed rates in 1, 2 and 4 mm cutting depths. Surface roughness was measured from the radial face of each sample according to TS 930 (1989) by using Mitutoyo SJ-301 stylus scanner device. These measurements were performed perpendicular to the fibers by the sampling length of 12.5 mm at a sensitivity level of ±0.01 μm. Considering between all types of the experimental preparations, Locust acacia had the smoothest surfaces than that of European oak. Comparing the results of the surface roughness of both species, it has been obtained that the surface roughness decreases when the feed rate and the cutting depth decreases, whereas it increases when the knives on the cutter heads decreases. Therefore, it may be suggested that the perfect faces could be particularly prepared for this considered species by the greater number of the knives (four) at the slow feed rate (5 m/min) in the condition of the light cutting depth (1 mm).     

基于遗传神经网络的岩土参数优化反分析

由于地下工程岩土力学参数的复杂性,在实际工程设计和施工中,要想得到比较准确的岩土力学参数是比较困难的,而岩土参数对地下工程的设计和施工的成败具有很重要的意义。本文利用遗传神经网络优化算法结合数值模拟试验对地下工程岩土力学参数进行优化反分析,并取得了良好的效果。     

Energy saving effect prediction and post evaluation of air-conditioning system in public buildings

Accurate energy saving effect evaluation analysis of building energy efficiency retrofit is of benefit to obtain technology optimization and fast return of investment. According to the implement sequence, evaluation methods can be divided into post evaluation and prediction evaluation. The energy saving effect of an air-conditioning system retrofit project was analyzed by these two models respectively. The post evaluation model was built based on the spot test data and a parameter called as Refrigeration Operation Energy saving Effect Ratio (ROEER). The prediction evaluation model was built based on Back-Propagation Artificial Neural Network by the use of MATLAB Neural Network Toolbox. The comparison result between these two kinds of evaluation models match well with each other. These two models can be used to predict and evaluate energy saving effect of air-conditioning system retrofit to further improve the real energy saving effect of building energy efficiency retrofit.     

工程勘察场地复杂程度划分及其专家系统的建立

《工程勘察场地复杂程度划分专家系统》是《工程勘察与地基评价计算机专家系统(EIFEES)》的一个相对独立的组成部分.系统采用二级推理,将模糊评判与神经元网络相结合,得到合理的场地评价结果.这种富有特色的推理机已经在EIFEES的其他子专家系统中应用,并可在有关领域中推广.     

神经网络动态模型在建筑物裂缝演变预测中的应用

探讨了人工神经网络用于建筑物裂缝演变过程的非线性动力学建模的可行性、数学依据、实现方法 ,通过工程实例 ,实现了裂缝演变的自适应在线预测 ,结果说明此方法具有较高的预测精度 ,比传统建模方法有明显的优越性 ,具有较强的工程应用价值