基于神经网络的哈尔滨高校教室热环境特征模型研究

为了研究哈尔滨高校教室热环境特征模型和人体热舒适,笔者于2004年9月～2005年12月在哈尔滨进行了20次现场研究.在测量室内热舒适参数的同时,受试者填写对室内环境的热感觉和热舒适主观调查表.而后利用人工神经网络方法,建立了哈尔滨高校教室热环境特征和人体热舒适的BP神经网络评判模型,实现了对哈尔滨高校教室热环境内人体热感觉的智能化预测.现场研究结果验证表明,该模型预测的哈尔滨高校教室热环境内人体热感觉与实际主观调查吻合.     

热湿环境下人体热反应的实验研究

采用问卷方式，对热湿环境下人体热感觉、对空气湿度的感觉、吹风感觉及热舒适感觉进行了研究，分析了空气相对湿度对热舒适的影响，给出了高温高湿条件下人体热反应的规律。并在分析人体散热的基础上，提出了一个可以对热湿环境中人体热舒适进行预测的数学模型。     

现场研究中热舒适指标的选取问题

对热舒适现场研究结果进行了总结，并对热舒适指标的选取、有效温度的计算、热感觉的表述方式等问题进行了讨论分析。认为当相对湿度在热舒适范围内时，采用有效温度作为热舒适指标并采用平均热感觉值，能更好地预测人体热感觉。     

关于"热舒适"的讨论

指出了人体热反应研究中关于热舒适的一些模糊概念及对热舒适与热感觉关系的含混认识。分析了热舒适与热感觉的不同含义、现有的不同解释及两者的稳态和动态条件下的差别。     

基于BP神经网络的过渡环境热舒适评判模型

突变环境下的人体热反应是由许多主客观因素所决定的,利用神经网络具有通过学习最佳逼近非线性映射的能力,将其应用于突变环境下人体热反应的研究,具有一定的可行性。本文通过局部非均匀环境与背景均匀环境之间的过渡实验,利用Matlab工具,分别建立了向热环境过渡和向冷环境过渡的整体热感觉以及头部执感觉的BP(Back Propagation)神经网络热舒适评判模型。经验证,该模型对不同工况过渡后的逐时热感觉预测较为准确,从而为非均匀环境与均匀环境之间过渡的热舒适模型的建立提供了一种可借鉴的方法。     

自然通风热舒适探讨

介绍了人体热舒适评价指标及自然通风热舒适评价指标,探讨了建立适合我国自然通风热舒适的评价模型,对进一步研究自然通风热舒适有一定的指导意义。     

哈尔滨高校教室热舒适现场研究

为了研究高校教室在学生上课期间的热环境和人体热舒适,在哈尔滨高校教室进行了现场研究。在测量室内热舒适参数的同时,学生填写对室内环境的热感觉和热舒适主观调查表,共调查了1285人次,得到了1285份人体热反应的样本。现场测试结果表明,哈尔滨高校自然通风教室全年人体热中性温度为23.4℃(t0)。     

人体热舒适区的实验研究

采用问卷调查的形式实验研究了空气温湿度对人体热舒适性的影响，分别根据热感觉投票值和热舒适投票值确定了人体热舒适区。研究发现，80％满意率的温度范围为22．1-27．5℃，试验得出的夏季舒适区范围比ASHRAE Standard 55-1992中夏季舒适区的温度上限高1．5℃。     

厦门高校教室冬季热环境测试及热舒适预测

为考察冬季非空调环境下人体热感觉,对厦门某高校教室的热舒适度进行了现场测试.在测量室内外热舒适参数的同时,通过问卷调查得到了人体热反应样本.分析样本得出厦门高校教室冬季非空调工况下人体热中性温度和热期望温度分别为19.3和19.4℃.综合考虑温度、相对湿度、平均辐射温度、风速及服装热阻对坐姿轻度活动状态人体的热舒适影响,使用MATLAB软件进行非线性回归,得到非空调工况下热舒适预测方程.该预测方程与实测得到的人体热舒适投票两者结果有较高相关度,同时较大程度上反映了冬季非空调环境下人体热感觉的变异.     

蒸发冷却空调房间气流组织的数值模拟

应用κ-ε二方程湍流模型和数值模拟方法对蒸发冷却空调房间的三维温度场，速度场以及热舒适指标进行了模拟，研究结果表明，蒸发冷却空调器能够有效地改善室内热环境，较好地满足了人体热舒适在通风和空气调节方面的要求。常规满足最不利条件时空调要求的设计方案，适用于蒸发冷却空调的设计。     

Fuzzy system modeling for forecasting water quality index in municipal distribution system

An attempt has been made to develop a fuzzy expert system capable of establishing a criterion for predicting water quality index (WQI) in the various zones of municipal distribution system using pH, alkalinity, hardness, dissolved oxygen (DO), total solids (TS) and most probable number (MPN). The proposed expert system includes a fuzzy model consisting of IF-THEN rules to determine WQI based on water quality characteristics. The fuzzy models are developed using triangular and trapezoidal membership functions, with centroid, bisector and mean of maxima (MOM) methods for defuzzification. Further, the performance of fuzzy models is compared with adaptive neuro fuzzy inference (ANFIS) models. ANFIS models are developed by using triangular, trapezoidal, bell and Gaussian membership function. The study reveals that fuzzy models outperform ANFIS models for all water quality classes. Out of twenty nine zones in the study area, for twenty two zones fuzzy model with triangular membership function performs better than trapezoidal membership function and, for sixteen zones, the centroid method, for seven zones bisector and for remaining six zones MOM method of defuzzification performs better.     

Prediction of thermal conductivity of rock through physico-mechanical properties

The transfer of energy between two adjacent parts of rock mainly depends on its thermal conductivity. Present study supports the use of artificial neural network (ANN) and adaptive neuro fuzzy inference system (ANFIS) in the study of thermal conductivity along with other intrinsic properties of rock due to its increasing importance in many areas of rock engineering, agronomy and geo environmental engineering field. In recent years, considerable effort has been made to develop techniques to determine these properties. Comparative analysis is made to analyze the capabilities among six different models of ANN and ANFIS. ANN models are based on feedforward backpropagation network with training functions resilient backpropagation (RP), one step secant (OSS) and Powell–Beale restarts (CGB) and radial basis with training functions generalized regression neural network (GRNN) and more efficient design radial basis network (NEWRB). A data set of 136 has been used for training different models and 15 were used for testing purposes. A statistical analysis is made to show the consistency among them. ANFIS is proved to be the best among all the networks tried in this case with average absolute percentage error of 0.03% and regression coefficient of 1, whereas best performance shown by the FFBP (RP) with average absolute error of 2.26%. Thermal conductivity is predicted using P-wave velocity, porosity, bulk density, uniaxial compressive strength of rock as input parameters.     

Predication of discharge coefficient of cylindrical weir-gate using adaptive neuro fuzzy inference systems (ANFIS)

Settlement of sediments behind weirs and accumulation of materials floating on water behind gates decreases the performance of these structures. Weir-gate is a combination of weir and gate structures which solves them Infirmities. Proposing a circular shape for crest of weirs to improve their performance, investigators have proposed cylindrical shape to improve the performance of weir-gate structure and call it cylindrical weir-gate. In this research, discharge coefficient of weir-gate was predicated using adaptive neuro fuzzy inference systems (ANFIS). To compare the performance of ANFIS with other types of soft computing techniques, multilayer perceptron neural network (MLP) was prepared as well. Results of MLP and ANFIS showed that both models have high ability for modeling and predicting discharge coefficient; however, ANFIS is a bit more accurate. The sensitivity analysis of MLP and ANFIS showed that Froude number of flow at upstream of weir and ratio of gate opening height to the diameter of weir are the most effective parameters on discharge coefficient.     

Estimation of deformation modulus of rock masses by using fuzzy clustering-based modeling

The paper describes a method which incorporates Takagi–Sugeno (TS) fuzzy modeling with two data clustering approaches including fuzzy-c-means (FCM) clustering and subtractive clustering to estimate the rock mass modulus of deformation. For this aim, a database including 120 cases collected from several galleries of dam sites locations was established. The information returned by fuzzy clustering was initially used to define the number of rules and antecedent membership functions and afterwards linear least squares estimation implemented to obtain fuzzy consequent parameters. An adaptive neuro-fuzzy inference system (ANFIS) was applied to modify the pre-determined TS clustering-based model structures to improve the generalization performance of those. For evaluation of the performance, root mean square error (RMSE) and variance account for (VAF) values have been utilized as performance criteria. It can be said, that ANFIS approach enhances the performances of fuzzy clustering-based models in predicting modulus of deformation of rock masses successfully.     

Intelligent control system for reconciliation of the energy savings with comfort in buildings using soft computing techniques

In this paper, we present a novel intelligent coordinator control system based on hierarchical structure. The presented structure consists of one coordinator and five fuzzy logic controllers. The intelligent coordinator architecture contains uses a master and a slave agent. The master agent is an economy behavior fuzzy system and the slave agent consists of two fuzzy negotiation machines (FNMs) and one decision logic unit. Type-1 FS models are chosen to characterize the concepts of thermal comfort, illuminance and carbon dioxide concentration. The word “comfort” is represented by a 3D fuzzy set in fuzzy cube. Using the symmetric fuzzy equality measure we can measure the membership grade of the 3D fuzzy comfort set. We present the structure of a fuzzy controller-agent (FCA) and propose the tuning of parameters of the FLC by genetic algorithms (GAs). The simulation results show that the proposed intelligent control system successfully manages the users’ preferences for thermal and illuminance comfort, indoor air quality and the energy conservation.     

Adaptive neuro-fuzzy based inferential sensor model for estimating the average air temperature in space heating systems

The heating systems are conventionally controlled by open-loop control systems because of the absence of practical methods for estimating average air temperature in the built environment. An inferential sensor model, based on adaptive neuro-fuzzy inference system modeling, for estimating the average air temperature in multi-zone space heating systems is developed. This modeling technique has the advantage of expert knowledge of fuzzy inference systems (FISs) and learning capability of artificial neural networks (ANNs). A hybrid learning algorithm, which combines the least-square method and the back-propagation algorithm, is used to identify the parameters of the network. This paper describes an adaptive network based inferential sensor that can be used to design closed-loop control for space heating systems. The research aims to improve the overall performance of heating systems, in terms of energy efficiency and thermal comfort. The average air temperature results estimated by using the developed model are strongly in agreement with the experimental results.     

A new predictive thermal sensation index of human response

The purpose of this paper is to investigate the problem of determining a human thermal sensation index that can be used in feedback control of HVAC systems. We present a new approach based on fuzzy logic to estimate the thermal comfort level depending on the state of the following six variables: the air temperature, the mean radiant temperature, the relative humidity, the air velocity, the activity level of occupants and their clothing insulation. The new fuzzy thermal sensation index is calculated implicitly as the consequence of linguistic rules that describe human's comfort level as the result of the interaction of the environmental variables with the occupant's personal parameters. The fuzzy comfort model is deduced on the basis of learning Fanger's `Predicted Mean Vote' (PMV) equation. Unlike Fanger's PMV, the new fuzzy PMV calculation does not require an iterative solution and can be easily adjusted depending on the specific thermal sensation of users. These characteristics make it an attractive index for feedback control of HVAC systems. The simulation results show that the new fuzzy PMV is as accurate as Fanger's PMV.     

Application of surrogate artificial intelligent models for real‐time flood routing

Developing a robust flood forecasting and warning system (FFWS) is essential in flood‐prone areas. Hydrodynamic models, which are a major part of such systems, usually suffer from computational instabilities and long runtime problems, which are particularly important in real‐time applications. In this study, two artificial intelligence models, namely artificial neural network (ANN) and adaptive neuro‐fuzzy inference system (ANFIS), were used for flood routing in an FFWS in Madarsoo river basin, Iran. For this purpose, different rainfall patterns were transformed to run‐off hydrographs using the Hydrologic Engineering Center (HEC)‐1 hydrological model and routed along the river using HEC river analysis system RAS hydrodynamic model. Then, the simulated hydrographs with different lag times were used as inputs for training of ANN and ANFIS models to simulate flood hydrograph at the basin outlet. Results showed that the simulations obtained from ANN and ANFIS coincided with the results simulated by the HEC‐RAS, and application of such models is strongly suggested as a backup tool for flood routing in FFWSs.     

Predicting performance of a ground-source heat pump system using fuzzy weighted pre-processing-based ANFIS

The goal of this work is to predict the daily performance (COP) of a ground-source heat pump (GSHP) system with the minimum data set based on an adaptive neuro-fuzzy inference system (ANFIS) with a fuzzy weighted pre-processing (FWP) method. To evaluate the effectiveness of our proposal (FWP–ANFIS), a computer simulation is developed on MATLAB environment. The comparison of the proposed hybridized system's results with the standard ANFIS results is carried out and the results are given in the tables. The efficiency of the proposed method was demonstrated by using the 3-fold cross-validation test. The statistical methods, such as the root-mean squared (RMS), the coefficient of multiple determinations (R²) and the coefficient of variation (cov), are given to compare the predicted and actual values for model validation. The average R² values is 0.9998, the average RMS value is 0.0272 and the average cov value is 0.7733, which can be considered as very promising. The data set for the COP of GSHP system available included 38 data patterns. The simulation results show that the FWP-based ANFIS can be used in an alternative way in these systems. The prediction results of the proposed structure were much better than the standard ANFIS results. Therefore, instead of limited experimental data found in the literature, faster and simpler solutions are obtained using hybridized structures such as FWP-based ANFIS.     

基于自适应神经-模糊推理系统和遗传算法的桥梁耐久性评估

将模糊推理、神经网络、遗传算法三种技术有机融合在一起,建立了基于自适应神经-模糊推理系统(ANFIS)和遗传算法(GAS)的桥梁耐久性评估专家系统。该系统将专家的模糊推理过程蕴含于神经网络结构中,使神经网络的节点和权值具有明确的物理意义,避免了传统神经网络工作过程的“黑盒”性。同时该系统又具有神经网络的自适应性和学习能力,克服了传统模糊推理系统学习能力差的缺点。而且采用遗传和反向传播相结合的GA-BP混合算法训练网络,充分发挥了遗传算法的全局搜索性和BP的局部微调快速性的优点。并以辽宁省13座桥300根梁的实测数据对其进行训练和测试,系统输出与期望输出吻合较好,证明该专家系统性能稳定、有效,具有实用价值。