Determining Inputs for Neural Network Models of Multivariate Time Series

In recent years, artificial neural networks have been used successfully to model multivariate water resources time series. By using analytical approaches to determine appropriate model inputs, network size and training time can be reduced. In this paper, it is proposed that the method of Haugh and Box and a new neural network–based approach can be used to identify the inputs for multivariate artificial neural network models. Both methods were used to obtain the inputs for a multivariate artificial neural network model used for forecasting salinity in the River Murray at Murray Bridge, South Australia. The methods were compared with a third method that uses knowledge of travel times in the river to identify a reasonable set of inputs. The results obtained indicate that all three methods are suitable for determining the inputs for multivariate time series models. However, the neural network–based method is preferable because it is quicker and simpler to use. Any prior knowledge of the underlying processes should be used in conjunction with the neural network method.     

The application of neural networks to rock engineering systems (RES)

This paper proposes a new approach for applying neural networks in Rock Engineering Systems (RES) based on the learning abilities of neural networks. By considering the analysis of the coding methods for the interaction matrix in RES and the learning processes of neural networks such as the Back Propagation (BP) method, neural networks can provide a useful mapping from system inputs to system outputs for rock engineering, so that the influence of inputs on outputs can be obtained. Then the results of the neural network analysis can be presented in a similar way to the global interaction matrix used in RES to present the fully-coupled system results. The neural network procedures are explained first, with illustrative demonstrations for simultaneous equations. Then, the link with the RES type of analysis is explained, together with some demonstration examples for rock engineering data sets. The specific analysis procedure is presented and then wider rock engineering examples are given relating to the characteristics of rock masses and engineering parameters. The main presentation tools used in this neural network approach are the Relative Strength Effect (RSE) and the Global Relative Strength Effect (GRSE) matrix. There is discussion of the value of this approach and an indication of the likely areas of future development.     

Representing Design Knowledge with Neural Networks

Neural networks have been used in a number of civil engineering applications because of their ability to implicitly learn an input–output relationship. Typically, the applications involve deriving an input–output relationship for problems that may be too complex to model mathematically, computationally expensive, or difficult to solve using the traditional procedural computing approach. Heuristic design knowledge used by structural engineers when performing structural design often falls in the latter category of being difficult to represent procedurally. Neural networks have been investigated for the representation of heuristic design knowledge, and the results of this investigation and the lessons learned regarding neural network training are presented.     

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。     

A fuzzy neural network approach for contractor prequalification

Non-linearity, uncertainty and subjectivity are the three predominant characteristics of contractors prequalification which lead to the process being more of an art than a scientific evaluation. A fuzzy neural network (FNN) model, amalgamating both the fuzzy set and neural network theories, has been developed aiming to improve the objectiveness of contractor prequalification. Through FNN theory, the fuzzy rules as used by the prequalifiers can be identified and the corresponding membership functions can be transformed. Eightyfive cases with detailed decision criteria and rules for prequalifying Hong Kong civil engineering contractors were collected. These cases were used for training (calibrating) and testing the FNN model. The performance of the FNN model was compared with the original results produced by the prequalifiers and those generated by the general feedforward neural network (GFNN, i.e. a crisp neural network) approach. Contractors' ranking orders, the model efficiency (R²) and the mean absolute percentage error (MAPE) were examined during the testing phase. These results indicate the applicability of the neural network approach for contractor prequalification and the benefits of the FNN model over the GFNN model. The fuzzy neural network is a practical approach for modelling contractor prequalification.     

On the energy consumption in residential buildings

A neural network approach is used in the present study for modelling and estimating the energy consumption time series for a residential building in Athens, using as inputs several climatic parameters.The hourly values of the energy consumption, for heating and cooling the building, are estimated for several years using feed forward backpropagation neural networks. Various neural network architectures are designed and trained for the output estimation, which is the building’s energy consumption. The results are tested with extensive sets of non-training measurements and it is found that they correspond well with the actual values.Furthermore, “multi-lag” output predictions of ambient air temperature and total solar radiation are used as inputs to the neural network models for modelling and predicting the future values of energy consumption with sufficient accuracy.     

StructNet: A Neural Network for Structural System Selection

Abstract: This paper describes StructNet, a computer application developed to select the most effective structural member materials given a building project's attributes. The system analyzes 15 parameters of a building project (e.g., available site space, budget, height) and determines the most appropriate structural system for the beam, column, and slab structural members. This paper first describes the process for selecting a structural system for a building. It was very important to understand this process before determining the best type and structure for the computer application. Then a comparison between a neural network approach and a rule-based expert-system approach for this application is presented. A discussion of the reasons for selecting a neural network approach is given. The StructNet application is described in detail, including the testing of the network. Along with the testing of the network is a discussion of how varying the learning rate and error limit affect the performance of the neural network application. The testing of the network shows that the program can reasonably select the same structural system types as the expert used to collect the training project data. Since the system will be used only as a preliminary tool to limit the number of possible structural systems for a project, the accuracy of the system is acceptable. However, additional experimentation needs to be conducted to determine the accuracy and practical use of this application. The final sections of the paper discuss the lack of adequate testing procedures for neural networks used in applications for unstructured or ill-defined decision making. The use of these types of networks and their relevance to the civil engineering computer field are also discussed.     

Predicting chaotic time series of PM10 concentration using artificial neural network

Respirable particulate matter (PM10) concentration at one residential site in Delhi, India was predicted using the neural network approach. The concepts of chaotic systems theory were utilized to build the neural network model. The embedding dimension was estimated to provide the inputs to the neural network. The model evaluation results indicated the importance of noise reduction before selecting the embedding dimension of the time series. The selection of a proper embedding dimension is considered to be essential for obtaining reliable predictions. The model’s performance shows the capability of neural networks in modelling the chaotic time series.     

Neural network model for resilient modulus of emulsified asphalt mixtures

This paper explores the potential use of neural networks (NNs) in the field of emulsified asphalt mixtures. A neural network model is developed for predicting, with sufficient approximation, relationship between the factors affecting resilient modulus (inputs: curing time, cement addition level, and residual asphalt content) and the resilient modulus (output) of emulsified asphalt mixture. A backpropagation neural network of three layers is employed. First resilient modulus data are obtained by conducting laboratory resilient modulus tests on emulsified asphalt samples, and then the results are used to train the neural network. The effectiveness of different neural network configurations is investigated. Effect of parameters such as curing time, cement addition level and residual asphalt content that influence the resilient modulus is also explored. Results indicate that NN predicts the resilient modulus with high accuracy. It is also demonstrated that NN is an excellent method that can reduce the time consumed and can be used as an important tool in evaluating the factors affecting resilient modulus of emulsified asphalt mixture at the design stage.     

基于LSTM网络的船舶机舱火灾多特征融合探测

针对船舶机舱火灾高效准确探测的需求,建立基于LSTM-ID3 判决的船舶火灾探测方法。首先确定采集船舶火灾特征的三类传感器,然后完成 LSTM 神经网络模型的构建、参数的优化,将 LSTM 神经网络输出的明火、阴燃火、无火的概率值与烟雾持续时间作为决策树的输入量,输出火灾探测结果。利用国家标准火典型数据进行训练,并开展相关试验,对船舶机舱火灾进行探测。试验结果表明,与其他算法进行对比,探测准确率达到97%以上,该方案能对机舱火灾做出有效探测,为船舶安全提供科学依据。     

Development of Recurrent Neural Network Considering Temporal‐Spatial Input Dynamics for Freeway Travel Time Modeling

Abstract: The artificial neural network (ANN) is one advance approach to freeway travel time prediction. Various studies using different inputs have come to no consensus on the effects of input selections. In addition, very little discussion has been made on the temporal–spatial aspect of the ANN travel time prediction process. In this study, we employ an ANN ensemble technique to analyze the effects of various input settings on the ANN prediction performances. Volume, occupancy, and speed are used as inputs to predict travel times. The predictions are then compared against the travel times collected from the toll collection system in Houston. The results show speed or occupancy measured at the segment of interest may be used as sole input to produce acceptable predictions, but all three variables together tend to yield the best prediction results. The inclusion of inputs from both upstream and downstream segments is statistically better than using only the inputs from current segment. It also appears that the magnitude of prevailing segment travel time can be used as a guideline to set up temporal input delays for better prediction accuracies. The evaluation of spatiotemporal input interactions reveals that past information on downstream and current segments is useful in improving prediction accuracy whereas past inputs from the upstream location do not provide as much constructive information. Finally, a variant of the state‐space model (SSNN), namely time‐delayed state‐space neural network (TDSSNN), is proposed and compared against other popular ANN models. The comparison shows that the TDSSNN outperforms other networks and remains very comparable with the SSNN. Future research is needed to analyze TDSSNN's ability in corridor prediction settings.     

Nonparametric Identification of a Building Structure from Experimental Data Using Wavelet Neural Network

Abstract:   This study presents a wavelet neural network-based approach to dynamically identifying and modeling a building structure. By combining wavelet decomposition and artificial neural networks (ANN), wavelet neural networks (WNN) are used for solving chaotic signal processing. The basic operations and training method of wavelet neural networks are briefly introduced, since these networks can approximate universal functions. The feasibility of structural behavior modeling and the possibility of structural health monitoring using wavelet neural networks are investigated. The practical application of a wavelet neural network to the structural dynamic modeling of a building frame in shaking tests is considered in an example. Structural acceleration responses under various levels of the strength of the Kobe earthquake were used to train and then test the WNNs. The results reveal that the WNNs not only identify the structural dynamic model, but also can be applied to monitor the health condition of a building structure under strong external excitation.     

A Fuzzy Expert System for Damage Assessment Using Genetic Algorithms and Neural Networks

Abstract: An efficient knowledge-acquisition support method is required for improvement and maintenance of the knowledge base in durability evaluation of an RC bridge deck. Such a method is proposed in this paper to automatically acquire fuzzy production rules. This method makes joint use of genetic algorithms and a neural network. Using a neural network as a subsystem, the evaluation function of genetic algorithms can be provided with the weights of the neural network. Introducing a neural network into genetic algorithms, it is possible to acquire new knowledge so that the method is useful when it is difficult to acquire knowledge in the field.     

Neural Networks in Structural Engineering

In the past few years literature on computational civil engineering has concentrated primarily on artificial intelligence (Al) applications involving expert system technology. This article discusses a different Al approach involving neural networks. Unlike their expert system counterparts, neural networks can be trained based on observed information. These systems exhibit a learning and memory capability similar to that of the human brain, a fact due to their simplified modeling of the brain's biological function. This article presents an introduction to neural network technology as it applies to structural engineering applications. Differing network types are discussed. A back-propagation learning algorithm is presented. The article concludes with a demonstration of the potential of the neural network approach. The demonstration involves three structural engineering problems. The first problem involves pattern recognition; the second, a simple concrete beam design; and the third, a rectangular plate analysis. The pattern recognition problem demonstrates a solution which would otherwise be difficult to code in a conventional program. The concrete beam problem indicates that typical design decisions can be made by neural networks. The last problem demonstrates that numerically complex solutions can be estimated almost instantaneously with a neural network.     

ANN-based empirical modelling of pile behaviour under static compressive loading

Artificial neural networks have been widely used over the past two decades to successfully develop empirical models for a variety of geotechnical problems. In this paper, an empirical model based on the product-unit neural network (PUNN) is developed to predict the load-deformation behaviour of piles based SPT values of the supporting soil. Other parameters used as inputs include particle grading, pile geometry, method of installation as well as the elastic modulus of the pile material. The model is trained using full-scale pile loading tests data retrieved from FHWA deep foundations database. From the results obtained, it is observed that the proposed model gives a better simulation of pile load-deformation curves compared to the Fleming’s hyperbolic model and t-z approach.     

Financially sustainable management strategies for urban wastewater collection infrastructure – development of a system dynamics model

Causal loop diagrams are developed for wastewater collection networks to identify complex interactions and feedback loops among physical, financial, and social sectors. Causal loop diagrams are then incorporated into a novel system dynamics based decision support tool that can be used for financially sustainable management of wastewater collection networks. Data requirements to develop the decision support tool are discussed along with how can the decision support tool be used to manage a utility.The presented causal loop diagram is the first known attempt to lay out the interrelationships among system components using a formal technique. The causal loop diagram establishes the existence of several interacting feedback loops and demonstrates that the management of wastewater collection networks constitutes a complex dynamic system for which traditional management tools are deemed inadequate. The use of causal loop diagrams can be useful to mitigate effects of the silo-based organizational culture prevalent in many water utilities.The system dynamics model is the first known decision support tool to quantitatively simulate the influence of interrelationships and feedback loops in wastewater collection network management. The model is a mathematical representation of the causal loop diagram to capture cost drivers and revenues sources in the system. It also includes a set of policy levers which allows formulation of various financing and rehabilitation strategies. The model can be used to develop short- and long-term management plans. The impact of financing and rehabilitation strategies on system performance can be simulated and evaluated in terms of financial and service level metrics. The decision support tool can also be used by utilities to ensure essential data is collected and flows within organizational units.     

Modeling and evaluating construction project competencies and their relationship to project performance

In contemporary construction environments, construction organizations measure their performance against a set of predefined performance measures. These performance measures are governed by the ability of the organization to maintain necessary sets of “competencies” that assist in the successful execution of its construction projects. Competencies are often difficult to define and measure due to the multidimensional and subjective nature of their assessment. This paper identifies 41 project competencies with a total of 248 criteria for evaluating the different project competencies. This paper also identifies seven performance categories with 46 project key performance indicators. A systematic framework and methodology are presented in this paper to measure project competencies and project key performance indicators. A new modeling approach considering prioritized fuzzy aggregation, factor analysis, and fuzzy neural networks is presented to identify the relationship between project competencies and project key performance indicators. Data collected from seven construction projects are first aggregated using prioritized fuzzy aggregation to measure the different construction project competencies. The different project competencies are then analyzed using factor analysis. The factor analysis results are used with the prioritized fuzzy aggregation results to calculate inputs for the fuzzy neural networks. The fuzzy neural networks are then trained and tested using the data collected from the seven construction projects to identify and quantify the relationship between the different project competencies and project key performance indicators. This paper contributes to the current body of knowledge in project competencies and performance by establishing a standardized framework and methodology for evaluating the impact of construction project competencies on project key performance indicators. Furthermore, this paper incorporates advanced modeling techniques through the application of fuzzy set theory and neural networks to identify the relationship between the different project competencies and project key performance indicators. Identifying the relationship between construction project competencies and project key performance indicators allows construction organizations to improve their overall construction project performance by enhancing their projects competencies.     

基于神经网络技术的复杂框架结构节点损伤的两步诊断法

大量研究表明,对于发生损伤的大型复杂结构,采用常规的一步方法进行损伤诊断将是十分困难,甚至是不可能的。因此,本文对多层及高层复杂框架结构节点损伤,提出了基于神经网络技术的两步诊断方法,此方法先将结构划分为n个子区域,将损伤引起的结构前n阶模态频率变化比与损伤区域的关系输入概率神经网络,建立系统,进行损伤子区域判定;然后将结构损伤子区域内第二阶杆端应变模态变化量与节点损伤位置和损伤程度的关系输入径向基神经网络,建立系统,进行损伤位置和损伤程度具体诊断。数值仿真分析结果表明,此方法可对多层及高层框架结构的地震节点损伤做出成功诊断,且具有较好的抗干扰能力。     

Modeling and predicting building's energy use with artificial neural networks: Methods and results

This paper discusses how neural networks, applied to predict energy consumption in buildings, can advantageously be improved, guided by statistical procedures, such as hypothesis testing, information criteria and cross validation. Recent literature has provided evidence that such methods, commonly used independently, when exploited together, can improve the selection and estimation of neural models.We use such an approach to design feed forward neural networks for modeling energy use and predicting hourly load profiles, where both the relevance of input variables and the number of free parameters are systematically treated. The model building process is divided in three parts: (a) the identification of all potential relevant input, (b) the selection of hidden units for this preliminary set of inputs, through an additive phase and (c) the remove of irrelevant inputs and useless hidden units through a subtractive phase.The predictive performance of short term predictors is also examined with regard to prediction horizon. A comparison of the predictive ability of a single-step predictor iteratively used to predict 24 h ahead and a 24-step independently designed predictor is presented.The performance of the developed models and predictors was evaluated using two different data sets, the energy use data of the Energy Prediction Shootout I contest, and of an office building, located in Athens. The results show that statistical analysis as an integral part of neural models, gives a valuable tool to design simple, yet efficient neural models for building energy applications.     

QUALITATIVE QUERYING OF PHYSICAL PROCESS SIMULATIONS

The preliminary design of a query system for the computer simulation of physical processes is presented. Most engineering simulations produce vast amounts of quantitative data. It often requires special training to interpret the data and many of them may not be directly relevant to a particular decision. Human beings usually find qualitative explanations easier to absorb than large quantities of detail. The query system described in the paper is a preliminary to the production of an interrogation system which can provide both qualitative answers and explanations. In the first part of the system, natural language queries are transformed into standard query types using a neural net. In the second part qualitative replies are formed from neural nets which are trained by data from the simulation. An object oriented hierarchy which facilitates the mappings of quantitative data into qualitative attributes is presented. The development of a more detailed and sophisticated explanation system is also discussed.