Welcome
Digital library of construction informatics
and information technology in civil engineering and construction
 

Works 

Search Results

Facilitated by the SciX project

Hits 1 to 10 of 20

A Asadi, A Hadavi, R J. Krizek

Bridge Life-Cycle Cost Analysis Using Artificial Neural Networks

Abstract: Life-Cycle Cost analysis can significantly assist in making investment decisions. Several recentstudies have recognized the potential benefits of Life-Cycle Cost analysis and call for use of suchanalyses when making infrastructure investments, including investments in bridges. The Life-CycleCost of a bridge consists of the total investment throughout the life of the bridge. This includes theinitial construction cost, repair and rehabilitation costs, and all maintenance costs. The ability toaccurately determine the Life-Cycle Cost of a bridge will help agencies evaluate the asset value ofexisting bridges, make better decisions on the design and construction of new ones, and chooseimproved methods and approaches for rehabilitating existing structures. Research has shown thattimely maintenance, repair, and rehabilitation can lower the Life-Cycle Cost of a bridge. However, thisis a complex and nonlinear problem, and previous studies have failed to develop a satisfactory model. One effective technique for solving nonlinear problems with complicated functions is an ArtificialNeural Network. A neural network is a powerful data-modeling tool that captures and representscomplex input/output relationships. Using a set of input and output data belonging to a particularproblem, a neural system can be trained to predict outcomes for new versions of the same problem.Accordingly, an extensive set of data (bridge dimensions, age, initial cost, and Life-Cycle Cost) for 14Chicago bridges was used to quantify the degree of success that could be achieved with this model.Sixty percent of the data was used as input to train the model and the remaining forty percent was usedto assess the success of the model for predicting the Life-Cycle Cost. The results achieved wereencouraging and suggest that the neural network model is a promising tool for predicting the LifeCycleCost ofa bridge.

Keywords: life-cycle cost, artificial neural network, Chicago Trunnion Bascule bridges. initial cost, repair and rehabilitation cost

DOI:

Full text: content.pdf (239,502 bytes) (available to registered users only)

Series: w78:2011 (browse)
Cluster:
Class:
Similar papers:
Sound: N/A.


A Lähr & K-U Bletzinger

Prediction of consequences for planning situation based decisions

Abstract: Consequences of a decision made by a planner (e.g. a project manager, or an engineer) within a collaborative environment can hardly be foreseen. For example, such a collaborative scenario is represented by a planning process in AEC. In particular, during certain planning stages alternatives have to be considered which significantly influence the overall result. Todays AEC planning procedures can be very much improved by predicting simulation methods to judge about the quality impact of certain design or planning modifications. Also, the proper interpretation of data is very crucial to give suitable insight into the characteristic consequences of individual planning decisions. This contribution presents an approach to achieve this goal by discussing needs, problems and implementation for the actual state of our research.

Keywords:

DOI:

Full text: content.pdf (972,202 bytes) (available to registered users only)

Series: w78:2005 (browse)
Cluster:
Class:
Similar papers:
Sound: N/A.

Permission to reproduce these papers has been graciously provided by the Technische Universität Dresden.


Andresen J, Baldwin A, Betts M, Carter C, Hamilton A, Stokes E, Thorpe T

A Framework for Measuring IT Innovation Benefits

Abstract: This paper presents a new framework for measuring the benefits of IT in construction. The framework is based on the principle that benefits realisation must be managed by: planning for strategic alignment and business-driven exploitation, managing the process of predicting benefits, and by measuring resulting benefits after a system or innovation is implemented. Three distinct types of benefits are identified within the new framework associated with business efficiency, business effectiveness and business performance. A key barrier to the more effective exploitation and application of IT in the construction sector has been the lack of investment on a scale comparable with other sectors. A primary reason cited for the low level of investment is the low level of perceived benefits from IT investments amongst construction business managers. Many benefits evaluation methods exist and are widely applied in other sectors. Benefits evaluation methods in construction are under-utilised. One reason for this is the lack of fit between these methods, and their associated language, with the peculiarities of the construction sector. The new framework presented in this paper has been derived for specific application to the construction sector. The framework has been subjected to testing and application within UK construction organisations. The results of this testing suggest a number of improvements in the benefits realisation process.

Keywords: information technology, business benefits, innovation, evaluation framework

DOI:

Full text: http://www.itcon.org/2000/4 (available to registered users only)

Series: itcon:2000 (browse)
Cluster:
Class:
Similar papers:
Sound: read aloud.


Bento J, Azevedo J, Oliveira C S

Predicting ground otion descriptions through artificial neural networks

Abstract: "The present paper addresses the problem of predicting the description of an expected earthquake through the associated ground motion record that would be recorded at a given site. For that purpose, a number of previous ground motion records referring to 100 different earthquakes occurring within a reasonably small geographic area (Northern California) have been acquired and processed in order to extract some of the features that could describe them more synthetically than the full records. The attributes thus generated were used to train a feedforward network in order to map them into what can be called higher level descriptors of each earthquake, such as the magnitude or the peak accelerations, for example. Once such mapping is obtained, one may infer a number of attributes that would allow the artificial generation of the accelerograms corresponding to ""expected earthquakes"" described resorting to those higher level descriptors"

Keywords:

DOI:

Full text: content.pdf (408,837 bytes) (available to registered users only)

Series: w78:2000 (browse)
Cluster: papers of the same cluster (result of machine made clusters)
Class: class.analysis (0.031791)
Similar papers:
Sound: read aloud.

Permission to reproduce these documents have been graciously provided by Icelandic Building Research Institute. The assistance of the editor, Mr. Gudni Gudnason, is gratefully appreciated


D Browne, K Menzel

Method for Validation of Building Simulation Results using Sensor Data

Abstract: In general, current Building Energy Simulation Tools are used for pre-construction design and comparison of designs rather than a full exact varying representation of reality. To provide the best level of detail full CFD analysis for the entire building would be required. However this is currently by far outside the scope of current computing power for a building energy system. Because these simulation tools are designed for comparison of potential designs and because of the difficulty in predicting occupant behaviour, very often the predicted results do not correlate with the real actual performance when buildings are in operation. From project experience encountered in the EU FP7 IntUBE project, a deficit has been encountered whereby the correlation between simulation results and real measured data is not entirely accurate. This paper discusses a method of validation, which will provide a means of comparing measured data (e.g. sensors and weather data), and simulated data (e.g. near future simulations). This method for validation of building simulation results initially involves a comparison of data from building simulation and respective measured sensor readings. From this comparison, value is added from correction of simulation results, and/or input to simulation parameters. Further worth can also be provided by gaining knowledge for creation of simulation profiles which are difficult to predict before construction & operation. Additional value can also be derived from identifying conditions of poor results and relevant factors which can be corrected. Simulation data and actual data is available from a housing unit in Barcelona Spain and research building in Cork Ireland.The expected result to be derived from this method is to give an indication of quality of simulated data results and provide feedback. If the difference between simulated and real data is too large, steps to improve results will be suggested. In future it is envisioned that automated adjustments may performed to simulation inputs to correct results. Aside from near future simulation validation, the tool may be able to provide long term commissioning feedback to detect and alert users to long term degradation of systems and possible maintenance or repair remedies.

Keywords: Simulation, Data Modelling, Validation

DOI:

Full text: content.pdf (109,859 bytes) (available to registered users only)

Series: w78:2011 (browse)
Cluster:
Class:
Similar papers:
Sound: N/A.


E Tobin,H Yin, K Menzel

Analysis of Performance Data from HVAC Components for Prediction of Maintenance Requirements

Abstract: This paper describes a methodology which manages a building’s maintenance activities by focusing on the timing of maintenance activities. Its goal is to optimise the trade-off between cost, which is incurred through maintenance activities, and the components health, which varies as a result of maintenance frequency. Here existing data from a BMS is utilises and analysis is performed on this data, with the objective of scheduling maintenance for a component, based on the measured performance of that component. This paper will investigate which data analysis technique provides the most certainty when determining the expected performance level. The major outcome of this paper is to present the certainty levels for each data analysis technique and illustrate how the analysis can be used for predicting maintenance requirements. Also this paper will have presented a methodology for managing maintenance activities and an implementation of these results using a Decision Support Framework for maintenance management. This research is performed as part of a nationally funded project ‘Information Technology for Optimised Building Operation’ (ITOBO).

Keywords: Energy-efficient buildings, Maintenance Management, Performance Based Maintenance, Performance Data Analysis, ITOBO.

DOI:

Full text: content.pdf (240,699 bytes) (available to registered users only)

Series: w78:2011 (browse)
Cluster:
Class:
Similar papers:
Sound: N/A.


Edwards D J, Yang J, Love P E D

A Computer Based Software Tool for Assessing Plant Operatives' Productivity

Abstract: Developments in computer hardware and software have significantly influenced the accuracy of estimating and predicting construction productivity. To date, a plethora of unique computer software packages is readily available and these packages have helped to increase production and profitability whilst simultaneously reducing financial risk. This paper presents and describes the development of a new prototype Computer Based Software (CBS) human resource management tool, that can be used to assess a plant operative's potential productivity output. The CBS utilizes information extracted from a range of factors and variables that exhibit a significant correlation between machine production and operator attributes (for example, management practices and site conditions).

Keywords: computer software, productivity, plant operative, off-highway plant and equipment

DOI:

Full text: content.pdf (301,404 bytes) (available to registered users only)

Series: itaec:2004 (browse)
Cluster:
Class:
Similar papers:
Sound: N/A.


Euthimios Glymis, Athanasios Kanelakis, Georgios Aretoulis and Theodoros Mastoras

Predicting Highway Projects' Actual Duration Using Neural Networks

Abstract: The current study predicts the actual duration of highway projects, based on the initial planned schedule. Highway projects suffer from delays and deviations, which in Greece are more often associated with law disputes, project financing, archaeological findings, environmental issues and private land acquisition procedures. In this research, data were obtained from 37 road projects in Greece and the purpose was to estimate the construction duration, using an artificial neural network. The Fast Artificial Neural Network (FANN) Tool program was used. FANN based on the available data, identifies the optimal training algorithm. The training algorithm and the activation function with the lowest mean square error (MSE) are selected. In order to achieve the best possible solution, numerous trials were made, applying different input data combinations, different variations in the architecture of the network, and different data values were used. This paper presents the three more reliable and effective networks produced from the current study. The results indicated that Artificial Neural Networks, employing the appropriate parameters do provide a relatively high accuracy in predicting actual construction time and more specifically appear as one of the most optimal methods for actual highway construction time prediction.

Keywords: Highway Projects, Actual Project Duration, Estimated Project Duration, Artificial Neural Networks

DOI: https://doi.org/10.24928/JC3-2017/0260

Full text: content.pdf (758,236 bytes) (available to registered users only)

Series: jc3:2017 (browse)
Cluster:
Class:
Similar papers:
Sound: N/A.


Guangchun Zhou, Yaqub M. Rafiq, Chengfei Sui and Lingyan Xie

A CA And ANN Technique Of Predicting Failure Load And Failure Pattern Of Laterally Loaded Masonry Panel

Abstract:

Keywords:

DOI:

Full text: content.pdf (768,071 bytes) (available to registered users only)

Series: w78:2006 (browse)
Cluster:
Class:
Similar papers:
Sound: N/A.


Haghighat F

Development of a procedure to evaluate the air leakage distribution from fan pressurization test - validation of three airflow models

Abstract: A number of airflow models have been developed to assist the designer in the design of energy efficient and healthy built environment. The models range from very simple empirical algorithms to calculate the global airflow rate to sophisticated computerized fluid-dynamic techniques solving the Navier-Stokes equations. The multi-zone approach falls between these two extreme cases. This approach assumes that the interior of the building is divided into regions of differing pressures interconnected by leakage paths. The advantage of multi-zone models, besides being able to simulate infiltration in larger buildings, is that they can be used to calculate mass flow interactions between the different zones inside buildings as well as inside and outside. This knowledge is needed for the design of heating/cooling and ventilation systems. An essential part of the development of any computer model is its validation, and the essential information needed for validation of airflow models is the distribution of air leakage distribution. This paper first describes a methodology to distribute global air leakage of whole house and whole garage among cracks and gaps on exterior walls and roof, and report the validation of three airflow models. From the comparisons it can be seen that there are good agreement between the predictions made by the models and measured data, as well as between three models. Therefore, it can be concluded that the methodology for air leakage distribution is correct, and the performances of COMIS, CONTAM and ESP-r for predicting airflow rates in single-family house are similar.

Keywords:

DOI:

Full text: content.pdf (198,669 bytes) (available to registered users only)

Series: w78:2003 (browse)
Cluster:
Class:
Similar papers:
Sound: N/A.

Permission to reproduce these papers has been graciously provided by the University of Auckland. The assistance of the editor who provided the full texts and the structured metadata, Dr. Robert Amor, is gratefully appreciated.


For more results click below:

 

hosted by University of Ljubljana



includes

W78




© itc.scix.net 2003
this is page 1 show page 2 Home page of this database login Powered by SciX Open Publishing Services 1.002 February 16, 2003