Comparative study in the use of neural networks for order of magnitude cost estimating in construction (original) (raw)
Related papers
A neural network approach for early cost estimation of structural systems of buildings
International Journal of Project …, 2004
The importance of decision making in cost estimation for building design processes points to a need for an estimation tool for both designers and project managers. This paper investigates the utility of neural network methodology to overcome cost estimation problems in early phases of building design processes. Cost and design data from thirty projects were used for training and testing our neural network methodology with eight design parameters utilized in estimating the square meter cost of reinforced concrete structural systems of 4-8 storey residential buildings in Turkey, an average cost estimation accuracy of 93% was achieved.
IJERT-Cost Estimation Model (Cem) for Residential Building using Artificial Neural Network
International Journal of Engineering Research and Technology (IJERT), 2016
https://www.ijert.org/cost-estimation-model-cem-for-residential-building-using-artificial-neural-network https://www.ijert.org/research/cost-estimation-model-cem-for-residential-building-using-artificial-neural-network-IJERTV5IS010431.pdf The achievement of any project undertaking is defined by improved quantity and cost estimation technique that facilitates optimum utilization of resources. The objective of this study is to develop a cost estimation technique by using an artificial neural network (ANN) model that will be able to forecast the total structural cost of residential buildings by considering various parameters. In this study, data of last twenty three years has been collected from Schedule of rate book (SOR) and general studies. Eight input parameters, namely, cost of cement, sand, steel, aggregates, mason, skilled worker, non-skilled worker and the contractor per square feet construction were selected. The parameters were simulated in NEURO XL Version 2.1 for developing ANN architecture. The resulting ANN model reasonably predicted the total structural cost of building projects with correlation factor R-0.9960 and RSquared-0.9905 giving favorable training and testing phase outcomes.
Cost is one of the major factors in decision making at the early stages of a building construction process. The real challenge in cost estimation of building projects at the early stage is lack of information. So decision making is important in cost estimation for building design processes which needs an estimation tool for designers, estimators and project managers. Artificial neural networks (ANN) method is most effective and appropriate technique for initial stage cost estimation. This project is highlighting the study of Application of Artificial neural network (ANN) for pre design cost estimation of building projects to investigate and overcome problems caused in estimating project cost at pre-design stage of building projects. As well as to develop & test a Graphical User Interface (GUI) model of cost estimating for building projects in the early design phase using MATLAB software. Twelve actual real-life cases of building projects constructed in Pune District during the Three...
Construction Cost Estimation for Government Building Using Artificial Neural Network Technique
2021
The construction bidding competition required effective precision to prevent losses in the bidding process, especially in the public sector. The bidders must have an estimate of the construction cost before the bidding. There are two widely used methods for construction cost estimation: 1) a rough estimation with an advantage of quick construction estimation cost and a disadvantage of a high price tolerance, and 2) a detailed estimation with an advantage of more accurate estimation of construction costs, and disadvantages of the need for a complete construction plan and time-consuming. Considering these disadvantages, research on the government construction cost estimation model was conducted by using the Artificial Neural Network (ANN) technique of forecasting modeling. The study's results showed that the model consisted of two hidden layers which each layer has ten and eight nodes, respectively, with the best Root Mean Square Error (RMSE) value ± 0.331 million Baht. When the new data set was tested for validity, the R 2 equal to 0.914 proving the accuracy of the forecasting model as an alternative for government bidding participants to reduce the tolerances and to spend less time to estimate construction costs more efficiently.
Construction Management and Economics, 2002
The importance of models to estimate the cost of buildings has been highlighted by . reviewed over 60 cost models and classi ed the techniques used to develop each model under eight headings, including regression techniques. However, in both cases no mention was made of the application of neural networks. Elhag and Boussabaine (1998) developed neural network models to predict the tender price of school buildings, and later (Elhag and Boussabaine, 1999a) they developed two models to predict the tender price of of ce buildings using linear regression and neural network techniques. They found that both techniques produced models that were able to map the underlying relationship between the cost factors and the tender price but, because the sample size was small (30 and 36 projects, respectively), concluded that more projects were required for meaningful conclusions to be drawn. This paper describes the development of neural network models of total construction project cost based on recent historical project data. The initial impetus for the research was the paucity of data available that can provide reliable information about the relative costs of using different procurement routes. However, in attempting to develop a model to address this strategic decision, it immediately became apparent that this variable cannot be isolated from the many other cost signi cant variables in a building project (Harding Neural network cost models have been developed using data collected from nearly 300 building projects. Data were collected from predominantly primary sources using real-life data contained in project les, with some data obtained from the Building Cost Information Service, supplemented with further information, and some from a questionnaire distributed nationwide. The data collected included nal account sums and, so that the model could evaluate the total cost to the client, clients' external and internal costs, in addition to construction costs. Models based on linear regression techniques have been used as a benchmark for evaluation of the neural network models. The results showed that the major bene t of the neural network approach was the ability of neural networks to model the nonlinearity in the data. The 'best' model obtained so far gives a mean absolute percentage error (MAPE) of 16.6%, which includes a percentage (unknown) for client changes. This compares favourably with traditional estimating where values of MAPE between 20.8% and 27.9% have been reported. However, it is anticipated that further analyses will result in the development of even more reliable models.
PRE-DESIGN STAGE CONSTRUCTION COST PREDICTION OF BUILDING PROJECTS USING ARTIFICIAL NEURAL NETWORK
Cost is one of the major factors in decision making at the early stages of a building construction process. The real challenge in cost estimation of building projects at the early stage is lack of information. So decision making is important in cost estimation for building design processes which needs an estimation tool for designers, estimators and project managers. Artificial neural networks (ANN) method is most effective and appropriate technique for initial stage cost estimation. This project is highlighting the study of Application of Artificial neural network (ANN) for pre design cost estimation of building projects to investigate and overcome problems caused in estimating project cost at pre-design stage of building projects. As well as to develop & test a Graphical User Interface (GUI) model of cost estimating for building projects in the early design phase using MATLAB software. Twelve actual real-life cases of building projects constructed in Pune District during the Three year period 2014-2017 were used as training materials. The architecture of Artificial neural network is presented for the estimation of the project cost at the initial stage.
Expert System-Based Predictive Cost Model For Building Works: Neural Network Approach
2010
Project managers need accurate estimate of building projects to be able to choose appropriate alternatives for their constructions. Estimated costs of building projects, which hitherto have been based on regression models, are usually left with gaps for high margin of errors and as well, they lack the capacity to accommodate certain intervening variables as construction works progress. Data of past construction projects of the past 2 years were adjusted and used for the study. This model is developed and tested as a predictive cost model for building projects based on Multilayer Perceptron Artificial Neural Networks (ANNs) with Levenberg Marqua. This model is capable of helping professionals save time, make more realistic decisions, and help avoid underestimating and overestimating of project costs. The model is a step ahead of Regression models.
2015
Cost estimating is a critical due to incomplete project details and drawings and has become a similar issue in Sri Lanka. Since, cost of a building is impacted by decisions made at the design phase, efficient cost estimation is essential. Therefore novel cost models have identified as simple, understandable and reliable. Thereby, Artificial Neural Networks (ANN) have established having the ability to learn patterns within given inputs and outputs and the end result was developed as the preliminary project cost estimation model for public sector office buildings in Sri Lanka. To accomplish the above aim, the survey approach was selected and semi structured interviews and documentary review were conducted in collecting data. Then training and testing of the Neural Networks (NN) under ten design parameters was carried out using the cost data of twenty office buildings in public sector. The data was applied to the back propagation NN technique to attain the optimal NN Architectures. The...
Prediction and estimation of civil construction cost using linear regression and neural network
International Journal of Intelligent Systems Design and Computing, 2018
Adequate construction cost estimation is a main factor for any type of construction projects. Forecasting cost of construction projects can be considered as a difficult task. In order to forecast the cost of the civil construction projects, we have used the ordinary least square regression (OLSR) model and multilayer perceptron (MLP) in our proposed model. The performance of the proposed model is analysed on the data of the 12 years of schedule rates of construction projects in Pune region of India. The experiment shows 91% to 97% of accuracy in prediction using ordinary least square regression model. Similarly, we have conducted series of experiments on multilayer perceptron model with different activation functions. It was observed that the multilayer perceptron model with 'softplus' activation function can be able to predict the project cost of the civil constructions with accuracy of 91% to 98%. Thus, it shows that the prediction of cost using multilayer perceptron model gives higher accuracy than the ordinary least square regression model.