An Artificial Neural Networks Model for the Estimation of Formwork Labour / Dirbtinių Neuroninių Tinklų Modelis, Kurio Paskirtis – Skaičiuoti Klojiniams Skirto Darbo Apimtis

The paper presents an original approach to construction cost analysis and development of predictive models based on ensembles of artificial neural networks. The research was focused on the application of two alternative approaches of ensemble averaging that allow for combining a number of multilayer perceptron neural networks and developing effective models for cost predictions. The models have been developed for the purpose of forecasting construction costs of sports fields as a specific type of construction objects. The research included simulation and selection of numerous neural networks that became the members of the ensembles. The ensembles included either the networks of different types in terms of their structure and activation functions or the networks of the same type. The research also included practical implementation of the developed models for cost analysis based on a sports field BIM model. This case study examined and confirmed all of the four models’ predictive capabilities and superiority over models based on single networks for the particular problem. Verification including testing and the case study enabled selection of the best ensemble-based model that combined ten networks of different types. The proposed approach is prospective for fast cost analyses and conceptual estimates in construction projects.

Section: State-of-the-art and Literature Reviewmentioning

confidence: 99%

Forecasting of Sports Fields Construction Costs Aided by Ensembles of Neural Networks

Juszczyk

Zima

Lelek

2019

“…ANN is developed in three layers; an input layer, hidden layer(s), and an output layer. The number of hidden layers changes according to the application (Dikmen, Sonmez 2011). The output layer receives the input and signals flow from the input layer through the hidden layers which are between the output and input layers (Apanaviciene, Juodis 2003).…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Risk analysis of BOT contracts using soft computing

Shahrara

Çelik

Gandomi

2016

Build-Operate-Transfer (BOT) contracts have been widely implemented in developing countries facing budget constraints. Analysing the expected variability in project viability requires extensive risk analysis. An objective analysis of various risk variables and their influence on a BOT project evaluation requires study and integration of many scenarios into the concession terms, which is complicated and time-consuming. If the process of negotiating the financial parameters and uncertainties of a BOT project could be automated, this would be a milestone in objective decision-making from various stakeholders’ points of view. A soft computing model would let the user incorporate as many scenarios as could be provided. Extensive risk analysis could then be easily performed, leading to more accurate and dependable results. In this research, an artificial neural network model with correlation coefficient of 0.9064 has been used to model the relationship between important project parameters and risk variables. This information was extracted from sensitivity analysis and Monte Carlo simulation results obtained from conventional spreadsheet data. The resulting consensus would yield to fair contractual agreements for both the government and the concession company.

“…In this method, a real experimental database is used to acquire relationships between involved parameters. The greater is the database of results, the more accurate is the prediction (Heshmati et al 2009;Dikmen, Sonmez 2011;Khosrowshahi 2011).…”

Section: Artificial Neural Networkmentioning

confidence: 99%

“…On the other hand, because of their multidisciplinary nature, artificial neural networks are commonly applied by the majority of researchers working in different branches of science (Goh et al 1995;Maity, Saha 2004;Schabowicz, Hoła 2008;Baalousha, Celik 2011). Besides, high capabilities of this tool in prediction of complicated functions have been broadly proved (Abu Kiefa 1998;Malinowski, Ziembicki 2006;Mang et al 2009;Dikmen, Sonmez 2011). Thus, to attain a rugged, cost-effective and timely prediction of the optimal bolt length, the applicability of ANNs has been investigated.…”

Section: Introductionmentioning

confidence: 99%

Superiority of Artificial Neural Networks Over Statistical Methods in Prediction of the Optimal Length of Rock Bolts

Hasanzadehshooiili

Lakirouhani

Medzvieckas

2012

Rock bolting is one of the most important support systems used for rock structures. Rock bolts are widely used in underground excavations as they are suitable for a wide range of geological conditions and allow using progressive design methods; besides, they help economising in the use of materials and manpower. Thus, to provide the most effective support at minimum cost by means of rock bolting, it is essential to optimise the elements contributing to bolt design, including their length, as well as bolt density and tension during installation. This paper considers the length of bolts for optimisation of the design phase, which is one of the most important parameters impacting the entire design procedure. Presenting and comparing results of some statistical models, neural network modeling is introduced as powerful means in prediction of the optimal length of rock bolts. Subsequent to training and testing of a large number of 1-layer and 2-layer backpropagation neural networks, it was reported that the optimal model was the network with the architecture of 6-18-3-1 as it demonstrated the minimum RMSE and MAE as well as the maximum R 2 . In comparison to statistical models (0.7182 for the value of R 2 in the multiple linear regression model, 0.68 in the polynomial model and 0.7 in the dimensionless model), the results obtained by the neural network modeling − i.e. the coefficient of determination R 2 of 0.9259, the value of mean absolute error MAE of 0.068, and the root mean squared error RMSE of 0.078 − not only proved their superiority but also introduced the neural network modelling as a highly capable prediction tool in forecasting the optimal length of rock bolts. Furthermore, sensitivity analysis was used to obtain parameters that have the greatest and the least impact on the optimal bolt length: the effect of the overburden thickness, tensile strength, cohesion and Poisson's ratio on the optimal bolt length was almost the same while the friction angle had the least influence.Keywords: optimal length of rock bolts, artificial neural networks, statistical methods, sensitivity analysis.