An analysis on material quantity relationship of reinforced concrete buildings between Multiple Linear Regression and Artificial Neural Network

Main Article Content

Wantana Prapaporn

Abstract

Pricing management is a key mechanism for the cost control before starting any project while the ability to validate the quantity take-off can be a method to increase the effectiveness for the construction workload accounting. The researcher conducted this study with the aims to: 1) investigate the effective factors toward the construction workload prediction; 2) compare the effectiveness between a multiple regression model and an artificial neural networks model; 3) describe the relationship amongst the construction materials. On this matter, the researcher assigned the experimental group as the representative to simulate the multiple regression equation model and the artificial neural network model comprising 30, 32, and 30 units respectively. Meanwhile, the representatives of any sample groups were selected by randomization comprising 14, 15, and 15 units respectively. Particularly, the sample group consisted of 136 units of residences, commercial buildings, and common housing buildings. Based on the study, it could be described that the independent variables as 1) the average area per floor and 2) Number of floors represents the significantly description of the dependent variable were: 1) Concrete Work; 2) Reinforced Steel Work; 3) Formwork; and 4) Precast Concrete Slabs; meanwhile, the architectural work consisted of: 1) Floor Material ; 2) Manasory work ; 3) Ceiling Material; and 4) Door and Window Material. Besides, the artificial neural network model could describe changes of the construction material quantity with more accurate result than did the multiple regression model. This study also noted that the works of each sample group were significantly different from one another; Namely, 1) A mutual relationship between Concrete quantity (m3) per Construction area (m2) was confirmed as 0.27, 0.195, and 0.168; 2) A mutual relationship between Reinforced steel (kg) per Concrete (m3) was confirmed as 85.44, 118.235, and 113.49; 3) A mutual relationship between Formwork (m2) per Concrete (m3) was confirmed as 9.46, 9.20, and 9.24 4; 4) A mutual relationship between Manasory work (m2) per Construction area (m2) was confirmed as 0.32, 1.62, and 1.33; and 5) A mutual relationship between Door and Window (m2) per Manasory work (m2) was confirmed as 0.12, 0.13, and 0.15. These data were the results found from the case studies on the residences, commercial buildings, and common housing buildings respectively.

Article Details

How to Cite
Prapaporn, W. (2019). An analysis on material quantity relationship of reinforced concrete buildings between Multiple Linear Regression and Artificial Neural Network. Naresuan University Engineering Journal, 14(1), 84–102. Retrieved from https://ph01.tci-thaijo.org/index.php/nuej/article/view/141406
Section
Research Paper

References

[1] Wisoot Jiradamkerng. (2010). Construction cost Estimation. (4 edition). ISBN 978-6167-770147 Bangkok, Wankawee

[2] Zhiting Wu, Xuedong Chen. (2015). The Material Consumption Estimation Model of Frame Shear Wall Structure, Journal of System and Management Sciences. Vol. 5 No. 1, pp. 38-51.

[3] The Comptroller General’s Department. (2012). Criteria for calculating the central price of building construction.

[4] The Engineering Institute of Thailand Under H.M. The King's Patronage. (1999). Construction Management Information for Construction Price Evaluation and Control. EIT Standard, ISBN 974-7197-31-6, Bangkok, Thailand.

[5] AACE International Recommended Practice No. 18R-97. (2005). Cost Estimate Classification System – AS Applied in Engineering, Procurement, and Construction For The Process Indistries, the association for the advancement of cost engineering.

[6] Thammasak Rujirayanyong. (2012). Estimate Cost for Apartment Building Using Regression Analysis. Rangsit University Journal of Engineering and Technology, Vol. 15, No. 2.

[7] Nikhil K Gilson, Alester Joseph Vanreyk. (2014). Review of Cost Estimation Models, International Journal of Scientific Engineering and Research (IJSER), ISSN (Online) : 2347-3878

[8] Nivea Thomas, and Dr. Anu V. Thomas. (2016). Regression Modelling for Prediction of Construction Cost and Duration, Applied Mechanics and Materials, Vol. 857, pp 195-199.

[9] Worasak Thawekitjakarn. (1990). An application of regression analysis in building cost estimating, Graduate Studies, Chulalongkorn University.

[10] Somchart Manprasert. (1998). A Study on Building Construction Cost Estimate Using Work Quantity Model Approach, Master. Engnineering (Civil Engineering), Graduate Studies, Chulalongkorn University.

[11] Gwang-Hee Kim, Jae-Min Shin, Sangyong Kim, Yoonseok Shin. (2013). Comparison of School Building Construction Costs Estimation Methods Using Regression Analysis, Neural Network, and Support Vector Machine , Journal of Building Construction and Planning Research, 2013, pp 1-7.

[12] Jessada Sarasinpithak, Tanit Thongthong. (2000). A study on quantity estimation of building construction using neural network models, Master of Engnineering (Civil Engineering), Graduate Studies, Chulalongkorn University.

[13] H. Murat Günaydın S Zeynep Doğan. (2004). A neural network approach for early cost estimation of structural systems of buildings, international Journal of Project Management Volume 22, Issue 7, Pages 595-602.

[14] Azme Bin Khamis, Nur Khalidah Khalilah Binti Kamarudin. (2014). Comparative Study On Estimate House Price Using Statistical And Neural Network Model, International journal of science & technology research volume 3, issue 12, ISSN 2277-8616.

[15] Smita K. Magdum and Amol C. Adamuthe. (2017). Construction cost prediction using neural networks. ICTACT Journal on soft computing, Volume 08, Issue 01, pp 1549 - 1556.

[16] Office of the council of state. (2522). BUILDING CONTROL ACT. Retrieved from http://www.krisdika.go.th/wps/portal/general,

[17] National Statistical Office. (2011) . Population Statics, Bureau of Social Statistics. Retrieved from http://popcensus.nso.go.th/upload/popcensus-08-08-55-E.pdf

[18] Construction Specifications Institute (CSI) and Construction Specifications Canada (CSC). MasterFormat ® (2016). MasterFormat ® Numbers & Titles. Retrieved from https://www.edmca.com/media/35207/masterformat-2016.pdf

[19] U.S. Department of Commerce Technology Administration National Institute of Standard and Technology. (1999). UNIFORMAT II Elemental classification for building specifications, Cost Estimating, and Cost analysis. Retrieved from https://arc-solutions.org/wp-content/uploads/2012/03/Charette-Marshall-1999-UNIFORMAT-II-Elemental-Classification....pdf

[20] The Engineering Institute of Thailand Under H.M. The King's Patronage. (2011). Building Survey Structural and Architectural Works, Engineering of Thailand, 2nd revised edition.

[21] Associate Professor Dr. Kanlaya Vanichbuncha. (2009). Statistical analysis with Excel, Bangkok : Faculty of Commerce and Accountancy Chulalongkorn University.

[22] D.A. Clevert, T. Unterthiner and S. Hochreiter. (2016). Fast and accurate deep learning. Proceeding of international conference on learning representations, pp 1- 14

[23] The Engineering Institute of Thailand Under H.M. The King's Patronage. (2013). General conditions. EIT Standard, ISBN 978-974-7197-80-8, Bangkok, Thailand.