Quantitative risk analysis model and decision tree for the classification and identification of wastes through making-do
DOI:
https://doi.org/10.46421/entac.v20i1.5732Keywords:
waste, Making-do, Machine learning, Database, Machine learning modelAbstract
Losses in civil construction works correspond to a significant percentage of the total cost of the project, especially those caused by improvisations and incompleteness (making-do). In this sense, it is necessary to create mechanisms to mitigate, as well as understand where these losses occur. Thus, this research aimed to develop a quantitative model for the classification and identification of wastes, increasing the reliability of the classification between different authors by defining a decision tree to classify and analyze the risk of wastes. The methodology employed consists of defining a protocol for identifying and analyzing losses by making a database of Goiás enterprises, followed by the characterization of the enterprises by the research group and analysis of the limits of the differences between the results of the research group; with the proposal of a model to minimize the "fragility" of the method developed. Subsequently, a decision tree model is defined to identify the losses due to making-do, which is tested with separate data to test and compare the results. The results obtained include a model based on Orange Data Mining and a decision tree, which contributes to automating data classification and simplifying the identification of making-do wastes.References
PIKAS, E.; SACKS, R.; PRIVEN, V. (2012). Go or No-Go Decisions at the Construction Workface: Uncertainty, Perceptions of Readiness, Making Ready and Making-do. 20th Annual Conference of the International Group for Lean Construction. San Diego, USA, 18-20 Jul 2012.
FIREMAN, M. C. T.; FORMOSO, C. T. Integrating production and quality control: monitoring making-do and unfinished work. Annual Conference of the International Group for Lean Construction, 21th, Fortaleza, 2013. Proceedings… Fortaleza, 2013.
LEÃO, C.F.; FORMOSO, C.T.; ISATTO, E. L. Integrating Production and Quality Control with the Support of Information Technology. Annual Conference of The International Group for Lean Construction, 22, IGLC, Oslo, 2014.
LEÃO, C. F.; ISATTO, E. L.; FORMOSO, C. T. Proposta de modelo para controle integrado da produção e da qualidade com apoio da computação móvel. Ambiente Construído, Porto Alegre, v. 16, n. 4, p. 109-124. 2016.
AMARAL, T. G.; BRAGA, P. B.; BARROS NETO, J. Application of Dynamic Spreadsheets in the Analysis of Waste by Making-do. Annual Conference of the International Group for Lean Construction, 28th, Berkeley, IGLC, Berkeley, 2020.
FLACH, P. Machine learning: The art and science of algorithms that make sense of data. Cambridge University Press, 2012.
ZHANG, C.; LIU, C.; ZHANG, X.; ALMPANIDIS, G. An up-to-date comparison of state-of-the-art classification algorithms. Expert Systems with Applications, v. 82, p. 128–150, 2017.
LOYOLA-GONZALEZ, Octavio. Black-Box vs. White-Box: Understanding Their Advantages and Weaknesses From a Practical Point of View. IEEE Access, v. 7, p. 154096–154113, 2019.
KOSKELA, L. Making-do – The Eighth Category of Waste. Annual Conference of the International Group for Lean Construction, 12, 2004, Dinamarca, 2004.
RONEN, B. The Complete Kit Concept. International Journal of Production, v. 30, n. 10, p. 2457–2466, 1992.
SOMMER, L. Contribuições Para Um Método de Identificação de Perdas Por improvisação em Canteiros de Obras. Porto Alegre, 2010. 150 f. Dissertação (Mestrado em Engenharia Civil) – Programa de Pós-Graduação em Engenharia Civil, Universidade Federal do Rio Grande do Sul, Porto Alegre, 2010.
SANTOS, P. R. R.; SANTOS, D. DE G. Investigação de perdas devido ao trabalho inacabado e o seu impacto no tempo de ciclo dos processos construtivos. Ambiente Construído, Porto Alegre, v. 17, n. 2, p. 39-52, abr./jun. 2017.
SANTOS, D. G. Modelo de gestão de processos na construção civil para identificação de atividades facilitadoras. Doutora Dissertação. Pós-Graduação no Programa de Engenharia de Produção, Universidade Federal de Santa Catarina, 2004.
KOSKELA, L. An exploration towards a production theory and its application to construction. Thesis (Ph.D) - Technical Research Centre of Finland, Espoo, 2000.
FORMOSO, C. T.; SOMMER, L.; KOSKELA, L.; ISATTO, E. L. The identification and analysis of making-do waste: insights from two Brazilian construction sites. Ambiente Construído, v. 17, n. 3, p. 183-197, jul. /set. 2017.
SANTOS, E. M.; FONTENELE, A. D.; MACHADO, M. L.; BARROS NETO, J. P.; AMARAL, T. G. Analysis of Making-do Waste at Site in Fortaleza, Ceará, Brazil. Annual Conference of the International Group for Lean Construction, 28th, Berkeley, IGLC, Berkeley, 2020.
ZHANG, C.; LIU, C.; ZHANG, X.; ALMPANIDIS, G. An up-to-date comparison of state-of-the-art classification algorithms. Expert Systems with Applications, v. 82, p. 128–150, 2017.
BERTRAND J. W. M.; FRASOO J.C. Modelling and simulation. Operations managemant research methodologies using quantitative modeling. International Journal of Operartions& Production Management. Vol. 22, No 22, 2002. P. 241-264.
LANE, H.; HOWARD, C.; HAPKE, H. M. Natural Language Processing in Action: Understanding, analyzing and Generation text with Python. Manning, Shelter, NY, 2019.
