Construction Project Cost and Duration Optimization Using Artificial Neural Network

摘要

Performance of neural networks mainly depends on the weights adopted and on the training the data including historic examples, which are used as input variables. The input of the ANN characterizes the different realizations of pumping, with each input indicating the pumping level of a well. The output is capable of characterizing the objectives and constraints of the optimization, such as attainment of regulatory goals, value of cost functions, and time. The supervised learning algorithm of back propagation was used to train the network. Once trained, the ANN begins a search through various realizations of pumping patterns to determine whether or not they will be successful. A case study of a project under JNNURM program being executed by K P C Projects Ltd., has been presented in this paper. Due to the recent severe global recession, company is facing severe problem and all the construction activities slowed down. To increase the productivity of all resources, it is necessary to forecast the costs arriving from resources so that the total cost of project can be reduced. This deals with the construction of 512 Houses in (G+3) pattern, in 32 blocks located at Karmanghat, Hyderabad. It was found from the results that the ANN approach was optimized the total cost of the project by 3.91% when compared with the actual cost of the project and the duration was reduced from 150 days to 142 days, which is around 5% of the duration of the project.