About the research
The estimation of design efforts and costs plays a vital role in authorizing funds and controlling the budget during the project development process. Typically, the design phase consists of various engineering activities that require substantial efforts to deliver the final construction documents for bid preparation. Estimating these efforts accurately and efficiently is critical for transportation agencies in properly allocating funds, time, and resources.
Previous studies have reported several problems associated with the estimation of design efforts, such as lack of predictive tools, inaccurate forecasts, and misallocation of efforts. Therefore, there is a need for a proactive scheme to more accurately and reliably estimate design efforts and costs in order to help the design office negotiate more confidently with consulting firms and, ultimately, to enhance the accountability and transparency of funding decisions.
In this Phase I study, a master database was first developed that included various attributes of historical pretensioned, prestressed concrete beam (PPCB) bridge design projects completed by consultants. The master database was used to develop PPCB design effort and cost estimation models using multivariate linear regression and artificial neural networks. The prediction models were then tested to evaluate their predictive power by using the mean average percentage error.
A case-based reasoning tool was developed to make logical inferences when estimating the design efforts and costs of a new PPCB project. The case-based reasoning approach uses the concept of similarity scores to retrieve the records of the most similar historical bridge design projects. Additionally, a spreadsheet tool was developed to automate the retrieval process. In addition to using the regression models and neural network models developed in this study, users can make reasonable judgements about the required efforts and costs of a new PPCB bridge design project by reviewing historically similar projects.