1 / 5

Quantifying change order impact on productivity by using ANN approach

Quantifying change order impact on productivity by using ANN approach. ECE 539 Project Presentation (Order: 316). Min-Jae Lee Construction Management Program Civil & Environmental Engineering Department University of Wisconsin - Madison . Change. Delta . Base.

hachi
Download Presentation

Quantifying change order impact on productivity by using ANN approach

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Quantifying change order impact on productivity by using ANN approach ECE 539 Project Presentation (Order: 316) Min-Jae Lee Construction Management Program Civil & Environmental Engineering Department University of Wisconsin - Madison

  2. Change Delta  Base Direct Field Labor Hours Estimate Total Actual Labor Hours (Base + Change) (Hanna et al. 1999a, 1999b) 0 100 Construction Phase (% Complete) Research Background • Productivity loss (Delta:  ) happen • “Owner” & “Contractor” conflict ---Claims • We need “Models” developed by historical data Model 1: Was the project impacted by change orders or not Model 2: How much impacted by change orders

  3. Data Characteristics • 140 case study from U.S. area [impacted(50) / unimpacted(50)] • Ask 70 Indicator factors related with change orders • Find “significant factors” by using Statistical method (20 factors, correlation test, significant test)

  4. Model1: Logistic Regression • Model2: Regression Model • % delta = • + 0.36866 • + 0.11957 Percent Change • - 0.08065 PM%TimeOnProject • 0.16723 %OwnerInitiatedCO • 0.09147 Productivity • 0.05213 Overmanning • + 0.022345 ProcessingTime lXactual – Xestimatedl Xestimated Average = =72.2% %Error 75% Accuracy Previous Research & ANN approach Training data size: 100 cases, Testing sample size: 30 cases Model1(Impact): bp Model2(%Delta): RBN Output Output 20 feature factors 20 feature factors Impacted or Not % Delta

  5. Results & Discussion Model1(Impact): bp Logistic Regression C_rate = 71% Training C_rate = 87% Testing C_rate = 82% Model2(%Delta): RBN Regression Model: 73% RBN Model: 14% lXactual – Xestimatedl Xestimated Average %Error =

More Related