Term Project Report for :Professor: Yu Hen HuLee, Min-JaeTABLE OF CONTENTSTable3: Classification rate for each caseTable4: Different Number of Neuron comparisonTable6: Confusion matrix for classificationTable7: Confusion matrix for testing classificationTable8: Comparison between Statistical and ANN methodBack-propagation Multi-Layer PerceptronAn Artificial Neural Network Approach to QuantifyChange Order Impact on Construction ProductivityTerm Project Report for :ECE/CS/ME 539(Fall 2001-Lecture 1)Professor: Yu Hen HuLee, Min-Jae(9014179882)[email protected] of Civil and Environmental EngineeringUniversity of Wisconsin - MadisonTABLE OF CONTENTS1 INTRODUCTION……………………………..…………………………………. 32 BACKGROUND ………………………………………………………………… 33 PREVIOUS RESEARCH AND PROBLEM STATEMENT ...………………. 54 DATA COLLECTION, TREATING, SETUP…………………………….…… 74.1 Data Collection... ………………………………………………….……… 74.2 Data Setup for the Neural Network…. ……………….……………….... 85 NEURAL NETWORK APPROACH... …………………………………….…… 95.1 Neural Network Design……………..……………………………….…… 95.2 Selection of Network Parameters……………..………………………… 105.3 Network Usage (Testing new case studies) ……………..……………… 136 RESULTS AND COMPARISON……. ………………………………...………. 147 CONCLUSION.. ………………………………...……………………….……… 158 DATA INPUT AND OUTPUT FEATURES…………………………………… 159 REFERENCE….……………………………………………………………….... 1721. INTRODUCTIONA fact of life for a construction project is change. Changes result from the necessity to modify aspects of the construction project in reaction to circumstances that develop during the construction process. The changes may be small, well managed, and have little effect on the whole construction project. On the other hand, changes may be large, poorly managed, and have tremendous negative impacts on the construction projectperformance in terms of time and cost.After the contract is awarded, owner only have right to change contract or scope of work. If there were mistakes in original design, owner has to change their original contract documents. When change orders happen, contractor usually has damage in their productivity. For example, when the project was stopped for sometime to change and fix their original design, contractor should pay for labor wage, equipment rental fee, etc. More seriously, if the delayed is continued for a while, contractor can lose next job. These kinds of problem happen frequently in construction business and often end up withcourt dispute (Claims). To solve this kind of problem, we need a reliable decision tool developed from historical data. In this report, author tries to develop a well-trained “Artificial Neural Network” can make decision (was the project impacted by change order or not) by using 140 case study (historical data).2. BACKGROUNDWhat is the change order? Change order can be defined as “any event, whichresults in a modification of the original scope, execution time or cost of work,” (Ibbs andAllen, 1995). Why change orders are occurred? First, due to the unique characteristics of theconstruction, there is no exactly same project. Second, the project should be completedwithin limited resources of time and money and this situation can cause change orders.The third is the contingency factors of construction projects. It’s inevitable and reality of3construction. Construction Industry Institute (CII 2001) reports some of the influencescan cause change orders: “Additions or deletions in project scope; changes in codes,laws, or standards; design optimization; project planning deficiencies; incomplete designdocuments; workers or material availability limitations; unknown site conditions;schedule compression; or unexpected weather problems.” Also, accident or damage couldbe causes of change orders. Because of these reasons, it is inevitable that changes mayarise.What is the problem with change orders? Construction contracts often include achange clause, which authorize the project owner to alter the work performed by thecontractor with appropriate change order process. However, such change orders oftenlead to result in loss of productivity, furthermore disruption of the whole project due toinefficient labor usage or cumulative impact (ripple effect) of the change orders.The idea behind cumulative impact is that the contractor is unable to predict theunforeseen impact of change on other areas of work. The construction industry is basedupon sequential production. Any disruption to a task in the sequence will impact theremaining tasks even if the change order itself does not involve these tasks. This iscommonly referred to as the ripple effect of changes.Even though there has been some study about the impact of change order on laborproductivity and change order management, the industry is still struggling with issuessurrounding change order management and the numerous related court cases.A recent report of state projects built in the state of Washington reviewed a totalof 865 projects and found that 87% (752) of the projects were completed with acombined total of 6,413 change orders of various sizes with an estimated value of $94million. The report stated that one-third of the total number of change orders, or $35.4million, could have been avoided. Inadequate field investigation, unclear specifications,plan error, and design change or mistakes by the consulting engineer were cited as causesfor these changes (Cambridge Systematics, Inc. 1998).By clearly understanding the cause of productivity loss by change order and therelationship between the factors that can influence on productivity loss, stakeholders canmanage the project change orders better and further, can avoid the loss of productivity.43. PREVIOUS RESEARCH AND PROBLEM STATEMENTFew studies have attempted to quantify the impact of change orders on projectcost and schedule as well as labor productivity.Leonard et al. (1991) provided a significant effort to quantify the effect of
View Full Document
Unlocking...