AUTOMATED SCHEDULE ADVISORY SYSTEM Ren-Jye Dzeng and Hsin-Yun Lee Department of Civil Engineering National Chiao-Tung University, Taiwan Planning and scheduling is one of the key factors to the success of a construction project. Because of the increasing complexity and size of construction projects nowadays, pre- construction schedules tend to comprise a large number of activities. These schedules often contain unintentional errors and conflicts, and those due to the lack of experience. With the increasing power and decreasing cost, personal computers have become a common tool used by construction professionals to facilitate their daily decisions. This research applies case-based reasoning and rule-based reasoning techniques, and develops a computer system called ScheduleCoach, which can analyze a computerized schedule and provide corrective advises. Keywords: Planning, Scheduling, Case-Based Reasoning, Expert System, Critique. 1. INTRODUCTION Planning and scheduling is one of the key factors to the success of a construction project. Because of the increasing complexity and size of construction projects nowadays, pre-construction schedules tend to comprise a large number of activities and much related information. These schedules often contain unintentional errors and conflicts, and those due to the lack of experience. These mistakes need to be corrected, and often they can be corrected easily by an experience scheduler. However, due to the number of activities involved, sometimes these mistakes are hard to be found. With the increasing power and decreasing cost, personal computers have become a common tool used by construction experts to facilitate their daily decisions such as scheduling, cost estimation, and cash flow analysis. This research applies artificial intelligence techniques (i.e., case-based reasoning and rule-based reasoning) and develops a computer system called ScheduleCoach, which can analyze a computerized schedule and provide corrective advises. The current knowledge base of the system focuses on high-rise building construction. 2. LITERATURE REVIEW Various research subjects related to planning and scheduling can be found in the construction related literature and texts. These include activity coding, activity sequential relationship, schedule representation, resource leveling, etc. As more artificial intelligence techniques are being developed, many automatic construction planner have also been developed. These planners define activities and their sequential relationships; some also estimate activity duration. The examples include BUILDER, Construction Planex, GHOST, Know-Plan, OARPLAN, SIPEC, ATOP, ConsPlans, CASCH, TCIS, HISCHED, and CasePlan. Except for CasePlan, the planners apply the rule-based reasoning, and create an activity network for a given project described using a predefined set of component hierarchy. The planners do not have the learning ability; i.e. given the same project, the output network are the same over the time. CasePlan focuses on the learning ability of a planner as the case in human planners, and recognizes that part of planning work cannot be predetermined by a set of rules, and is dependent on the planner’s experience and preference. De la Garza and William Ibbs (De La Garza and Ibbs 1990) developed a schedule critique system, called CRITEX, which applies the rule-based reasoning, and evaluates construction schedules of high-rise buildings based on a set of critique rules obtained through interviews with several human schedulers. The output of CRITEX is a set of critique statement. However, the report does not include the suggestions regarding how the schedules should be revised. Our research extends the critique knowledge with a different knowledge representation. The output 145_.doc- 1 -