Modeling of and Reasoning about Construction Specificationsfor Automated Defect Detection

PROBLEM DESCRIPTION:

As several different studies have pointed out, the construction industry faces the problem of errors occurring frequently on construction sites. Deviations and defects on construction sites need to be identified early on to improve the quality and to minimize future rework costs. The main reasons for construction errors, e.g. human error and changing environmental conditions, are uncontrollable. Therefore, improving the inspection process and the assessment of as-built conditions is critical to prevent the propagation of defects, reduce costs and time for rework and prevent defects from occurring. Current inspection approaches are error-prone since they rely on inspectors' experiences. As studies have shown, different inspectors inspecting the same construction site can assess the project differently, sometimes overlooking critical issues. Main reasons for this are the different experiences of the inspectors and the large amount of project information, e.g. project related construction specifications, that they need to consider during inspection. There is a need for a formalized inspection system that will enable inspecting construction sites more thoroughly and reasoning about construction specifications more systematically. This includes helping to collect information, to manage the collection process, to reason about the collected information with respect to the construction specifications, and to identify deviations and construction defects.

With new reality capture technologies available, like laser-scanners and embedded sensors, new possibilities for collecting large amounts of construction site information are evolving. Laser scanners can be used to collect 3D information of the construction environment and embedded sensors can help in collecting and monitoring material information. However, the evaluation of the data collected using these devices is still a critical task and is currently being done manually. This has three major limitations: (1) Inspectors still focus on only a small sample set of the as-built data available at a given time, which can result in overlooking some errors; (2) It still relies on inspectors' knowledge about specifications and on their previous experiences; (3) The manual evaluation of the data is time consuming.

To get the most out of the collected information, there is a need for an automated defect-detection system that is capable of reasoning about specifications, the designed and the collected as-built information. This automated defect-detection system should be able to model and reason about all relevant project related design, schedule, construction specification and as-built information to identify possible deviations in the as-built environment. The system, finally, should be able to provide the inspectors with the necessary information on the construction defects that are identified automatically.

This research aims to improve the process of identifying construction defects. The specific objectives of this research include: (1) Developing general and computer-interpretable representations of construction specifications to enable automated reasoning; (2) Developing related reasoning mechanisms to identify deviations, assess the deviations identified, and if necessary classify them as construction defects; (3) Formalizing the scheduling of inspection tasks based on the construction specifications modeled and project-specific design and schedule information.

OVERVIEW OF THE APPROACH:

Identification of deviations, defects ,and upcoming inspections

Click image for the enlarged diagram

Due to the broad range of construction specifications and defects appearing on nowadays construction sites, it was decided to focus this research on the modeling of specifications for cast-in-place concrete construction in commercial construction projects and the automated reasoning about these specifications from the perspective of a general contractor's construction inspector.

A taxonomy of construction specifications will be created based on the intent of the specifications, e.g. whether they specify tolerances on as-built conditions, whether they suggest certain types of inspections at certain points in time, etc. Based on this taxonomy the research will focus on developing a representation schema to model the construction specifications related to tolerances and scheduling of inspections. The approach envisioned for this research will be built on the context-oriented specification modeling approach developed for modeling design specifications which has been developed by H. Kiliccote at Carnegie Mellon University. Furthermore, a modified version of the Industry Foundation Classes-framework will be used for representing design, schedule and as-built data of a construction project within one integrated product and process model. Model-based reasoning combined with heuristic classification and geometric reasoning will help in identifying deviations between the as-built and design model and in categorizing those as being a deviation or a defect based on whether they violate a relevant construction specification.

For describing the defects found, an ontology will be developed that will guide the automated defect detection system in gathering all the necessary data about the identified defects. The defect ontology is envisioned to be derived from defect descriptions acquired from other construction projects and case-studies. Also other previous work done in the area of defect-ontology development will be considered.

Finally, this research will investigate how different views on defects can be generated. To provide useful output to a user, the system needs to know the user's affiliation. For example, an architect will be interested in different/more information about defects and deviations than an owner. To understand the different views necessary, interviews with different stakeholders of the construction industry, like inspectors, architects, engineers and owners are planned.

Case studies performed within the ASDMCon-research group will be the basis for developing test-cases for this research and for the evaluation of this research.

RESULTS TO DATE:

Successfully represented and reasoned about specifications targeting alignment behavior of cast-in-place concrete columns.

RELATED PUBLICATIONS AND PRESENTATIONS:

Boukamp, F. and Akinci, B. (2004) "Towards Automated Defect Detection: Object-oriented Modeling of Construction Specifications." Xth International Conference on Computing in Civil and Building Engineering(ICCCBE-X), June02-04, 2004, Weimar, Germany.

Gordon, C., Boukamp, F., Huber, D., Latimer, E., Park, K., Akinci, B. (2003) "Combining Reality Capture Technologies for Construction Defect Detection: A Case Study."9th EuropIA International Conference(EIA9): E-Activities and Intelligent Support in Design and the Built Environment, pg. 99-108, Istanbul, Turkey.

Akinci, B. and Boukamp, F. (2002). "Representation and Integration of As-Built Information to IFC Based Product and Process Models for Automated Assessment of As-Built Conditions." Nineteenth International Symposium on Automation and Robotics in Construction (ISARC 2002), September 23-25, 2002, Washington, DC, USA.