This project developed and tested a prototype system for the life-cycle modelling of buildings. The research team developed a prototype system and the report documents how and what data mining techniques can be applied, the results of their application and the benefits gained from the system. The report presents the prototype system and documents how and what data mining techniques can be applied to building maintenance data, its results and the benefits of applying such techniques.
The application of the prototype system on building models and their maintenance data (supplied by Construction Innovation industry partners) uses various data mining algorithms and the maintenance data is analysed using interactive visual tools. The application of the prototype system to help in improving maintenance management and building life cycle includes:
- data preparation and cleaning
- integrating meaningful domain attributes
- performing extensive data mining experiments in which visual analysis, classification and clustering techniques, associative rule mining algorithm such as Apriori were implemented
- filtering and refining data mining results, including the potential implications of these results for improving maintenance management.
A case study of the The Royal Prince Alfred Hospital, Building No.10 is provided to demonstrate data-mining techniques and test the prototype system.
The project also develops and assesses the integration of data mining with a number of technologies, including agent-based technology, database management systems, object-based CAD systems and 3D virtual environments. The report includes discussion and recommendations of the overall performance and capacity of maintenance data requirements, CAD requirements, the database engine, data-mining algorithms and virtual environments.