DEVELOPMENT OF AN EXPERT SYSTEM FOR DESIGN AND DISTRESS DIAGNOSES OF FLEXIBLE PAVEMENT

Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia

In the design process of a flexible road pavement, there are various long step calculations and

supported by graphs and monograph readings. The readings must be taken carefully and

patiently to minimize errors. Additionally, the designed pavement needs a good maintenance for

sustainability. Normally, the pavement is maintained at certain intervals either by manually or

mechanically inspections to identify or diagnose the location of distresses or failures. The

important key of a good maintenance is to identify the causes of failures and give accurate

instruction for maintenance works and rehabilitation. In the early stage, knowledge and

experience from several maintenance experts are needed to advise for the pavement maintenance

works and rehabilitation. The experts’ advice may increase the overall maintenance cost

indirectly. The application of computer in design and maintenance of road pavement will help so

that the planning and maintenance process will be faster, easier and reduced the errors. In this

study, the knowledge-based expert system approach was used to design a programmer using shell

expert system of KAPPA PC Version 2.4 that is object oriented and displaying higher graphic

resolutions. The study stressed on the provision of design output and diagnose of pavement

failure based on the accumulation of knowledge from several experts by applying the modular

approach. Normally, the process of pavement layer design and distress diagnose are done by

experts. The process was computerised and apply artificial intelligent that is a new technology in

providing a system that can design and diagnose efficiently. The expert system uses the

AASHTO 1993 design standard to calculate the minimum layers thickness, able to diagnose

pavement surface distress and suggest suitable maintenance technique for the failure occurred.

The expert system was tested using several design calculation samples and failures of road cases.

From the test, the success is 100% for pavement design and 70% for diagnoses on actual cases.

The expert system has revealed satisfactorily findings in a faster layers design, better in failure

diagnoses and suggests a reasonable rehabilitation works.