Design and Implementation of an Expert Management System for Automobile Fault Detection

Abstract

A system has been developed to communicate with the On-Board Diagnostics system of a car using the Controller Area Network communication protocol. The system requests the stored trouble codes that might have been detected by the diagnostics system and sends them to a server. The information is accessed through a web interface. The web interface allows the user to find the solutions in the database together with the detected faults. The database also contains information about trouble codes, such as their symptoms, causes and how to fix them. Monitoring the communications while testing the prototype showed that the system works as intended and can communicate with cars from different manufacturers and extract the data. The prototype system was compared with a commercial scan tool and testing showed that they both produced the same results. The second module of the project deals with the design and implementation of an expert system for car faults diagnosis. The project is motivated by the need to guide car owners and learners' motor mechanics in the maintenance and troubleshooting of motor problems without having to resort to presumptions and conjectures. Particularly, it is expected that the proposed design would ensure that car owners have proper assistance in times of crisis and what’s more, will save them from the clutches of exploitative roadside mechanics. For this purpose, a rule-based artificial intelligence (AI) technique was utilized to obtain theoretical and practical expert system parameters, and then a conceptual expert system was designed. The expert system functioning is based on the database of car faults, symptoms and their correction, which make up its knowledge base. The new system was developed using PHP and MySQL database. This language was chosen because of its easy syntax and features for developing web-based applications.