ABSTRACT
This work presents an intelligent system for fault diagnosis for automobiles. The main goal of this work is to use the vast knowledge previously acquired from human experts by system experts, to visualize, localize and fix a fault in a car. The project is motivated by the need to guide car owners and motor mechanics in the maintenance and troubleshooting of motor problems without having to resort to assumptions. A rule-based artificial intelligence (AI) technique was used to establish theoretical and practical expert system parameters, and then a conceptual expert system was designed. The expert system purpose is based on the database of car faults, symptoms and their correction, which make up its knowledge base. The new system was developed using web technologies such as HTML, CSS, Java script, PHP and MYSQL. The methodology adopted here is an improvement from the previous methodologies since this expert system will be an integration of these technologies. The methodology used by the researcher were web based technologies which includes client side scripting programming languages such as HTML, CSS and JAVA script and server side scripting languages such as PHP and MYSQL. The client side scripting languages function in data presentation and the server side scripting languages function in back end processing. PHP is an acronym for hypertext pre-processors, an efficient web based programming language through which data can be retrieved from the database using PHP/MYSQL functions. The research of this work would go into reviewing the literature of underlying concepts behind the development of several applications of expert systems. This phase is quite important as we got to know on how well expert system performs in their ability of assisting and replacing the human expert as well as the user, the result of researchers and reviews that have been conducted help much in giving the idea and insight to the development on the existing application of expert system to be implemented in this system. Before the designed system can be fully implemented, there must be a top-down testing of the modules to ensure that each phase of the design is error-free. When this is ascertained, it is important that there is an instruction for the end-user to ensure that the package is used with smooth operation.
In conclusion, the proposed system can help inexperienced mechanics and motorists in diagnosing the fault on the car. In addition, the system has benefits such as enabling mechanics complete tasks quickly, reducing the need for skilled mechanics (repairing a car requires a high level of expertise but with this system, inexperienced mechanics or individuals can be guided to find the fault of the car), capture the knowledge of company experts who someday will retire, resign or die and train new employees to solve problems the way experienced professionals do.