Expert System for Automobile Industry

Abstract

During the last century, civilization has undergone a knowledge explosion, and it has become impractical if not impossible for an individual to gain ever emerging are of human endeavor. We are a species of specialists. Similarly, intelligence computer system must also specialize. Instead of trying to design a computer system capable of expertise in several fields, the focus must be on a single, carefully chosen, clearly defined subject. Books and manuals have tremendous amount of knowledge but a human being has to read and interpret the knowledge for it to be used. Thus to exploit the available wisdom, knowledge based systems have been devised. Knowledge-based system collect the small fragments of human know-how into a knowledge base which is used to reason through a specific problem area, with the help of a computer, using the knowledge that is appropriate for that problem domain.The objective of the thesis " Expert System for Automobile Industry" is to develop an expert system for Automobile Problem Diagnostics and Maintenance. The objective of the expert system is to identify the problem in an automobile from the information provided by the user and the information stored in the knowledge based of the system. Finding and diagnosing problems in Automobiles is not an easy task. Everyday new models are being released in the market. It is difficult to keep track of each and every model and the problems occurring in each of them for a human being even if he is an expert in the field. In the domain of Automobiles, the problems, to a great extent, are very much common but genuine experts in the field of automobiles are not so common, or not so easily accessible. Thus use of a computer system to diagnose and suggest solutions is the need of the hour.Expert systems are the end products of knowledge engineers. To build an expert system a knowledge engineer starts by reading domain-related literature to become familiar with the issues and the terminology, with that as a foundation, the knowledge engineer then holds interviews with one or more domain experts to "acquire" their knowledge. Human knowledge is immense and it is impossible, with the computing resources available with us today, to capture all the available knowledge. The expert system developed in the thesis captures the small fragments of human know-how about "automobile related problems and their solutions" into a knowledge base that is used to reason through a problem, with the help of a computer. Conventional programming languages, such as FORTRAN and C/C++, are designed and optimized for the procedural manipulation of data (such as numbers and arrays). Humans, however, often solve complex problems using very abstract, symbolic approaches which are not well suited for implementation in conventional languages.Prolong uses heuristics to solve problems. It allows representing knowledge in an abstract from, which is closer to the human thinking procedure. The expert system has been developed using Prolog. The knowledge base of the expert system consists of rules of thumb that are used to assert the authenticity of a problem. In this thesis, as a knowledge engineer, the knowledge from the domain of "Automobiles" has been organized in the expert system's knowledge base. The knowledge gathered from the experts and literature related to automobiles has been translated into software that a computer can use to solve problems. The knowledge of the automobile experts has been abstracted into an objective from for the database of the expert system, which is used to diagnose and resolve problems related to the automobiles. And this knowledge base can be extended to include new problem domains. The expert system is quite easy to use, the interface is menu driven and uncomplicated. The user responds to lucid questions, in YES or NO only, as queried by the system. The answers to these questions help the expert system to locate the solution to the problem encountered by the user of the expert system. Those people, who have to deal with an automobile everyday, or frequently, like a mechanic, automobile owner, engineers, service personnel, workshops etc can find extensive use of this system.