EXPERT SYSTEM FOR TUNNEL IN ROCK

Abstract

Since World War II, computer scientists have tried to develop techniques that would allow computers to act more like human beings. A collection of Artificial Intelligence (AI) techniques that enables computers to assist engineers in analysing problems and making decisions, called knowledge based expert system has recently proved its worth and today numerous, commmercial applications are underway. An expert system is an AI software incorporating a knowledge base and an inferencing system. The expert system attempts to duplicate the functions of an expert in some field of expertise. The program acts as an intelligent consultant or advisor in the domain of interest, capturing the knowledge of one or more experts. Non-experts can interact with the expert system to answer the questions and make decisions in the particular domain. The purpose of expert system is not to replace the experts, but to make their knowledge and experience, more widely available. For many real world problems, an algorithm can not be formulated and and expert system provides the best solution for such problems. This dissertation addresses the problem of design, development and implementation of a production type expert system for analysis and design of tunnels and their supporting systems. This system is developed using an expert system development shell namely, EXSYS and runs on personal computers. There are about 150 rules in the knowledge base. Besides these rules, there are 10 external programs in FORTRAN and PLOTS8 that are called by the main knowledge base as and when required. This expert system suggests different types of tunnel supporting systems under varying field conditions. It must be realised that the expert system can only mimic the human intelligence in a limited way and hence can never replace the human experts. Also the development of an expert system is extremely tedious as compared to conventional software.