Problem solving expert systems

The appearance of expert systems to solve practical problems, also in chemistry, started in the eighties. During this period much experience has been acquired through the expected and unexpected problems that arose during such projects. Until now there are only a few commercially available expert systems and this is not likely to change in the near future. This implies that expert systems will be mostly in-house developments. The different steps to consider are ... 

The next few steps are very similar to those required in any software project. One of the first stages is the clear definition of the knowledge domain. It must be clear which problems the expert system must solve. It is at this stage not the intention to define how this can be done. Clarity and specificity must be the major guides here. Fuzziness at this stage will, more than in classical software projects, have to be paid for later when different interpretations cause misunderstandings. Equally important is the clear definition of the end user(s). An expert system set up as decision support tool for professionals is totally different from an expert system that can be used as a training support for less professional people. 

Fourth, the scope of the application must be bounded. There must be some specification of the functionality of the expert system and characteristics of the problems it is expected to solve. Trying to build an expert system to solve the world s economic problems is not a good application to choose. However, selecting a product mix from an oil refinery based on the current state of supply and demand in the world s energy markets might be a good application. 

Fourth, an expert must be available, and, the problem must be capable of being solved by conventional means. Some systems may incorporate the knowledge of more than one expert, while others reflect the knowledge and strategies of a single individual. It makes no sense to attempt to use an expert system to solve a problem if the answers are unknown. The reason is that it will be impossible to validate the expert system because users will not know if the system is providing correct answers. If no true expert exists, then the problem may be too nebulous and ill-defined to be effectively addressed by an expert system. 

The main thrust of this book is to present examples of how expert systems can solve chemical problems. To make the book more useful to novices in the field of artificial intelligence, we have written a brief introductory chapter explaining expert systems. The glossary at the end of the introduction should be of help to novices and experts alike. We have also included highlights of a panel discussion held at the symposium. The panel was posed the question, Can knowledge bases be made generally available in a useful format Unfortunately, more issues were raised than questions answered. 

Roles for an expert system can be learned by rule induction from a set of examples. This makes this method similar to the use of classifiers - it will solve problems of similar complexity and have similar disadvantages (e.g. possibility of unnoticed misclassifications). 

Definition / An expert system is a computer program that manipulates large amounts of symboHc knowledge using quaUtative techniques, to solve problems that can otherwise be solved only by expert human problem solvers. Expert systems capture the human problem solver s expertise in the form of domain-specific knowledge and domain-independent problem-solving strategies. 

An expert system is a computer program that uses an experts knowledge in a particular domain to solve a narrowly focused, complex problem. An off-line system uses information entered manually and produces results in visual form to guide the user in solving the problem at hand. An on-line system uses information taken direc tly from process measurements to perform tasks automatically or instruct or alert operating personnel to the status of the plant. 

To be successful, the scope of an expert system must be limited to a narrow group of common problems that are readily solved by conventional means, and where the return on investment is greatest. Widening the scope usually requires more complex methods and treats less common problems having lower return. 

Visual inspection techniques are stressed as the most important tools used to study failures. This text is not a substitute for rigorous failure analysis conducted by experts, but it will help the reader identify and eliminate many cooling water system problems. Still, on occasion, the experienced, skilled, failure analyst using sophisticated analytical techniques and specialized equipment may be required to solve complex or unusual problems. Common sense, appropriate experience, and systematic investigation are, however, often superior to the more elaborate, but less effective, techniques used by some. 

An expert system is a knowledge-based system that emulates expert thought to solve significant problems in a particular domain of expertise. [1]... 

An expert system is a computer program that draws upon the knowledge of human experts captured in a knowledge base to solve problems that normally require human expertise. [2],... 

Ramesh, T. S., Shum, S. K., and Davis, J. F., A structured framework for efficient problem solving in diagnostic expert systems, Comput. Chem. Eng. 12, 891 (1988). 

In fact, expert systems are almost the exact opposite of a machine that could solve a problem in some arbitrary area from scratch. They focus on a single specialist topic and know almost nothing outside it. They make up for this blinkered outlook on life by possessing a knowledge of the topic that few humans could match and then complement it with a reasoning ability that mimics that of a human expert, allowing them to make deductions from data supplied by the user, so that their naming as an "expert" system is appropriate. 

An expert system does much more than extract information from a database, format it, and offer it up to the user it analyzes and processes the information to make deductions and generate recommendations. Because an ES may be required to present alternative strategies and give an estimate of the potential value of different courses of action, it must contain a reasoning capacity, which relies on some sort of general problem-solving method. 

---