Expert systems experiments

SOURCE K. Niida, et al.. Some Expert System Experiments in Process Engineering, Chem. Eng, Res. Des, vol. 64, September 1986, p. 374 Generon Systems, 400 W. Sam Houston Parkway South, Houston, Tex., 1993. 

The earliest practical use of an expert system was made in the software named MYCIN for diagnosing a toxic poison from the symptoms of a patient and recommending the antidote (62). This type of activity is generally carried out by a human expert who processes information about a situation (in this case, symptoms of a patient), refers to the expert s experience and expert knowledge, and then recommends action (in this case, the antidote). 

There are some aspects of process design in which decisions are based primarily on past experience rather than on quantitative performance models. Problems of this type include the selection of constraction materials, the selection of appropriate models for evaluating the physical properties of homogeneous and heterogeneous mixtures of components, and the selection of safety systems. Advances in expert systems technology and information management will have a profound impact on expressing the solutions to these problems. 

The first recorded reference to the use of expert systems in pharmaceutical product formulation was in the London Financial Times in the spring of 1989 [3], closely followed by an article in the autumn of the same year [4], Both referred to the work then being undertaken by personnel at ICI Pharmaceuticals, UK (now AstraZeneca) to develop an expert system for formulating pharmaceuticals ab initio. Since that time several companies and academic institutions have reported their experiences. 

As an example, consider the automation efforts for chemical laboratories in the last decades. Chemical laboratories of today are equipped with instruments that, in principle, can run automatically for 24 hours a day. This results in a higher productivity, since more samples can be analysed with an equal technical effort. Decisions about the analysis itself, how many and which samples must be analysed with what method or technique, etc., are still the responsibility of the laboratory personnel. Since experience can be incorporated into expert systems, they can provide significant benefits as decision-supporting tools. Therefore, the main ideas of expert systems and their development are explained in this chapter. More detailed information can be found in the numerous textbooks on expert systems [7-10]. 

Sometimes these heuristics are an extension of the theory and sometimes they are experience-based rules, with no apparent theoretical justification, but they simply work most of the time. One way of explaining human reasoning that has influenced the expert system research is that these heuristic rules of thumb are... 

The typical structure of an expert system is shown in Fig. 43.1. Three basic components are present in all expert systems the knowledge base, the inference engine and the interaction module (user interface). The knowledge base is the heart of the expert system. It contains the necessary expert knowledge and experience to act as a decision support. Only if this is correct and complete enough the expert system can produce meaningful and useful conclusions and advice. The inference... 

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 ... 

In Chapter 43 the incorporation of expertise and experience in data analysis by means of expert systems is described. The knowledge acquisition bottleneck and the brittleness of domain expertise are, however, the major drawbacks in the development of expert systems. This has stimulated research on alternative techniques. Artificial neural networks (ANN) were first developed as a model of the human brain structure. The computerized version turned out to be suitable for performing tasks that are considered to be difficult to solve by classical techniques. 

Two major areas are likely to be the focus of expert systems in the scientific software area assisting users without extensive statistical training in starting to use statistics, and helping design multifactor experiments. 

This is a fairly mundane exchange. You would not need years of experience before you were able to decide for yourself where you should go on a holiday, so there is little commercial potential for an expert system advising overworked biologists on how to spend their summer break. Nevertheless, this simple interaction gives us an early insight into how an expert system appears to the user. The system has provided one half of a conversation, eliciting information from the user through a sequence of focused questions as... 

Interpretation and Design of Chemically Based Experiments with Expert Systems... 

The relevant calculations are commonly handled poorly, because the equilibrium equations involved are difficult to solve manually (but not with computers). The few calculations that are actually reported in the biochemical literature use simplified methods of limited and frequently unknown validity. Large excesses of magnesium ion are frequently used in experiments, perhaps in an attempt to avoid such calculations. The relevant theory is well worked out and there are excellent reviews. The limitation appears to involve diffusion to the (mathematically) inexpert user, which is one of the motivations of building expert systems. 

---