Expert systems equipment selection

Lahdenpera, E., Korhonen, E., and Nystrom, L. (1989) An expert system for selection of solid/liquid separation equipment. Chemical Engineering, 13,... 

It is clear that there has previously been no accepted standard approach to solid/liquid equipment selection. With the now widespread availability of personal computers, however, the development of computer software is an ideal way to solve the problem of equipment selection. While rule-based expert systems appeared to provide the optimum solution at first, it became apparent to some researchers that inherent restrictions would prevent their widespread application. Thus, interactive personal computer software, partly based on an expert system approach, was developed to corrrmercial standards (i.e. p -SELECT, Tarleton and Wakeman, 1991 see also Wakeman and Tarletorr, 1991a) and further adapted for incorporation within FDS (Filter Design Software, 2005). The philosophies, charts, tables and knowledge used are described in the remainder of this section. 

Korhonen E., LahdenperU E. and Nystrom L., 1989. Selection of equipment for solid-liquid separation by expert systems, Proc. Filtech Conference, pp. 436-443, The Filtration Society, Karlsruhe. 

Expert systems in solid-liquid separation have now gone out of fashion somewhat and the pre-selection of equipment now tends to be built into much larger design software. In any case, computerized advice, although helpful to complete beginners as a first approach, is no substitute for experience and in-depth knowledge of the subject. 

Equipment selection in solid-liquid separation, a simple expert system , Catalogue of In-Company Short Courses, Books and Particle Technology Software, Fine Particle Software, The Lares, Maple Avenue, Gooden, Bexhill-on-Sea, TN39 4ST (2000), also on website http / /memhers.aol.com/lsvarovsky/... 

Nystrom, L. and Oja, M., Expert systems for method and equipment selection . Centre for Separation Technology, University of Lappenranta, research topics on wehsite http / /www.lut.fi/research fields.htm tesu, email Lars.Nystrom lut.fi... 

The reliability of data communication elements is an important constituent part on the quality of transferred information (IQ). It may be stated that IQ consists of accessibility, actual value, completeness, credibility, flexibility, form, meaning over time, relevance, reliability, selectivity, validity (Olaisen 1990, MITIQ). All the above components of IQ tend to be encumbered by some uncertainty. Whether associated with measurement or caused by the unreliability of equipment or software. Hence, the proposal to determine IQ using uncertainty modelling. There are several major methods of uncertainty modelling. The best known are Bayes networks based on conditional probability, the theory mathematical evidence based on the Dempster-Shafer theory, the method making use of the Certainty Factor (Clf) created by Buchanan, Shortliffe for the MYCIN expert system, the theory of fuzzy sets or the theory of rough sets. 

The variety of expert systems in the field of equipment selection is very large. Examples are pumps, compressors, control equipment, column internals, reactors, valves, absorbers and extractors. The structure of these selection systems is often very similar. The knowledge base contains a set of objects (similar to an equipment list). For each of these equipment items a list of criteria is available which allows the user to decide whether the object can be used or not. Moreover, a ranking list can be derived from a set of evaluation criteria. 

---