A review of expert systems for chromatography

C.H. Bryant, A. Adam, D.R. Tayior, R.C. Rowe
1994 Analytica Chimica Acta  
Expert systems for chromatography are reviewed. A taxonomy is proposed that allows present (and future) expert systems in this area to be classi ed and facilitates an understanding of their inter-relationship. All the systems are described focusing on the reasons for their development, what their purpose was and how they were to be used. The engineering methods, knowledge representations, tools and architectures used for the systems are compared and contrasted in a discussion covering all the
more » ... ages of the development l i f e cycle of expert systems. The review reveals that too often developers of expert systems for chromatography do not justify their decisions on engineering matters and that the literature suggests that many ideas advocated by k n o wledge engineers are not being used. 1 Sections 7, 8, and 9 are arranged in a taxonomic fashion corresponding the taxonomy and explain why each system was developed, what its purpose was and how i t was to be used. Sections 11, 12, 13, and 14 discuss the engineering methods, knowledge representations, tools and architectures used in the development of expert systems for chromatography. Previous Reviews Many papers have been published that review arti cial intelligence for chemistry but their scope is so wide as to prohibit the inclusion of a review of expert systems for chromatography as detailed as that given here. For an example see 1]. In addition to arti cial intelligence for chemistry, the more speci c topic of expert systems for analytical chemistry has been reviewed in a number of papers. 2] prov i d e s a n i n troduction to knowledge representation and explanation facilities for expert systems for analytical chemistry but only gives four references for expert systems for chromatography. 3] also discusses topics such a s k n o wledge representation but it does not mention any expert systems for chromatography. 4] compares the use of arti cial intelligence languages and expert system shells for building expert systems for limited domains but only reviews one expert system for chromatography. Three papers 5] 6] 7] h a ve been published that speci cally review expert systems for chromatography. 5] reviews expert systems for liquid chromatography v ery brie y. It lacks the authoritative tone that usually accompanies an academic paper: the style of writing is imprecise, some of the analogies used are weak and only two references are given. 6] does not give a n y references and only reviews four systems of which only one is an expert system, the other three being simulation programs. 7] mentions more than sixty 1 computer systems but only about a quarter of these are expert systems for chromatography. This paper reviews all the expert systems for chromatography that 7] reviews and a further eleven expert systems for chromatography that 7] does not mention. 7] does not make t h e relationship between di erent expert systems for chromatography clear this paper proposes a taxonomy which facilitates an understanding of their inter-relationship. 7] has a useful explanation of how expert systems in general are structured and introduces some aspects of knowledge engineering. However its analysis of how expert systems for chromatography have been engineered is super cial and, in contrast to this paper, no conclusions are drawn on this engineering. This paper reviews expert systems for chromatography comprehensively, covering more than twenty-ve systems and gives over eighty references. 1 This number does not include subsystems of expert systems for chromatography. 2 This section discusses all the expert systems for chromatography t h a t w ere not speci cally designed for a particular method or a particular class of chemical compounds. 7 10 12
doi:10.1016/0003-2670(94)00209-6 fatcat:ezlq6r7r2jbctjrz3kj2xkk6gy