Knowledge-based tools for batch processing systems

Hofmeister, Marius; Halasz, L.; Rippin, D.W.T.

doi:10.1016/0098-1354(89)87031-0

Cited by 14 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, knowledge-based reasoning techniques have been applied to simulation of discrete event processes (21), hazard and operability studies (22), intelligent multivariable process control (23), process operations planning (24), and scheduling of batch processes (25)(26)(27).…”

Section: Knowledge-based Systems In Chemical Engineeringmentioning

confidence: 99%

Expert Systems

Ramesh

2000

Kirk-Othmer Encyclopedia of Chemical Technology

View full text Add to dashboard Cite

Expert systems, or more appropriately knowledge‐based systems, are essentially computer programs that encode the expertise of human problem solvers in some well‐defined domain. A practical offshoot of the field of artificial intelligence, knowledge‐based technology has emerged as an important area of computer applications, with significant business impact on the industry. This is because knowledge‐based systems can automate problem‐solving tasks that hitherto could not be computerized by conventional, numeric modeling techniques. In the domain of chemical engineering, knowledge‐based systems have been used to automate such tasks as equipment and process design, control of complex processes, troubleshooting process operations, scheduling batch processes under uncertain conditions, and simulation of discrete event operations. This article discusses the motivations and benefits of knowledge‐based technology as applied to chemical engineering problems; the differences between knowledge‐based systems and quantitative, numerical techniques; the theoretical underpinnings of the technology; approaches to selecting, designing, and implementing knowledge‐based system applications; and some of the tools available to implement such systems. Alternatives to expert systems such as neural networks (nets) and case‐based reasoning are also briefly discussed. Throughout, the concepts are illustrated using examples from chemical engineering.

show abstract

Section: Knowledge-based Systems In Chemical Engineeringmentioning

confidence: 99%

Expert Systems

Ramesh

2000

Kirk-Othmer Encyclopedia of Chemical Technology

View full text Add to dashboard Cite

show abstract

“…Ku et Karimi [36] estiment que la seule prise en compte détaillée des politiques de stockage pour les intermédiaires reactionnels rend le problème suffisamment complexe pour condamner une approche purement mathématique. De même, Hofmeister et al [32] signalent deux limitations principales à l'utilisation des méthodes à approche optimale:…”

Section: Analyse Bibliographiqueunclassified

Un couplage entre un algorithme génétique et un modèle de simulation pour l'ordonnancement à court terme d'un atelier discontinu de chimie fine

Baudet¹,

Azzaro‐Pantel²,

Pibouleau³

et al. 1999

RAIRO-Oper. Res.

View full text Add to dashboard Cite

Un couplage entre un algorithme génétique et un modèle de simulation pour l'ordonnancement à court terme d'un atelier discontinu de chimie fine RAIRO. Recherche opérationnelle, tome 33, n o 3 (1999), p. 299-338 © AFCET, 1999, tous droits réservés. L'accès aux archives de la revue « RAIRO. Recherche opérationnelle » implique l'accord avec les conditions générales d'utilisation (http://www. numdam.org/conditions). Toute utilisation commerciale ou impression systématique est constitutive d'une infraction pénale. Toute copie ou impression de ce fichier doit contenir la présente mention de copyright. Article numérisé dans le cadre du programme Numérisation de documents anciens mathématiques http://www.numdam.org/

show abstract

“…The use of shortcut methods and a hierarchical approach to design, pioneered by Douglas,5 allows the shaping of a process with less detailed information. Heuristic methods and AI tools, as exemplified by some of the work of Rippin's group,6 also provide a means to work earlier in the design life cycle, although rule‐based design can be criticized as being a way of reproducing existing best practice, rather than supporting innovation. Hybrid methods of various types have also been proposed.…”

Section: Introductionmentioning

confidence: 99%

Generating innovative process designs using limited data

Sharratt

Wall

Borland

2003

J of Chemical Tech & Biotech

View full text Add to dashboard Cite

Key constraints in process innovation are the time and cost spent obtaining data to identify and verify novel processes. Businesses are under increasing pressure to deliver products in shorter times; pressure which restricts and often prevents access to innovative and intensive processing options. The Britest project has identified key decisions in process design and the associated minimum data requirements. These involve identification and manipulation of the relevant rate processes and consideration of the phases of matter that are (or could be) present. By use of qualitative and semiquantitative reasoning it is possible to produce a range of possible process options very early in design. This is particularly useful in the low-tonnage chemicals sectors (fine and effect chemicals) where process design is primarily an empirical activity. It also helps to deal rationally with the complex chemistry prevalent in those industries. The early identification of options allows timely development of experimental programmes to evaluate the options. An illustrative example based on a diazotisation and the associated decomposition reaction is presented.

show abstract

Knowledge-based tools for batch processing systems

Cited by 14 publications

References 5 publications

Expert Systems

Expert Systems

Un couplage entre un algorithme génétique et un modèle de simulation pour l'ordonnancement à court terme d'un atelier discontinu de chimie fine

Generating innovative process designs using limited data

Contact Info

Product

Resources

About