Case Based Reasoning for Chemical Engineering Design

Abstract With current industrial environment (competition, lower profit margin, reduced time to market, decreased product life cycle, environmental constraints, sustainable development, reactivity, innovation…), we must decrease the time for design of new products or processes. While the design activity is marked out by several steps, this article proposed a decision support tool for the preliminary design. This tool is based on the case-based reasoning (CBR) method. This method has demonstrated its effectiveness in other domains (medical, architecture…) and more recently in chemical engineering. This method, coming from Artificial Intelligence, is based on the reusing of earlier experiences to solve new problems. The goal of this article is to show the utility of such a method for unit operation (for example) pre-design but also to propose several evolutions for CBR through a domain as complex as the chemical engineering is (because of its interactions, non-linearity, intensification problems…). During the pre-design step, some parameters like operating conditions are not precisely known but we have an interval of possible values, worse we only have a partial description of the problem. To take into account this imprecision in the problem description, the CBR method is coupled with the fuzzy sets theory. After a mere presentation of the CBR method, a practical implementation is described with the choice and the pre-design of packing for separation columns.

[1]  Bertrand Braunschweig,et al.  Case-base retrieval in process engineering: Supporting design by reusing flowsheets , 1996 .

[2]  Andrzej Kraslawski,et al.  Case-based reasoning system for mixing equipment selection , 1995 .

[3]  J. R. Quinlan.  Discovering rules by induction from large collections of examples Intro-ductory readings in expert s , 1979 .

[4]  Guillermo Cortes Robles,et al.  Management de l'innovation technologique et des connaissances : synergie entre la théorie TRIZ et le raisonnement à partir de cas : application en génie des procédés et systèmes industriels , 2006 .

[5]  Agnar Aamodt,et al.  Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches , 1994, AI Commun..

[6]  Markku Hurme,et al.  Synthesis of separation processes by using case-based reasoning , 2001 .

[7]  Andrzej Kraslawski,et al.  Selection of internals for reactive distillation column - case-based reasoning approach , 2004, Comput. Chem. Eng..

[8]  C SchankRoger,et al.  Dynamic Memory: A Theory of Reminding and Learning in Computers and People , 1983 .

[9]  Ž. Olujić,et al.  Three-component distillation using structured packings : Performance evaluation and model validation , 2006 .

[10]  René Bañares-Alcántara,et al.  Minimising environmental impact using CBR: an azeotropic distillation case study , 1999, Environ. Model. Softw..

[11]  Barry Smyth,et al.  Adaptation-Guided Retrieval: Questioning the Similarity Assumption in Reasoning , 1998, Artif. Intell..

[12]  René Bañares-Alcántara,et al.  Generation of process alternatives using abstract models and case-based reasoning , 2007, Comput. Chem. Eng..