Yuri Avramenko

Similarity concept for case-based design in process engineering

The design process requires significant engineering experience, intuition and creativeness. To facilitate the preliminary design, the authors have proposed approach based on the re-use of design experience. The design problems in chemical engineering are often quite difficult to represent as a well-structured list of features of one-type data. Many problems in chemical engineering are very large and complex, the problem description is often incomplete and uncertain, and sometimes it changes dynamically. In order to cope with design cases that have different structure representation the general similarity concept has been developed. The paper surveys the existing mathematical methods for similarity measurements and extends them to cope with different data formats. The main idea of this paper is an integration of representation and retrieval of the cases into one step. The proposed concept is illustrated by the examples of the model selection for synthesis of distillation systems and formulation of a fats and oils product.

Case Based Design

The book by Professors Avramenko and Kraslawski is unique in several important ways. First, it is an impressive and in-depth treatment of the essence of the casebased reasoning strategy and case-based design dwelling upon the algorithmic facet of the paradigm. Second, the authors provided an excellent applied research framework by showing how this development can be effectively utilized in real word complicated environment of process engineering- a pursuit that is rarely reported in the literature in such a comprehensive manner as done in this book. In a highly authoritative and systematic manner, the authors guide the reader through the essential features of the CBR machinery.

Selection of internals for reactive distillation column¿case-based reasoning approach

The design of reactive distillation (RD) systems is considerably more complex than design of the individual, conventional reactors and distillation columns. One of the main issues in the design of RD column is a definition of type and specification of geometric features of the internal devices. In this work, there is described a design supporting tool for pre-selection of packing type for RD column. Case-based reasoning has been applied as a basic method for decision support. The computer system for pre-design of reactive column internals has been built as an implementation of developed methodology. The acid catalysed reaction of 2-methylpropylacetate synthesis was used to test the system. The CBR system can significantly reduce the development time for design of reactive distillation column and suggests a good start points for further design activity.

Selection of Internals for Reactive Distillation Column—Case-based Reasoning Approach

The design of reactive distillation (RD) systems is considerably more complex than design of the individual, conventional reactors and distillation columns. One of the main issues in the design of RD column is a definition of type and specification of geometric features of the internal devices. In this work, there is described a design supporting tool for pre-selection of packing type for RD column. Case-based reasoning has been applied as a basic method for decision support. The computer system for pre-design of reactive column internals has been built as an implementation of developed methodology. The acid catalysed reaction of 2-methylpropylacetate synthesis was used to test the system. The CBR system significantly reduces the development time for design of reactive distillation column and suggests a good start points for further design activity.

Mining of graphics for information and knowledge retrieval

Abstract The oversupply of data, information and knowledge, even after preliminary keywords and topics search, is a well-known problem in R&D activities. One of the approaches aimed at limiting the negative impact of the surplus of information is its automated intelligent preprocessing and reuse. The paper describes a method for identification of the concepts which is based on combination of subject-driven document clustering, shape analysis, trends understanding and relevant context retrieval via semantic analysis. The goal is to extract potentially interesting knowledge from a set of documents based on analysis of graphical information and next to explain the mechanism of the studied process. The proposed method is implemented in the software suite which contains source searching tool, plot comparator and semantic analyzer. The method has been applied to identify the calculation process, using channel geometry characteristics, of the longitudinal dispersion coefficients for one branch of the Somes river in Romania.

Selection of Models for Pollutant Transport in River Reaches Using Case Based Reasoning

Abstract The paper presents a case based reasoning (CBR) tool designed for the identification of crucial information for the modelling of pollutant transport in rivers. The developed CBR tool is using a case base comprising published information. This information regards pollutant transport modelling work carried out for different rivers. The models from the case base are designed for a specific river reach. For an unstudied reach it is possible to find a model for pollutant transport based on the comparison between the characteristics of that river reach with the characteristics of the already studied reaches, stored in the case base. The reaches of Somes River were compared against the reaches in the case base, and information for pollutant transport modelling was identified. The developed tool is also applicable in the case of other rivers were no detailed concentration measurements are available and the mathematical models for pollutant transport are needed.

Case-Based Reasoning Tool for the Support of Process and Product Design

Abstract The reuse of tested and optimized design is an important aspect for decreasing design times and increasing design quality. Case-based reasoning is applied to support design process. The case description is composed of information entities which enable to represent diverse design data. To remove the gap between the past design and the current problem the parametric adaptation is considered. The computer tool CM-DS is developed to assist the designer in his activity. The applications of the tool for problems of process and product design in food industry are described.

Decision supporting system for design of wastewater treatment

Abstract The conceptual design of industrial wastewater treatment flowsheets implies the selection and sequencing of technologies in order to obtain a set of feasible treatment options. A design methodology was developed to support engineers in the conceptual design of wastewater treatment facilities and to help them to improve creativeness and effectiveness. The paper describes the method and the computer tool for support of preliminary design of wastewater treatment system by using past design knowledge. The computer tool has been successfully used for preliminary design phase of flowsheet synthesis for treatment of several wastewater streams from electroplating plants.

Selection of process scheme and conditions for drying of pharmaceutical materials

Abstract The work presents the method and tool for reuse of experimental data in the selection of dryer and its operating conditions for drying pharmaceutical materials. The method involves 3 stages: screening, retrieval, and refining. First stage includes screening of materials on the basis of their toxicity and other critical properties for the selection according to the proposed classification. In second stage, the materials with the most similar properties to the material under consideration are found. The process data such as dryer design, operating conditions and process parameters, which is used for drying of corresponding similar materials, are retrieved and provided as a preliminary solution for the drying problem. Third stage can be used in two ways: to refine the obtained solutions based on comparison with the proposed classifications, and to derive new solution based on method of decision trees. The tool, proposed to find the appropriate drying system and its specifications, is developed as script in Microsoft Excel. It consists of the case-based reasoning routine and the rule-based reasoning one based on constructed decision trees. It is implemented as a macrocode and questionnaires. The developed tool has been used to select the drying process requirements for few materials used in pharmaceutical industry. The paper includes example of drying of barium titanate.

Mining of graphics for identification of mechanisms and trends of processes

Abstract The paper describes a method for identification of mechanisms and process trends based on combination of subject-driven document clustering, shape analysis, trends understanding and relevant context retrieval via semantic analysis. The goal is to extract potentially interesting knowledge from a set of technical information based on analysis of graphical information in order to find explanation for a specific process behavior.