{"title":"An integrated framework for intelligent computer aided design of chemical processes","authors":"M. S. Gandikota, N. Narayanan, J. Maroldt","doi":"10.1145/98894.98933","DOIUrl":null,"url":null,"abstract":"In this paper we develop an integrated framework for intelligent computer aided design of chemical processes. First we propose a task-structure for design. The task-structure for a problem solving activity characterizes it in terms of various information processing tasks which underlie that activity and methods that can accomplish those tasks (Chandrasekaran, 1989a). The task-structure for process design is a hierarchy consisting of ten tasks and subtasks, and reasoning methods to accomplish them. The framework for process design is based on this task-structure and it integrates the various tasks delineated in the task-structure by specifying the control flow among them. By making the structure of knowledge and inference required for process design explicit, this framework facilitates the design and development of automated process design systems. We also propose an information structure called a Design History to record all design choices made during a design episode and their justifications. The generation of the Design History within the framework and its utility are described. The design of a process for ethanol production is used as an example to illustrate the framework's applicability.","PeriodicalId":175812,"journal":{"name":"Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2","volume":"228 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1990-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/98894.98933","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In this paper we develop an integrated framework for intelligent computer aided design of chemical processes. First we propose a task-structure for design. The task-structure for a problem solving activity characterizes it in terms of various information processing tasks which underlie that activity and methods that can accomplish those tasks (Chandrasekaran, 1989a). The task-structure for process design is a hierarchy consisting of ten tasks and subtasks, and reasoning methods to accomplish them. The framework for process design is based on this task-structure and it integrates the various tasks delineated in the task-structure by specifying the control flow among them. By making the structure of knowledge and inference required for process design explicit, this framework facilitates the design and development of automated process design systems. We also propose an information structure called a Design History to record all design choices made during a design episode and their justifications. The generation of the Design History within the framework and its utility are described. The design of a process for ethanol production is used as an example to illustrate the framework's applicability.