Knowledge engineering framework for automated HAZOP analysis
Abstract
A software system (PHASuite) for automated process hazard and operability analysis (HAZOP) for chemical processes has been developed in this work. An automated HAZOP system is a highly complex system both in terms of conceptual ideas and implementation. It is also highly knowledge intensive. This thesis work is divided into two parts: the knowledge engineering framework and implementation. From the function point of view, the framework consists of four main parts: information sharing, representation, knowledge base and reasoning engine. Ontology based information sharing schemes are developed to share process information and results with other systems. Colored Petri Nets based representation, created from process information, is used for representing chemical processes as well as the methodology for HAZOP analysis. In this framework, a process is decomposed into two abstraction levels, operation level and equipment level, which are bridged using functional representation. Analysis is carried out on both of the levels; i.e. integration of operation-centered analysis and equipment-centered analysis. Knowledge used in this system is divided into operation knowledge and safety knowledge, both of which are stored in models. Models, general model and specific model, which are created based on general models to incorporate the experience system gains from analyzing different processes, form the case base. Case-based techniques are adopted for knowledge management. Knowledge base is stored externally in structured databases. A two-level, two-layer reasoning engine is designed to operate on the Petri Nets representation of the process using the knowledge base to perform HAZOP analysis. Software engineering methodologies have been applied to guide the design and development of PHASuite in order to achieve the goal of efficiency, flexibility and high quality. Layered and repository software architecture have been designed to handle the complex information flow and the multipart knowledge base in the system. Objected-oriented and component-oriented methodologies have been adopted in the design and implementation. Unified modeling language is used in design and documentation of development details. An industrial case study of a pharmaceutical process is presented to illustrate the applicability and procedure of using PHASuite for automated HAZOP analysis.
Degree
Ph.D.
Advisors
Venkatasubramanian, Purdue University.
Subject Area
Chemical engineering
Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server.