Decision-making on pipe stress analysis enabled by knowledge-based systems

This paper presents engineering decision-making on pipe stress analysis through the application of knowledge-based systems (KBS). Stress analysis, as part of the design and analysis of process pipe networks, serves to identify whether a given pipe arrangement can cope with weight, thermal, and pressure stress at safe operation levels. An iterative process of design and analysis cycle is done routinely by engineers while analyzing the existing networks or while designing the process pipe networks. In our proposal, the KBS establishes a bidirectional communication with the current engineering software for pipe stress analysis, so that the user benefits from this integration. The stress analysis knowledge base is constructed by registering the senior engineers’ know-how. The engineers’ overall strategy to follow up during the pipe stress analysis, to some extent contained by the KBS, is presented. Advantages in saving engineering man-hours and usefulness in guiding experts in pipe stress analysis are the major services for the process industry. Matías Alvarado is a Research Scientist at the Centre of Research and Advanced Studies (CINVESTAV-IPN, México). He got a Ph.D. degree in computer science at the Technical University of Catalonia with a major in artificial intelligence. He has a B.Sc. degree in mathematics from the National Autonomous University of Mexico. His interests in research and technological applications include knowledge management and decision-making, autonomous agents and multiagent systems for supply chain disruption management, concurrency control, pattern recognition, and computational logic. He is the author of about 50 scientific papers, the Guest Editor of journal Special Issues on topics of artificial intelligence and knowledge management for the oil industry, and an Academic, invited to the National University of Singapore, Technical University of Catalonia, University of Oxford, University of Utrecht, and Benemérita Universidad Autónoma de Puebla. Miguel A. Rodríguez-Toral is a Chemical Engineer educated at the University of Edinburgh, U.K. (Ph.D.), UMIST, U.K. (M.Sc.), and UNAM, México (B.Sc.). He has 13 years of work experience at the Mexican Petroleum Institute (IMP) in the areas of engineering design of heat transfer equipment, cogeneration, and process engineering for the oil, gas, and petroleum refining industry. He is currently the topside leader of the Deepwater program at the IMP. He has interest in the applications of mathematical optimization and knowledge-based systems for the solution of process engineering and energy efficiency design problems. Armando Rosas Elguera is a Civil Engineer working at the IMP. He has 27 years of experience as a Specialist in flexibility and support of critical piping systems for the process industry. In 1979, he was a piping stress and flexibility Specialist, then an Office Head of piping flexibility, Coordinator and Representative of the IMP in the Laguna Verde project (a nuclear power plant in Mexico). He was also the Head of the pipe stress analysis department from 1994 to 1998. Currently, he is a Researcher in the applications of pipe stress analysis. He has deep practical experience in pipe stress analysis for nuclear power projects, for process and power plants involving all the different phases of engineering projects, from engineering design to plants start-up and operation. Sergio Ayala got a B.Sc. degree in civil engineering from the Mexican National Polytechnic Institute (IPN). He is now retired from the IMP. He has more than 30 years of industrial experience gained at the IMP in the area of pipe stress analysis of process plants. He has extensive practical experience in the engineering design and technical advice during start-up and operations of piping systems for the upstream and downstream sectors of the Mexican petroleum industry. He is a Senior Specialist in pipe stress analysis. He has interest in the applications of computer science for the implementation of a corporate memory in his area of speciality.