Título: Computer software for the control of potato storage environment
Autores: Landry, Jacques-André
Fecha: 1994
Publicador: McGill University - MCGILL
Fuente:
Tipo: Electronic Thesis or Dissertation
Tema: Potatoes -- Storage -- Computer programs.
Environmental engineering -- Computer programs.
Expert systems (Computer science) -- Industrial applications.
Descripción: Much research has proven that computer controlled vegetable storage can achieve better storage conditions than traditional control systems. During the last 10 years, the use of microcomputer-based environmental control systems has become commonplace. However, to take full advantage of this computerization of the control process, it is not enough only to program the control functions that are performed by normal analog equipment. New and better control strategies must be developed. Recent advances in computer technology have made possible the development of expert systems; a branch of artificial intelligence. One of the advantages of developing such a system is that it provides a reasoning tool which approaches the level of proficiency human experts exhibit in that field. The application of new control methods using expert systems has been extensively demonstrated for greenhouse environments. However, the application of expert systems for the control of vegetable storage is still to be investigated. In the first phase of this project, the development and implementation of a sophisticated control software, using a conventional algorithm-based programming language, were achieved. Throughout the three years of experimentation in an industrial potato storage, the software proved to be appropriate for the control of storage environmental parameters (temperature and relative humidity). During the second phase, the application of an expert system for the on-line control of potato storage was explored. The development of a rule-based expert system, that could replace the conventional algorithm-based control routines was achieved. The integration of the expert system into the control software will result in a highly efficient control software, which can easily be maintained and improved as new knowledge emerges. The use of an expert system will also render possible the representation of heuristic knowledge in the form of rules, which was not possible with the use of conven
Idioma: en