The purpose of this dissertation is to develop a method, based on Genetics Algorithms and Rule Base Systems, to optimize the production scheduling of fuel oil and asphalt area in a petroleum refinery. The refinery is a multi- product plant, with two machine stages - one mixer and a set of tanks - with no setup time and with resource constrains in continuous operation. Two genetic algorithms models were developed to establish the sequence and the lot- size of all production shares. The first model proposed has a direct representation of the production scheduling which the time interval of scheduling is shared in one hour discrete intervals. The second model proposed has a indirect representation that need to be decoded in order to make the real production scheduling. The Rule Base Systems were developed to choice the tanks that receive the production and the tanks that provide the demand of the several consumer centers. A special mutation operator - Neighborhood Mutation - was proposed to minimize the number of changes in the production. A Multi-objective Fitness Evaluation technique, based on a Energy Minimization Method, was also incorporated to the Genetic Algorithm models. The results obtained confirm that the proposed Genetic Algorithm models, associated with the Multi- objective Energy Minimization Method and the Neighborhood Mutation, are able to solve the scheduling problem, optimizing the refinery operational objectives.