Management of the product life cycle and of the corresponding supply network largely depends on information in which specific phase of the life cycle one or another product is. Finding a phase of the product life cycle can be interpreted as recognition of transitions between phases of life of these products. This paper provides a formulation of the above mentioned task of recognition of transitions and presents the structured data mining system for solving that task. The developed system is based on the analysis of demand of historical products and on information about transitions between phases in those products. The paper describes necessary data pre-processing and transformation steps, whose aim is to create a possibility of discovering rules in those data. The created rule discovering framework does not need a complicated realization, because the rules themselves can be discovered by a well-known and available classifier.