Algorithm for identification of emergencies prerequisites based on “if-then” rules

Abstract

The article is devoted to solving the scientific problem of decision support for the prevention and elimination of emergencies consequences based on solving the problem of emergencies identification types. The relevance of this problem is due to the need to optimize the risk of adverse effects on human health and the environment in connection with emergencies. The increased complexity of the tasks solved within the framework of the designated scientific problem is associated with the presence of information uncertainty in the complex accounting of heterogeneous characteristics, which in some cases can’t be normalized and brought to a single measurement scale. The authors have developed a heuristic algorithm for identifying the risks of emergency situations based on the “if-then” rules. New models of fuzzy inference have been built, for the implementation of which an algorithm has been developed for identifying the prerequisites for the occurrence of emergencies based on the “if-then” rules when solving problems of mass evacuation in the event of floods, hurricanes and other natural disasters, which allow making decisions on evacuation, partial evacuation, refusal to evacuate and others. Combinations of low-level “if-then” rules built for specific precedents for the occurrence and development of emergencies create unique sets of decision support alternatives to eliminate the consequences of a particular emergency. Each such alternative is essentially a trajectory that reflects the sequence of actions with many clarifying variations built on the basis of the fuzzy methods use for structuring operational information. To create test examples of specific ESs, the basic architecture of the ontological model of rules has been built, which has the form of a three-sided tensor. The main elements of this ontological model are entity concepts and relationships between them, the presence of which at the upper level of decomposition will indicate the risk of an emergency, and at each lower level it will expand the taxonomy of emergency situations possible detailed description and the necessary actions to prevent them or elimination of consequences.