Today in industrial units, the monitoring of the equipment performance is done by the operator and due to the vastness of the operating environment and the high volume of the equipment, coordination between the units is difficult and irreparable damages follow. Considering that industrial equipment is one of the essentials and important investments of every production unit; This research has been done with the aim of providing an optimal model for intelligent monitoring of the performance of industrial equipment and management of their correct performance, which despite the significant advances in technology in the field of monitoring, this task can be entrusted to smart tools and the Internet of Things. On the other hand; With the advent of "edge computing" computing technology, many researchers have taken advantage of edge computing based designs due to its advantages. In this research, a mathematical model combining Internet of Things and civilian drones for intelligent monitoring of industrial equipment performance with an edge computing approach is presented, which has been investigated as a case study of wind turbines. In this model, the performance of the drone for intelligent monitoring of wind turbines in three stages of the process; Detection UAV computational offloading and UAV local computation are investigated. Considering the two-objective of model, which was a combination of the above three steps, the model was solved by genetic methods with sparse sorting and the enhanced epsilon limit method using random numbers, and the results show that the genetic method with sparse sorting performed better.