Reseach On Optimal Control Of Elevator Group Based Upon Fuzzy Neural Network

With the development of the society, there are more and more high buildings. The elevator is important in the life. In the large buildings, elevators are installed to provide better service for the people. The optimal control of the elevator group has been the need of the development. The elevator group control system (EGCS) is a control system which makes three or more elevators be a whole and manage the whole. The purpose is to assign the elevator group which is made up with the least elevators. In the paper, the EGCS is studied. There are two main contents, including the elevator traffic pattern recognition and the scheduling algorithm of the elevator. Intelligent control is introduced in the paper.First, the characters and the targets of performance evaluation for the EGCS are studied. The elevator group control system is a complicated control system, which embodies in nonlinear characteristics, uncertain characteristics, imperfect characteristics of information and multi-target characteristics. There are measure targets as follows, including target of time evaluation, target of energy consuming evaluation, target of passengers'state and target of passengers'tolerance. The characters and the targets of performance evaluation are researched on detailedly. The basic concept of the traffic flow is given, and the forecast methods are analyzed. The composing of the EGCS is studied, which includes the management of the traffic data, the form of the control strategy and the hall call distribution.Meanwhile, the intelligent control technique applied in the EGCS is studied, including the fuzzy neural network (FNN) based upon the mamdani model and the FNN based upon the T-S model. The knowledge can be expressed by the fuzzy logic easily, while in the neural network the information storage is distributed and the study capacity is strong. Combining with the fuzzy control and the neural network, the FNN can be used to design model and realize the control in the complicated system. The structure of the FNN is given in the paper, which is the basic theory for the traffic pattern recognition and the elevator assignment.Then the FNN is applied to identify the traffic pattern. The typical traffic...