Research On Elevator Group Control System Based On Artificial Neural Network

With the development of high-rise buildings and intelligent buildings, elevator group is playing a more important role in high-rise buildings and intelligent buildings, so the elevator group control system (EGCS) is now the focus of the researchers at home and aboard. In the EGCS, it is a stochastic, multi-object decision-making because of many uncertain factors. This paper researches the EGCS, especially in the group control system of four elevators. The main contents are as follows:Firstly, the paper puts forward background, purpose and significance, then the history and status quo are reviewed, some intelligent algorithms used in the EGCS are introduced in recent years and the paper presents the development tendency of the EGCS.Secondly, after analyzing the EGCS’s multi-object, uncertainty, nonlinearity, disturbance and so on, the paper solves the problem of multi-object by processing the complex control system as a multi-object programming and briefly introduces four different traffic patterns: Up-Peak Traffic Pattern, Down-Peak Traffic Pattern, Random Inter-Floor Traffic Pattern and Idle Traffic Pattern. Some main control modes and eigenvalues affecting distribution of elevators are discussed in the EGCS.Thirdly, it is hard to build the model of the EGCS. After relating network structure and algorithm of Back-Propagation neural network, which belongs to Artificial Neural Network, the membership function of main factor affecting the three optimized object is constructed by combining ANN with Fuzzy Logic System. Then, the paper builds a three layer of BP neural network model to seek for the optimal solution of the EGCS.At last, the Artificial Neural Network (ANN) is applied to the EGCS to build simulation model and the relevant MATLAB program is written for different traffic patterns. Then the program and model is simulated to verify the effectiveness and reliability of the ANN.