This paper reports the classification of 90 sample pavilions in Shanghai World Expo. An artificial intelligence based nonlinear clustering method known as Self-Organizing Map(SOM) has been used to classify expo pavilions. SOM is an efficient tool for visualization of multidimensional data. To conduct the classification, four characteristics namely Hurst exponent for queue length, Hurst exponent for waiting time, mean queue length and mean waiting time have been applied. The classification results show that Shanghai World Expo pavilions can be optimally classified into four classes. This result will shed light on further studies that how to manage the queue of World Expo pavilions in the future. This paper reports the classification of 90 sample pavilions in Shanghai World Expo. An artificial intelligence based nonlinear clustering method classified as Self-Organizing Map(SOM) has been used to classify expo pavilions. SOM is an efficient tool for visualization of multidimensional data. To The classification results show that Shanghai World Expo pavilions can be optimally classified into four classes. This result will Shed light on further studies that how to manage the queue of World Expo pavilions in the future.