Abstract: Classification is a very important part in the domain of data mining，however，single classifiers have many defects，such as very finite applicability and low accuracy.Combining multiple classifiers can overcome the defects.The existent combination rule，which is the pivotal conception during the process of combination，including product rule，sum rule，median rule，voting rule and so on，but these are not steady enough.In this paper，the authors develop a new model of combining multiple classifiers based on nerve net，and it is proved that it can improve not only the accuracy of classification but also its applicability.