Dissolved gas analysis (DGA) is one of the most useful techniques to detect the incipient faults of power transformer. However, the identification of the faulted location by the traditional method is not always an easy task due to the variability of gas data and operational natures. In this paper, a novel cerebellar model articulation controller (CMAC) neural network (NN) method is presented for the fault diagnosis of power transformers. By introducing the IEC standard 599 to generate the training data, and using the characteristic of self-learning and generalization, like the cerebellum of human being, a CMAC NN fault diagnosis scheme enables a powerful, straightforward, and efficient fault diagnosis. With application of this scheme to published transformers data, the diagnoses demonstrate the new scheme with high accuracy and high noise rejection ability. Moreover, the results also proved the ability of multiple incipient faults detection.