This paper introduces the new intelligence technology in the transformer fault diagnosis - artificial intelligence system (TFDAI). An artificial intelligence system design includes selection of input, network topology, synaptic connection weight, and output. TFDAI module structure, data processing and diagnostic techniques are described in detail. It consists of expert system (ES) and artificial neural network (ANN). This paper covers TFDAI developing and application. It states that artificial intelligence system is very useful tool for transformer early hidden faults achieves the possibility and accuracy of primary diagnosis.